System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting communication environment data and floating population data immediately before a disaster; means for calculating the number of evacuees in each shelter using an artificial intelligence model based on the collected data; means for calculating the amount of necessary relief supplies based on the calculation result and instructing the preparation and delivery of supplies; and means for collecting the situation of the site after communication recovery, updating data, recalculating necessary supplies, and instructing additional supply.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When communications and power supplies are cut off during an earthquake, it becomes difficult to quickly and accurately grasp the situation at evacuation centers. As a result, there is a possibility that the supply of relief supplies will be delayed, which could lead to a deterioration in the living environment of evacuees. The present invention aims to provide a system that accurately grasps the population distribution at evacuation centers in the event of an earthquake and efficiently supplies necessary relief supplies. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a means for collecting communication environment data and population mobility data immediately before an earthquake, a means for estimating the number of evacuees at each evacuation shelter using an AI model based on the collected data, a means for calculating the amount of relief supplies needed based on the estimated results and issuing instructions for the preparation and delivery of supplies, and a means for collecting information on the local situation after communication is restored, updating the data, recalculating the amount of supplies needed, and issuing instructions for additional supplies. Furthermore, by configuring the AI ​​model to learn from past earthquake data and the means for calculating the amount of supplies needed to include specific relief supplies such as water, food, medicine, and blankets, more effective and efficient supply of supplies is achieved.

[0006] "Communication environment data" refers to data regarding network usage and communication volume obtained from telecommunications carriers and Internet service providers (ISPs).

[0007] "Floating population data" is data that shows people's movements and stays, and is mainly obtained from mobile phone location information and transportation usage data.

[0008] An "artificial intelligence model" is an algorithm that learns using past data and predicts future situations and figures.

[0009] "Estimating the number of evacuees" involves using an artificial intelligence model to estimate how many people are evacuated to each shelter.

[0010] "Necessary relief supplies" are items such as water, food, medicine, and blankets needed by people evacuated to evacuation centers.

[0011] "Preparing supplies" means securing necessary relief supplies and taking steps to place them in designated locations.

[0012] "Supply delivery" refers to the transportation process for delivering prepared relief supplies to evacuation centers.

[0013] "Data updating" means updating the database in the system based on the latest local information collected.

[0014] "Additional supplies" refers to the provision of additional supplies when the initial supplies are insufficient.

[0015] "Past earthquake disaster data" refers to statistical information and case data on earthquake disasters that have occurred in the past.

[0016] "Calculating the amount of relief supplies" means calculating the specific amount of supplies needed for each evacuation shelter based on the number of evacuees. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake disaster and to effectively supply necessary relief supplies.

[0039] This system functions in cooperation with the server, terminals, and users.

[0040] Data collection

[0041] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[0042] Example: The server uses APIs provided by each telecommunications carrier and ISP to obtain demographic information and communication usage status for each region in real time.

[0043] AI estimation

[0044] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0045] Example: The server uses calibration data to standardize collected data and convert it into a format for the AI ​​model.

[0046] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0047] Example: The server uses a trained neural network model to output results such as "The predicted number of evacuees at shelter A in Tokyo is 500."

[0048] Estimating necessary supplies and preparing for delivery

[0049] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[0050] Example: The server calculates that "500 evacuees require 500 liters of water, 500 meals, and 500 blankets."

[0051] 2. The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[0052] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0053] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[0054] Example: The server creates a delivery schedule such as "send one truckload of supplies from Warehouse X to Evacuation Center A."

[0055] Gathering information at evacuation shelters

[0056] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[0057] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[0058] 2. The terminal sends the entered information to the server.

[0059] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0060] Data updates and supply adjustments

[0061] 1. The server updates the database based on the latest information sent from the evacuation center.

[0062] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0063] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0064] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0065] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0066] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0067] In this way, the system operates in cooperation with servers, terminals, and users, making it possible to efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[0071] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[0072] Step 2:

[0073] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0074] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[0075] Step 3:

[0076] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0077] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[0078] Step 4:

[0079] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[0080] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0081] Step 5:

[0082] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[0083] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0084] Step 6:

[0085] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[0086] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0087] Step 7:

[0088] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[0089] Example: A shelter manager uses a terminal to input, "Current number of evacuees: 600, water shortage."

[0090] Step 8:

[0091] The terminal transmits the input information to the server.

[0092] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0093] Step 9:

[0094] The server updates the database based on the latest information sent from the evacuation center.

[0095] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0096] Step 10:

[0097] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0098] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0099] Step 11:

[0100] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0101] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0102] This series of processes allows us to quickly grasp the situation at evacuation centers in the event of an earthquake and effectively provide necessary relief supplies.

[0103] Example 1

[0104] 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."

[0105] During an earthquake, it is difficult to quickly and accurately grasp the situation at evacuation centers and effectively provide the necessary relief supplies. In particular, when there are large fluctuations in the communication environment and the flow of population, or when it is difficult to predict the number of evacuees, it is difficult to make an appropriate plan for the supply of supplies based on that, and relief activities may be delayed.

[0106] 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.

[0107] In this invention, the server includes means for collecting moving population data and communication environment data from communication service providers, means for standardizing the collected data and inputting it into an artificial intelligence model, and means for predicting the number of evacuees at each evacuation shelter using the artificial intelligence model. This makes it possible to accurately predict the number of evacuees in real time based on the moving population data and communication environment data in the event of an earthquake, and to quickly and appropriately supply necessary relief supplies.

[0108] "Communication service providers" is a general term for telecommunications carriers and internet service providers that provide floating population data and communication environment data.

[0109] "Floating population data" is information on the movement of population and the number of people within a specific area.

[0110] "Communication environment data" is information related to the communication usage status and line congestion within a specific area.

[0111] A "server" is a computer system for collecting, processing, and performing various calculations on data.

[0112] An "artificial intelligence model" is software that includes machine learning algorithms to analyze collected data and make predictions and estimates.

[0113] A "terminal" is a device such as a smartphone or tablet that is used by shelter managers to input local information and send it to a server.

[0114] "Prediction methods" are methods or algorithms for predicting the number of evacuees at each shelter using an artificial intelligence model based on collected data.

[0115] "Calculation methods" are methods or algorithms for calculating the amount of relief supplies needed based on the forecast results.

[0116] "Inventory confirmation means" refers to a method or system for confirming the inventory status of supplies to be delivered to each evacuation shelter after estimating the required amount of relief supplies.

[0117] The "delivery plan creation means" refers to a method or algorithm that works in conjunction with a logistics company system to automatically generate an efficient material delivery plan after inventory confirmation.

[0118] "Database update means" refers to a method or system for keeping the database up to date based on information sent from evacuation shelters.

[0119] A "supply adjustment means" is a method or system for adjusting the additional supply of needed relief supplies based on updated data.

[0120] The system based on this invention is designed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively provide the necessary relief supplies. This system functions in cooperation with the server, terminals, and users.

[0121] First, the server collects data on the population flow and communication environment from communication service providers. To do this, it uses APIs provided by communication carriers and internet service providers. For example, it obtains data in real time such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[0122] The server then preprocesses the collected data and converts it into a format that can be input into the AI ​​model. Specifically, it standardizes the data using calibration data. This reduces data variability and improves the accuracy of analysis by the AI ​​model.

[0123] The collected and preprocessed data is input into a generative AI model on the server. This model has previously learned data from past earthquakes, and is able to predict with high accuracy the number of evacuees at each evacuation shelter. An example of a prompt sentence is: "Use part of the input data and parameters as the prompt sentence to input into the generative AI model. Example: Please calculate the predicted number of evacuees at shelter A in Tokyo."

[0124] Based on the prediction results, the server estimates the amount of relief supplies needed for each shelter. For example, if the predicted number of evacuees at shelter A is 500, it estimates that 500 liters of water, 500 meals, and 500 blankets will be needed. Specific relief supplies such as water, food, medicine, and blankets are also taken into account when calculating the amount of supplies needed.

[0125] Based on the estimated results, the server accesses the local government's stockpile database and checks the stock status of necessary supplies. Specifically, it verifies that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0126] After completing the inventory check, the server connects with the logistics company's system to automatically generate a delivery plan for supplies. This creates an efficient delivery schedule, such as "send supplies from Warehouse X to Evacuation Center A using one truck."

[0127] Meanwhile, the shelter manager uses a terminal to input the number of evacuees and the status of supplies on site. This information is immediately sent to the server and the database is updated in real time. For example, if the shelter manager inputs "The current number of evacuees is 600, and there is a water shortage," this is sent to the server.

[0128] Finally, the server updates the database based on the transmitted information and recalculates the amount of supplies needed. As a result, it recalculates that "an additional 100 liters of water and 100 meals are needed," and instructs the logistics company to supply additional supplies. This makes it possible to efficiently and accurately grasp the situation at evacuation centers even in the event of an earthquake, and to quickly provide the necessary relief supplies.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] The server collects floating population data and communication environment data from communication service providers.

[0132] Input: Uses APIs provided by telecommunications carriers or internet service providers.

[0133] Data processing: Obtain demographic information and communication usage status for each region in real time.

[0134] Output: Save the collected data on the server.

[0135] Specific operation: The server calls the API and obtains data such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[0136] Step 2:

[0137] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0138] Input: Raw data collected in step 1.

[0139] Data processing: Standardize using calibration data and convert into a format suitable for AI models.

[0140] Output: Standardized data.

[0141] Specific operation: The server performs processing such as "normalizing population data by standard deviation" to reduce the variability of the data.

[0142] Step 3:

[0143] The server uses the generated AI model to predict the number of evacuees at each shelter.

[0144] Input: The preprocessed data from step 2.

[0145] Data calculation: Using neural network model.

[0146] Output: Predicted number of evacuees.

[0147] Specific operation: The server inputs data into the AI ​​model along with the prompt "Please calculate the number of evacuees predicted for shelter A in Tokyo," and obtains a result such as "500 evacuees are predicted for shelter A."

[0148] Step 4:

[0149] Based on the prediction results, the server estimates the amount of relief supplies needed.

[0150] Input: Prediction results from step 3.

[0151] Data calculation: Calculation based on standard consumption of relief supplies.

[0152] Output: The amount of supplies needed.

[0153] Specific operation: The server calculates, "There are 500 evacuees in shelter A, so 500 liters of water, 500 meals, and 500 blankets are needed."

[0154] Step 5:

[0155] The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[0156] Input: Estimated amount of relief supplies.

[0157] Data processing: Querying the stockpile database.

[0158] Output: Stock availability.

[0159] Specific operation: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0160] Step 6:

[0161] The server works in conjunction with the logistics company's system to create a delivery plan for supplies.

[0162] Input: Stock status and estimated amount of relief supplies.

[0163] Data calculation: Delivery route optimization algorithm.

[0164] Output: Delivery schedule.

[0165] Specific operation: The server generates a delivery schedule that "sends supplies from warehouse X to shelter A in one truck."

[0166] Step 7:

[0167] The terminals will be used by shelter managers to input the number of evacuees and the status of supplies on site.

[0168] Input: Local information entered by shelter manager.

[0169] Data processing: Input via application.

[0170] Output: The information entered.

[0171] Specific operation: The shelter manager enters "Current number of evacuees is 600, water shortage" into the terminal.

[0172] Step 8:

[0173] The terminal transmits the input information to the server.

[0174] Input: Local information entered.

[0175] Data processing: Communication from the terminal to the server.

[0176] Output: Information sent to the server.

[0177] Specific operation: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0178] Step 9:

[0179] The server updates the database based on the latest information and recalculates the amount of supplies needed.

[0180] Input: The local information sent to the server.

[0181] Data calculation: Recalculation algorithm.

[0182] Output: Recalculated amount of aid supplies.

[0183] Specific operation: The server updates the database with "The latest number of evacuees at shelter A is 600, and there is a water shortage," and recalculates that "An additional 100 liters of water and 100 meals are needed."

[0184] Step 10:

[0185] The server sends a delivery instruction for the additional supplies to the logistics company.

[0186] Input: Recalculated amount of aid.

[0187] Data processing: Update shipping schedule.

[0188] Output: The new delivery schedule.

[0189] Specific operation: The server generates a new delivery schedule such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A" and sends instructions to the logistics company.

[0190] (Application example 1)

[0191] 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."

[0192] During an earthquake, it is important to quickly and accurately grasp the situation at evacuation centers and effectively supply the necessary relief supplies. However, due to communication environment problems and sudden increases and decreases in the number of evacuees, it is difficult to accurately grasp the situation on site, which can lead to problems with delays in the timely delivery of relief supplies. In addition, insufficient coordination with logistics companies can make it difficult to distribute supplies appropriately.

[0193] 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.

[0194] In this invention, the server includes means for collecting communication environment data and mobile population data immediately before the earthquake, means for estimating the number of evacuees at each evacuation shelter using an artificial intelligence model based on the collected data, means for calculating the amount of relief supplies needed based on the estimate results and issuing instructions for the preparation and delivery of supplies, means for collecting information on the local situation after communication is restored, updating the data, recalculating the needed supplies, and issuing instructions for additional supplies, means for automatically and dynamically generating a delivery schedule for needed supplies and sending instructions to logistics companies, and means for quickly sending the latest information via a terminal used by the evacuation shelter manager. This makes it possible to efficiently and accurately grasp the situation at evacuation shelters and provide needed supplies even during communication disruptions.

[0195] "Communication environment data immediately before the earthquake" is data obtained from communication carriers and internet service providers that indicates the communication conditions immediately before the earthquake occurred.

[0196] "Floating population data" is data that shows the movement and distribution of population in a specific area over a certain period of time.

[0197] An "artificial intelligence model" is a statistical model that uses machine learning and deep learning to learn from past data and predict future situations.

[0198] "Means for estimating the number of evacuees" refers to techniques and methods for predicting the number of evacuees at each evacuation shelter using an artificial intelligence model based on collected data.

[0199] "Means for calculating the amount of necessary relief supplies" refers to techniques and methods for calculating the required amount of supplies such as water, food, medicine, blankets, health supplies, and consumables based on the predicted number of evacuees.

[0200] "Means for directing the preparation and delivery of supplies" refers to the techniques and methods for preparing needed relief supplies and planning and directing their delivery to each evacuation shelter.

[0201] "Means for collecting on-site information and updating data after communications are restored" refers to the technology and methods for collecting the latest information from evacuation centers and updating the database based on that information when communications are restored after a disaster occurs.

[0202] "Means for ordering additional supplies" refers to techniques and methods for recalculating the required supplies based on updated data and issuing instructions if additional supplies are required.

[0203] "Means for automatically generating dynamic delivery schedules for necessary supplies" refers to technologies and methods for automatically creating optimal supply delivery schedules in real time using AI models and algorithms.

[0204] The "means for sending instructions to the logistics company" refers to a technique or method for notifying the logistics company of the generated delivery schedule and the need for additional supplies, and for instructing them on how to respond.

[0205] "Devices used by evacuation shelter managers" are devices such as smartphones and tablets that evacuation shelter managers use to enter information such as local conditions and necessary supplies and send it to a server.

[0206] The system based on this invention is constructed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively supply the necessary relief supplies. The system operates in cooperation with the server, terminals, and users, and performs processing in the following steps.

[0207] System Configuration

[0208] 1. Server

[0209] Hardware: High-performance web server (e.g., Amazon Web Services (AWS®), Microsoft® Azure®)

[0210] Software: Communication API, TENSORFLOW (registered trademark), Requests library

[0211] Functions: Data collection, data standardization, predictions using AI models, and sending instructions to logistics companies

[0212] 2. Terminal

[0213] Hardware: Smartphones, tablets (e.g., ANDROID (registered trademark), iOS)

[0214] Function: The shelter manager inputs local information and sends it to the server.

[0215] 3. Users

[0216] Role: Evacuation center manager, inputting the number of evacuees and the status of supplies via terminal

[0217] Operation flow

[0218] Data collection

[0219] The server collects data on the communication environment and population movement immediately before the earthquake from telecommunications carriers and internet service providers. The collected data is standardized into the required data format.

[0220] Prediction by AI model

[0221] The standardized data is input into an artificial intelligence model (e.g., a neural network using TensorFlow) to predict the number of evacuees at each shelter in real time. For example, the server calculates that "the predicted number of evacuees at shelter A immediately after the earthquake is 500 people."

[0222] Estimating supplies and preparing for delivery

[0223] Based on the prediction results, the server calculates the amount of relief supplies needed and automatically generates a dynamic delivery schedule. The calculation includes specific relief supplies such as water, food, medicine, blankets, health supplies, and consumables. For example, it calculates that "500 evacuees need 500 liters of water, 500 meals, and 500 blankets." The calculated results are sent as instructions to logistics companies.

[0224] The server generates a specific delivery schedule, such as "send supplies from warehouse X to shelter A in one truck," and sends instructions.

[0225] Gathering information at evacuation shelters

[0226] The shelter manager uses a device (smartphone or tablet) to input the number of evacuees and the status of supplies. For example, if the manager inputs "the current number of evacuees is 600, and there is a water shortage," the information is immediately sent to the server.

[0227] Data updates and additional supplies

[0228] The server updates the database based on the latest information received and recalculates the amount of supplies needed. If the recalculation shows that additional supplies are needed, it quickly issues instructions to logistics companies to provide the additional supplies. For example, it may recalculate the amount to "an additional 100 liters of water and 100 meals are needed," and immediately send delivery instructions.

[0229] Specific examples

[0230] At shelter A, the server collects the latest local information and predicts the number of evacuees. Based on these results, it dynamically calculates the amount of relief supplies needed and automatically generates a truck delivery schedule. The shelter manager uses a smartphone to instantly send the actual number of evacuees and the status of supplies to the server, which then updates the database with this information and draws up a plan for additional supplies.

[0231] Prompt Sentence Examples

[0232] "Collect the latest population and communication data for shelter A from the server, and use an AI model to predict the number of evacuees. Based on the prediction, calculate the necessary relief supplies and generate Python code to schedule the delivery of supplies to shelter A."

[0233] By operating in this way, the system can efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[0234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0235] Step 1: Data collection

[0236] The server collects real-time data on the communication environment immediately before the earthquake and data on the local population flow from telecommunications carriers and internet service providers via API. It uses API endpoints as input and obtains the collected data as output. The server saves the collected data in JSON format or other formats.

[0237] Step 2: Data Standardization

[0238] The server standardizes the collected data before applying it to the AI ​​model. Specifically, it fills in any imperfections in the data, removes outliers, and converts it into the required format. It uses the collected raw data as input and obtains standardized data as output. The server then adapts this data to the input format of the AI ​​model.

[0239] Step 3: Predict the number of evacuees

[0240] The server inputs the standardized data into an artificial intelligence model to predict the number of evacuees at each shelter. Using the standardized data as input, the server obtains the predicted number of evacuees as output. Specifically, the neural network model performs the calculations using machine learning libraries such as TensorFlow.

[0241] Step 4: Calculate supply needs

[0242] The server calculates the amount of supplies needed based on the predicted number of evacuees. It uses the predicted number of evacuees as input and gets a detailed list of needed supplies as output. For example, it calculates "500 evacuees need 500 liters of water, 500 meals, and 500 blankets."

[0243] Step 5: Auto-generate delivery schedules

[0244] The server automatically generates a delivery schedule for logistics companies based on the relief supply list. It uses the supply list as input and obtains a specific delivery plan as output. For example, the server generates a schedule such as "Send supplies from Warehouse X to Evacuation Center A by one truck."

[0245] Step 6: Send instructions to logistics provider

[0246] The server sends the generated delivery schedule as instructions to the logistics company. It uses the automatically generated delivery schedule as input and verifies that the instructions were sent correctly as output. The server does this via HTTP requests, etc.

[0247] Step 7: Gather local information

[0248] The terminal is used by the shelter manager to input the latest local situation. For example, the shelter manager might use the terminal to input "the current number of evacuees is 600, and there is a water shortage." The information obtained on-site is used as input, and that information is sent to the server as output.

[0249] Step 8: Update the Database

[0250] The server updates the database based on the latest information sent from the terminal. It uses the data sent from the field as input and obtains the updated database as output. The server then updates the database to show that "the latest number of evacuees at shelter A is 600, and there is a water shortage."

[0251] Step 9: Recalculate and order additional supplies

[0252] The server recalculates the amount of supplies needed based on the updated database and issues instructions if additional supplies are required. It uses the latest database information as input and obtains a recalculated list of supplies as output. For example, it may recalculate, "We need an additional 100 liters of water and 100 meals of food," and send additional delivery instructions to the logistics company.

[0253] By implementing each of the above steps, we will create a system that will enable efficient and accurate assessment of the situation at evacuation centers and the supply of necessary supplies, even if communications and power supplies are cut off during an earthquake.

[0254] 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.

[0255] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply necessary relief supplies. This system functions in cooperation with the server, terminals, and users, and by combining it with an emotion engine, it also provides psychological support to evacuees.

[0256] Data collection

[0257] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[0258] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[0259] AI estimation

[0260] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0261] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[0262] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0263] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[0264] Estimating necessary supplies and preparing for delivery

[0265] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[0266] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0267] 2. The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[0268] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0269] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[0270] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0271] Gathering information at evacuation shelters

[0272] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[0273] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[0274] 2. The terminal sends the entered information to the server.

[0275] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0276] Data updates and supply adjustments

[0277] 1. The server updates the database based on the latest information sent from the evacuation center.

[0278] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0279] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0280] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0281] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0282] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0283] Emotion engine integration

[0284] 1. The device collects facial expressions, voice, and text data from shelter managers and evacuees and sends it to the emotion engine.

[0285] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[0286] 2. The emotion engine analyzes the collected data and recognizes the user's emotional state.

[0287] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[0288] 3. The emotion engine sends the recognized emotion data to the server.

[0289] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[0290] 4. The server will use the emotional data to direct additional psychological support or special supplies.

[0291] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[0292] In this way, the system operates in cooperation with the server, terminals, users, and emotion engine, making it possible to efficiently and accurately grasp the situation at evacuation centers, provide necessary supplies, and even provide psychological care for evacuees, even if communications and power supplies are cut off during an earthquake.

[0293] The processing flow will be explained below.

[0294] Step 1:

[0295] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[0296] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[0297] Step 2:

[0298] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0299] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[0300] Step 3:

[0301] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0302] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[0303] Step 4:

[0304] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[0305] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0306] Step 5:

[0307] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[0308] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0309] Step 6:

[0310] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[0311] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0312] Step 7:

[0313] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[0314] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[0315] Step 8:

[0316] The terminal transmits the input information to the server.

[0317] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0318] Step 9:

[0319] The server updates the database based on the latest information sent from the evacuation center.

[0320] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0321] Step 10:

[0322] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0323] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0324] Step 11:

[0325] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0326] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0327] Step 12:

[0328] The device collects facial expressions, voice, and text data from shelter managers and evacuees, and sends it to the emotion engine.

[0329] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[0330] Step 13:

[0331] The emotion engine analyzes the collected data and recognizes the user's emotional state.

[0332] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[0333] Step 14:

[0334] The emotion engine sends the recognized emotion data to the server.

[0335] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[0336] Step 15:

[0337] The server uses the emotional data to direct additional psychological support or special supplies.

[0338] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[0339] Example 2

[0340] 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."

[0341] There is a need for a system that can quickly and accurately grasp the situation at evacuation centers during earthquakes, effectively provide necessary relief supplies, and comprehensively provide psychological support to evacuees. Conventional systems do not collect and update local information about evacuation centers in real time, which can lead to delays in recalculating needed supplies and providing additional supplies, and insufficient psychological support for evacuees. Therefore, a system is needed that can improve the efficiency of evacuation center management and the safety and psychological care of evacuees.

[0342] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication environment data and floating population data, means for normalizing and imputing the collected data and inputting it into an AI model, means for predicting the number of evacuees at each evacuation shelter using the AI ​​model, means for calculating the amount of relief supplies needed based on the prediction results and instructing the preparation and delivery of supplies, means for the evacuation shelter manager to send local information to the server using a terminal, means for updating the database based on the local information, recalculating the amount of needed supplies, and instructing the additional supply, means for collecting emotional data of evacuees via the terminal and sending it to the emotion engine, and means for instructing psychological support and the supply of special supplies based on the emotional data analyzed by the emotion engine. This enables efficient and accurate assessment of the situation at evacuation shelters, the supply of necessary supplies, and psychological care for evacuees during an earthquake disaster.

[0343] "Communication environment data" refers to information such as communication network usage status, connection status, and communication speed obtained from communication carriers and Internet service providers.

[0344] "Floating population data" is statistical information that shows the movement patterns and number of people in a specific area, and is mainly calculated from location information of communication devices.

[0345] An "artificial intelligence model" is a calculation algorithm that learns from past data and predicts new situations, and in this invention it is used to predict the number of evacuees and the amount of necessary supplies.

[0346] "Normalization" is a process in data processing that converts collected raw data into a unified format, and is a means of improving data quality.

[0347] "Gap imputation" is the process of filling in missing data with appropriate values ​​in order to build a complete dataset.

[0348] "Terminal" refers to a device such as a smartphone or tablet used by shelter managers and other users, and is used to input and transmit information.

[0349] An "emotion engine" is a software system that recognizes a user's emotional state by analyzing collected data such as facial expressions, voice, and text.

[0350] "Evacuation forecasting" is the process of using artificial intelligence models to estimate the number of people who will evacuate to a particular shelter in the event of a disaster.

[0351] "Relief supplies" refer to basic daily necessities and services that evacuees need in the event of a disaster, such as water, food, medicine, blankets, and recreational items.

[0352] "Psychological support" refers to counseling and other support activities aimed at reducing the psychological distress and stress of evacuees.

[0353] "Database updating" is the process of updating existing data to reflect the latest information, and is done to keep information accurate in real time.

[0354] "Delivery instructions" are instructions given to deliver supplies to where they are needed, and refer to the act of providing logistics companies with specific delivery plans and schedules.

[0355] "Emotion data" is information indicating emotions extracted from the user's facial expressions, voice, text, etc., and is analyzed by the emotion engine.

[0356] The system based on this invention involves the cooperation of a server, terminals, users, and an emotion engine in order to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply the necessary relief supplies. This system is configured as follows:

[0357] Data collection

[0358] The server collects data on the current population and communication environment from telecommunications carriers and internet service providers (ISPs). It uses APIs to obtain data in real time from each telecommunications carrier and ISP. For example, the server uses APIs to collect demographic information from telecommunications carriers.

[0359] Data preprocessing and AI calculations

[0360] The collected data is normalized on the server and missing data is supplemented. The formatted data is then input into an artificial intelligence model. This artificial intelligence model is a neural network model that has been trained based on data from past earthquakes. This model is used to predict the number of evacuees at each evacuation shelter. For example, the server outputs a calculated result such as "The predicted number of evacuees at shelter A is 500."

[0361] Estimating necessary supplies and preparing for delivery

[0362] Based on the estimates, the server calculates the amount of relief supplies needed for each evacuation center. This includes water, food, medicine, blankets, and recreational items. For example, the server might calculate that 500 evacuees need 500 liters of water, 500 meals, and 500 blankets. It then accesses the local government's stockpile database to check the inventory status of the necessary supplies. It then connects to the logistics company's system to automatically generate a specific delivery schedule and issue instructions to the logistics company.

[0363] Gathering information at evacuation shelters

[0364] The terminal allows the shelter manager to input the number of evacuees and the current status of supplies via a smartphone or tablet. For example, the shelter manager might input "the current number of evacuees is 600, and there is a water shortage" into the terminal, and this information is then sent to the server.

[0365] Data updates and supply adjustments

[0366] The server updates the database based on the latest information sent from the evacuation center. This allows it to recalculate the amount of supplies needed based on the latest situation and calculate the amount of additional supplies that should be provided. For example, the server may recalculate that an additional 100 liters of water and 100 meals are needed. Based on the recalculated results, it issues instructions to the logistics company to deliver the additional supplies.

[0367] Emotion engine integration

[0368] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state. For example, the emotion engine may recognize that "evacuee A is in a state of stress, while evacuee B is in a state of relief." The analysis results are sent to the server, which then issues instructions for additional psychological support or the provision of special supplies based on the emotional data.

[0369] (Example of a prompt for a generative AI model):

[0370] "Use this system to understand the situation at evacuation centers, calculate supplies needed, plan distribution, and conduct simulations to provide emotional support."

[0371] In this way, by linking all the elements together, the system will be able to efficiently and accurately grasp the situation at evacuation centers during earthquakes, provide necessary supplies, and even provide psychological care for evacuees.

[0372] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0373] Step 1:

[0374] Data collection

[0375] The server collects population mobility data and communication environment data from telecommunications carriers and Internet service providers (ISPs) through APIs. It uses API endpoints and parameters as input and obtains real-time demographic and communication data as output. For example, the server performs the following operation: "call NTT Docomo's API and obtain demographic information."

[0376] Step 2:

[0377] Data Preprocessing

[0378] The server normalizes the collected data and fills in missing data. It uses floating population data and communication environment data as input, and obtains a normalized dataset as output. Specific operations include filling in missing values ​​based on the preceding and following data, and standardizing the data format. For example, it performs the process of "filling in zeros in the collected data and converting it into a standard format."

[0379] Step 3:

[0380] Prediction of the number of evacuees

[0381] The server uses the preprocessed data to input into an AI model to predict the number of evacuees. The normalized dataset is used as input, and the output is the predicted number of evacuees at each evacuation shelter. The AI ​​model is a neural network trained based on data from past earthquakes. For example, the operation is as follows: "Enter data into the AI ​​model and predict the number of evacuees at shelter A to be 500."

[0382] Step 4:

[0383] Estimated cost of relief supplies

[0384] The server calculates the amount of relief supplies needed at each evacuation center based on the prediction results. It uses the predicted number of evacuees as input and obtains the required amount of supplies as output. Specifically, it calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0385] Step 5:

[0386] Check stockpile data

[0387] The server accesses the local government's stockpile database and checks the stock status of necessary supplies. It uses the list of supplies and the number of evacuees as input, and obtains stock information as output. For example, it checks whether "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0388] Step 6:

[0389] Generate a delivery plan

[0390] The server works in conjunction with the logistics company's system to automatically generate a delivery plan for supplies. It uses inventory information and a list of necessary supplies as input, and obtains a delivery schedule as output. For example, it performs an operation such as "creating a plan to deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0391] Step 7:

[0392] Gathering local information

[0393] The terminal allows the shelter manager to input the number of evacuees and the status of supplies on site via a smartphone or tablet. The latest local information is used as input, and updated information is output and sent to the server. For example, the operation might be, "The shelter manager inputs into the terminal that the current number of evacuees is 600 and there is a water shortage, and then sends the information to the server."

[0394] Step 8:

[0395] Database Update

[0396] The server updates the database based on the latest information sent from the evacuation center. It uses the latest data on the number of evacuees and the status of supplies as input, and obtains the updated database status as output. For example, it performs an operation such as "reflect the latest information from evacuation center A in the database."

[0397] Step 9:

[0398] Supply Recalculation

[0399] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be provided. It uses the updated number of evacuees and supply status data as input, and obtains a list of additional supplies as output. For example, it performs an operation such as "recalculating that an additional 100 liters of water and 100 meals are needed."

[0400] Step 10:

[0401] Delivery instructions for additional supplies

[0402] The server then issues instructions to the logistics company to deliver additional supplies based on the recalculation results. It uses the list of additional supplies and delivery destination information as input, and obtains a new delivery schedule as output. For example, it performs an operation such as "instructing Warehouse Y to deliver an additional 100 liters of water and 100 meals to Evacuation Center A."

[0403] Step 11:

[0404] Collecting Emotional Data

[0405] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. Data photographed or recorded by the device is used as input, and emotion data is output and sent to the emotion engine. For example, the device performs an operation such as "taking a photo of the evacuees' facial expressions with a smartphone camera and sending it to the emotion engine."

[0406] Step 12:

[0407] Emotional Data Analysis

[0408] The emotion engine analyzes the collected data and recognizes the user's emotional state. It uses facial expressions, voice, and text data as input and obtains the analysis results as output. For example, the emotion engine recognizes that evacuee A is in a stressed state and evacuee B is in a relieved state.

[0409] Step 13:

[0410] Sending emotional data

[0411] The emotion engine sends the recognized emotion data to the server. It uses the analyzed emotional state data as input and gets a report that is sent to the server as output. For example, the emotion engine reports to the server that most of the evacuees at shelter A are in a stressed state.

[0412] Step 14:

[0413] Psychological support instructions

[0414] The server then uses the emotional data to provide additional psychological support and special supplies. It uses the emotional state data sent from the emotion engine as input and obtains a psychological support plan and a supply list as output. For example, it can perform an action such as "dispatch a psychological counselor to shelter A and provide recreational supplies to relieve stress."

[0415] (Application example 2)

[0416] 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."

[0417] In managing evacuation shelters after a disaster, it is extremely important to quickly and accurately grasp the situation of evacuees and provide appropriate relief supplies. However, the current system makes it difficult to grasp the psychological state of evacuees, which results in issues such as inadequate psychological support for evacuees and insufficient maintenance of order and safety within the shelter.

[0418] 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.

[0419] In this invention, the server includes means for collecting communication environment data and population mobility data immediately before the earthquake, means for using an AI model to estimate the number of evacuees at each evacuation shelter based on the collected data, means for calculating the amount of relief supplies needed based on the estimate and issuing instructions for the preparation and delivery of supplies, means for collecting on-site conditions after communication is restored, updating the data, recalculating the needed supplies, and issuing instructions for additional supplies, means for collecting video data within the evacuation shelter and recognizing the emotional state of the evacuees, means for issuing instructions for psychological support and the delivery of special supplies based on the recognized emotional data, and means for monitoring the situation in real time and implementing security measures to prevent crime and maintain order. This allows for comprehensive management of the situation within the evacuation shelter, making it possible to efficiently not only provide supplies but also provide psychological care and ensure safety.

[0420] "Communication environment data" is information that indicates the state and usage of the communication network at the time of the earthquake.

[0421] "Floating population data" is information that indicates the movement of people and population density within a specific area.

[0422] An "artificial intelligence model" is an algorithm that is trained on past data to make predictions or classifications based on specific inputs.

[0423] "Number of evacuees" refers to the number of people staying in evacuation shelters.

[0424] "Relief supplies" are supplies such as water, food, medicine, and blankets that evacuees need in the event of a disaster.

[0425] "Preparation and delivery of supplies" refers to all activities involved in preparing necessary relief supplies in appropriate locations and delivering them to evacuation shelters.

[0426] "Local situation" refers to real-time information such as the current number of evacuees at evacuation centers and the shortage of supplies.

[0427] "Data updating" means reflecting newly obtained local information in the existing database.

[0428] "Additional supply" means the re-delivery of supplies to make up for any shortages that have already been made.

[0429] "Video data" refers to video information of evacuees and the inside of evacuation shelters obtained through cameras, etc.

[0430] "Emotional state" is information that indicates the psychological stability and stress level of evacuees.

[0431] "Psychological support" refers to providing care and support to evacuees to ensure their psychological well-being.

[0432] "Security measures" refer to surveillance and crime prevention measures to ensure safety within the shelter.

[0433] To implement this invention, it is necessary to build a system in which servers, terminals, and users work together. This system aims to streamline the operation of evacuation shelters in the event of an earthquake, and to comprehensively provide psychological support and security measures for evacuees.

[0434] Components

[0435] 1. Data Collection

[0436] The server collects real-time data on the population flow and communication environment from telecommunications carriers and internet service providers (ISPs) via APIs. For example, data obtained through APIs includes communication usage status and regional demographics.

[0437] Example prompt sentence:

[0438] text

[0439] curl -X GET "API_URL" -H ​​"accept: application / json"

[0440] 2. AI estimation

[0441] The server preprocesses the collected data and inputs it into an artificial intelligence model. After normalizing the data and filling in missing data, the number of evacuees at each shelter is predicted based on the neural network model.

[0442] The collected data is normalized using tools such as MinMaxScaler, and then the number of evacuees is estimated using a neural network model built with TensorFlow and Keras.

[0443] 3. Estimate the amount of supplies needed and prepare for delivery

[0444] Based on the estimates, the server calculates the amount of relief supplies (e.g., water, food, medicine, blankets) needed at each evacuation center. It also checks inventory and automatically generates delivery schedules.

[0445] Specifically, estimates include "500 evacuees will need 500 liters of water, 500 meals, 50 sets of medicine, and 500 blankets."

[0446] 4. Gathering information at evacuation shelters

[0447] The terminals are smartphones or tablets used by shelter managers, and they input the number of evacuees and the status of supplies on site. This information is sent to a server and the database is updated.

[0448] For example, a shelter manager might enter "Current number of evacuees: 600, water shortage" into a terminal and update the information on the server.

[0449] 5. Data updates and supply adjustments

[0450] The server recalculates the amount of supplies needed based on the latest data, calculates the amount of additional supplies that should be supplied, and issues instructions to the logistics company to deliver the additional supplies.

[0451] As a specific example, instructions may be given such as "Deliver an additional 100 liters of water and 100 meals from the warehouse to evacuation centers."

[0452] 6. Emotion engine integration

[0453] The device collects facial expressions, voice, and text data from shelter managers and evacuees, and sends it to an emotion engine, which analyzes this data and recognizes the emotional state of the evacuees.

[0454] For example, a shelter manager can take pictures of evacuees' facial expressions with a smartphone camera and use the emotion engine to recognize that "evacuee A is in a stressed state, while evacuee B is in a relaxed state."

[0455] Example prompt sentence:

[0456] text

[0457] Analyze the emotions of individuals in the video feed from "http: / / camera_feed_url". Identify and report back on the number of individuals showing signs of stress versus those who appear calm.

[0458] 7. Security Measures

[0459] The server collects video data from inside the evacuation center and monitors it in real time to ensure safety. It also uses facial recognition and object detection technologies to implement measures to prevent crime and maintain order.

[0460] For example, facial recognition technology can be used to monitor specific individuals entering and leaving evacuation shelters and detect suspicious individuals.

[0461] Specific examples

[0462] As a concrete example of the system, immediately after an earthquake, communication environment data and population mobility data are collected, and the number of evacuees at each evacuation center is predicted using an AI model. The system then estimates the amount of relief supplies needed and issues delivery instructions to logistics companies. Furthermore, by repeatedly collecting and updating local information about evacuation centers, the system ensures efficient supply of supplies. It also recognizes emotional states, provides psychological support, and implements security measures to ensure safety and security within the evacuation center.

[0463] This will enable comprehensive management of the situation within the shelter, and will make it possible to efficiently provide not only necessary supplies but also psychological care and ensure safety.

[0464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0465] Step 1:

[0466] The server collects real-time population flow data and communication environment data from telecommunications carriers and Internet service providers (ISPs) via APIs. Using data obtained from API endpoints as input, the data is sent to the server and stored in a database. A specific example would be information such as "demographic data from telecommunications carrier A."

[0467] Step 2:

[0468] The server preprocesses the collected data and inputs it into an artificial intelligence model. Preprocessing includes normalizing the data and filling in missing data. For example, MinMaxScaler is used to scale the data to a range of 0 to 1, and missing data is filled in with the historical average value. The preprocessed data is then input into the artificial intelligence model (a model trained with TensorFlow or Keras).

[0469] Step 3:

[0470] The server uses an artificial intelligence model to predict the number of evacuees at each shelter. It uses preprocessed data as input and obtains the predicted number of evacuees at each shelter as output. For example, it outputs a specific estimated result such as "The predicted number of evacuees at shelter A is 500 people."

[0471] Step 4:

[0472] The server calculates the amount of relief supplies needed based on the results of the calculation. It uses the predicted number of evacuees as input and obtains a list of necessary supplies as output. For example, the calculation results may be, "For 500 evacuees, 500 liters of water, 500 meals, and 500 blankets are needed."

[0473] Step 5:

[0474] The server accesses the local government's stockpile database and checks the stock status of necessary supplies. It uses a list of supplies as input and obtains the stock status as output. For example, the output might be "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0475] Step 6:

[0476] The server works in conjunction with the logistics company's system to automatically generate a delivery plan for supplies. It uses inventory status and evacuation shelter location information as input, and obtains a specific delivery schedule as output. For example, it generates specific delivery instructions such as "Deliver supplies from Warehouse X to Evacuation Shelter A using one truck."

[0477] Step 7:

[0478] The terminal is a smartphone or tablet used by the shelter manager, and the number of evacuees and the status of supplies on site are input. The data reported by the shelter manager is used as input, and the latest number of evacuees and the status of supplies are obtained as output. For example, the latest information such as "the current number of evacuees is 600, and there is a water shortage" is input.

[0479] Step 8:

[0480] The terminal sends the input information to the server. The latest data entered by the shelter manager is used as input, and the information sent to the server is obtained as output. For example, the latest number of evacuees and information on shortages of supplies at shelter A are sent to the server.

[0481] Step 9:

[0482] The server updates the database based on the latest information sent from the evacuation center. The latest data received is used as input, and the updated database is obtained as output. For example, the database may be updated to show "The latest number of evacuees at evacuation center A is 600, and there is a water shortage."

[0483] Step 10:

[0484] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be provided. It uses the latest number of evacuees and information on shortages as input, and outputs a list of supplies that should be provided. For example, the recalculation result might be, "An additional 100 liters of water and 100 meals are needed."

[0485] Step 11:

[0486] Based on the recalculation results, the server issues delivery instructions to logistics companies to deliver additional supplies. Using the recalculation results as input, a specific delivery schedule is obtained as output. For example, a new delivery instruction may be generated such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A."

[0487] Step 12:

[0488] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. The facial expressions of the evacuees are used as input, and the data sent to the emotion engine is obtained as output. As a specific example, the facial expressions of the evacuees are photographed with a smartphone camera, and then analyzed by the emotion engine.

[0489] Step 13:

[0490] The emotion engine analyzes the collected data and recognizes the user's emotional state. It uses the collected facial and voice data as input and obtains the recognition result of the emotional state as output. For example, it recognizes that "evacuee A is in a stressed state, and evacuee B is in a relieved state."

[0491] Step 14:

[0492] The emotion engine sends the recognized emotion data to the server. Using the recognized emotional state as input, the emotion data sent to the server is obtained as output. For example, a report may be made such as "Many of the evacuees at shelter A are in a state of stress."

[0493] Step 15:

[0494] The server then uses the emotional data to provide additional psychological support or special supplies. Using the recognized emotional data as input, the server can obtain specific support instructions as output. For example, measures such as "dispatch psychological counselors to shelter A" or "provide additional recreational supplies to relieve stress" may be implemented.

[0495] Step 16:

[0496] The server collects video data from inside the evacuation center and monitors it in real time to ensure safety. The video data is used as input, and the monitoring results for ensuring safety are obtained as output. For example, facial recognition technology can be used to identify suspicious individuals and issue a warning.

[0497] 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.

[0498] 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.

[0499] 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.

[0500] [Second embodiment]

[0501] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0502] 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.

[0503] 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).

[0504] 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.

[0505] 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.

[0506] 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).

[0507] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0508] 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.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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."

[0513] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake disaster and to effectively supply necessary relief supplies.

[0514] This system functions in cooperation with the server, terminals, and users.

[0515] Data collection

[0516] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[0517] Example: The server uses APIs provided by each telecommunications carrier and ISP to obtain demographic information and communication usage status for each region in real time.

[0518] AI estimation

[0519] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0520] Example: The server uses calibration data to standardize collected data and convert it into a format for the AI ​​model.

[0521] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0522] Example: The server uses a trained neural network model to output results such as "The predicted number of evacuees at shelter A in Tokyo is 500."

[0523] Estimating necessary supplies and preparing for delivery

[0524] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[0525] Example: The server calculates that "500 evacuees require 500 liters of water, 500 meals, and 500 blankets."

[0526] 2. The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[0527] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0528] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[0529] Example: The server creates a delivery schedule such as "send one truckload of supplies from Warehouse X to Evacuation Center A."

[0530] Gathering information at evacuation shelters

[0531] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[0532] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[0533] 2. The terminal sends the entered information to the server.

[0534] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0535] Data updates and supply adjustments

[0536] 1. The server updates the database based on the latest information sent from the evacuation center.

[0537] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0538] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0539] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0540] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0541] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0542] In this way, the system operates in cooperation with servers, terminals, and users, making it possible to efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[0543] The processing flow will be explained below.

[0544] Step 1:

[0545] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[0546] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[0547] Step 2:

[0548] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0549] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[0550] Step 3:

[0551] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0552] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[0553] Step 4:

[0554] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[0555] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0556] Step 5:

[0557] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[0558] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0559] Step 6:

[0560] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[0561] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0562] Step 7:

[0563] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[0564] Example: A shelter manager uses a terminal to input, "Current number of evacuees: 600, water shortage."

[0565] Step 8:

[0566] The terminal transmits the input information to the server.

[0567] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0568] Step 9:

[0569] The server updates the database based on the latest information sent from the evacuation center.

[0570] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0571] Step 10:

[0572] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0573] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0574] Step 11:

[0575] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0576] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0577] This series of processes allows us to quickly grasp the situation at evacuation centers in the event of an earthquake and effectively provide necessary relief supplies.

[0578] Example 1

[0579] 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."

[0580] During an earthquake, it is difficult to quickly and accurately grasp the situation at evacuation centers and effectively provide the necessary relief supplies. In particular, when there are large fluctuations in the communication environment and the flow of population, or when it is difficult to predict the number of evacuees, it is difficult to make an appropriate plan for the supply of supplies based on that, and relief activities may be delayed.

[0581] 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.

[0582] In this invention, the server includes means for collecting moving population data and communication environment data from communication service providers, means for standardizing the collected data and inputting it into an artificial intelligence model, and means for predicting the number of evacuees at each evacuation shelter using the artificial intelligence model. This makes it possible to accurately predict the number of evacuees in real time based on the moving population data and communication environment data in the event of an earthquake, and to quickly and appropriately supply necessary relief supplies.

[0583] "Communication service providers" is a general term for telecommunications carriers and internet service providers that provide floating population data and communication environment data.

[0584] "Floating population data" is information on the movement of population and the number of people within a specific area.

[0585] "Communication environment data" is information related to the communication usage status and line congestion within a specific area.

[0586] A "server" is a computer system for collecting, processing, and performing various calculations on data.

[0587] An "artificial intelligence model" is software that includes machine learning algorithms to analyze collected data and make predictions and estimates.

[0588] A "terminal" is a device such as a smartphone or tablet that is used by shelter managers to input local information and send it to a server.

[0589] "Prediction methods" are methods or algorithms for predicting the number of evacuees at each shelter using an artificial intelligence model based on collected data.

[0590] "Calculation methods" are methods or algorithms for calculating the amount of relief supplies needed based on the forecast results.

[0591] "Inventory confirmation means" refers to a method or system for confirming the inventory status of supplies to be delivered to each evacuation shelter after estimating the required amount of relief supplies.

[0592] The "delivery plan creation means" refers to a method or algorithm that works in conjunction with a logistics company system to automatically generate an efficient material delivery plan after inventory confirmation.

[0593] "Database update means" refers to a method or system for keeping the database up to date based on information sent from evacuation shelters.

[0594] A "supply adjustment means" is a method or system for adjusting the additional supply of needed relief supplies based on updated data.

[0595] The system based on this invention is designed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively provide the necessary relief supplies. This system functions in cooperation with the server, terminals, and users.

[0596] First, the server collects data on the population flow and communication environment from communication service providers. To do this, it uses APIs provided by communication carriers and internet service providers. For example, it obtains data in real time such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[0597] The server then preprocesses the collected data and converts it into a format that can be input into the AI ​​model. Specifically, it standardizes the data using calibration data. This reduces data variability and improves the accuracy of analysis by the AI ​​model.

[0598] The collected and preprocessed data is input into a generative AI model on the server. This model has previously learned data from past earthquakes, and is able to predict with high accuracy the number of evacuees at each evacuation shelter. An example of a prompt sentence is: "Use part of the input data and parameters as the prompt sentence to input into the generative AI model. Example: Please calculate the predicted number of evacuees at shelter A in Tokyo."

[0599] Based on the prediction results, the server estimates the amount of relief supplies needed for each shelter. For example, if the predicted number of evacuees at shelter A is 500, it estimates that 500 liters of water, 500 meals, and 500 blankets will be needed. Specific relief supplies such as water, food, medicine, and blankets are also taken into account when calculating the amount of supplies needed.

[0600] Based on the estimated results, the server accesses the local government's stockpile database and checks the stock status of necessary supplies. Specifically, it verifies that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0601] After completing the inventory check, the server connects with the logistics company's system to automatically generate a delivery plan for supplies. This creates an efficient delivery schedule, such as "send supplies from Warehouse X to Evacuation Center A using one truck."

[0602] Meanwhile, the shelter manager uses a terminal to input the number of evacuees and the status of supplies on site. This information is immediately sent to the server and the database is updated in real time. For example, if the shelter manager inputs "The current number of evacuees is 600, and there is a water shortage," this is sent to the server.

[0603] Finally, the server updates the database based on the transmitted information and recalculates the amount of supplies needed. As a result, it recalculates that "an additional 100 liters of water and 100 meals are needed," and instructs the logistics company to supply additional supplies. This makes it possible to efficiently and accurately grasp the situation at evacuation centers even in the event of an earthquake, and to quickly provide the necessary relief supplies.

[0604] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0605] Step 1:

[0606] The server collects floating population data and communication environment data from communication service providers.

[0607] Input: Uses APIs provided by telecommunications carriers or internet service providers.

[0608] Data processing: Obtain demographic information and communication usage status for each region in real time.

[0609] Output: Save the collected data on the server.

[0610] Specific operation: The server calls the API and obtains data such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[0611] Step 2:

[0612] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0613] Input: Raw data collected in step 1.

[0614] Data processing: Standardize using calibration data and convert into a format suitable for AI models.

[0615] Output: Standardized data.

[0616] Specific operation: The server performs processing such as "normalizing population data by standard deviation" to reduce the variability of the data.

[0617] Step 3:

[0618] The server uses the generated AI model to predict the number of evacuees at each shelter.

[0619] Input: The preprocessed data from step 2.

[0620] Data calculation: Using neural network model.

[0621] Output: Predicted number of evacuees.

[0622] Specific operation: The server inputs data into the AI ​​model along with the prompt "Please calculate the number of evacuees predicted for shelter A in Tokyo," and obtains a result such as "500 evacuees are predicted for shelter A."

[0623] Step 4:

[0624] Based on the prediction results, the server estimates the amount of relief supplies needed.

[0625] Input: Prediction results from step 3.

[0626] Data calculation: Calculation based on standard consumption of relief supplies.

[0627] Output: The amount of supplies needed.

[0628] Specific operation: The server calculates, "There are 500 evacuees in shelter A, so 500 liters of water, 500 meals, and 500 blankets are needed."

[0629] Step 5:

[0630] The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[0631] Input: Estimated amount of relief supplies.

[0632] Data processing: Querying the stockpile database.

[0633] Output: Stock availability.

[0634] Specific operation: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0635] Step 6:

[0636] The server works in conjunction with the logistics company's system to create a delivery plan for supplies.

[0637] Input: Stock status and estimated amount of relief supplies.

[0638] Data calculation: Delivery route optimization algorithm.

[0639] Output: Delivery schedule.

[0640] Specific operation: The server generates a delivery schedule that "sends supplies from warehouse X to shelter A in one truck."

[0641] Step 7:

[0642] The terminals will be used by shelter managers to input the number of evacuees and the status of supplies on site.

[0643] Input: Local information entered by shelter manager.

[0644] Data processing: Input via application.

[0645] Output: The information entered.

[0646] Specific operation: The shelter manager enters "Current number of evacuees is 600, water shortage" into the terminal.

[0647] Step 8:

[0648] The terminal transmits the input information to the server.

[0649] Input: Local information entered.

[0650] Data processing: Communication from the terminal to the server.

[0651] Output: Information sent to the server.

[0652] Specific operation: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0653] Step 9:

[0654] The server updates the database based on the latest information and recalculates the amount of supplies needed.

[0655] Input: The local information sent to the server.

[0656] Data calculation: Recalculation algorithm.

[0657] Output: Recalculated amount of aid supplies.

[0658] Specific operation: The server updates the database with "The latest number of evacuees at shelter A is 600, and there is a water shortage," and recalculates that "An additional 100 liters of water and 100 meals are needed."

[0659] Step 10:

[0660] The server sends a delivery instruction for the additional supplies to the logistics company.

[0661] Input: Recalculated amount of aid.

[0662] Data processing: Update shipping schedule.

[0663] Output: The new delivery schedule.

[0664] Specific operation: The server generates a new delivery schedule such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A" and sends instructions to the logistics company.

[0665] (Application example 1)

[0666] 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."

[0667] During an earthquake, it is important to quickly and accurately grasp the situation at evacuation centers and effectively supply the necessary relief supplies. However, due to communication environment problems and sudden increases and decreases in the number of evacuees, it is difficult to accurately grasp the situation on site, which can lead to problems with delays in the timely delivery of relief supplies. In addition, insufficient coordination with logistics companies can make it difficult to distribute supplies appropriately.

[0668] 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.

[0669] In this invention, the server includes means for collecting communication environment data and mobile population data immediately before the earthquake, means for estimating the number of evacuees at each evacuation shelter using an artificial intelligence model based on the collected data, means for calculating the amount of relief supplies needed based on the estimate results and issuing instructions for the preparation and delivery of supplies, means for collecting information on the local situation after communication is restored, updating the data, recalculating the needed supplies, and issuing instructions for additional supplies, means for automatically and dynamically generating a delivery schedule for needed supplies and sending instructions to logistics companies, and means for quickly sending the latest information via a terminal used by the evacuation shelter manager. This makes it possible to efficiently and accurately grasp the situation at evacuation shelters and provide needed supplies even during communication disruptions.

[0670] "Communication environment data immediately before the earthquake" is data obtained from communication carriers and internet service providers that indicates the communication conditions immediately before the earthquake occurred.

[0671] "Floating population data" is data that shows the movement and distribution of population in a specific area over a certain period of time.

[0672] An "artificial intelligence model" is a statistical model that uses machine learning and deep learning to learn from past data and predict future situations.

[0673] "Means for estimating the number of evacuees" refers to techniques and methods for predicting the number of evacuees at each evacuation shelter using an artificial intelligence model based on collected data.

[0674] "Means for calculating the amount of necessary relief supplies" refers to techniques and methods for calculating the required amount of supplies such as water, food, medicine, blankets, health supplies, and consumables based on the predicted number of evacuees.

[0675] "Means for directing the preparation and delivery of supplies" refers to the techniques and methods for preparing needed relief supplies and planning and directing their delivery to each evacuation shelter.

[0676] "Means for collecting on-site information and updating data after communications are restored" refers to the technology and methods for collecting the latest information from evacuation centers and updating the database based on that information when communications are restored after a disaster occurs.

[0677] "Means for ordering additional supplies" refers to techniques and methods for recalculating the required supplies based on updated data and issuing instructions if additional supplies are required.

[0678] "Means for automatically generating dynamic delivery schedules for necessary supplies" refers to technologies and methods for automatically creating optimal supply delivery schedules in real time using AI models and algorithms.

[0679] The "means for sending instructions to the logistics company" refers to a technique or method for notifying the logistics company of the generated delivery schedule and the need for additional supplies, and for instructing them on how to respond.

[0680] "Devices used by evacuation shelter managers" are devices such as smartphones and tablets that evacuation shelter managers use to enter information such as local conditions and necessary supplies and send it to a server.

[0681] The system based on this invention is constructed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively supply the necessary relief supplies. The system operates in cooperation with the server, terminals, and users, and performs processing in the following steps.

[0682] System Configuration

[0683] 1. Server

[0684] Hardware: High-performance web servers (e.g., Amazon Web Services (AWS), Microsoft Azure)

[0685] Software: Communication API, TensorFlow, Requests library

[0686] Functions: Data collection, data standardization, predictions using AI models, and sending instructions to logistics companies

[0687] 2. Terminal

[0688] Hardware: Smartphones, tablets (e.g. Android, iOS)

[0689] Function: The shelter manager inputs local information and sends it to the server.

[0690] 3. Users

[0691] Role: Evacuation center manager, inputting the number of evacuees and the status of supplies via terminal

[0692] Operation flow

[0693] Data collection

[0694] The server collects data on the communication environment and population movement immediately before the earthquake from telecommunications carriers and internet service providers. The collected data is standardized into the required data format.

[0695] Prediction by AI model

[0696] The standardized data is input into an artificial intelligence model (e.g., a neural network using TensorFlow) to predict the number of evacuees at each shelter in real time. For example, the server calculates that "the predicted number of evacuees at shelter A immediately after the earthquake is 500 people."

[0697] Estimating supplies and preparing for delivery

[0698] Based on the prediction results, the server calculates the amount of relief supplies needed and automatically generates a dynamic delivery schedule. The calculation includes specific relief supplies such as water, food, medicine, blankets, health supplies, and consumables. For example, it calculates that "500 evacuees need 500 liters of water, 500 meals, and 500 blankets." The calculated results are sent as instructions to logistics companies.

[0699] The server generates a specific delivery schedule, such as "send supplies from warehouse X to shelter A in one truck," and sends instructions.

[0700] Gathering information at evacuation shelters

[0701] The shelter manager uses a device (smartphone or tablet) to input the number of evacuees and the status of supplies. For example, if the manager inputs "the current number of evacuees is 600, and there is a water shortage," the information is immediately sent to the server.

[0702] Data updates and additional supplies

[0703] The server updates the database based on the latest information received and recalculates the amount of supplies needed. If the recalculation shows that additional supplies are needed, it quickly issues instructions to logistics companies to provide the additional supplies. For example, it may recalculate the amount to "an additional 100 liters of water and 100 meals are needed," and immediately send delivery instructions.

[0704] Specific examples

[0705] At shelter A, the server collects the latest local information and predicts the number of evacuees. Based on these results, it dynamically calculates the amount of relief supplies needed and automatically generates a truck delivery schedule. The shelter manager uses a smartphone to instantly send the actual number of evacuees and the status of supplies to the server, which then updates the database with this information and draws up a plan for additional supplies.

[0706] Prompt Sentence Examples

[0707] "Collect the latest population and communication data for shelter A from the server, and use an AI model to predict the number of evacuees. Based on the prediction, calculate the necessary relief supplies and generate Python code to schedule the delivery of supplies to shelter A."

[0708] By operating in this way, the system can efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[0709] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0710] Step 1: Data collection

[0711] The server collects real-time data on the communication environment immediately before the earthquake and data on the local population flow from telecommunications carriers and internet service providers via API. It uses API endpoints as input and obtains the collected data as output. The server saves the collected data in JSON format or other formats.

[0712] Step 2: Data Standardization

[0713] The server standardizes the collected data before applying it to the AI ​​model. Specifically, it fills in any imperfections in the data, removes outliers, and converts it into the required format. It uses the collected raw data as input and obtains standardized data as output. The server then adapts this data to the input format of the AI ​​model.

[0714] Step 3: Predict the number of evacuees

[0715] The server inputs the standardized data into an artificial intelligence model to predict the number of evacuees at each shelter. Using the standardized data as input, the server obtains the predicted number of evacuees as output. Specifically, the neural network model performs the calculations using machine learning libraries such as TensorFlow.

[0716] Step 4: Calculate supply needs

[0717] The server calculates the amount of supplies needed based on the predicted number of evacuees. It uses the predicted number of evacuees as input and gets a detailed list of needed supplies as output. For example, it calculates "500 evacuees need 500 liters of water, 500 meals, and 500 blankets."

[0718] Step 5: Auto-generate delivery schedules

[0719] The server automatically generates a delivery schedule for logistics companies based on the relief supply list. It uses the supply list as input and obtains a specific delivery plan as output. For example, the server generates a schedule such as "Send supplies from Warehouse X to Evacuation Center A by one truck."

[0720] Step 6: Send instructions to logistics provider

[0721] The server sends the generated delivery schedule as instructions to the logistics company. It uses the automatically generated delivery schedule as input and verifies that the instructions were sent correctly as output. The server does this via HTTP requests, etc.

[0722] Step 7: Gather local information

[0723] The terminal is used by the shelter manager to input the latest local situation. For example, the shelter manager might use the terminal to input "the current number of evacuees is 600, and there is a water shortage." The information obtained on-site is used as input, and that information is sent to the server as output.

[0724] Step 8: Update the Database

[0725] The server updates the database based on the latest information sent from the terminal. It uses the data sent from the field as input and obtains the updated database as output. The server then updates the database to show that "the latest number of evacuees at shelter A is 600, and there is a water shortage."

[0726] Step 9: Recalculate and order additional supplies

[0727] The server recalculates the amount of supplies needed based on the updated database and issues instructions if additional supplies are required. It uses the latest database information as input and obtains a recalculated list of supplies as output. For example, it may recalculate, "We need an additional 100 liters of water and 100 meals of food," and send additional delivery instructions to the logistics company.

[0728] By implementing each of the above steps, we will create a system that will enable efficient and accurate assessment of the situation at evacuation centers and the supply of necessary supplies, even if communications and power supplies are cut off during an earthquake.

[0729] 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.

[0730] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply necessary relief supplies. This system functions in cooperation with the server, terminals, and users, and by combining it with an emotion engine, it also provides psychological support to evacuees.

[0731] Data collection

[0732] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[0733] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[0734] AI estimation

[0735] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0736] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[0737] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0738] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[0739] Estimating necessary supplies and preparing for delivery

[0740] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[0741] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0742] 2. The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[0743] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0744] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[0745] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0746] Gathering information at evacuation shelters

[0747] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[0748] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[0749] 2. The terminal sends the entered information to the server.

[0750] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0751] Data updates and supply adjustments

[0752] 1. The server updates the database based on the latest information sent from the evacuation center.

[0753] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0754] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0755] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0756] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0757] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0758] Emotion engine integration

[0759] 1. The device collects facial expressions, voice, and text data from shelter managers and evacuees and sends it to the emotion engine.

[0760] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[0761] 2. The emotion engine analyzes the collected data and recognizes the user's emotional state.

[0762] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[0763] 3. The emotion engine sends the recognized emotion data to the server.

[0764] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[0765] 4. The server will use the emotional data to direct additional psychological support or special supplies.

[0766] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[0767] In this way, the system operates in cooperation with the server, terminals, users, and emotion engine, making it possible to efficiently and accurately grasp the situation at evacuation centers, provide necessary supplies, and even provide psychological care for evacuees, even if communications and power supplies are cut off during an earthquake.

[0768] The processing flow will be explained below.

[0769] Step 1:

[0770] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[0771] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[0772] Step 2:

[0773] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0774] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[0775] Step 3:

[0776] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0777] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[0778] Step 4:

[0779] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[0780] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0781] Step 5:

[0782] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[0783] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0784] Step 6:

[0785] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[0786] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0787] Step 7:

[0788] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[0789] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[0790] Step 8:

[0791] The terminal transmits the input information to the server.

[0792] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[0793] Step 9:

[0794] The server updates the database based on the latest information sent from the evacuation center.

[0795] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[0796] Step 10:

[0797] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[0798] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[0799] Step 11:

[0800] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[0801] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[0802] Step 12:

[0803] The device collects facial expressions, voice, and text data from shelter managers and evacuees, and sends it to the emotion engine.

[0804] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[0805] Step 13:

[0806] The emotion engine analyzes the collected data and recognizes the user's emotional state.

[0807] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[0808] Step 14:

[0809] The emotion engine sends the recognized emotion data to the server.

[0810] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[0811] Step 15:

[0812] The server uses the emotional data to direct additional psychological support or special supplies.

[0813] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[0814] Example 2

[0815] 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."

[0816] There is a need for a system that can quickly and accurately grasp the situation at evacuation centers during earthquakes, effectively provide necessary relief supplies, and comprehensively provide psychological support to evacuees. Conventional systems do not collect and update local information about evacuation centers in real time, which can lead to delays in recalculating needed supplies and providing additional supplies, and insufficient psychological support for evacuees. Therefore, a system is needed that can improve the efficiency of evacuation center management and the safety and psychological care of evacuees.

[0817] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication environment data and floating population data, means for normalizing and imputing the collected data and inputting it into an AI model, means for predicting the number of evacuees at each evacuation shelter using the AI ​​model, means for calculating the amount of relief supplies needed based on the prediction results and instructing the preparation and delivery of supplies, means for the evacuation shelter manager to send local information to the server using a terminal, means for updating the database based on the local information, recalculating the amount of needed supplies, and instructing the additional supply, means for collecting emotional data of evacuees via the terminal and sending it to the emotion engine, and means for instructing psychological support and the supply of special supplies based on the emotional data analyzed by the emotion engine. This enables efficient and accurate assessment of the situation at evacuation shelters, the supply of necessary supplies, and psychological care for evacuees during an earthquake disaster.

[0818] "Communication environment data" refers to information such as communication network usage status, connection status, and communication speed obtained from communication carriers and Internet service providers.

[0819] "Floating population data" is statistical information that shows the movement patterns and number of people in a specific area, and is mainly calculated from location information of communication devices.

[0820] An "artificial intelligence model" is a calculation algorithm that learns from past data and predicts new situations, and in this invention it is used to predict the number of evacuees and the amount of necessary supplies.

[0821] "Normalization" is a process in data processing that converts collected raw data into a unified format, and is a means of improving data quality.

[0822] "Gap imputation" is the process of filling in missing data with appropriate values ​​in order to build a complete dataset.

[0823] "Terminal" refers to a device such as a smartphone or tablet used by shelter managers and other users, and is used to input and transmit information.

[0824] An "emotion engine" is a software system that recognizes a user's emotional state by analyzing collected data such as facial expressions, voice, and text.

[0825] "Evacuation forecasting" is the process of using artificial intelligence models to estimate the number of people who will evacuate to a particular shelter in the event of a disaster.

[0826] "Relief supplies" refer to basic daily necessities and services that evacuees need in the event of a disaster, such as water, food, medicine, blankets, and recreational items.

[0827] "Psychological support" refers to counseling and other support activities aimed at reducing the psychological distress and stress of evacuees.

[0828] "Database updating" is the process of updating existing data to reflect the latest information, and is done to keep information accurate in real time.

[0829] "Delivery instructions" are instructions given to deliver supplies to where they are needed, and refer to the act of providing logistics companies with specific delivery plans and schedules.

[0830] "Emotion data" is information indicating emotions extracted from the user's facial expressions, voice, text, etc., and is analyzed by the emotion engine.

[0831] The system based on this invention involves the cooperation of a server, terminals, users, and an emotion engine in order to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply the necessary relief supplies. This system is configured as follows:

[0832] Data collection

[0833] The server collects data on the current population and communication environment from telecommunications carriers and internet service providers (ISPs). It uses APIs to obtain data in real time from each telecommunications carrier and ISP. For example, the server uses APIs to collect demographic information from telecommunications carriers.

[0834] Data preprocessing and AI calculations

[0835] The collected data is normalized on the server and missing data is supplemented. The formatted data is then input into an artificial intelligence model. This artificial intelligence model is a neural network model that has been trained based on data from past earthquakes. This model is used to predict the number of evacuees at each evacuation shelter. For example, the server outputs a calculated result such as "The predicted number of evacuees at shelter A is 500."

[0836] Estimating necessary supplies and preparing for delivery

[0837] Based on the estimates, the server calculates the amount of relief supplies needed for each evacuation center. This includes water, food, medicine, blankets, and recreational items. For example, the server might calculate that 500 evacuees need 500 liters of water, 500 meals, and 500 blankets. It then accesses the local government's stockpile database to check the inventory status of the necessary supplies. It then connects to the logistics company's system to automatically generate a specific delivery schedule and issue instructions to the logistics company.

[0838] Gathering information at evacuation shelters

[0839] The terminal allows the shelter manager to input the number of evacuees and the current status of supplies via a smartphone or tablet. For example, the shelter manager might input "the current number of evacuees is 600, and there is a water shortage" into the terminal, and this information is then sent to the server.

[0840] Data updates and supply adjustments

[0841] The server updates the database based on the latest information sent from the evacuation center. This allows it to recalculate the amount of supplies needed based on the latest situation and calculate the amount of additional supplies that should be provided. For example, the server may recalculate that an additional 100 liters of water and 100 meals are needed. Based on the recalculated results, it issues instructions to the logistics company to deliver the additional supplies.

[0842] Emotion engine integration

[0843] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state. For example, the emotion engine may recognize that "evacuee A is in a state of stress, while evacuee B is in a state of relief." The analysis results are sent to the server, which then issues instructions for additional psychological support or the provision of special supplies based on the emotional data.

[0844] (Example of a prompt for a generative AI model):

[0845] "Use this system to understand the situation at evacuation centers, calculate supplies needed, plan distribution, and conduct simulations to provide emotional support."

[0846] In this way, by linking all the elements together, the system will be able to efficiently and accurately grasp the situation at evacuation centers during earthquakes, provide necessary supplies, and even provide psychological care for evacuees.

[0847] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0848] Step 1:

[0849] Data collection

[0850] The server collects population mobility data and communication environment data from telecommunications carriers and Internet service providers (ISPs) through APIs. It uses API endpoints and parameters as input and obtains real-time demographic and communication data as output. For example, the server performs the following operation: "call NTT Docomo's API and obtain demographic information."

[0851] Step 2:

[0852] Data Preprocessing

[0853] The server normalizes the collected data and fills in missing data. It uses floating population data and communication environment data as input, and obtains a normalized dataset as output. Specific operations include filling in missing values ​​based on the preceding and following data, and standardizing the data format. For example, it performs the process of "filling in zeros in the collected data and converting it into a standard format."

[0854] Step 3:

[0855] Prediction of the number of evacuees

[0856] The server uses the preprocessed data to input into an AI model to predict the number of evacuees. The normalized dataset is used as input, and the output is the predicted number of evacuees at each evacuation shelter. The AI ​​model is a neural network trained based on data from past earthquakes. For example, the operation is as follows: "Enter data into the AI ​​model and predict the number of evacuees at shelter A to be 500."

[0857] Step 4:

[0858] Estimated cost of relief supplies

[0859] The server calculates the amount of relief supplies needed at each evacuation center based on the prediction results. It uses the predicted number of evacuees as input and obtains the required amount of supplies as output. Specifically, it calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[0860] Step 5:

[0861] Check stockpile data

[0862] The server accesses the local government's stockpile database and checks the stock status of necessary supplies. It uses the list of supplies and the number of evacuees as input, and obtains stock information as output. For example, it checks whether "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0863] Step 6:

[0864] Generate a delivery plan

[0865] The server works in conjunction with the logistics company's system to automatically generate a delivery plan for supplies. It uses inventory information and a list of necessary supplies as input, and obtains a delivery schedule as output. For example, it performs an operation such as "creating a plan to deliver supplies from Warehouse X to Evacuation Center A using one truck."

[0866] Step 7:

[0867] Gathering local information

[0868] The terminal allows the shelter manager to input the number of evacuees and the status of supplies on site via a smartphone or tablet. The latest local information is used as input, and updated information is output and sent to the server. For example, the operation might be, "The shelter manager inputs into the terminal that the current number of evacuees is 600 and there is a water shortage, and then sends the information to the server."

[0869] Step 8:

[0870] Database Update

[0871] The server updates the database based on the latest information sent from the evacuation center. It uses the latest data on the number of evacuees and the status of supplies as input, and obtains the updated database status as output. For example, it performs an operation such as "reflect the latest information from evacuation center A in the database."

[0872] Step 9:

[0873] Supply Recalculation

[0874] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be provided. It uses the updated number of evacuees and supply status data as input, and obtains a list of additional supplies as output. For example, it performs an operation such as "recalculating that an additional 100 liters of water and 100 meals are needed."

[0875] Step 10:

[0876] Delivery instructions for additional supplies

[0877] The server then issues instructions to the logistics company to deliver additional supplies based on the recalculation results. It uses the list of additional supplies and delivery destination information as input, and obtains a new delivery schedule as output. For example, it performs an operation such as "instructing Warehouse Y to deliver an additional 100 liters of water and 100 meals to Evacuation Center A."

[0878] Step 11:

[0879] Collecting Emotional Data

[0880] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. Data photographed or recorded by the device is used as input, and emotion data is output and sent to the emotion engine. For example, the device performs an operation such as "taking a photo of the evacuees' facial expressions with a smartphone camera and sending it to the emotion engine."

[0881] Step 12:

[0882] Emotional Data Analysis

[0883] The emotion engine analyzes the collected data and recognizes the user's emotional state. It uses facial expressions, voice, and text data as input and obtains the analysis results as output. For example, the emotion engine recognizes that evacuee A is in a stressed state and evacuee B is in a relieved state.

[0884] Step 13:

[0885] Sending emotional data

[0886] The emotion engine sends the recognized emotion data to the server. It uses the analyzed emotional state data as input and gets a report that is sent to the server as output. For example, the emotion engine reports to the server that most of the evacuees at shelter A are in a stressed state.

[0887] Step 14:

[0888] Psychological support instructions

[0889] The server then uses the emotional data to provide additional psychological support and special supplies. It uses the emotional state data sent from the emotion engine as input and obtains a psychological support plan and a supply list as output. For example, it can perform an action such as "dispatch a psychological counselor to shelter A and provide recreational supplies to relieve stress."

[0890] (Application example 2)

[0891] 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."

[0892] In managing evacuation shelters after a disaster, it is extremely important to quickly and accurately grasp the situation of evacuees and provide appropriate relief supplies. However, the current system makes it difficult to grasp the psychological state of evacuees, which results in issues such as inadequate psychological support for evacuees and insufficient maintenance of order and safety within the shelter.

[0893] 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.

[0894] In this invention, the server includes means for collecting communication environment data and population mobility data immediately before the earthquake, means for using an AI model to estimate the number of evacuees at each evacuation shelter based on the collected data, means for calculating the amount of relief supplies needed based on the estimate and issuing instructions for the preparation and delivery of supplies, means for collecting on-site conditions after communication is restored, updating the data, recalculating the needed supplies, and issuing instructions for additional supplies, means for collecting video data within the evacuation shelter and recognizing the emotional state of the evacuees, means for issuing instructions for psychological support and the delivery of special supplies based on the recognized emotional data, and means for monitoring the situation in real time and implementing security measures to prevent crime and maintain order. This allows for comprehensive management of the situation within the evacuation shelter, making it possible to efficiently not only provide supplies but also provide psychological care and ensure safety.

[0895] "Communication environment data" is information that indicates the state and usage of the communication network at the time of the earthquake.

[0896] "Floating population data" is information that indicates the movement of people and population density within a specific area.

[0897] An "artificial intelligence model" is an algorithm that is trained on past data to make predictions or classifications based on specific inputs.

[0898] "Number of evacuees" refers to the number of people staying in evacuation shelters.

[0899] "Relief supplies" are supplies such as water, food, medicine, and blankets that evacuees need in the event of a disaster.

[0900] "Preparation and delivery of supplies" refers to all activities involved in preparing necessary relief supplies in appropriate locations and delivering them to evacuation shelters.

[0901] "Local situation" refers to real-time information such as the current number of evacuees at evacuation centers and the shortage of supplies.

[0902] "Data updating" means reflecting newly obtained local information in the existing database.

[0903] "Additional supply" means the re-delivery of supplies to make up for any shortages that have already been made.

[0904] "Video data" refers to video information of evacuees and the inside of evacuation shelters obtained through cameras, etc.

[0905] "Emotional state" is information that indicates the psychological stability and stress level of evacuees.

[0906] "Psychological support" refers to providing care and support to evacuees to ensure their psychological well-being.

[0907] "Security measures" refer to surveillance and crime prevention measures to ensure safety within the shelter.

[0908] To implement this invention, it is necessary to build a system in which servers, terminals, and users work together. This system aims to streamline the operation of evacuation shelters in the event of an earthquake, and to comprehensively provide psychological support and security measures for evacuees.

[0909] Components

[0910] 1. Data Collection

[0911] The server collects real-time data on the population flow and communication environment from telecommunications carriers and internet service providers (ISPs) via APIs. For example, data obtained through APIs includes communication usage status and regional demographics.

[0912] Example prompt sentence:

[0913] text

[0914] curl -X GET "API_URL" -H ​​"accept: application / json"

[0915] 2. AI estimation

[0916] The server preprocesses the collected data and inputs it into an artificial intelligence model. After normalizing the data and filling in missing data, the number of evacuees at each shelter is predicted based on the neural network model.

[0917] The collected data is normalized using tools such as MinMaxScaler, and then the number of evacuees is estimated using a neural network model built with TensorFlow and Keras.

[0918] 3. Estimate the amount of supplies needed and prepare for delivery

[0919] Based on the estimates, the server calculates the amount of relief supplies (e.g., water, food, medicine, blankets) needed at each evacuation center. It also checks inventory and automatically generates delivery schedules.

[0920] Specifically, estimates include "500 evacuees will need 500 liters of water, 500 meals, 50 sets of medicine, and 500 blankets."

[0921] 4. Gathering information at evacuation shelters

[0922] The terminals are smartphones or tablets used by shelter managers, and they input the number of evacuees and the status of supplies on site. This information is sent to a server and the database is updated.

[0923] For example, a shelter manager might enter "Current number of evacuees: 600, water shortage" into a terminal and update the information on the server.

[0924] 5. Data updates and supply adjustments

[0925] The server recalculates the amount of supplies needed based on the latest data, calculates the amount of additional supplies that should be supplied, and issues instructions to the logistics company to deliver the additional supplies.

[0926] As a specific example, instructions may be given such as "Deliver an additional 100 liters of water and 100 meals from the warehouse to evacuation centers."

[0927] 6. Emotion engine integration

[0928] The device collects facial expressions, voice, and text data from shelter managers and evacuees, and sends it to an emotion engine, which analyzes this data and recognizes the emotional state of the evacuees.

[0929] For example, a shelter manager can take pictures of evacuees' facial expressions with a smartphone camera and use the emotion engine to recognize that "evacuee A is in a stressed state, while evacuee B is in a relaxed state."

[0930] Example prompt sentence:

[0931] text

[0932] Analyze the emotions of individuals in the video feed from "http: / / camera_feed_url". Identify and report back on the number of individuals showing signs of stress versus those who appear calm.

[0933] 7. Security Measures

[0934] The server collects video data from inside the evacuation center and monitors it in real time to ensure safety. It also uses facial recognition and object detection technologies to implement measures to prevent crime and maintain order.

[0935] For example, facial recognition technology can be used to monitor specific individuals entering and leaving evacuation shelters and detect suspicious individuals.

[0936] Specific examples

[0937] As a concrete example of the system, immediately after an earthquake, communication environment data and population mobility data are collected, and the number of evacuees at each evacuation center is predicted using an AI model. The system then estimates the amount of relief supplies needed and issues delivery instructions to logistics companies. Furthermore, by repeatedly collecting and updating local information about evacuation centers, the system ensures efficient supply of supplies. It also recognizes emotional states, provides psychological support, and implements security measures to ensure safety and security within the evacuation center.

[0938] This will enable comprehensive management of the situation within the shelter, and will make it possible to efficiently provide not only necessary supplies but also psychological care and ensure safety.

[0939] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0940] Step 1:

[0941] The server collects real-time population flow data and communication environment data from telecommunications carriers and Internet service providers (ISPs) via APIs. Using data obtained from API endpoints as input, the data is sent to the server and stored in a database. A specific example would be information such as "demographic data from telecommunications carrier A."

[0942] Step 2:

[0943] The server preprocesses the collected data and inputs it into an artificial intelligence model. Preprocessing includes normalizing the data and filling in missing data. For example, MinMaxScaler is used to scale the data to a range of 0 to 1, and missing data is filled in with the historical average value. The preprocessed data is then input into the artificial intelligence model (a model trained with TensorFlow or Keras).

[0944] Step 3:

[0945] The server uses an artificial intelligence model to predict the number of evacuees at each shelter. It uses preprocessed data as input and obtains the predicted number of evacuees at each shelter as output. For example, it outputs a specific estimated result such as "The predicted number of evacuees at shelter A is 500 people."

[0946] Step 4:

[0947] The server calculates the amount of relief supplies needed based on the results of the calculation. It uses the predicted number of evacuees as input and obtains a list of necessary supplies as output. For example, the calculation results may be, "For 500 evacuees, 500 liters of water, 500 meals, and 500 blankets are needed."

[0948] Step 5:

[0949] The server accesses the local government's stockpile database and checks the stock status of necessary supplies. It uses a list of supplies as input and obtains the stock status as output. For example, the output might be "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[0950] Step 6:

[0951] The server works in conjunction with the logistics company's system to automatically generate a delivery plan for supplies. It uses inventory status and evacuation shelter location information as input, and obtains a specific delivery schedule as output. For example, it generates specific delivery instructions such as "Deliver supplies from Warehouse X to Evacuation Shelter A using one truck."

[0952] Step 7:

[0953] The terminal is a smartphone or tablet used by the shelter manager, and the number of evacuees and the status of supplies on site are input. The data reported by the shelter manager is used as input, and the latest number of evacuees and the status of supplies are obtained as output. For example, the latest information such as "the current number of evacuees is 600, and there is a water shortage" is input.

[0954] Step 8:

[0955] The terminal sends the input information to the server. The latest data entered by the shelter manager is used as input, and the information sent to the server is obtained as output. For example, the latest number of evacuees and information on shortages of supplies at shelter A are sent to the server.

[0956] Step 9:

[0957] The server updates the database based on the latest information sent from the evacuation center. The latest data received is used as input, and the updated database is obtained as output. For example, the database may be updated to show "The latest number of evacuees at evacuation center A is 600, and there is a water shortage."

[0958] Step 10:

[0959] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be provided. It uses the latest number of evacuees and information on shortages as input, and outputs a list of supplies that should be provided. For example, the recalculation result might be, "An additional 100 liters of water and 100 meals are needed."

[0960] Step 11:

[0961] Based on the recalculation results, the server issues delivery instructions to logistics companies to deliver additional supplies. Using the recalculation results as input, a specific delivery schedule is obtained as output. For example, a new delivery instruction may be generated such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A."

[0962] Step 12:

[0963] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. The facial expressions of the evacuees are used as input, and the data sent to the emotion engine is obtained as output. As a specific example, the facial expressions of the evacuees are photographed with a smartphone camera, and then analyzed by the emotion engine.

[0964] Step 13:

[0965] The emotion engine analyzes the collected data and recognizes the user's emotional state. It uses the collected facial and voice data as input and obtains the recognition result of the emotional state as output. For example, it recognizes that "evacuee A is in a stressed state, and evacuee B is in a relieved state."

[0966] Step 14:

[0967] The emotion engine sends the recognized emotion data to the server. Using the recognized emotional state as input, the emotion data sent to the server is obtained as output. For example, a report may be made such as "Many of the evacuees at shelter A are in a state of stress."

[0968] Step 15:

[0969] The server then uses the emotional data to provide additional psychological support or special supplies. Using the recognized emotional data as input, the server can obtain specific support instructions as output. For example, measures such as "dispatch psychological counselors to shelter A" or "provide additional recreational supplies to relieve stress" may be implemented.

[0970] Step 16:

[0971] The server collects video data from inside the evacuation center and monitors it in real time to ensure safety. The video data is used as input, and the monitoring results for ensuring safety are obtained as output. For example, facial recognition technology can be used to identify suspicious individuals and issue a warning.

[0972] 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.

[0973] 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.

[0974] 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.

[0975] [Third embodiment]

[0976] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0977] 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.

[0978] 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).

[0979] 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.

[0980] 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.

[0981] 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).

[0982] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0983] 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.

[0984] 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.

[0985] 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.

[0986] 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.

[0987] 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."

[0988] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake disaster and to effectively supply necessary relief supplies.

[0989] This system functions in cooperation with the server, terminals, and users.

[0990] Data collection

[0991] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[0992] Example: The server uses APIs provided by each telecommunications carrier and ISP to obtain demographic information and communication usage status for each region in real time.

[0993] AI estimation

[0994] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[0995] Example: The server uses calibration data to standardize collected data and convert it into a format for the AI ​​model.

[0996] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[0997] Example: The server uses a trained neural network model to output results such as "The predicted number of evacuees at shelter A in Tokyo is 500."

[0998] Estimating necessary supplies and preparing for delivery

[0999] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[1000] Example: The server calculates that "500 evacuees require 500 liters of water, 500 meals, and 500 blankets."

[1001] 2. The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[1002] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1003] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[1004] Example: The server creates a delivery schedule such as "send one truckload of supplies from Warehouse X to Evacuation Center A."

[1005] Gathering information at evacuation shelters

[1006] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[1007] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[1008] 2. The terminal sends the entered information to the server.

[1009] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1010] Data updates and supply adjustments

[1011] 1. The server updates the database based on the latest information sent from the evacuation center.

[1012] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1013] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1014] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1015] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1016] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1017] In this way, the system operates in cooperation with servers, terminals, and users, making it possible to efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[1018] The processing flow will be explained below.

[1019] Step 1:

[1020] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[1021] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[1022] Step 2:

[1023] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1024] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[1025] Step 3:

[1026] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[1027] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[1028] Step 4:

[1029] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[1030] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[1031] Step 5:

[1032] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[1033] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1034] Step 6:

[1035] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[1036] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[1037] Step 7:

[1038] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[1039] Example: A shelter manager uses a terminal to input, "Current number of evacuees: 600, water shortage."

[1040] Step 8:

[1041] The terminal transmits the input information to the server.

[1042] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1043] Step 9:

[1044] The server updates the database based on the latest information sent from the evacuation center.

[1045] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1046] Step 10:

[1047] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1048] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1049] Step 11:

[1050] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1051] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1052] This series of processes allows us to quickly grasp the situation at evacuation centers in the event of an earthquake and effectively provide necessary relief supplies.

[1053] Example 1

[1054] 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."

[1055] During an earthquake, it is difficult to quickly and accurately grasp the situation at evacuation centers and effectively provide the necessary relief supplies. In particular, when there are large fluctuations in the communication environment and the flow of population, or when it is difficult to predict the number of evacuees, it is difficult to make an appropriate plan for the supply of supplies based on that, and relief activities may be delayed.

[1056] 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.

[1057] In this invention, the server includes means for collecting moving population data and communication environment data from communication service providers, means for standardizing the collected data and inputting it into an artificial intelligence model, and means for predicting the number of evacuees at each evacuation shelter using the artificial intelligence model. This makes it possible to accurately predict the number of evacuees in real time based on the moving population data and communication environment data in the event of an earthquake, and to quickly and appropriately supply necessary relief supplies.

[1058] "Communication service providers" is a general term for telecommunications carriers and internet service providers that provide floating population data and communication environment data.

[1059] "Floating population data" is information on the movement of population and the number of people within a specific area.

[1060] "Communication environment data" is information related to the communication usage status and line congestion within a specific area.

[1061] A "server" is a computer system for collecting, processing, and performing various calculations on data.

[1062] An "artificial intelligence model" is software that includes machine learning algorithms to analyze collected data and make predictions and estimates.

[1063] A "terminal" is a device such as a smartphone or tablet that is used by shelter managers to input local information and send it to a server.

[1064] "Prediction methods" are methods or algorithms for predicting the number of evacuees at each shelter using an artificial intelligence model based on collected data.

[1065] "Calculation methods" are methods or algorithms for calculating the amount of relief supplies needed based on the forecast results.

[1066] "Inventory confirmation means" refers to a method or system for confirming the inventory status of supplies to be delivered to each evacuation shelter after estimating the required amount of relief supplies.

[1067] The "delivery plan creation means" refers to a method or algorithm that works in conjunction with a logistics company system to automatically generate an efficient material delivery plan after inventory confirmation.

[1068] "Database update means" refers to a method or system for keeping the database up to date based on information sent from evacuation shelters.

[1069] A "supply adjustment means" is a method or system for adjusting the additional supply of needed relief supplies based on updated data.

[1070] The system based on this invention is designed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively provide the necessary relief supplies. This system functions in cooperation with the server, terminals, and users.

[1071] First, the server collects data on the population flow and communication environment from communication service providers. To do this, it uses APIs provided by communication carriers and internet service providers. For example, it obtains data in real time such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[1072] The server then preprocesses the collected data and converts it into a format that can be input into the AI ​​model. Specifically, it standardizes the data using calibration data. This reduces data variability and improves the accuracy of analysis by the AI ​​model.

[1073] The collected and preprocessed data is input into a generative AI model on the server. This model has previously learned data from past earthquakes, and is able to predict with high accuracy the number of evacuees at each evacuation shelter. An example of a prompt sentence is: "Use part of the input data and parameters as the prompt sentence to input into the generative AI model. Example: Please calculate the predicted number of evacuees at shelter A in Tokyo."

[1074] Based on the prediction results, the server estimates the amount of relief supplies needed for each shelter. For example, if the predicted number of evacuees at shelter A is 500, it estimates that 500 liters of water, 500 meals, and 500 blankets will be needed. Specific relief supplies such as water, food, medicine, and blankets are also taken into account when calculating the amount of supplies needed.

[1075] Based on the estimated results, the server accesses the local government's stockpile database and checks the stock status of necessary supplies. Specifically, it verifies that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1076] After completing the inventory check, the server connects with the logistics company's system to automatically generate a delivery plan for supplies. This creates an efficient delivery schedule, such as "send supplies from Warehouse X to Evacuation Center A using one truck."

[1077] Meanwhile, the shelter manager uses a terminal to input the number of evacuees and the status of supplies on site. This information is immediately sent to the server and the database is updated in real time. For example, if the shelter manager inputs "The current number of evacuees is 600, and there is a water shortage," this is sent to the server.

[1078] Finally, the server updates the database based on the transmitted information and recalculates the amount of supplies needed. As a result, it recalculates that "an additional 100 liters of water and 100 meals are needed," and instructs the logistics company to supply additional supplies. This makes it possible to efficiently and accurately grasp the situation at evacuation centers even in the event of an earthquake, and to quickly provide the necessary relief supplies.

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Step 1:

[1081] The server collects floating population data and communication environment data from communication service providers.

[1082] Input: Uses APIs provided by telecommunications carriers or internet service providers.

[1083] Data processing: Obtain demographic information and communication usage status for each region in real time.

[1084] Output: Save the collected data on the server.

[1085] Specific operation: The server calls the API and obtains data such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[1086] Step 2:

[1087] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1088] Input: Raw data collected in step 1.

[1089] Data processing: Standardize using calibration data and convert into a format suitable for AI models.

[1090] Output: Standardized data.

[1091] Specific operation: The server performs processing such as "normalizing population data by standard deviation" to reduce the variability of the data.

[1092] Step 3:

[1093] The server uses the generated AI model to predict the number of evacuees at each shelter.

[1094] Input: The preprocessed data from step 2.

[1095] Data calculation: Using neural network model.

[1096] Output: Predicted number of evacuees.

[1097] Specific operation: The server inputs data into the AI ​​model along with the prompt "Please calculate the number of evacuees predicted for shelter A in Tokyo," and obtains a result such as "500 evacuees are predicted for shelter A."

[1098] Step 4:

[1099] Based on the prediction results, the server estimates the amount of relief supplies needed.

[1100] Input: Prediction results from step 3.

[1101] Data calculation: Calculation based on standard consumption of relief supplies.

[1102] Output: The amount of supplies needed.

[1103] Specific operation: The server calculates, "There are 500 evacuees in shelter A, so 500 liters of water, 500 meals, and 500 blankets are needed."

[1104] Step 5:

[1105] The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[1106] Input: Estimated amount of relief supplies.

[1107] Data processing: Querying the stockpile database.

[1108] Output: Stock availability.

[1109] Specific operation: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1110] Step 6:

[1111] The server works in conjunction with the logistics company's system to create a delivery plan for supplies.

[1112] Input: Stock status and estimated amount of relief supplies.

[1113] Data calculation: Delivery route optimization algorithm.

[1114] Output: Delivery schedule.

[1115] Specific operation: The server generates a delivery schedule that "sends supplies from warehouse X to shelter A in one truck."

[1116] Step 7:

[1117] The terminals will be used by shelter managers to input the number of evacuees and the status of supplies on site.

[1118] Input: Local information entered by shelter manager.

[1119] Data processing: Input via application.

[1120] Output: The information entered.

[1121] Specific operation: The shelter manager enters "Current number of evacuees is 600, water shortage" into the terminal.

[1122] Step 8:

[1123] The terminal transmits the input information to the server.

[1124] Input: Local information entered.

[1125] Data processing: Communication from the terminal to the server.

[1126] Output: Information sent to the server.

[1127] Specific operation: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1128] Step 9:

[1129] The server updates the database based on the latest information and recalculates the amount of supplies needed.

[1130] Input: The local information sent to the server.

[1131] Data calculation: Recalculation algorithm.

[1132] Output: Recalculated amount of aid supplies.

[1133] Specific operation: The server updates the database with "The latest number of evacuees at shelter A is 600, and there is a water shortage," and recalculates that "An additional 100 liters of water and 100 meals are needed."

[1134] Step 10:

[1135] The server sends a delivery instruction for the additional supplies to the logistics company.

[1136] Input: Recalculated amount of aid.

[1137] Data processing: Update shipping schedule.

[1138] Output: The new delivery schedule.

[1139] Specific operation: The server generates a new delivery schedule such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A" and sends instructions to the logistics company.

[1140] (Application example 1)

[1141] 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."

[1142] During an earthquake, it is important to quickly and accurately grasp the situation at evacuation centers and effectively supply the necessary relief supplies. However, due to communication environment problems and sudden increases and decreases in the number of evacuees, it is difficult to accurately grasp the situation on site, which can lead to problems with delays in the timely delivery of relief supplies. In addition, insufficient coordination with logistics companies can make it difficult to distribute supplies appropriately.

[1143] 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.

[1144] In this invention, the server includes means for collecting communication environment data and mobile population data immediately before the earthquake, means for estimating the number of evacuees at each evacuation shelter using an artificial intelligence model based on the collected data, means for calculating the amount of relief supplies needed based on the estimate results and issuing instructions for the preparation and delivery of supplies, means for collecting information on the local situation after communication is restored, updating the data, recalculating the needed supplies, and issuing instructions for additional supplies, means for automatically and dynamically generating a delivery schedule for needed supplies and sending instructions to logistics companies, and means for quickly sending the latest information via a terminal used by the evacuation shelter manager. This makes it possible to efficiently and accurately grasp the situation at evacuation shelters and provide needed supplies even during communication disruptions.

[1145] "Communication environment data immediately before the earthquake" is data obtained from communication carriers and internet service providers that indicates the communication conditions immediately before the earthquake occurred.

[1146] "Floating population data" is data that shows the movement and distribution of population in a specific area over a certain period of time.

[1147] An "artificial intelligence model" is a statistical model that uses machine learning and deep learning to learn from past data and predict future situations.

[1148] "Means for estimating the number of evacuees" refers to techniques and methods for predicting the number of evacuees at each evacuation shelter using an artificial intelligence model based on collected data.

[1149] "Means for calculating the amount of necessary relief supplies" refers to techniques and methods for calculating the required amount of supplies such as water, food, medicine, blankets, health supplies, and consumables based on the predicted number of evacuees.

[1150] "Means for directing the preparation and delivery of supplies" refers to the techniques and methods for preparing needed relief supplies and planning and directing their delivery to each evacuation shelter.

[1151] "Means for collecting on-site information and updating data after communications are restored" refers to the technology and methods for collecting the latest information from evacuation centers and updating the database based on that information when communications are restored after a disaster occurs.

[1152] "Means for ordering additional supplies" refers to techniques and methods for recalculating the required supplies based on updated data and issuing instructions if additional supplies are required.

[1153] "Means for automatically generating dynamic delivery schedules for necessary supplies" refers to technologies and methods for automatically creating optimal supply delivery schedules in real time using AI models and algorithms.

[1154] The "means for sending instructions to the logistics company" refers to a technique or method for notifying the logistics company of the generated delivery schedule and the need for additional supplies, and for instructing them on how to respond.

[1155] "Devices used by evacuation shelter managers" are devices such as smartphones and tablets that evacuation shelter managers use to enter information such as local conditions and necessary supplies and send it to a server.

[1156] The system based on this invention is constructed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively supply the necessary relief supplies. The system operates in cooperation with the server, terminals, and users, and performs processing in the following steps.

[1157] System Configuration

[1158] 1. Server

[1159] Hardware: High-performance web servers (e.g., Amazon Web Services (AWS), Microsoft Azure)

[1160] Software: Communication API, TensorFlow, Requests library

[1161] Functions: Data collection, data standardization, predictions using AI models, and sending instructions to logistics companies

[1162] 2. Terminal

[1163] Hardware: Smartphones, tablets (e.g. Android, iOS)

[1164] Function: The shelter manager inputs local information and sends it to the server.

[1165] 3. Users

[1166] Role: Evacuation center manager, inputting the number of evacuees and the status of supplies via terminal

[1167] Operation flow

[1168] Data collection

[1169] The server collects data on the communication environment and population movement immediately before the earthquake from telecommunications carriers and internet service providers. The collected data is standardized into the required data format.

[1170] Prediction by AI model

[1171] The standardized data is input into an artificial intelligence model (e.g., a neural network using TensorFlow) to predict the number of evacuees at each shelter in real time. For example, the server calculates that "the predicted number of evacuees at shelter A immediately after the earthquake is 500 people."

[1172] Estimating supplies and preparing for delivery

[1173] Based on the prediction results, the server calculates the amount of relief supplies needed and automatically generates a dynamic delivery schedule. The calculation includes specific relief supplies such as water, food, medicine, blankets, health supplies, and consumables. For example, it calculates that "500 evacuees need 500 liters of water, 500 meals, and 500 blankets." The calculated results are sent as instructions to logistics companies.

[1174] The server generates a specific delivery schedule, such as "send supplies from warehouse X to shelter A in one truck," and sends instructions.

[1175] Gathering information at evacuation shelters

[1176] The shelter manager uses a device (smartphone or tablet) to input the number of evacuees and the status of supplies. For example, if the manager inputs "the current number of evacuees is 600, and there is a water shortage," the information is immediately sent to the server.

[1177] Data updates and additional supplies

[1178] The server updates the database based on the latest information received and recalculates the amount of supplies needed. If the recalculation shows that additional supplies are needed, it quickly issues instructions to logistics companies to provide the additional supplies. For example, it may recalculate the amount to "an additional 100 liters of water and 100 meals are needed," and immediately send delivery instructions.

[1179] Specific examples

[1180] At shelter A, the server collects the latest local information and predicts the number of evacuees. Based on these results, it dynamically calculates the amount of relief supplies needed and automatically generates a truck delivery schedule. The shelter manager uses a smartphone to instantly send the actual number of evacuees and the status of supplies to the server, which then updates the database with this information and draws up a plan for additional supplies.

[1181] Prompt Sentence Examples

[1182] "Collect the latest population and communication data for shelter A from the server, and use an AI model to predict the number of evacuees. Based on the prediction, calculate the necessary relief supplies and generate Python code to schedule the delivery of supplies to shelter A."

[1183] By operating in this way, the system can efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[1184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1185] Step 1: Data collection

[1186] The server collects real-time data on the communication environment immediately before the earthquake and data on the local population flow from telecommunications carriers and internet service providers via API. It uses API endpoints as input and obtains the collected data as output. The server saves the collected data in JSON format or other formats.

[1187] Step 2: Data Standardization

[1188] The server standardizes the collected data before applying it to the AI ​​model. Specifically, it fills in any imperfections in the data, removes outliers, and converts it into the required format. It uses the collected raw data as input and obtains standardized data as output. The server then adapts this data to the input format of the AI ​​model.

[1189] Step 3: Predict the number of evacuees

[1190] The server inputs the standardized data into an artificial intelligence model to predict the number of evacuees at each shelter. Using the standardized data as input, the server obtains the predicted number of evacuees as output. Specifically, the neural network model performs the calculations using machine learning libraries such as TensorFlow.

[1191] Step 4: Calculate supply needs

[1192] The server calculates the amount of supplies needed based on the predicted number of evacuees. It uses the predicted number of evacuees as input and gets a detailed list of needed supplies as output. For example, it calculates "500 evacuees need 500 liters of water, 500 meals, and 500 blankets."

[1193] Step 5: Auto-generate delivery schedules

[1194] The server automatically generates a delivery schedule for logistics companies based on the relief supply list. It uses the supply list as input and obtains a specific delivery plan as output. For example, the server generates a schedule such as "Send supplies from Warehouse X to Evacuation Center A by one truck."

[1195] Step 6: Send instructions to logistics provider

[1196] The server sends the generated delivery schedule as instructions to the logistics company. It uses the automatically generated delivery schedule as input and verifies that the instructions were sent correctly as output. The server does this via HTTP requests, etc.

[1197] Step 7: Gather local information

[1198] The terminal is used by the shelter manager to input the latest local situation. For example, the shelter manager might use the terminal to input "the current number of evacuees is 600, and there is a water shortage." The information obtained on-site is used as input, and that information is sent to the server as output.

[1199] Step 8: Update the Database

[1200] The server updates the database based on the latest information sent from the terminal. It uses the data sent from the field as input and obtains the updated database as output. The server then updates the database to show that "the latest number of evacuees at shelter A is 600, and there is a water shortage."

[1201] Step 9: Recalculate and order additional supplies

[1202] The server recalculates the amount of supplies needed based on the updated database and issues instructions if additional supplies are required. It uses the latest database information as input and obtains a recalculated list of supplies as output. For example, it may recalculate, "We need an additional 100 liters of water and 100 meals of food," and send additional delivery instructions to the logistics company.

[1203] By implementing each of the above steps, we will create a system that will enable efficient and accurate assessment of the situation at evacuation centers and the supply of necessary supplies, even if communications and power supplies are cut off during an earthquake.

[1204] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1205] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply necessary relief supplies. This system functions in cooperation with the server, terminals, and users, and by combining it with an emotion engine, it also provides psychological support to evacuees.

[1206] Data collection

[1207] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[1208] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[1209] AI estimation

[1210] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1211] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[1212] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[1213] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[1214] Estimating necessary supplies and preparing for delivery

[1215] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[1216] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[1217] 2. The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[1218] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1219] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[1220] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[1221] Gathering information at evacuation shelters

[1222] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[1223] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[1224] 2. The terminal sends the entered information to the server.

[1225] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1226] Data updates and supply adjustments

[1227] 1. The server updates the database based on the latest information sent from the evacuation center.

[1228] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1229] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1230] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1231] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1232] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1233] Emotion engine integration

[1234] 1. The device collects facial expressions, voice, and text data from shelter managers and evacuees and sends it to the emotion engine.

[1235] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[1236] 2. The emotion engine analyzes the collected data and recognizes the user's emotional state.

[1237] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[1238] 3. The emotion engine sends the recognized emotion data to the server.

[1239] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[1240] 4. The server will use the emotional data to direct additional psychological support or special supplies.

[1241] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[1242] In this way, the system operates in cooperation with the server, terminals, users, and emotion engine, making it possible to efficiently and accurately grasp the situation at evacuation centers, provide necessary supplies, and even provide psychological care for evacuees, even if communications and power supplies are cut off during an earthquake.

[1243] The processing flow will be explained below.

[1244] Step 1:

[1245] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[1246] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[1247] Step 2:

[1248] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1249] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[1250] Step 3:

[1251] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[1252] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[1253] Step 4:

[1254] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[1255] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[1256] Step 5:

[1257] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[1258] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1259] Step 6:

[1260] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[1261] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[1262] Step 7:

[1263] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[1264] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[1265] Step 8:

[1266] The terminal transmits the input information to the server.

[1267] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1268] Step 9:

[1269] The server updates the database based on the latest information sent from the evacuation center.

[1270] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1271] Step 10:

[1272] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1273] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1274] Step 11:

[1275] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1276] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1277] Step 12:

[1278] The device collects facial expressions, voice, and text data from shelter managers and evacuees, and sends it to the emotion engine.

[1279] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[1280] Step 13:

[1281] The emotion engine analyzes the collected data and recognizes the user's emotional state.

[1282] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[1283] Step 14:

[1284] The emotion engine sends the recognized emotion data to the server.

[1285] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[1286] Step 15:

[1287] The server uses the emotional data to direct additional psychological support or special supplies.

[1288] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[1289] Example 2

[1290] 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."

[1291] There is a need for a system that can quickly and accurately grasp the situation at evacuation centers during earthquakes, effectively provide necessary relief supplies, and comprehensively provide psychological support to evacuees. Conventional systems do not collect and update local information about evacuation centers in real time, which can lead to delays in recalculating needed supplies and providing additional supplies, and insufficient psychological support for evacuees. Therefore, a system is needed that can improve the efficiency of evacuation center management and the safety and psychological care of evacuees.

[1292] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication environment data and floating population data, means for normalizing and imputing the collected data and inputting it into an AI model, means for predicting the number of evacuees at each evacuation shelter using the AI ​​model, means for calculating the amount of relief supplies needed based on the prediction results and instructing the preparation and delivery of supplies, means for the evacuation shelter manager to send local information to the server using a terminal, means for updating the database based on the local information, recalculating the amount of needed supplies, and instructing the additional supply, means for collecting emotional data of evacuees via the terminal and sending it to the emotion engine, and means for instructing psychological support and the supply of special supplies based on the emotional data analyzed by the emotion engine. This enables efficient and accurate assessment of the situation at evacuation shelters, the supply of necessary supplies, and psychological care for evacuees during an earthquake disaster.

[1293] "Communication environment data" refers to information such as communication network usage status, connection status, and communication speed obtained from communication carriers and Internet service providers.

[1294] "Floating population data" is statistical information that shows the movement patterns and number of people in a specific area, and is mainly calculated from location information of communication devices.

[1295] An "artificial intelligence model" is a calculation algorithm that learns from past data and predicts new situations, and in this invention it is used to predict the number of evacuees and the amount of necessary supplies.

[1296] "Normalization" is a process in data processing that converts collected raw data into a unified format, and is a means of improving data quality.

[1297] "Gap imputation" is the process of filling in missing data with appropriate values ​​in order to build a complete dataset.

[1298] "Terminal" refers to a device such as a smartphone or tablet used by shelter managers and other users, and is used to input and transmit information.

[1299] An "emotion engine" is a software system that recognizes a user's emotional state by analyzing collected data such as facial expressions, voice, and text.

[1300] "Evacuation forecasting" is the process of using artificial intelligence models to estimate the number of people who will evacuate to a particular shelter in the event of a disaster.

[1301] "Relief supplies" refer to basic daily necessities and services that evacuees need in the event of a disaster, such as water, food, medicine, blankets, and recreational items.

[1302] "Psychological support" refers to counseling and other support activities aimed at reducing the psychological distress and stress of evacuees.

[1303] "Database updating" is the process of updating existing data to reflect the latest information, and is done to keep information accurate in real time.

[1304] "Delivery instructions" are instructions given to deliver supplies to where they are needed, and refer to the act of providing logistics companies with specific delivery plans and schedules.

[1305] "Emotion data" is information indicating emotions extracted from the user's facial expressions, voice, text, etc., and is analyzed by the emotion engine.

[1306] The system based on this invention involves the cooperation of a server, terminals, users, and an emotion engine in order to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply the necessary relief supplies. This system is configured as follows:

[1307] Data collection

[1308] The server collects data on the current population and communication environment from telecommunications carriers and internet service providers (ISPs). It uses APIs to obtain data in real time from each telecommunications carrier and ISP. For example, the server uses APIs to collect demographic information from telecommunications carriers.

[1309] Data preprocessing and AI calculations

[1310] The collected data is normalized on the server and missing data is supplemented. The formatted data is then input into an artificial intelligence model. This artificial intelligence model is a neural network model that has been trained based on data from past earthquakes. This model is used to predict the number of evacuees at each evacuation shelter. For example, the server outputs a calculated result such as "The predicted number of evacuees at shelter A is 500."

[1311] Estimating necessary supplies and preparing for delivery

[1312] Based on the estimates, the server calculates the amount of relief supplies needed for each evacuation center. This includes water, food, medicine, blankets, and recreational items. For example, the server might calculate that 500 evacuees need 500 liters of water, 500 meals, and 500 blankets. It then accesses the local government's stockpile database to check the inventory status of the necessary supplies. It then connects to the logistics company's system to automatically generate a specific delivery schedule and issue instructions to the logistics company.

[1313] Gathering information at evacuation shelters

[1314] The terminal allows the shelter manager to input the number of evacuees and the current status of supplies via a smartphone or tablet. For example, the shelter manager might input "the current number of evacuees is 600, and there is a water shortage" into the terminal, and this information is then sent to the server.

[1315] Data updates and supply adjustments

[1316] The server updates the database based on the latest information sent from the evacuation center. This allows it to recalculate the amount of supplies needed based on the latest situation and calculate the amount of additional supplies that should be provided. For example, the server may recalculate that an additional 100 liters of water and 100 meals are needed. Based on the recalculated results, it issues instructions to the logistics company to deliver the additional supplies.

[1317] Emotion engine integration

[1318] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. The emotion engine analyzes this data and recognizes the user's emotional state. For example, the emotion engine may recognize that "evacuee A is in a state of stress, while evacuee B is in a state of relief." The analysis results are sent to the server, which then issues instructions for additional psychological support or the provision of special supplies based on the emotional data.

[1319] (Example of a prompt for a generative AI model):

[1320] "Use this system to understand the situation at evacuation centers, calculate supplies needed, plan distribution, and conduct simulations to provide emotional support."

[1321] In this way, by linking all the elements together, the system will be able to efficiently and accurately grasp the situation at evacuation centers during earthquakes, provide necessary supplies, and even provide psychological care for evacuees.

[1322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1323] Step 1:

[1324] Data collection

[1325] The server collects population mobility data and communication environment data from telecommunications carriers and Internet service providers (ISPs) through APIs. It uses API endpoints and parameters as input and obtains real-time demographic and communication data as output. For example, the server performs the following operation: "call NTT Docomo's API and obtain demographic information."

[1326] Step 2:

[1327] Data Preprocessing

[1328] The server normalizes the collected data and fills in missing data. It uses floating population data and communication environment data as input, and obtains a normalized dataset as output. Specific operations include filling in missing values ​​based on the preceding and following data, and standardizing the data format. For example, it performs the process of "filling in zeros in the collected data and converting it into a standard format."

[1329] Step 3:

[1330] Prediction of the number of evacuees

[1331] The server uses the preprocessed data to input into an AI model to predict the number of evacuees. The normalized dataset is used as input, and the output is the predicted number of evacuees at each evacuation shelter. The AI ​​model is a neural network trained based on data from past earthquakes. For example, the operation is as follows: "Enter data into the AI ​​model and predict the number of evacuees at shelter A to be 500."

[1332] Step 4:

[1333] Estimated cost of relief supplies

[1334] The server calculates the amount of relief supplies needed at each evacuation center based on the prediction results. It uses the predicted number of evacuees as input and obtains the required amount of supplies as output. Specifically, it calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[1335] Step 5:

[1336] Check stockpile data

[1337] The server accesses the local government's stockpile database and checks the stock status of necessary supplies. It uses the list of supplies and the number of evacuees as input, and obtains stock information as output. For example, it checks whether "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1338] Step 6:

[1339] Generate a delivery plan

[1340] The server works in conjunction with the logistics company's system to automatically generate a delivery plan for supplies. It uses inventory information and a list of necessary supplies as input, and obtains a delivery schedule as output. For example, it performs an operation such as "creating a plan to deliver supplies from Warehouse X to Evacuation Center A using one truck."

[1341] Step 7:

[1342] Gathering local information

[1343] The terminal allows the shelter manager to input the number of evacuees and the status of supplies on site via a smartphone or tablet. The latest local information is used as input, and updated information is output and sent to the server. For example, the operation might be, "The shelter manager inputs into the terminal that the current number of evacuees is 600 and there is a water shortage, and then sends the information to the server."

[1344] Step 8:

[1345] Database Update

[1346] The server updates the database based on the latest information sent from the evacuation center. It uses the latest data on the number of evacuees and the status of supplies as input, and obtains the updated database status as output. For example, it performs an operation such as "reflect the latest information from evacuation center A in the database."

[1347] Step 9:

[1348] Supply Recalculation

[1349] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be provided. It uses the updated number of evacuees and supply status data as input, and obtains a list of additional supplies as output. For example, it performs an operation such as "recalculating that an additional 100 liters of water and 100 meals are needed."

[1350] Step 10:

[1351] Delivery instructions for additional supplies

[1352] The server then issues instructions to the logistics company to deliver additional supplies based on the recalculation results. It uses the list of additional supplies and delivery destination information as input, and obtains a new delivery schedule as output. For example, it performs an operation such as "instructing Warehouse Y to deliver an additional 100 liters of water and 100 meals to Evacuation Center A."

[1353] Step 11:

[1354] Collecting Emotional Data

[1355] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. Data photographed or recorded by the device is used as input, and emotion data is output and sent to the emotion engine. For example, the device performs an operation such as "taking a photo of the evacuees' facial expressions with a smartphone camera and sending it to the emotion engine."

[1356] Step 12:

[1357] Emotional Data Analysis

[1358] The emotion engine analyzes the collected data and recognizes the user's emotional state. It uses facial expressions, voice, and text data as input and obtains the analysis results as output. For example, the emotion engine recognizes that evacuee A is in a stressed state and evacuee B is in a relieved state.

[1359] Step 13:

[1360] Sending emotional data

[1361] The emotion engine sends the recognized emotion data to the server. It uses the analyzed emotional state data as input and gets a report that is sent to the server as output. For example, the emotion engine reports to the server that most of the evacuees at shelter A are in a stressed state.

[1362] Step 14:

[1363] Psychological support instructions

[1364] The server then uses the emotional data to provide additional psychological support and special supplies. It uses the emotional state data sent from the emotion engine as input and obtains a psychological support plan and a supply list as output. For example, it can perform an action such as "dispatch a psychological counselor to shelter A and provide recreational supplies to relieve stress."

[1365] (Application example 2)

[1366] 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."

[1367] In managing evacuation shelters after a disaster, it is extremely important to quickly and accurately grasp the situation of evacuees and provide appropriate relief supplies. However, the current system makes it difficult to grasp the psychological state of evacuees, which results in issues such as inadequate psychological support for evacuees and insufficient maintenance of order and safety within the shelter.

[1368] 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.

[1369] In this invention, the server includes means for collecting communication environment data and population mobility data immediately before the earthquake, means for using an AI model to estimate the number of evacuees at each evacuation shelter based on the collected data, means for calculating the amount of relief supplies needed based on the estimate and issuing instructions for the preparation and delivery of supplies, means for collecting on-site conditions after communication is restored, updating the data, recalculating the needed supplies, and issuing instructions for additional supplies, means for collecting video data within the evacuation shelter and recognizing the emotional state of the evacuees, means for issuing instructions for psychological support and the delivery of special supplies based on the recognized emotional data, and means for monitoring the situation in real time and implementing security measures to prevent crime and maintain order. This allows for comprehensive management of the situation within the evacuation shelter, making it possible to efficiently not only provide supplies but also provide psychological care and ensure safety.

[1370] "Communication environment data" is information that indicates the state and usage of the communication network at the time of the earthquake.

[1371] "Floating population data" is information that indicates the movement of people and population density within a specific area.

[1372] An "artificial intelligence model" is an algorithm that is trained on past data to make predictions or classifications based on specific inputs.

[1373] "Number of evacuees" refers to the number of people staying in evacuation shelters.

[1374] "Relief supplies" are supplies such as water, food, medicine, and blankets that evacuees need in the event of a disaster.

[1375] "Preparation and delivery of supplies" refers to all activities involved in preparing necessary relief supplies in appropriate locations and delivering them to evacuation shelters.

[1376] "Local situation" refers to real-time information such as the current number of evacuees at evacuation centers and the shortage of supplies.

[1377] "Data updating" means reflecting newly obtained local information in the existing database.

[1378] "Additional supply" means the re-delivery of supplies to make up for any shortages that have already been made.

[1379] "Video data" refers to video information of evacuees and the inside of evacuation shelters obtained through cameras, etc.

[1380] "Emotional state" is information that indicates the psychological stability and stress level of evacuees.

[1381] "Psychological support" refers to providing care and support to evacuees to ensure their psychological well-being.

[1382] "Security measures" refer to surveillance and crime prevention measures to ensure safety within the shelter.

[1383] To implement this invention, it is necessary to build a system in which servers, terminals, and users work together. This system aims to streamline the operation of evacuation shelters in the event of an earthquake, and to comprehensively provide psychological support and security measures for evacuees.

[1384] Components

[1385] 1. Data Collection

[1386] The server collects real-time data on the population flow and communication environment from telecommunications carriers and internet service providers (ISPs) via APIs. For example, data obtained through APIs includes communication usage status and regional demographics.

[1387] Example prompt sentence:

[1388] text

[1389] curl -X GET "API_URL" -H ​​"accept: application / json"

[1390] 2. AI estimation

[1391] The server preprocesses the collected data and inputs it into an artificial intelligence model. After normalizing the data and filling in missing data, the number of evacuees at each shelter is predicted based on the neural network model.

[1392] The collected data is normalized using tools such as MinMaxScaler, and then the number of evacuees is estimated using a neural network model built with TensorFlow and Keras.

[1393] 3. Estimate the amount of supplies needed and prepare for delivery

[1394] Based on the estimates, the server calculates the amount of relief supplies (e.g., water, food, medicine, blankets) needed at each evacuation center. It also checks inventory and automatically generates delivery schedules.

[1395] Specifically, estimates include "500 evacuees will need 500 liters of water, 500 meals, 50 sets of medicine, and 500 blankets."

[1396] 4. Gathering information at evacuation shelters

[1397] The terminals are smartphones or tablets used by shelter managers, and they input the number of evacuees and the status of supplies on site. This information is sent to a server and the database is updated.

[1398] For example, a shelter manager might enter "Current number of evacuees: 600, water shortage" into a terminal and update the information on the server.

[1399] 5. Data updates and supply adjustments

[1400] The server recalculates the amount of supplies needed based on the latest data, calculates the amount of additional supplies that should be supplied, and issues instructions to the logistics company to deliver the additional supplies.

[1401] As a specific example, instructions may be given such as "Deliver an additional 100 liters of water and 100 meals from the warehouse to evacuation centers."

[1402] 6. Emotion engine integration

[1403] The device collects facial expressions, voice, and text data from shelter managers and evacuees, and sends it to an emotion engine, which analyzes this data and recognizes the emotional state of the evacuees.

[1404] For example, a shelter manager can take pictures of evacuees' facial expressions with a smartphone camera and use the emotion engine to recognize that "evacuee A is in a stressed state, while evacuee B is in a relaxed state."

[1405] Example prompt sentence:

[1406] text

[1407] Analyze the emotions of individuals in the video feed from "http: / / camera_feed_url". Identify and report back on the number of individuals showing signs of stress versus those who appear calm.

[1408] 7. Security Measures

[1409] The server collects video data from inside the evacuation center and monitors it in real time to ensure safety. It also uses facial recognition and object detection technologies to implement measures to prevent crime and maintain order.

[1410] For example, facial recognition technology can be used to monitor specific individuals entering and leaving evacuation shelters and detect suspicious individuals.

[1411] Specific examples

[1412] As a concrete example of the system, immediately after an earthquake, communication environment data and population mobility data are collected, and the number of evacuees at each evacuation center is predicted using an AI model. The system then estimates the amount of relief supplies needed and issues delivery instructions to logistics companies. Furthermore, by repeatedly collecting and updating local information about evacuation centers, the system ensures efficient supply of supplies. It also recognizes emotional states, provides psychological support, and implements security measures to ensure safety and security within the evacuation center.

[1413] This will enable comprehensive management of the situation within the shelter, and will make it possible to efficiently provide not only necessary supplies but also psychological care and ensure safety.

[1414] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1415] Step 1:

[1416] The server collects real-time population flow data and communication environment data from telecommunications carriers and Internet service providers (ISPs) via APIs. Using data obtained from API endpoints as input, the data is sent to the server and stored in a database. A specific example would be information such as "demographic data from telecommunications carrier A."

[1417] Step 2:

[1418] The server preprocesses the collected data and inputs it into an artificial intelligence model. Preprocessing includes normalizing the data and filling in missing data. For example, MinMaxScaler is used to scale the data to a range of 0 to 1, and missing data is filled in with the historical average value. The preprocessed data is then input into the artificial intelligence model (a model trained with TensorFlow or Keras).

[1419] Step 3:

[1420] The server uses an artificial intelligence model to predict the number of evacuees at each shelter. It uses preprocessed data as input and obtains the predicted number of evacuees at each shelter as output. For example, it outputs a specific estimated result such as "The predicted number of evacuees at shelter A is 500 people."

[1421] Step 4:

[1422] The server calculates the amount of relief supplies needed based on the results of the calculation. It uses the predicted number of evacuees as input and obtains a list of necessary supplies as output. For example, the calculation results may be, "For 500 evacuees, 500 liters of water, 500 meals, and 500 blankets are needed."

[1423] Step 5:

[1424] The server accesses the local government's stockpile database and checks the stock status of necessary supplies. It uses a list of supplies as input and obtains the stock status as output. For example, the output might be "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1425] Step 6:

[1426] The server works in conjunction with the logistics company's system to automatically generate a delivery plan for supplies. It uses inventory status and evacuation shelter location information as input, and obtains a specific delivery schedule as output. For example, it generates specific delivery instructions such as "Deliver supplies from Warehouse X to Evacuation Shelter A using one truck."

[1427] Step 7:

[1428] The terminal is a smartphone or tablet used by the shelter manager, and the number of evacuees and the status of supplies on site are input. The data reported by the shelter manager is used as input, and the latest number of evacuees and the status of supplies are obtained as output. For example, the latest information such as "the current number of evacuees is 600, and there is a water shortage" is input.

[1429] Step 8:

[1430] The terminal sends the input information to the server. The latest data entered by the shelter manager is used as input, and the information sent to the server is obtained as output. For example, the latest number of evacuees and information on shortages of supplies at shelter A are sent to the server.

[1431] Step 9:

[1432] The server updates the database based on the latest information sent from the evacuation center. The latest data received is used as input, and the updated database is obtained as output. For example, the database may be updated to show "The latest number of evacuees at evacuation center A is 600, and there is a water shortage."

[1433] Step 10:

[1434] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be provided. It uses the latest number of evacuees and information on shortages as input, and outputs a list of supplies that should be provided. For example, the recalculation result might be, "An additional 100 liters of water and 100 meals are needed."

[1435] Step 11:

[1436] Based on the recalculation results, the server issues delivery instructions to logistics companies to deliver additional supplies. Using the recalculation results as input, a specific delivery schedule is obtained as output. For example, a new delivery instruction may be generated such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A."

[1437] Step 12:

[1438] The device collects facial expressions, voice, and text data from the shelter manager and evacuees, and sends it to the emotion engine. The facial expressions of the evacuees are used as input, and the data sent to the emotion engine is obtained as output. As a specific example, the facial expressions of the evacuees are photographed with a smartphone camera, and then analyzed by the emotion engine.

[1439] Step 13:

[1440] The emotion engine analyzes the collected data and recognizes the user's emotional state. It uses the collected facial and voice data as input and obtains the recognition result of the emotional state as output. For example, it recognizes that "evacuee A is in a stressed state, and evacuee B is in a relieved state."

[1441] Step 14:

[1442] The emotion engine sends the recognized emotion data to the server. Using the recognized emotional state as input, the emotion data sent to the server is obtained as output. For example, a report may be made such as "Many of the evacuees at shelter A are in a state of stress."

[1443] Step 15:

[1444] The server then uses the emotional data to provide additional psychological support or special supplies. Using the recognized emotional data as input, the server can obtain specific support instructions as output. For example, measures such as "dispatch psychological counselors to shelter A" or "provide additional recreational supplies to relieve stress" may be implemented.

[1445] Step 16:

[1446] The server collects video data from inside the evacuation center and monitors it in real time to ensure safety. The video data is used as input, and the monitoring results for ensuring safety are obtained as output. For example, facial recognition technology can be used to identify suspicious individuals and issue a warning.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] [Fourth embodiment]

[1451] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1452] 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.

[1453] 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).

[1454] 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.

[1455] 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.

[1456] 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).

[1457] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] 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."

[1464] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake disaster and to effectively supply necessary relief supplies.

[1465] This system functions in cooperation with the server, terminals, and users.

[1466] Data collection

[1467] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[1468] Example: The server uses APIs provided by each telecommunications carrier and ISP to obtain demographic information and communication usage status for each region in real time.

[1469] AI estimation

[1470] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1471] Example: The server uses calibration data to standardize collected data and convert it into a format for the AI ​​model.

[1472] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[1473] Example: The server uses a trained neural network model to output results such as "The predicted number of evacuees at shelter A in Tokyo is 500."

[1474] Estimating necessary supplies and preparing for delivery

[1475] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[1476] Example: The server calculates that "500 evacuees require 500 liters of water, 500 meals, and 500 blankets."

[1477] 2. The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[1478] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1479] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[1480] Example: The server creates a delivery schedule such as "send one truckload of supplies from Warehouse X to Evacuation Center A."

[1481] Gathering information at evacuation shelters

[1482] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[1483] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[1484] 2. The terminal sends the entered information to the server.

[1485] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1486] Data updates and supply adjustments

[1487] 1. The server updates the database based on the latest information sent from the evacuation center.

[1488] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1489] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1490] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1491] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1492] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1493] In this way, the system operates in cooperation with servers, terminals, and users, making it possible to efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[1494] The processing flow will be explained below.

[1495] Step 1:

[1496] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[1497] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[1498] Step 2:

[1499] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1500] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[1501] Step 3:

[1502] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[1503] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[1504] Step 4:

[1505] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[1506] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[1507] Step 5:

[1508] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[1509] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1510] Step 6:

[1511] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[1512] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[1513] Step 7:

[1514] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[1515] Example: A shelter manager uses a terminal to input, "Current number of evacuees: 600, water shortage."

[1516] Step 8:

[1517] The terminal transmits the input information to the server.

[1518] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1519] Step 9:

[1520] The server updates the database based on the latest information sent from the evacuation center.

[1521] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1522] Step 10:

[1523] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1524] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1525] Step 11:

[1526] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1527] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1528] This series of processes allows us to quickly grasp the situation at evacuation centers in the event of an earthquake and effectively provide necessary relief supplies.

[1529] Example 1

[1530] 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."

[1531] During an earthquake, it is difficult to quickly and accurately grasp the situation at evacuation centers and effectively provide the necessary relief supplies. In particular, when there are large fluctuations in the communication environment and the flow of population, or when it is difficult to predict the number of evacuees, it is difficult to make an appropriate plan for the supply of supplies based on that, and relief activities may be delayed.

[1532] 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.

[1533] In this invention, the server includes means for collecting moving population data and communication environment data from communication service providers, means for standardizing the collected data and inputting it into an artificial intelligence model, and means for predicting the number of evacuees at each evacuation shelter using the artificial intelligence model. This makes it possible to accurately predict the number of evacuees in real time based on the moving population data and communication environment data in the event of an earthquake, and to quickly and appropriately supply necessary relief supplies.

[1534] "Communication service providers" is a general term for telecommunications carriers and internet service providers that provide floating population data and communication environment data.

[1535] "Floating population data" is information on the movement of population and the number of people within a specific area.

[1536] "Communication environment data" is information related to the communication usage status and line congestion within a specific area.

[1537] A "server" is a computer system for collecting, processing, and performing various calculations on data.

[1538] An "artificial intelligence model" is software that includes machine learning algorithms to analyze collected data and make predictions and estimates.

[1539] A "terminal" is a device such as a smartphone or tablet that is used by shelter managers to input local information and send it to a server.

[1540] "Prediction methods" are methods or algorithms for predicting the number of evacuees at each shelter using an artificial intelligence model based on collected data.

[1541] "Calculation methods" are methods or algorithms for calculating the amount of relief supplies needed based on the forecast results.

[1542] "Inventory confirmation means" refers to a method or system for confirming the inventory status of supplies to be delivered to each evacuation shelter after estimating the required amount of relief supplies.

[1543] The "delivery plan creation means" refers to a method or algorithm that works in conjunction with a logistics company system to automatically generate an efficient material delivery plan after inventory confirmation.

[1544] "Database update means" refers to a method or system for keeping the database up to date based on information sent from evacuation shelters.

[1545] A "supply adjustment means" is a method or system for adjusting the additional supply of needed relief supplies based on updated data.

[1546] The system based on this invention is designed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively provide the necessary relief supplies. This system functions in cooperation with the server, terminals, and users.

[1547] First, the server collects data on the population flow and communication environment from communication service providers. To do this, it uses APIs provided by communication carriers and internet service providers. For example, it obtains data in real time such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[1548] The server then preprocesses the collected data and converts it into a format that can be input into the AI ​​model. Specifically, it standardizes the data using calibration data. This reduces data variability and improves the accuracy of analysis by the AI ​​model.

[1549] The collected and preprocessed data is input into a generative AI model on the server. This model has previously learned data from past earthquakes, and is able to predict with high accuracy the number of evacuees at each evacuation shelter. An example of a prompt sentence is: "Use part of the input data and parameters as the prompt sentence to input into the generative AI model. Example: Please calculate the predicted number of evacuees at shelter A in Tokyo."

[1550] Based on the prediction results, the server estimates the amount of relief supplies needed for each shelter. For example, if the predicted number of evacuees at shelter A is 500, it estimates that 500 liters of water, 500 meals, and 500 blankets will be needed. Specific relief supplies such as water, food, medicine, and blankets are also taken into account when calculating the amount of supplies needed.

[1551] Based on the estimated results, the server accesses the local government's stockpile database and checks the stock status of necessary supplies. Specifically, it verifies that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1552] After completing the inventory check, the server connects with the logistics company's system to automatically generate a delivery plan for supplies. This creates an efficient delivery schedule, such as "send supplies from Warehouse X to Evacuation Center A using one truck."

[1553] Meanwhile, the shelter manager uses a terminal to input the number of evacuees and the status of supplies on site. This information is immediately sent to the server and the database is updated in real time. For example, if the shelter manager inputs "The current number of evacuees is 600, and there is a water shortage," this is sent to the server.

[1554] Finally, the server updates the database based on the transmitted information and recalculates the amount of supplies needed. As a result, it recalculates that "an additional 100 liters of water and 100 meals are needed," and instructs the logistics company to supply additional supplies. This makes it possible to efficiently and accurately grasp the situation at evacuation centers even in the event of an earthquake, and to quickly provide the necessary relief supplies.

[1555] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1556] Step 1:

[1557] The server collects floating population data and communication environment data from communication service providers.

[1558] Input: Uses APIs provided by telecommunications carriers or internet service providers.

[1559] Data processing: Obtain demographic information and communication usage status for each region in real time.

[1560] Output: Save the collected data on the server.

[1561] Specific operation: The server calls the API and obtains data such as "The current population of Tokyo's 23 wards is 9,500,000, and the communication usage rate is 80%."

[1562] Step 2:

[1563] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1564] Input: Raw data collected in step 1.

[1565] Data processing: Standardize using calibration data and convert into a format suitable for AI models.

[1566] Output: Standardized data.

[1567] Specific operation: The server performs processing such as "normalizing population data by standard deviation" to reduce the variability of the data.

[1568] Step 3:

[1569] The server uses the generated AI model to predict the number of evacuees at each shelter.

[1570] Input: The preprocessed data from step 2.

[1571] Data calculation: Using neural network model.

[1572] Output: Predicted number of evacuees.

[1573] Specific operation: The server inputs data into the AI ​​model along with the prompt "Please calculate the number of evacuees predicted for shelter A in Tokyo," and obtains a result such as "500 evacuees are predicted for shelter A."

[1574] Step 4:

[1575] Based on the prediction results, the server estimates the amount of relief supplies needed.

[1576] Input: Prediction results from step 3.

[1577] Data calculation: Calculation based on standard consumption of relief supplies.

[1578] Output: The amount of supplies needed.

[1579] Specific operation: The server calculates, "There are 500 evacuees in shelter A, so 500 liters of water, 500 meals, and 500 blankets are needed."

[1580] Step 5:

[1581] The server accesses the local government's stockpile database and checks the inventory status of supplies to be delivered to each evacuation shelter.

[1582] Input: Estimated amount of relief supplies.

[1583] Data processing: Querying the stockpile database.

[1584] Output: Stock availability.

[1585] Specific operation: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1586] Step 6:

[1587] The server works in conjunction with the logistics company's system to create a delivery plan for supplies.

[1588] Input: Stock status and estimated amount of relief supplies.

[1589] Data calculation: Delivery route optimization algorithm.

[1590] Output: Delivery schedule.

[1591] Specific operation: The server generates a delivery schedule that "sends supplies from warehouse X to shelter A in one truck."

[1592] Step 7:

[1593] The terminals will be used by shelter managers to input the number of evacuees and the status of supplies on site.

[1594] Input: Local information entered by shelter manager.

[1595] Data processing: Input via application.

[1596] Output: The information entered.

[1597] Specific operation: The shelter manager enters "Current number of evacuees is 600, water shortage" into the terminal.

[1598] Step 8:

[1599] The terminal transmits the input information to the server.

[1600] Input: Local information entered.

[1601] Data processing: Communication from the terminal to the server.

[1602] Output: Information sent to the server.

[1603] Specific operation: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1604] Step 9:

[1605] The server updates the database based on the latest information and recalculates the amount of supplies needed.

[1606] Input: The local information sent to the server.

[1607] Data calculation: Recalculation algorithm.

[1608] Output: Recalculated amount of aid supplies.

[1609] Specific operation: The server updates the database with "The latest number of evacuees at shelter A is 600, and there is a water shortage," and recalculates that "An additional 100 liters of water and 100 meals are needed."

[1610] Step 10:

[1611] The server sends a delivery instruction for the additional supplies to the logistics company.

[1612] Input: Recalculated amount of aid.

[1613] Data processing: Update shipping schedule.

[1614] Output: The new delivery schedule.

[1615] Specific operation: The server generates a new delivery schedule such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A" and sends instructions to the logistics company.

[1616] (Application example 1)

[1617] 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."

[1618] During an earthquake, it is important to quickly and accurately grasp the situation at evacuation centers and effectively supply the necessary relief supplies. However, due to communication environment problems and sudden increases and decreases in the number of evacuees, it is difficult to accurately grasp the situation on site, which can lead to problems with delays in the timely delivery of relief supplies. In addition, insufficient coordination with logistics companies can make it difficult to distribute supplies appropriately.

[1619] 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.

[1620] In this invention, the server includes means for collecting communication environment data and mobile population data immediately before the earthquake, means for estimating the number of evacuees at each evacuation shelter using an artificial intelligence model based on the collected data, means for calculating the amount of relief supplies needed based on the estimate results and issuing instructions for the preparation and delivery of supplies, means for collecting information on the local situation after communication is restored, updating the data, recalculating the needed supplies, and issuing instructions for additional supplies, means for automatically and dynamically generating a delivery schedule for needed supplies and sending instructions to logistics companies, and means for quickly sending the latest information via a terminal used by the evacuation shelter manager. This makes it possible to efficiently and accurately grasp the situation at evacuation shelters and provide needed supplies even during communication disruptions.

[1621] "Communication environment data immediately before the earthquake" is data obtained from communication carriers and internet service providers that indicates the communication conditions immediately before the earthquake occurred.

[1622] "Floating population data" is data that shows the movement and distribution of population in a specific area over a certain period of time.

[1623] An "artificial intelligence model" is a statistical model that uses machine learning and deep learning to learn from past data and predict future situations.

[1624] "Means for estimating the number of evacuees" refers to techniques and methods for predicting the number of evacuees at each evacuation shelter using an artificial intelligence model based on collected data.

[1625] "Means for calculating the amount of necessary relief supplies" refers to techniques and methods for calculating the required amount of supplies such as water, food, medicine, blankets, health supplies, and consumables based on the predicted number of evacuees.

[1626] "Means for directing the preparation and delivery of supplies" refers to the techniques and methods for preparing needed relief supplies and planning and directing their delivery to each evacuation shelter.

[1627] "Means for collecting on-site information and updating data after communications are restored" refers to the technology and methods for collecting the latest information from evacuation centers and updating the database based on that information when communications are restored after a disaster occurs.

[1628] "Means for ordering additional supplies" refers to techniques and methods for recalculating the required supplies based on updated data and issuing instructions if additional supplies are required.

[1629] "Means for automatically generating dynamic delivery schedules for necessary supplies" refers to technologies and methods for automatically creating optimal supply delivery schedules in real time using AI models and algorithms.

[1630] The "means for sending instructions to the logistics company" refers to a technique or method for notifying the logistics company of the generated delivery schedule and the need for additional supplies, and for instructing them on how to respond.

[1631] "Devices used by evacuation shelter managers" are devices such as smartphones and tablets that evacuation shelter managers use to enter information such as local conditions and necessary supplies and send it to a server.

[1632] The system based on this invention is constructed to quickly and accurately grasp the situation at evacuation centers in the event of an earthquake and to effectively supply the necessary relief supplies. The system operates in cooperation with the server, terminals, and users, and performs processing in the following steps.

[1633] System Configuration

[1634] 1. Server

[1635] Hardware: High-performance web servers (e.g., Amazon Web Services (AWS), Microsoft Azure)

[1636] Software: Communication API, TensorFlow, Requests library

[1637] Functions: Data collection, data standardization, predictions using AI models, and sending instructions to logistics companies

[1638] 2. Terminal

[1639] Hardware: Smartphones, tablets (e.g. Android, iOS)

[1640] Function: The shelter manager inputs local information and sends it to the server.

[1641] 3. Users

[1642] Role: Evacuation center manager, inputting the number of evacuees and the status of supplies via terminal

[1643] Operation flow

[1644] Data collection

[1645] The server collects data on the communication environment and population movement immediately before the earthquake from telecommunications carriers and internet service providers. The collected data is standardized into the required data format.

[1646] Prediction by AI model

[1647] The standardized data is input into an artificial intelligence model (e.g., a neural network using TensorFlow) to predict the number of evacuees at each shelter in real time. For example, the server calculates that "the predicted number of evacuees at shelter A immediately after the earthquake is 500 people."

[1648] Estimating supplies and preparing for delivery

[1649] Based on the prediction results, the server calculates the amount of relief supplies needed and automatically generates a dynamic delivery schedule. The calculation includes specific relief supplies such as water, food, medicine, blankets, health supplies, and consumables. For example, it calculates that "500 evacuees need 500 liters of water, 500 meals, and 500 blankets." The calculated results are sent as instructions to logistics companies.

[1650] The server generates a specific delivery schedule, such as "send supplies from warehouse X to shelter A in one truck," and sends instructions.

[1651] Gathering information at evacuation shelters

[1652] The shelter manager uses a device (smartphone or tablet) to input the number of evacuees and the status of supplies. For example, if the manager inputs "the current number of evacuees is 600, and there is a water shortage," the information is immediately sent to the server.

[1653] Data updates and additional supplies

[1654] The server updates the database based on the latest information received and recalculates the amount of supplies needed. If the recalculation shows that additional supplies are needed, it quickly issues instructions to logistics companies to provide the additional supplies. For example, it may recalculate the amount to "an additional 100 liters of water and 100 meals are needed," and immediately send delivery instructions.

[1655] Specific examples

[1656] At shelter A, the server collects the latest local information and predicts the number of evacuees. Based on these results, it dynamically calculates the amount of relief supplies needed and automatically generates a truck delivery schedule. The shelter manager uses a smartphone to instantly send the actual number of evacuees and the status of supplies to the server, which then updates the database with this information and draws up a plan for additional supplies.

[1657] Prompt Sentence Examples

[1658] "Collect the latest population and communication data for shelter A from the server, and use an AI model to predict the number of evacuees. Based on the prediction, calculate the necessary relief supplies and generate Python code to schedule the delivery of supplies to shelter A."

[1659] By operating in this way, the system can efficiently and accurately grasp the situation at evacuation centers and provide necessary supplies even if communications and power supplies are cut off during an earthquake.

[1660] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1661] Step 1: Data collection

[1662] The server collects real-time data on the communication environment immediately before the earthquake and data on the local population flow from telecommunications carriers and internet service providers via API. It uses API endpoints as input and obtains the collected data as output. The server saves the collected data in JSON format or other formats.

[1663] Step 2: Data Standardization

[1664] The server standardizes the collected data before applying it to the AI ​​model. Specifically, it fills in any imperfections in the data, removes outliers, and converts it into the required format. It uses the collected raw data as input and obtains standardized data as output. The server then adapts this data to the input format of the AI ​​model.

[1665] Step 3: Predict the number of evacuees

[1666] The server inputs the standardized data into an artificial intelligence model to predict the number of evacuees at each shelter. Using the standardized data as input, the server obtains the predicted number of evacuees as output. Specifically, the neural network model performs the calculations using machine learning libraries such as TensorFlow.

[1667] Step 4: Calculate supply needs

[1668] The server calculates the amount of supplies needed based on the predicted number of evacuees. It uses the predicted number of evacuees as input and gets a detailed list of needed supplies as output. For example, it calculates "500 evacuees need 500 liters of water, 500 meals, and 500 blankets."

[1669] Step 5: Auto-generate delivery schedules

[1670] The server automatically generates a delivery schedule for logistics companies based on the relief supply list. It uses the supply list as input and obtains a specific delivery plan as output. For example, the server generates a schedule such as "Send supplies from Warehouse X to Evacuation Center A by one truck."

[1671] Step 6: Send instructions to logistics provider

[1672] The server sends the generated delivery schedule as instructions to the logistics company. It uses the automatically generated delivery schedule as input and verifies that the instructions were sent correctly as output. The server does this via HTTP requests, etc.

[1673] Step 7: Gather local information

[1674] The terminal is used by the shelter manager to input the latest local situation. For example, the shelter manager might use the terminal to input "the current number of evacuees is 600, and there is a water shortage." The information obtained on-site is used as input, and that information is sent to the server as output.

[1675] Step 8: Update the Database

[1676] The server updates the database based on the latest information sent from the terminal. It uses the data sent from the field as input and obtains the updated database as output. The server then updates the database to show that "the latest number of evacuees at shelter A is 600, and there is a water shortage."

[1677] Step 9: Recalculate and order additional supplies

[1678] The server recalculates the amount of supplies needed based on the updated database and issues instructions if additional supplies are required. It uses the latest database information as input and obtains a recalculated list of supplies as output. For example, it may recalculate, "We need an additional 100 liters of water and 100 meals of food," and send additional delivery instructions to the logistics company.

[1679] By implementing each of the above steps, we will create a system that will enable efficient and accurate assessment of the situation at evacuation centers and the supply of necessary supplies, even if communications and power supplies are cut off during an earthquake.

[1680] 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.

[1681] The system based on this invention is implemented as follows to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply necessary relief supplies. This system functions in cooperation with the server, terminals, and users, and by combining it with an emotion engine, it also provides psychological support to evacuees.

[1682] Data collection

[1683] 1. The server collects mobile population data and communication environment data from telecommunications carriers and Internet service providers (ISPs).

[1684] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[1685] AI estimation

[1686] 1. The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1687] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[1688] 2. The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[1689] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[1690] Estimating necessary supplies and preparing for delivery

[1691] 1. Based on the estimated results, the server calculates the amount of relief supplies needed for each evacuation shelter.

[1692] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[1693] 2. The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[1694] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1695] 3. The server connects to the logistics company system and automatically generates a delivery plan for supplies.

[1696] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[1697] Gathering information at evacuation shelters

[1698] 1. The terminal is a smartphone or tablet used by the shelter manager, who inputs the number of evacuees and the status of supplies on site.

[1699] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[1700] 2. The terminal sends the entered information to the server.

[1701] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1702] Data updates and supply adjustments

[1703] 1. The server updates the database based on the latest information sent from the evacuation center.

[1704] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1705] 2. The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1706] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1707] 3. Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1708] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1709] Emotion engine integration

[1710] 1. The device collects facial expressions, voice, and text data from shelter managers and evacuees and sends it to the emotion engine.

[1711] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[1712] 2. The emotion engine analyzes the collected data and recognizes the user's emotional state.

[1713] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[1714] 3. The emotion engine sends the recognized emotion data to the server.

[1715] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[1716] 4. The server will use the emotional data to direct additional psychological support or special supplies.

[1717] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[1718] In this way, the system operates in cooperation with the server, terminals, users, and emotion engine, making it possible to efficiently and accurately grasp the situation at evacuation centers, provide necessary supplies, and even provide psychological care for evacuees, even if communications and power supplies are cut off during an earthquake.

[1719] The processing flow will be explained below.

[1720] Step 1:

[1721] The server collects mobile population data and communication environment data from telecommunications carriers and internet service providers (ISPs).

[1722] Example: The server uses an API to obtain demographic information from each telecommunications carrier and communication usage information from ISPs in real time.

[1723] Step 2:

[1724] The server preprocesses the collected data and inputs it into an artificial intelligence model.

[1725] Example: The server normalizes the acquired data, fills in missing data, and converts it into a data format for the AI ​​model.

[1726] Step 3:

[1727] The server uses an artificial intelligence model to predict the number of evacuees at each shelter.

[1728] Example: The server uses a neural network model trained on data from past earthquakes to output the estimated result that "the predicted number of evacuees at shelter A is 500."

[1729] Step 4:

[1730] Based on the estimated results, the server calculates the amount of relief supplies needed at each evacuation shelter.

[1731] Example: The server calculates that "500 evacuees will need 500 liters of water, 500 meals, and 500 blankets."

[1732] Step 5:

[1733] The server accesses the local government's stockpile database and checks the stock status of needed supplies.

[1734] Example: The server confirms that "Warehouse X has 500 liters of water, 500 meals, and 500 blankets in stock."

[1735] Step 6:

[1736] The server connects to the logistics company's system and automatically generates a delivery plan for supplies.

[1737] Example: The server creates a specific delivery schedule such as "Deliver supplies from Warehouse X to Evacuation Center A using one truck."

[1738] Step 7:

[1739] The terminals are smartphones or tablets used by shelter managers, who input the number of evacuees and the status of supplies on site.

[1740] Example: A shelter manager types into a terminal, "Current number of evacuees: 600, water shortage."

[1741] Step 8:

[1742] The terminal transmits the input information to the server.

[1743] Example: The terminal sends the latest information on the number of evacuees and shortages of supplies at shelter A to the server.

[1744] Step 9:

[1745] The server updates the database based on the latest information sent from the evacuation center.

[1746] Example: The server updates the database with the following information: "The latest number of evacuees at shelter A is 600, and there is a water shortage."

[1747] Step 10:

[1748] The server recalculates the amount of supplies needed based on the latest data and calculates the amount of additional supplies that should be supplied.

[1749] Example: The server recalculates and concludes, "We need an additional 100 liters of water and 100 meals."

[1750] Step 11:

[1751] Based on the recalculation results, the server issues instructions to the logistics company to deliver additional supplies.

[1752] Example: The server generates a new delivery schedule, such as "Deliver an additional 100 liters of water and 100 meals from Warehouse Y to Evacuation Center A," and sends instructions to the logistics company.

[1753] Step 12:

[1754] The device collects facial expressions, voice, and text data from shelter managers and evacuees, and sends it to the emotion engine.

[1755] Example: The shelter manager takes pictures of the evacuees' facial expressions using a smartphone camera and analyzes them using an emotion engine.

[1756] Step 13:

[1757] The emotion engine analyzes the collected data and recognizes the user's emotional state.

[1758] Example: The emotion engine recognizes that "evacuee A is in a stressful state, and evacuee B is in a relieved state."

[1759] Step 14:

[1760] The emotion engine sends the recognized emotion data to the server.

[1761] Example: The emotion engine reports to the server that "Many of the evacuees at shelter A are in a state of stress."

[1762] Step 15:

[1763] The server uses the emotional data to direct additional psychological support or special supplies.

[1764] Example: The server issues instructions to the local government such as "dispatch psychological counselors to shelter A" and also implements measures such as "provide additional entertainment materials to relieve stress."

[1765] Example 2

[1766] 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."

[1767] There is a need for a system that can quickly and accurately grasp the situation at evacuation centers during earthquakes, effectively provide necessary relief supplies, and comprehensively provide psychological support to evacuees. Conventional systems do not collect and update local information about evacuation centers in real time, which can lead to delays in recalculating needed supplies and providing additional supplies, and insufficient psychological support for evacuees. Therefore, a system is needed that can improve the efficiency of evacuation center management and the safety and psychological care of evacuees.

[1768] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication environment data and floating population data, means for normalizing and imputing the collected data and inputting it into an AI model, means for predicting the number of evacuees at each evacuation shelter using the AI ​​model, means for calculating the amount of relief supplies needed based on the prediction results and instructing the preparation and delivery of supplies, means for the evacuation shelter manager to send local information to the server using a terminal, means for updating the database based on the local information, recalculating the amount of needed supplies, and instructing the additional supply, means for collecting emotional data of evacuees via the terminal and sending it to the emotion engine, and means for instructing psychological support and the supply of special supplies based on the emotional data analyzed by the emotion engine. This enables efficient and accurate assessment of the situation at evacuation shelters, the supply of necessary supplies, and psychological care for evacuees during an earthquake disaster.

[1769] "Communication environment data" refers to information such as communication network usage status, connection status, and communication speed obtained from communication carriers and Internet service providers.

[1770] "Floating population data" is statistical information that shows the movement patterns and number of people in a specific area, and is mainly calculated from location information of communication devices.

[1771] An "artificial intelligence model" is a calculation algorithm that learns from past data and predicts new situations, and in this invention it is used to predict the number of evacuees and the amount of necessary supplies.

[1772] "Normalization" is a process in data processing that converts collected raw data into a unified format, and is a means of improving data quality.

[1773] "Gap imputation" is the process of filling in missing data with appropriate values ​​in order to build a complete dataset.

[1774] "Terminal" refers to a device such as a smartphone or tablet used by shelter managers and other users, and is used to input and transmit information.

[1775] An "emotion engine" is a software system that recognizes a user's emotional state by analyzing collected data such as facial expressions, voice, and text.

[1776] "Evacuation forecasting" is the process of using artificial intelligence models to estimate the number of people who will evacuate to a particular shelter in the event of a disaster.

[1777] "Relief supplies" refer to basic daily necessities and services that evacuees need in the event of a disaster, such as water, food, medicine, blankets, and recreational items.

[1778] "Psychological support" refers to counseling and other support activities aimed at reducing the psychological distress and stress of evacuees.

[1779] "Database updating" is the process of updating existing data to reflect the latest information, and is done to keep information accurate in real time.

[1780] "Delivery instructions" are instructions given to deliver supplies to where they are needed, and refer to the act of providing logistics companies with specific delivery plans and schedules.

[1781] "Emotion data" is information indicating emotions extracted from the user's facial expressions, voice, text, etc., and is analyzed by the emotion engine.

[1782] The system based on this invention involves the cooperation of a server, terminals, users, and an emotion engine in order to quickly and accurately grasp the situation at evacuation shelters in the event of an earthquake and to effectively supply the necessary relief supplies. This system is configured as follows:

[1783] Data collection

[1784] The server collects data on the current population and communication environment from telecommunications carriers and internet service providers (ISPs). It uses APIs to obtain data in real time from each telecommunications carrier and ISP. For example, the server uses APIs to collect demographic information from telecommunications carriers.

[1785] Data preprocessing and AI calculations

[1786] The collected data is normalized on the server and missing data is supplemented. The formatted data is then input into an artificial intelligence model. This artificial intelligence model is a neural network model that has been trained based on data from past earthquakes. This model is used to predict the number of evacuees at each evacuation shelter. For example, the server outputs a calculated result such as "The predicted number of evacuees at shelter A is 500."

[1787] Estimating necessary supplies and preparing for delivery

[1788] Based on the estimates, the server calculates the amount of relief supplies needed for each evacuation center. This includes water, food, medicine, blankets, and recreational items. For example, the server might calculate that 500 evacuees need 500 liters of water, 500 meals, and 500 blankets. It then accesses the local government's stockpile database to check the inventory status of the necessary supplies. It then connects to the logistics company's system to automatically generate a specific delivery schedule and issue instructions to the logistics company.

[1789] Gathering information at evacuation shelters

[1790] The terminal allows the shelter manager to input the number of evacuees and the current status of supplies via a smartphone or tablet. For example, the shelter manager might input "the current number of evacuees is 600, and there is a water shortage" into the terminal, and this information is then sent to the server.

[1791] Data updates and supply adjustments

[1792] The server updates the database based on the latest information sent from the evacuation center. This allows it to recalculate the amount of supplies needed based on the latest situation and calculate the amount of additional supplies that should be provided. For example, the server may recalculate that an additional 100 liters of ...

Claims

1. A means of collecting data on the communication environment and the floating population immediately before the earthquake; A method to estimate the number of evacuees at each shelter using an artificial intelligence model based on the collected data, and A means to calculate the amount of relief supplies needed based on the estimated results and to give instructions for the preparation and delivery of the supplies; A means of collecting information on the situation on the ground after communication is restored, updating the data, recalculating the required supplies, and ordering additional supplies; A system including:

2. The system according to claim 1 , wherein the artificial intelligence model learns data on past earthquake disasters.

3. 2. The system of claim 1, wherein the means for calculating the amount of supplies needed includes specific relief supplies such as water, food, medicine, and blankets.

Images