System

Abstract

To provide a system capable of realizing efficient and rapid supply of relief supplies.SOLUTION: A terminal means for inputting necessary items by a user in a chat format or a voice input format, a server means including a means for transmitting input data to a server, a natural language processing means for converting voice data into text data, a necessary item specifying means for analyzing the text data and specifying necessary items and urgency thereof, a means for visualizing necessary items on a map based on an analysis result and geographical information, a disaster data collecting means for collecting disaster data and predicting needs of items, and a prediction model learning means for learning a prediction model; The system includes a machine learning means for improving accuracy, a means for generating an article distribution plan based on an analysis result and a prediction, and a means for notifying the generated distribution plan.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] During a disaster, many victims require different items, making it extremely difficult to grasp in real time which evacuation centers need what kind of relief supplies. Furthermore, not all victims are accustomed to text-based input, which can delay understanding relief needs. It is also difficult to predict supply needs based on the disaster situation and past data, resulting in delays and shortages of relief. It is desirable to solve these issues and realize the efficient and rapid supply of relief supplies. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] A means is provided for users to input needed items via chat or voice input. The terminal has a means for transmitting the input data to a server. The server includes a means for converting voice data into text data and a natural language processing means for analyzing the text data and identifying needed items and their urgency. The server further provides a means for visualizing needed items on a map based on the analysis results and geographic information. The server also has a means for collecting disaster data and predicting needs for items. It also provides a machine learning means for training a predictive model and improving accuracy. It also has a means for generating an item distribution plan based on the analysis results and predictions, and a means for notifying the generated distribution plan. This makes it possible to grasp support needs in real time and realizes the rapid and appropriate supply of relief supplies.

[0007] "User" refers to victims or people in need of assistance who use the system.

[0008] "Chat format" refers to an interactive interface that uses text input.

[0009] "Voice input format" refers to an interface that uses voice input.

[0010] "Goods" refers to relief supplies needed by disaster victims, including water, food, blankets, etc.

[0011] "Terminal" refers to electronic devices used by users, such as smartphones, tablets, and personal computers.

[0012] "Server" refers to a central computer system that receives, analyzes, and processes data.

[0013] "Voice data" refers to voice information input by a user in a voice input format.

[0014] "Text data" refers to character information obtained by converting voice data into text format.

[0015] "Natural language processing means" refers to technology that analyzes text data and extracts necessary information from it.

[0016] "Geographic information" refers to data that includes information related to locations, such as map information.

[0017] "Disaster data" refers to information related to weather, earthquakes, and other disasters.

[0018] "Machine learning" refers to the technology that allows computers to analyze data to learn and improve predictive models.

[0019] "Materials distribution plan" refers to a plan that determines how much of the necessary materials will be sent to which locations.

[0020] "Means of notification" refers to the means by which the distribution plan will be communicated to the support team and related parties. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] Overview of the entire system

[0043] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0044] User input of items

[0045] Users can use devices such as smartphones or computers to input what items they need via chat or voice input. For example, users can input information such as "I need water" or "Please give me a blanket."

[0046] Data transmission by the terminal

[0047] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0048] Data preprocessing by the server

[0049] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0050] Data analysis using natural language processing

[0051] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0052] Aggregation and visualization of needs information

[0053] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0054] Disaster data collection and needs forecasting

[0055] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0056] Updating predictive models with machine learning

[0057] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[0058] Generate and notify material distribution plans

[0059] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0060] Specific examples

[0061] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model and obtains the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0062] This will enable the efficient and rapid supply of relief goods, and the system aims to provide faster and more accurate support in the event of a disaster.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0066] Step 2:

[0067] The device sends the data entered by the user to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3. In the case of text input, the data is sent in its original format.

[0068] Step 3:

[0069] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[0070] Step 4:

[0071] The server uses a natural language processing model to analyze the text data, extracting information such as "Items needed: water, Urgency: high." The same analysis is done for text input in chat format.

[0072] Step 5:

[0073] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored.

[0074] Step 6:

[0075] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on the supplies needed. For example, an icon saying "Water needed" is displayed at the location of shelter A.

[0076] Step 7:

[0077] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[0078] Step 8:

[0079] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[0080] Step 9:

[0081] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[0082] Step 10:

[0083] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[0084] Step 11:

[0085] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[0086] These steps ensure efficient and rapid delivery of support items.

[0087] Example 1

[0088] 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."

[0089] In the event of a disaster, it is extremely important to provide necessary items to victims quickly and effectively, but current methods often result in insufficient information gathering and needs analysis, which delays appropriate assistance. Furthermore, the accuracy of predictive models is low, making it difficult to provide necessary items appropriately. The aim of this project is to solve these issues.

[0090] 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.

[0091] In this invention, the server includes a means for storing data generated from user input in a database, a means including a data analysis engine for extracting necessary information from the database, a means for analyzing past disaster data and identifying demand patterns for necessary items, a means for integrating multiple external data sources to predict future needs, and a means for optimizing item distribution plans using a machine learning predictive model, thereby enabling the prompt and appropriate distribution of relief items based on the needs of disaster victims.

[0092] A "user" is an individual or entity that uses the system to input required items.

[0093] A "terminal" is a device used by a user to send data entered by the user to a server via the Internet, and includes smartphones and personal computers.

[0094] A "server" is a central computer system that processes received data and analyzes user needs.

[0095] "Audio data" refers to digital data that represents an audio signal input by a user in the form of a voice input.

[0096] "Text data" is character-based data converted from voice data by a voice recognition engine.

[0097] "Natural language processing" refers to a set of technologies and methods for analyzing text data to identify needed items and their urgency.

[0098] "Geographic information" refers to location information of disaster areas and evacuation centers displayed using a geographic information system.

[0099] "Disaster data" refers to various types of data related to disasters, such as weather data and earthquake information.

[0100] A "predictive model" is a mathematical model for predicting future product needs based on collected data.

[0101] "Machine learning" is a collection of algorithms and techniques that improve the accuracy of predictive models based on data.

[0102] "Item distribution plan" refers to a specific item supply plan generated based on needs and forecasts.

[0103] A "database" is a collection of data collected, stored, and managed by a system.

[0104] A "data analysis engine" refers to a technology or system that analyzes information stored in a database and extracts the necessary information.

[0105] "External Data Source" means an external information source used by the system to gather data.

[0106] "Distribution plan optimization" refers to the process of formulating optimal distribution strategies to supply goods efficiently and effectively.

[0107] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0108] Hardware and Software Configuration

[0109] The user's terminal can be a smartphone, PC, or other general device. These terminals connect to the Internet and transmit user input to the server. Specific software includes a voice conversion module and a chat application.

[0110] The server is a central computer system for processing received data. It is equipped with a speech recognition engine, a natural language processing model, a database management system, a data analysis engine, and a machine learning model. Specific software used includes Google® Cloud Speech-to-Text, BERT, and GPT-3®.

[0111] System Operation Overview

[0112] The user uses the terminal to input the items they need through chat or voice input. For example, the user inputs information such as "I need water" or "Please give me a blanket." This input data is sent by the terminal to the server via the Internet.

[0113] When a voice input is received, the server uses a voice recognition engine to convert the voice data into text data. Through this process, the voice data is converted into text data such as "I need water."

[0114] The server then uses a natural language processing model to analyze the text data. This process extracts information about the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0115] The analyzed information is stored in a database and visualized on a map using a geographic information system, allowing support teams to see at a glance what is needed at each evacuation shelter.

[0116] In addition, the server uses external APIs to collect weather data, earthquake information, and other disaster data. This data is analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0117] The server uses machine learning models to learn from past disaster data and improve its accuracy, which in turn makes forecasts of demand for goods more accurate.

[0118] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific plan might be created, such as "Send 50 liters of water to shelter A."

[0119] Specific examples

[0120] During a disaster, if a user uses a device to voice-input "I need food," the device sends this voice data to a server. The server uses a speech recognition engine to convert the voice data into text data, generating the text "I need food." Next, it analyzes the text data using a natural language processing model and extracts the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0121] Prompt Sentence Examples

[0122] 1. "Can you give me a Python code example for implementing an API for disaster data collection?"

[0123] 2. "How do I train a natural language processing model to extract supply needs during a disaster?"

[0124] 3. "Explain how to use TENSORFLOW® to forecast demand for goods from disaster data."

[0125] 4. "How do I update a product demand forecast model using past disaster data?"

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1:

[0128] Users use devices such as smartphones or PCs to input the items they need through chat or voice input. Specifically, the user opens the application on their device and types "I need water" into the chat box, or presses the voice input button and speaks "I need a blanket." This input is received as the system's initial data.

[0129] Step 2:

[0130] The device receives user input, and if there is voice input, it uses the device's voice conversion module to convert the voice data into WAV or MP3 format. This converted data is then sent to the server via the Internet. Specifically, the device saves the voice input data as a WAV file and sends this data to the server via an HTTP request.

[0131] Step 3:

[0132] The server passes the received voice data to a speech recognition engine (for example, Google Cloud Speech-to-Text), which converts the voice data into text data. Specifically, the server sends the received wav file to the speech recognition engine, which receives the text data "I need a blanket." The output is the text data "I need a blanket."

[0133] Step 4:

[0134] The server uses a natural language processing model (e.g., BERT or GPT-3) to analyze the text data and extract the items needed and their urgency. The input is the text data "I need a blanket," and the output is "Item needed: Blanket, Urgency: High." Specifically, the server applies a natural language processing algorithm to analyze the text data.

[0135] Step 5:

[0136] The server stores the analysis results in a database. Specifically, it records information such as "Needed items: Blanket, Urgency: High" in the appropriate fields of the database. This process allows the server to accumulate information for subsequent processing.

[0137] Step 6:

[0138] The server uses a geographic information system (GIS) to visualize information about needed items on a map. For example, information such as "Shelter C: Necessary items = Blankets, Quantity = 10, Urgency = High" is displayed at a glance on the map. This allows support teams to instantly understand what is needed at each shelter.

[0139] Step 7:

[0140] The server uses external APIs (e.g., OpenWeatherMap and USGS Earthquake Data) to collect weather data, earthquake information, and other disaster data. An API request is sent as input, and weather data and earthquake information are returned as output. Specifically, the server sends a request to the API to obtain the latest disaster data.

[0141] Step 8:

[0142] The server analyzes the acquired disaster data and predicts future needs for supplies. The acquired disaster data is used as input, and the predicted information that "demand for water will increase" in the future is obtained as output. Specifically, the server runs a prediction algorithm and analyzes the disaster data.

[0143] Step 9:

[0144] The server trains a machine learning model using past disaster data to improve the accuracy of the predictive model. Past disaster data is given as input, and a machine learning algorithm is applied. A highly accurate predictive model is generated as output. Specifically, the server trains a new model using TensorFlow.

[0145] Step 10:

[0146] The server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific distribution plan may be created, such as "send 50 liters of water to shelter A." The output is a notification via the support team's dedicated app or email.

[0147] (Application example 1)

[0148] 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."

[0149] In the event of a disaster, it is extremely important to quickly and efficiently supply the necessary supplies to affected areas. However, conventional systems have had difficulty properly receiving and analyzing supply requests from affected areas and formulating and executing supply plans for relief supplies in real time. Furthermore, there was a lack of means to accurately predict future demand for supplies through the collection and analysis of disaster data. This limited the ability of logistics centers and relief organizations to respond appropriately, resulting in a high likelihood of delays in the supply of supplies to disaster victims and / or shortages and surpluses. Therefore, to solve these issues, a system is needed that can analyze and visualize requests from affected areas in real time and formulate appropriate supply plans.

[0150] 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.

[0151] In this invention, the server includes a means for users to input needed items via chat or voice input, a terminal means for transmitting the input data to the server, and a means for converting voice data into text data. This enables accurate and rapid receipt and analysis of requests for items from disaster-stricken areas. The server also includes a natural language processing means for analyzing the text data to identify needed items and their urgency, a means for visualizing needed items on a map based on the analysis results and geographic information, a means for collecting disaster data and predicting item needs, a machine learning means for training a prediction model to improve accuracy, a means for generating an item distribution plan based on the analysis results and predictions, a means for notifying the generated distribution plan, a means for optimizing the supply of relief items based on the item requests received by the logistics center, a means for visualizing user requests in real time, and a means for acquiring disaster data from an external data source and predicting item demand. This enables effective supply of items in line with the needs of disaster victims, thereby achieving rapid and accurate support for disaster-stricken areas.

[0152] The "chat format" is a form of communication in which users input text, and is an interface that allows messages to be sent and received in real time.

[0153] The "voice input format" is a format in which users input information using voice, and is an interface that receives and analyzes user requests by converting voice into text.

[0154] "Terminal means" refers to a device that allows a user to input information and send it to a server, and includes, for example, a smartphone, tablet, or PC.

[0155] The "server means" is a central computer system for performing data processing, and is a device that converts voice data into text data, performs natural language processing, and performs various data analyses.

[0156] "Natural language processing means" refers to technology for analyzing text data and identifying needed items and their urgency, and refers to the function of understanding and processing language data using machine learning models and algorithms.

[0157] "Visualization means" refers to technology that displays analyzed data on a map, allowing people to intuitively grasp the needs for goods.

[0158] "Disaster data" is a general term for disaster-related data such as meteorological information and earthquake information, and by collecting and analyzing this data, it can be used to forecast demand for goods.

[0159] "Prediction methods" are technologies and models for predicting future supply needs based on collected disaster data.

[0160] "Machine learning methods" are techniques that use past data to learn and improve the accuracy of predictive models, usually using algorithms or neural networks.

[0161] A "distribution plan" is a plan that specifically outlines how necessary items will be supplied to disaster-stricken areas, and determines the optimal distribution route and quantities.

[0162] "Notification methods" refer to technologies used to inform support teams and related organizations of the generated distribution plan, such as email, SMS, and notification apps.

[0163] A "logistics center" is a central facility for efficiently storing and managing goods and delivering them to disaster-stricken areas.

[0164] "Real-time visualization means" refers to technology that instantly displays user requests, enabling timely confirmation of needs for support items.

[0165] "External data sources" are external databases or APIs that provide disaster data and other relevant information that can be used to improve the accuracy of the predictive models.

[0166] This invention is a system for quickly and efficiently supplying necessary items to disaster victims in the event of a disaster. This system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[0167] User input of items

[0168] Users can input what items they need using chat or voice input on devices such as smartphones or computers. For example, users can input information such as "I need water" or "Please give me a blanket."

[0169] Data transmission by the terminal

[0170] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0171] Data preprocessing by the server

[0172] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0173] Data analysis using natural language processing

[0174] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0175] Aggregation and visualization of needs information

[0176] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0177] Disaster data collection and needs forecasting

[0178] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0179] Updating predictive models with machine learning

[0180] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[0181] Generate and notify material distribution plans

[0182] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0183] Addition of functions for logistics centers

[0184] This system also includes a function that enables logistics centers to optimize the supply of disaster relief supplies. The logistics center receives request data from users in real time and can create optimal supply plans based on needs information visualized on a map. In addition, by using disaster data obtained from external data sources, it is possible to accurately predict future demand for supplies and supply them accordingly.

[0185] Usage example

[0186] For example, if a user uses a device to say "I need food" during a disaster, this voice data is sent to a server and converted into text data by a speech recognition engine. Then, using a natural language processing model, the information "Needed items: food, Urgency: high" is extracted. This information is stored in a database and visualized on a map. Based on this information, the logistics center can create and execute a food supply plan for disaster-stricken areas. Furthermore, by collecting and analyzing weather data and other disaster data, future demand for goods can be predicted, enabling more effective support.

[0187] Prompt Sentence Examples

[0188] Here are some examples of prompts for generative AI models:

[0189] "We are developing an application that predicts the need for relief supplies during disasters and creates optimal distribution plans. It converts voice input into text, uses natural language processing to analyze the supplies needed and their urgency, and visualizes them on a map. It also obtains weather data from an external API to predict future needs. This will enable efficient supply of supplies."

[0190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0191] Step 1:

[0192] The user inputs the items they need in chat or voice input format. Using a device such as a smartphone or PC, the user inputs information such as "I need water" or "Can I have a blanket?" This generates text data or voice data. Input: Text data or voice data from the user. Output: Text data or voice data.

[0193] Step 2:

[0194] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the voice data is converted on the device into a common audio format such as WAV or MP3, and then sent to the server along with the text data. Input: Text data or voice data. Output: Text data or voice data sent to the server.

[0195] Step 3:

[0196] When the server receives the voice data, it uses a voice recognition engine to convert the voice data into text data. As a result, voice data such as "I need water" is converted into text data. Input: Voice data. Output: Text data.

[0197] Step 4:

[0198] The server uses a natural language processing model to analyze the text data. This process extracts needed items and their urgency from the text data. For example, from the text "I need water," the information "Needed items: Water, Urgency: High" is obtained. Input: Text data. Output: Information on needed items and urgency.

[0199] Step 5:

[0200] The server stores the analyzed information in a database. Next, using a geographic information system, the location of each evacuation center and disaster victims, along with information on necessary items, are visualized on a map. Input: Information on necessary items and urgency. Output: Needs information displayed on a map.

[0201] Step 6:

[0202] The server uses an external API to collect disaster data such as weather data and earthquake information. It analyzes this disaster data and predicts future needs for goods. For example, it predicts future increases in demand for water based on rainfall data. Input: Disaster data obtained from the external API. Output: Predicted demand for goods.

[0203] Step 7:

[0204] The server uses past disaster data to train the predictive model and improve its accuracy. This makes demand forecasts for goods more accurate. Input: Past disaster data. Output: Improved predictive model.

[0205] Step 8:

[0206] The server generates an optimal distribution plan based on the analysis results and prediction data. For example, a specific plan such as "Send 50 liters of water to shelter A" is created. Input: Analysis results and prediction data. Output: Distribution plan.

[0207] Step 9:

[0208] The server notifies the support team and local governments of the generated item distribution plan, allowing support items to be supplied quickly and accurately. Input: Item distribution plan. Output: Notified distribution plan.

[0209] Step 10:

[0210] The logistics center optimizes the supply of relief goods based on the goods requests received from the server. It determines the optimal supply route and quantity of goods, taking into account congestion and logistics efficiency. Input: Goods requests from users and disaster data. Output: Optimized supply plan.

[0211] 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.

[0212] Overview of the entire system

[0213] This invention is a system for efficiently supplying disaster victims with necessary items. By combining it with an emotion engine, it provides support that takes into account the emotional state of the disaster victims. The system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0214] User input of items

[0215] Users can input the items they need using chat or voice input using devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0216] Data transmission by the terminal

[0217] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0218] Data preprocessing by the server

[0219] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0220] Data analysis using natural language processing

[0221] The server uses natural language processing models to analyze text data, extracting information such as "Item needed: water, Urgency: high." Chat input is also analyzed.

[0222] Emotion analysis using an emotion engine

[0223] The server also uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from voice tone and text content.

[0224] Emotional information integration

[0225] Emotional information from the emotion engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[0226] Aggregation and visualization of needs information

[0227] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0228] Disaster data collection and needs forecasting

[0229] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data and predicts future needs for supplies. For example, it predicts future increases in water demand based on rainfall data.

[0230] Updating predictive models with machine learning

[0231] The server uses past disaster data to train and improve the predictive model, which will lead to more accurate forecasts of future supply needs.

[0232] Generate and notify material distribution plans

[0233] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0234] Specific examples

[0235] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model to obtain the information "Needed items: food, Urgency: high." Furthermore, it uses an emotion engine to extract the information "Stress level: high" from the voice data. This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0236] This will enable the efficient and rapid supply of relief goods, while also enabling support that takes into consideration the emotional state of the victims.The system aims to provide faster and more accurate support during disasters.

[0237] The processing flow will be explained below.

[0238] Step 1:

[0239] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0240] Step 2:

[0241] The device sends the user's input data to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3 before sending it. In the case of text input, the data is sent in its original format.

[0242] Step 3:

[0243] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[0244] Step 4:

[0245] The server uses a natural language processing model to analyze text data, extracting information such as "Items needed: water, Urgency: high." Chat input is also analyzed in the same way.

[0246] Step 5:

[0247] The server uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[0248] Step 6:

[0249] The server generates analysis results by integrating the emotion information from the emotion engine with natural language processing means. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotion information "Stress level: high."

[0250] Step 7:

[0251] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored along with emotional information.

[0252] Step 8:

[0253] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on necessary supplies. For example, the location of shelter A displays an icon that reads "Water needed" along with a "Stress level: High" icon.

[0254] Step 9:

[0255] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[0256] Step 10:

[0257] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[0258] Step 11:

[0259] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[0260] Step 12:

[0261] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[0262] Step 13:

[0263] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[0264] These steps will enable efficient and rapid delivery of relief supplies. In addition, by combining it with an emotion engine, it will be possible to provide support that takes into account the emotional state of the victims.

[0265] Example 2

[0266] 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."

[0267] Conventional disaster relief systems have difficulty quickly and accurately grasping the needs of disaster victims, resulting in delays in the supply of relief supplies and shortages and surpluses. Furthermore, relief efforts did not take into account the emotional state of disaster victims, resulting in a lack of psychological support. This resulted in issues that reduced the efficiency and accuracy of relief activities.

[0268] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0269] In this invention, the server includes a means for converting voice data into text data, a natural language processing means, and a sentiment analysis means, which enable the server to quickly and accurately grasp the material needs and emotional state of disaster victims, and to generate an optimal relief supply distribution plan by integrating the analysis results.

[0270] "User" refers to a disaster victim or a supporter who uses the system to input their needs for goods.

[0271] "Terminal means" refers to a device that allows a user to input product needs and transmit the data to the server, including a smartphone or PC.

[0272] "Central Processing Unit" refers to a server for processing and analyzing input data.

[0273] "Audio data" refers to the recorded data when the user inputs voice.

[0274] "Text data" refers to voice data or text entered in chat format.

[0275] "Natural language processing means" refers to algorithms and models that analyze input text data and extract information such as required items and urgency.

[0276] "Emotion analysis means" refers to algorithms or models that analyze a user's emotional state from their input and identify stress, anxiety, etc.

[0277] "Means for visualizing on a map" refers to a method for displaying analyzed information on a map using a geographic information system (GIS).

[0278] "Disaster data" refers to data related to disasters, such as weather information and earthquake information.

[0279] "Machine learning methods" refer to algorithms and technologies that use past disaster data to train predictive models and improve their accuracy.

[0280] "Item distribution plan" refers to an item supply plan created based on analysis results and forecast data.

[0281] "Means for notifying distribution plans" refers to methods and techniques for notifying support teams and local governments of the generated item distribution plans.

[0282] This invention is a system for efficiently providing necessary items to disaster victims in the event of a disaster, and provides support that takes into account the emotional state of the victims by combining it with emotion analysis. This system works by allowing users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[0283] Users can input the items they need using chat or voice input on devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone, or type "I don't have any blankets" into the chat window.

[0284] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it.

[0285] The server converts the transmitted voice data into text data using a speech recognition engine (for example, Google Cloud Speech-to-Text API). Specifically, the voice data is converted into text data such as "I need water."

[0286] Next, the server analyzes the text data using a natural language processing model (e.g., BERT or GPT). This analysis extracts information such as "Items needed: water, Urgency: high." The same analysis is performed even if the data is entered in chat format.

[0287] The server further uses an emotion analysis engine (e.g., IBM Watson® Natural Language Understanding) to analyze the user's emotional state from the input data, for example, recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[0288] Emotional information from the emotion analysis engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[0289] The analyzed information is stored in a database on a server, and then a geographic information system is used to visualize the location of each evacuation shelter and disaster victims, along with information on the necessary supplies, on a map, allowing support teams to see at a glance what is needed at each shelter.

[0290] The server uses external APIs (e.g., OpenWeatherMap API or USGS Earthquake Hazards Program API) to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data to predict future needs for goods. For example, it can predict an increase in demand for water based on rainfall data.

[0291] Furthermore, the server uses past disaster data to train and improve the accuracy of predictive models using machine learning algorithms (such as Random Forest and XGBoost). This update enables highly accurate needs predictions.

[0292] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan to send 50 liters of water to shelter A and 25 kg of food to shelter B, and notifies the support team and local government in real time.

[0293] Specific examples

[0294] During a disaster, a user uses a device to voice input, "We need blankets." The device sends the voice data to a server, which converts it into text data using a voice recognition engine. The server analyzes the text data, "We need blankets," using a natural language processing model to obtain the information, "Needed items: blankets, Urgency: high." The server then uses an emotion analysis engine to extract the information, "Anxiety level: medium," from the voice data. This information is stored in a database and displayed on a map. The server checks current weather data and predicts that the demand for blankets will continue. Finally, it notifies the support team of a distribution plan, "Send 30 blankets to shelter C."

[0295] Example prompts to input to the generative AI model

[0296] "Please explain a system that efficiently supplies items needed by disaster victims in the event of a disaster. Please provide a detailed description, including the roles and specific processes of users, terminals, and servers."

[0297] This system will enable the rapid and accurate provision of relief supplies, and will also enable support that takes into consideration the emotional state of disaster victims.

[0298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0299] Step 1:

[0300] Users use devices such as smartphones or PCs to input the items they need in chat or voice input format. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into a chat window. The input data is saved on the device as voice or text data.

[0301] Step 2:

[0302] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it, and in the case of text input, it sends the text data as is. This transfers the input data to the server.

[0303] Step 3:

[0304] The server converts the received voice data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, the voice data is converted into text data such as "I need water." This converted text data is used in the next analysis step.

[0305] Step 4:

[0306] The server analyzes the text data using a natural language processing model (e.g., BERT or GPT). In this step, information such as "needed items: water, urgency: high" is extracted from the text data. The input text is output as categorized information through the analysis process.

[0307] Step 5:

[0308] The server uses an emotion analysis engine (for example, IBM Watson Natural Language Understanding) to analyze the user's emotional state from the input data. Specifically, it recognizes emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content, and obtains information such as "stress level: high" as output.

[0309] Step 6:

[0310] The server integrates the results of natural language processing analysis and sentiment analysis. Specifically, it integrates the analysis results of the text data "Necessary items: water, urgency: high" with the emotional information "Stress level: high" into a single dataset. This generates data that comprehensively captures the necessary items, their urgency, and the user's emotional state.

[0311] Step 7:

[0312] The server stores the analyzed integrated information in a database and visualizes it on a map using a geographic information system (GIS). Information on the location of victims and the necessary supplies is displayed on the map. This allows support teams and other relevant parties to understand in real time what items are needed at each evacuation shelter.

[0313] Step 8:

[0314] The server uses external APIs (e.g., OpenWeatherMap API and USGS Earthquake Hazards Program API) to collect current weather data, earthquake information, and other disaster data. The collected data undergoes analysis and processing and is used as input data for predicting future product needs.

[0315] Step 9:

[0316] The server uses machine learning algorithms (such as Random Forest and XGBoost) to train and improve the accuracy of predictive models using past disaster data, which will lead to more accurate forecasts of future supply needs.

[0317] Step 10:

[0318] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, a specific plan may be created such as "send 50 liters of water to shelter A and 25 kg of food to shelter B." This plan is notified to relief teams and local governments in real time. This information serves as the basis for rapid relief activities.

[0319] (Application example 2)

[0320] 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."

[0321] While it is important to efficiently and quickly provide disaster victims with the supplies they need, conventional methods have difficulty providing support that takes into account the emotional state of the victims. Furthermore, it is difficult to integrate real-time geographic information and supply needs, which means it takes time to formulate an optimal supply distribution plan.

[0322] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input needed items in chat format or voice input format; a terminal means for transmitting the input data to the server; a means for converting voice data into text data; a natural language processing means for analyzing the text data and identifying needed items and their urgency; a means for visualizing needed items on a map based on the analysis results and geographic information; a means for collecting disaster data and predicting needs for items; a machine learning means for training a prediction model and improving accuracy; a means for generating an item distribution plan based on the analysis results and predictions; a means for notifying the generated distribution plan; an emotion analysis means for analyzing the user's emotional state; a means for adjusting the urgency of items taking the emotional state into consideration; and a means for integrating item request information with a geographic information system in real time and displaying it. This enables efficient and rapid delivery of needed items during a disaster while taking the emotional state of disaster victims into consideration.

[0323] A "user" is an individual or organization that uses the system to input items needed in the event of a disaster.

[0324] "Chat format" refers to a text-based communication format in which users input messages using a keyboard or touch screen.

[0325] The "voice input format" is a format in which information is input through voice using a microphone or the like.

[0326] "Necessary items" refers to the supplies and support items that disaster victims require in the event of a disaster.

[0327] "Terminal means" refers to a device, such as a smartphone or a personal computer, that transmits data entered by a user to a server.

[0328] "Audio data" refers to audio signals entered by a user using an audio input form.

[0329] "Text data" is voice data converted into character information.

[0330] "Natural language processing means" refers to a technical means for analyzing text data, understanding its meaning, and identifying the items needed and their urgency.

[0331] A "geographic information system" is a system that collects, displays, and analyzes geographic information.

[0332] "Disaster data" refers to data that includes various types of information related to disasters, such as weather information and earthquake information.

[0333] "Machine learning means" refers to technical means for learning data and improving the accuracy of predictive models based on the learning results.

[0334] A "distribution plan" is a plan that includes schedules and routes for optimally distributing necessary items to disaster victims.

[0335] "Emotion analysis means" is a technical means for analyzing the emotional state of a user from their voice or text and understanding the situation.

[0336] "Urgency" is an index that indicates the degree of need for an item.

[0337] "Means for integrating and displaying" refers to a technical means for integrating data obtained from multiple information sources and displaying it on a single display screen.

[0338] The "notification means" is a technical means for notifying the relevant parties of the generated product distribution plan.

[0339] This invention is a system for efficiently and quickly supplying items needed by disaster victims, and by combining it with an emotion engine, it provides support that takes into account the emotional state of the victims. Specific embodiments for carrying out the invention are described below.

[0340] System Overview

[0341] The system is made up of a server, terminals, and users working together. Users use terminals such as smartphones and PCs to input the items they need via chat or voice input. The terminals then send the input data to the server via the internet.

[0342] Voice Recognition

[0343] The device sends voice data to the server, which converts the voice data into text data using a speech recognition engine (e.g., Python's speech_recognition library). For example, if a user says "I need water" into their smartphone, this voice input is converted into the text data "I need water."

[0344] Emotion analysis

[0345] The server analyzes the text data using a natural language processing engine (e.g., sentiment analysis model from the transformers library) to identify the items needed and their urgency. The sentiment analysis engine also analyzes the user's emotional state (e.g., stress, anxiety).

[0346] Data aggregation and visualization

[0347] The analyzed data is stored in a database on the server. Next, using a geographic information system (e.g., the folium library), the necessary item information and the location information of each evacuation shelter are visualized on a map.

[0348] Collecting disaster data and predicting supply needs

[0349] The server uses an external disaster data API (e.g., API access with the requests library) to collect weather data, earthquake information, etc. This data is analyzed to predict future product needs.

[0350] Generate and notify material distribution plans

[0351] The server generates an optimal distribution plan based on the analysis results and disaster data (e.g., by processing the data using the pandas library). The generated distribution plan is notified to the support team and local governments via notification methods (e.g., email, app notification).

[0352] Specific examples

[0353] During a disaster, a user uses a device to voice-input the phrase "I need food." The device sends this voice data to a server, which then uses a speech recognition engine to generate text data saying "I need food." The text data is then analyzed using a natural language processing model to obtain information such as "Needed items: food, Urgency: high." A sentiment analysis engine is also used to extract information such as "Stress level: high." This information is integrated with a geographic information system and visualized on a map. The server checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0354] Prompt Sentence Examples

[0355] When a user says "I need water" into their smartphone, the application does the following:

[0356] 1. Convert audio data into text data.

[0357] 2. Conduct sentiment analysis to understand the user's emotional state.

[0358] 3. Collect disaster data and predict future needs.

[0359] 4. Integrate needed goods with geographic information to generate optimal distribution plans.

[0360] 5. Notify the logistics center of specific distribution instructions and provide support such as "send 50 liters of water to shelter A."

[0361] The above is a specific embodiment for carrying out the invention.

[0362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0363] Step 1:

[0364] The user inputs the items they need through voice input or chat. For example, the user speaks into their smartphone, saying, "I need water," and voice data is generated.

[0365] Step 2:

[0366] The device sends the user's voice data to the server, which then converts the data into a common audio format (e.g., WAV, MP3, etc.) and sends it to the server via the Internet.

[0367] Step 3:

[0368] The server converts the transmitted voice data into text data using a speech recognition engine. Specifically, it analyzes the voice signal using Python's speech_recognition library and generates the text data "I need water."

[0369] Step 4:

[0370] The server analyzes the text data using a natural language processing engine. The library used is transformers. The information extracted from the text is "Needed items: water, Urgency: high."

[0371] Step 5:

[0372] At the same time, the server uses an emotion analysis engine to analyze the user's emotional state. It analyzes "stress," "anxiety," etc. from the tone of voice and the content of the text. As a result, it obtains the data "Stress level: High."

[0373] Step 6:

[0374] The server integrates the text analysis results with the sentiment analysis results, generating integrated data such as "Needed items: water, Urgency: high, Stress level: high."

[0375] Step 7:

[0376] The server stores the integrated data in a database, and simultaneously visualizes the location of each evacuation center and necessary supplies on a map using a geographic information system (GIS). This is done using the folium library.

[0377] Step 8:

[0378] The server collects weather and earthquake data from external disaster data APIs using the requests library to obtain real-time disaster data.

[0379] Step 9:

[0380] The server analyzes the disaster data collected and predicts future needs for supplies. Based on past data, predictions are made using a machine learning model that uses a generative AI model.

[0381] Step 10:

[0382] The server generates an optimal distribution plan based on the analysis results and predicted data. Specifically, it processes the data using the pandas library and creates a specific distribution plan, such as "send 25 kg of food to shelter B."

[0383] Step 11:

[0384] The server notifies the support team and local governments of the generated distribution plan using methods such as email and app notifications to ensure information is transmitted quickly.

[0385] Through the above processing steps, it becomes possible to efficiently and quickly supply necessary items in the event of a disaster while taking into consideration the emotional state of the user.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] [Second embodiment]

[0390] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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."

[0402] Overview of the entire system

[0403] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0404] User input of items

[0405] Users can use devices such as smartphones or computers to input what items they need via chat or voice input. For example, users can input information such as "I need water" or "Please give me a blanket."

[0406] Data transmission by the terminal

[0407] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0408] Data preprocessing by the server

[0409] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0410] Data analysis using natural language processing

[0411] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0412] Aggregation and visualization of needs information

[0413] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0414] Disaster data collection and needs forecasting

[0415] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0416] Updating predictive models with machine learning

[0417] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[0418] Generate and notify material distribution plans

[0419] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0420] Specific examples

[0421] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model and obtains the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0422] This will enable the efficient and rapid supply of relief goods, and the system aims to provide faster and more accurate support in the event of a disaster.

[0423] The processing flow will be explained below.

[0424] Step 1:

[0425] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0426] Step 2:

[0427] The device sends the data entered by the user to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3. In the case of text input, the data is sent in its original format.

[0428] Step 3:

[0429] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[0430] Step 4:

[0431] The server uses a natural language processing model to analyze the text data, extracting information such as "Items needed: water, Urgency: high." The same analysis is done for text input in chat format.

[0432] Step 5:

[0433] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored.

[0434] Step 6:

[0435] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on the supplies needed. For example, an icon saying "Water needed" is displayed at the location of shelter A.

[0436] Step 7:

[0437] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[0438] Step 8:

[0439] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[0440] Step 9:

[0441] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[0442] Step 10:

[0443] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[0444] Step 11:

[0445] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[0446] These steps ensure efficient and rapid delivery of support items.

[0447] Example 1

[0448] 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."

[0449] In the event of a disaster, it is extremely important to provide necessary items to victims quickly and effectively, but current methods often result in insufficient information gathering and needs analysis, which delays appropriate assistance. Furthermore, the accuracy of predictive models is low, making it difficult to provide necessary items appropriately. The aim of this project is to solve these issues.

[0450] 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.

[0451] In this invention, the server includes a means for storing data generated from user input in a database, a means including a data analysis engine for extracting necessary information from the database, a means for analyzing past disaster data and identifying demand patterns for necessary items, a means for integrating multiple external data sources to predict future needs, and a means for optimizing item distribution plans using a machine learning predictive model, thereby enabling the prompt and appropriate distribution of relief items based on the needs of disaster victims.

[0452] A "user" is an individual or entity that uses the system to input required items.

[0453] A "terminal" is a device used by a user to send data entered by the user to a server via the Internet, and includes smartphones and personal computers.

[0454] A "server" is a central computer system that processes received data and analyzes user needs.

[0455] "Audio data" refers to digital data that represents an audio signal input by a user in the form of a voice input.

[0456] "Text data" is character-based data converted from voice data by a voice recognition engine.

[0457] "Natural language processing" refers to a set of technologies and methods for analyzing text data to identify needed items and their urgency.

[0458] "Geographic information" refers to location information of disaster areas and evacuation centers displayed using a geographic information system.

[0459] "Disaster data" refers to various types of data related to disasters, such as weather data and earthquake information.

[0460] A "predictive model" is a mathematical model for predicting future product needs based on collected data.

[0461] "Machine learning" is a collection of algorithms and techniques that improve the accuracy of predictive models based on data.

[0462] "Item distribution plan" refers to a specific item supply plan generated based on needs and forecasts.

[0463] A "database" is a collection of data collected, stored, and managed by a system.

[0464] A "data analysis engine" refers to a technology or system that analyzes information stored in a database and extracts the necessary information.

[0465] "External Data Source" means an external information source used by the system to gather data.

[0466] "Distribution plan optimization" refers to the process of formulating optimal distribution strategies to supply goods efficiently and effectively.

[0467] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0468] Hardware and Software Configuration

[0469] The user's terminal can be a smartphone, PC, or other general device. These terminals connect to the Internet and transmit user input to the server. Specific software includes a voice conversion module and a chat application.

[0470] The server is the central computing system for processing the received data. It is equipped with a speech recognition engine, natural language processing model, database management system, data analysis engine, and machine learning model. Specific software used includes Google Cloud Speech-to-Text, BERT, and GPT-3.

[0471] System Operation Overview

[0472] The user uses the terminal to input the items they need through chat or voice input. For example, the user inputs information such as "I need water" or "Please give me a blanket." This input data is sent by the terminal to the server via the Internet.

[0473] When a voice input is received, the server uses a voice recognition engine to convert the voice data into text data. Through this process, the voice data is converted into text data such as "I need water."

[0474] The server then uses a natural language processing model to analyze the text data. This process extracts information about the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0475] The analyzed information is stored in a database and visualized on a map using a geographic information system, allowing support teams to see at a glance what is needed at each evacuation shelter.

[0476] In addition, the server uses external APIs to collect weather data, earthquake information, and other disaster data. This data is analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0477] The server uses machine learning models to learn from past disaster data and improve its accuracy, which in turn makes forecasts of demand for goods more accurate.

[0478] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific plan might be created, such as "Send 50 liters of water to shelter A."

[0479] Specific examples

[0480] During a disaster, if a user uses a device to voice-input "I need food," the device sends this voice data to a server. The server uses a speech recognition engine to convert the voice data into text data, generating the text "I need food." Next, it analyzes the text data using a natural language processing model and extracts the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0481] Prompt Sentence Examples

[0482] 1. "Can you give me a Python code example for implementing an API for disaster data collection?"

[0483] 2. "How do I train a natural language processing model to extract supply needs during a disaster?"

[0484] 3. "Explain how TensorFlow can be used to predict demand for goods from disaster data."

[0485] 4. "How do I update a product demand forecast model using past disaster data?"

[0486] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0487] Step 1:

[0488] Users use devices such as smartphones or PCs to input the items they need through chat or voice input. Specifically, the user opens the application on their device and types "I need water" into the chat box, or presses the voice input button and speaks "I need a blanket." This input is received as the system's initial data.

[0489] Step 2:

[0490] The device receives user input, and if there is voice input, it uses the device's voice conversion module to convert the voice data into WAV or MP3 format. This converted data is then sent to the server via the Internet. Specifically, the device saves the voice input data as a WAV file and sends this data to the server via an HTTP request.

[0491] Step 3:

[0492] The server passes the received voice data to a speech recognition engine (for example, Google Cloud Speech-to-Text), which converts the voice data into text data. Specifically, the server sends the received wav file to the speech recognition engine, which receives the text data "I need a blanket." The output is the text data "I need a blanket."

[0493] Step 4:

[0494] The server uses a natural language processing model (e.g., BERT or GPT-3) to analyze the text data and extract the items needed and their urgency. The input is the text data "I need a blanket," and the output is "Item needed: Blanket, Urgency: High." Specifically, the server applies a natural language processing algorithm to analyze the text data.

[0495] Step 5:

[0496] The server stores the analysis results in a database. Specifically, it records information such as "Needed items: Blanket, Urgency: High" in the appropriate fields of the database. This process allows the server to accumulate information for subsequent processing.

[0497] Step 6:

[0498] The server uses a geographic information system (GIS) to visualize information about needed items on a map. For example, information such as "Shelter C: Necessary items = Blankets, Quantity = 10, Urgency = High" is displayed at a glance on the map. This allows support teams to instantly understand what is needed at each shelter.

[0499] Step 7:

[0500] The server uses external APIs (e.g., OpenWeatherMap and USGS Earthquake Data) to collect weather data, earthquake information, and other disaster data. An API request is sent as input, and weather data and earthquake information are returned as output. Specifically, the server sends a request to the API to obtain the latest disaster data.

[0501] Step 8:

[0502] The server analyzes the acquired disaster data and predicts future needs for supplies. The acquired disaster data is used as input, and the predicted information that "demand for water will increase" in the future is obtained as output. Specifically, the server runs a prediction algorithm and analyzes the disaster data.

[0503] Step 9:

[0504] The server trains a machine learning model using past disaster data to improve the accuracy of the predictive model. Past disaster data is given as input, and a machine learning algorithm is applied. A highly accurate predictive model is generated as output. Specifically, the server trains a new model using TensorFlow.

[0505] Step 10:

[0506] The server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific distribution plan may be created, such as "send 50 liters of water to shelter A." The output is a notification via the support team's dedicated app or email.

[0507] (Application example 1)

[0508] 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."

[0509] In the event of a disaster, it is extremely important to quickly and efficiently supply the necessary supplies to affected areas. However, conventional systems have had difficulty properly receiving and analyzing supply requests from affected areas and formulating and executing supply plans for relief supplies in real time. Furthermore, there was a lack of means to accurately predict future demand for supplies through the collection and analysis of disaster data. This limited the ability of logistics centers and relief organizations to respond appropriately, resulting in a high likelihood of delays in the supply of supplies to disaster victims and / or shortages and surpluses. Therefore, to solve these issues, a system is needed that can analyze and visualize requests from affected areas in real time and formulate appropriate supply plans.

[0510] 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.

[0511] In this invention, the server includes a means for users to input needed items via chat or voice input, a terminal means for transmitting the input data to the server, and a means for converting voice data into text data. This enables accurate and rapid receipt and analysis of requests for items from disaster-stricken areas. The server also includes a natural language processing means for analyzing the text data to identify needed items and their urgency, a means for visualizing needed items on a map based on the analysis results and geographic information, a means for collecting disaster data and predicting item needs, a machine learning means for training a prediction model to improve accuracy, a means for generating an item distribution plan based on the analysis results and predictions, a means for notifying the generated distribution plan, a means for optimizing the supply of relief items based on the item requests received by the logistics center, a means for visualizing user requests in real time, and a means for acquiring disaster data from an external data source and predicting item demand. This enables effective supply of items in line with the needs of disaster victims, thereby achieving rapid and accurate support for disaster-stricken areas.

[0512] The "chat format" is a form of communication in which users input text, and is an interface that allows messages to be sent and received in real time.

[0513] The "voice input format" is a format in which users input information using voice, and is an interface that receives and analyzes user requests by converting voice into text.

[0514] "Terminal means" refers to a device that allows a user to input information and send it to a server, and includes, for example, a smartphone, tablet, or PC.

[0515] The "server means" is a central computer system for performing data processing, and is a device that converts voice data into text data, performs natural language processing, and performs various data analyses.

[0516] "Natural language processing means" refers to technology for analyzing text data and identifying needed items and their urgency, and refers to the function of understanding and processing language data using machine learning models and algorithms.

[0517] "Visualization means" refers to technology that displays analyzed data on a map, allowing people to intuitively grasp the needs for goods.

[0518] "Disaster data" is a general term for disaster-related data such as meteorological information and earthquake information, and by collecting and analyzing this data, it can be used to forecast demand for goods.

[0519] "Prediction methods" are technologies and models for predicting future supply needs based on collected disaster data.

[0520] "Machine learning methods" are techniques that use past data to learn and improve the accuracy of predictive models, usually using algorithms or neural networks.

[0521] A "distribution plan" is a plan that specifically outlines how necessary items will be supplied to disaster-stricken areas, and determines the optimal distribution route and quantities.

[0522] "Notification methods" refer to technologies used to inform support teams and related organizations of the generated distribution plan, such as email, SMS, and notification apps.

[0523] A "logistics center" is a central facility for efficiently storing and managing goods and delivering them to disaster-stricken areas.

[0524] "Real-time visualization means" refers to technology that instantly displays user requests, enabling timely confirmation of needs for support items.

[0525] "External data sources" are external databases or APIs that provide disaster data and other relevant information that can be used to improve the accuracy of the predictive models.

[0526] This invention is a system for quickly and efficiently supplying necessary items to disaster victims in the event of a disaster. This system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[0527] User input of items

[0528] Users can input what items they need using chat or voice input on devices such as smartphones or computers. For example, users can input information such as "I need water" or "Please give me a blanket."

[0529] Data transmission by the terminal

[0530] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0531] Data preprocessing by the server

[0532] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0533] Data analysis using natural language processing

[0534] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0535] Aggregation and visualization of needs information

[0536] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0537] Disaster data collection and needs forecasting

[0538] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0539] Updating predictive models with machine learning

[0540] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[0541] Generate and notify material distribution plans

[0542] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0543] Addition of functions for logistics centers

[0544] This system also includes a function that enables logistics centers to optimize the supply of disaster relief supplies. The logistics center receives request data from users in real time and can create optimal supply plans based on needs information visualized on a map. In addition, by using disaster data obtained from external data sources, it is possible to accurately predict future demand for supplies and supply them accordingly.

[0545] Usage example

[0546] For example, if a user uses a device to say "I need food" during a disaster, this voice data is sent to a server and converted into text data by a speech recognition engine. Then, using a natural language processing model, the information "Needed items: food, Urgency: high" is extracted. This information is stored in a database and visualized on a map. Based on this information, the logistics center can create and execute a food supply plan for disaster-stricken areas. Furthermore, by collecting and analyzing weather data and other disaster data, future demand for goods can be predicted, enabling more effective support.

[0547] Prompt Sentence Examples

[0548] Here are some examples of prompts for generative AI models:

[0549] "We are developing an application that predicts the need for relief supplies during disasters and creates optimal distribution plans. It converts voice input into text, uses natural language processing to analyze the supplies needed and their urgency, and visualizes them on a map. It also obtains weather data from an external API to predict future needs. This will enable efficient supply of supplies."

[0550] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0551] Step 1:

[0552] The user inputs the items they need in chat or voice input format. Using a device such as a smartphone or PC, the user inputs information such as "I need water" or "Can I have a blanket?" This generates text data or voice data. Input: Text data or voice data from the user. Output: Text data or voice data.

[0553] Step 2:

[0554] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the voice data is converted on the device into a common audio format such as WAV or MP3, and then sent to the server along with the text data. Input: Text data or voice data. Output: Text data or voice data sent to the server.

[0555] Step 3:

[0556] When the server receives the voice data, it uses a voice recognition engine to convert the voice data into text data. As a result, voice data such as "I need water" is converted into text data. Input: Voice data. Output: Text data.

[0557] Step 4:

[0558] The server uses a natural language processing model to analyze the text data. This process extracts needed items and their urgency from the text data. For example, from the text "I need water," the information "Needed items: Water, Urgency: High" is obtained. Input: Text data. Output: Information on needed items and urgency.

[0559] Step 5:

[0560] The server stores the analyzed information in a database. Next, using a geographic information system, the location of each evacuation center and disaster victims, along with information on necessary items, are visualized on a map. Input: Information on necessary items and urgency. Output: Needs information displayed on a map.

[0561] Step 6:

[0562] The server uses an external API to collect disaster data such as weather data and earthquake information. It analyzes this disaster data and predicts future needs for goods. For example, it predicts future increases in demand for water based on rainfall data. Input: Disaster data obtained from the external API. Output: Predicted demand for goods.

[0563] Step 7:

[0564] The server uses past disaster data to train the predictive model and improve its accuracy. This makes demand forecasts for goods more accurate. Input: Past disaster data. Output: Improved predictive model.

[0565] Step 8:

[0566] The server generates an optimal distribution plan based on the analysis results and prediction data. For example, a specific plan such as "Send 50 liters of water to shelter A" is created. Input: Analysis results and prediction data. Output: Distribution plan.

[0567] Step 9:

[0568] The server notifies the support team and local governments of the generated item distribution plan, allowing support items to be supplied quickly and accurately. Input: Item distribution plan. Output: Notified distribution plan.

[0569] Step 10:

[0570] The logistics center optimizes the supply of relief goods based on the goods requests received from the server. It determines the optimal supply route and quantity of goods, taking into account congestion and logistics efficiency. Input: Goods requests from users and disaster data. Output: Optimized supply plan.

[0571] 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.

[0572] Overview of the entire system

[0573] This invention is a system for efficiently supplying disaster victims with necessary items. By combining it with an emotion engine, it provides support that takes into account the emotional state of the disaster victims. The system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0574] User input of items

[0575] Users can input the items they need using chat or voice input using devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0576] Data transmission by the terminal

[0577] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0578] Data preprocessing by the server

[0579] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0580] Data analysis using natural language processing

[0581] The server uses natural language processing models to analyze text data, extracting information such as "Item needed: water, Urgency: high." Chat input is also analyzed.

[0582] Emotion analysis using an emotion engine

[0583] The server also uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from voice tone and text content.

[0584] Emotional information integration

[0585] Emotional information from the emotion engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[0586] Aggregation and visualization of needs information

[0587] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0588] Disaster data collection and needs forecasting

[0589] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data and predicts future needs for supplies. For example, it predicts future increases in water demand based on rainfall data.

[0590] Updating predictive models with machine learning

[0591] The server uses past disaster data to train and improve the predictive model, which will lead to more accurate forecasts of future supply needs.

[0592] Generate and notify material distribution plans

[0593] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0594] Specific examples

[0595] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model to obtain the information "Needed items: food, Urgency: high." Furthermore, it uses an emotion engine to extract the information "Stress level: high" from the voice data. This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0596] This will enable the efficient and rapid supply of relief goods, while also enabling support that takes into consideration the emotional state of the victims.The system aims to provide faster and more accurate support during disasters.

[0597] The processing flow will be explained below.

[0598] Step 1:

[0599] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0600] Step 2:

[0601] The device sends the user's input data to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3 before sending it. In the case of text input, the data is sent in its original format.

[0602] Step 3:

[0603] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[0604] Step 4:

[0605] The server uses a natural language processing model to analyze text data, extracting information such as "Items needed: water, Urgency: high." Chat input is also analyzed in the same way.

[0606] Step 5:

[0607] The server uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[0608] Step 6:

[0609] The server generates analysis results by integrating the emotion information from the emotion engine with natural language processing means. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotion information "Stress level: high."

[0610] Step 7:

[0611] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored along with emotional information.

[0612] Step 8:

[0613] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on necessary supplies. For example, the location of shelter A displays an icon that reads "Water needed" along with a "Stress level: High" icon.

[0614] Step 9:

[0615] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[0616] Step 10:

[0617] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[0618] Step 11:

[0619] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[0620] Step 12:

[0621] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[0622] Step 13:

[0623] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[0624] These steps will enable efficient and rapid delivery of relief supplies. In addition, by combining it with an emotion engine, it will be possible to provide support that takes into account the emotional state of the victims.

[0625] Example 2

[0626] 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."

[0627] Conventional disaster relief systems have difficulty quickly and accurately grasping the needs of disaster victims, resulting in delays in the supply of relief supplies and shortages and surpluses. Furthermore, relief efforts did not take into account the emotional state of disaster victims, resulting in a lack of psychological support. This resulted in issues that reduced the efficiency and accuracy of relief activities.

[0628] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0629] In this invention, the server includes a means for converting voice data into text data, a natural language processing means, and a sentiment analysis means, which enable the server to quickly and accurately grasp the material needs and emotional state of disaster victims, and to generate an optimal relief supply distribution plan by integrating the analysis results.

[0630] "User" refers to a disaster victim or a supporter who uses the system to input their needs for goods.

[0631] "Terminal means" refers to a device that allows a user to input product needs and transmit the data to the server, including a smartphone or PC.

[0632] "Central Processing Unit" refers to a server for processing and analyzing input data.

[0633] "Audio data" refers to the recorded data when the user inputs voice.

[0634] "Text data" refers to voice data or text entered in chat format.

[0635] "Natural language processing means" refers to algorithms and models that analyze input text data and extract information such as required items and urgency.

[0636] "Emotion analysis means" refers to algorithms or models that analyze a user's emotional state from their input and identify stress, anxiety, etc.

[0637] "Means for visualizing on a map" refers to a method for displaying analyzed information on a map using a geographic information system (GIS).

[0638] "Disaster data" refers to data related to disasters, such as weather information and earthquake information.

[0639] "Machine learning methods" refer to algorithms and technologies that use past disaster data to train predictive models and improve their accuracy.

[0640] "Item distribution plan" refers to an item supply plan created based on analysis results and forecast data.

[0641] "Means for notifying distribution plans" refers to methods and techniques for notifying support teams and local governments of the generated item distribution plans.

[0642] This invention is a system for efficiently providing necessary items to disaster victims in the event of a disaster, and provides support that takes into account the emotional state of the victims by combining it with emotion analysis. This system works by allowing users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[0643] Users can input the items they need using chat or voice input on devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone, or type "I don't have any blankets" into the chat window.

[0644] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it.

[0645] The server converts the transmitted voice data into text data using a speech recognition engine (for example, Google Cloud Speech-to-Text API). Specifically, the voice data is converted into text data such as "I need water."

[0646] Next, the server analyzes the text data using a natural language processing model (e.g., BERT or GPT). This analysis extracts information such as "Items needed: water, Urgency: high." The same analysis is performed even if the data is entered in chat format.

[0647] The server then uses an emotion analysis engine (e.g., IBM Watson Natural Language Understanding) to analyze the user's emotional state from the input data, for example, recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[0648] Emotional information from the emotion analysis engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[0649] The analyzed information is stored in a database on a server, and then a geographic information system is used to visualize the location of each evacuation shelter and disaster victims, along with information on the necessary supplies, on a map, allowing support teams to see at a glance what is needed at each shelter.

[0650] The server uses external APIs (e.g., OpenWeatherMap API or USGS Earthquake Hazards Program API) to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data to predict future needs for goods. For example, it can predict an increase in demand for water based on rainfall data.

[0651] Furthermore, the server uses past disaster data to train and improve the accuracy of predictive models using machine learning algorithms (such as Random Forest and XGBoost). This update enables highly accurate needs predictions.

[0652] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan to send 50 liters of water to shelter A and 25 kg of food to shelter B, and notifies the support team and local government in real time.

[0653] Specific examples

[0654] During a disaster, a user uses a device to voice input, "We need blankets." The device sends the voice data to a server, which converts it into text data using a voice recognition engine. The server analyzes the text data, "We need blankets," using a natural language processing model to obtain the information, "Needed items: blankets, Urgency: high." The server then uses an emotion analysis engine to extract the information, "Anxiety level: medium," from the voice data. This information is stored in a database and displayed on a map. The server checks current weather data and predicts that the demand for blankets will continue. Finally, it notifies the support team of a distribution plan, "Send 30 blankets to shelter C."

[0655] Example prompts to input to the generative AI model

[0656] "Please explain a system that efficiently supplies items needed by disaster victims in the event of a disaster. Please provide a detailed description, including the roles and specific processes of users, terminals, and servers."

[0657] This system will enable the rapid and accurate provision of relief supplies, and will also enable support that takes into consideration the emotional state of disaster victims.

[0658] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0659] Step 1:

[0660] Users use devices such as smartphones or PCs to input the items they need in chat or voice input format. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into a chat window. The input data is saved on the device as voice or text data.

[0661] Step 2:

[0662] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it, and in the case of text input, it sends the text data as is. This transfers the input data to the server.

[0663] Step 3:

[0664] The server converts the received voice data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, the voice data is converted into text data such as "I need water." This converted text data is used in the next analysis step.

[0665] Step 4:

[0666] The server analyzes the text data using a natural language processing model (e.g., BERT or GPT). In this step, information such as "needed items: water, urgency: high" is extracted from the text data. The input text is output as categorized information through the analysis process.

[0667] Step 5:

[0668] The server uses an emotion analysis engine (for example, IBM Watson Natural Language Understanding) to analyze the user's emotional state from the input data. Specifically, it recognizes emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content, and obtains information such as "stress level: high" as output.

[0669] Step 6:

[0670] The server integrates the results of natural language processing analysis and sentiment analysis. Specifically, it integrates the analysis results of the text data "Necessary items: water, urgency: high" with the emotional information "Stress level: high" into a single dataset. This generates data that comprehensively captures the necessary items, their urgency, and the user's emotional state.

[0671] Step 7:

[0672] The server stores the analyzed integrated information in a database and visualizes it on a map using a geographic information system (GIS). Information on the location of victims and the necessary supplies is displayed on the map. This allows support teams and other relevant parties to understand in real time what items are needed at each evacuation shelter.

[0673] Step 8:

[0674] The server uses external APIs (e.g., OpenWeatherMap API and USGS Earthquake Hazards Program API) to collect current weather data, earthquake information, and other disaster data. The collected data undergoes analysis and processing and is used as input data for predicting future product needs.

[0675] Step 9:

[0676] The server uses machine learning algorithms (such as Random Forest and XGBoost) to train and improve the accuracy of predictive models using past disaster data, which will lead to more accurate forecasts of future supply needs.

[0677] Step 10:

[0678] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, a specific plan may be created such as "send 50 liters of water to shelter A and 25 kg of food to shelter B." This plan is notified to relief teams and local governments in real time. This information serves as the basis for rapid relief activities.

[0679] (Application example 2)

[0680] 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."

[0681] While it is important to efficiently and quickly provide disaster victims with the supplies they need, conventional methods have difficulty providing support that takes into account the emotional state of the victims. Furthermore, it is difficult to integrate real-time geographic information and supply needs, which means it takes time to formulate an optimal supply distribution plan.

[0682] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input needed items in chat format or voice input format; a terminal means for transmitting the input data to the server; a means for converting voice data into text data; a natural language processing means for analyzing the text data and identifying needed items and their urgency; a means for visualizing needed items on a map based on the analysis results and geographic information; a means for collecting disaster data and predicting needs for items; a machine learning means for training a prediction model and improving accuracy; a means for generating an item distribution plan based on the analysis results and predictions; a means for notifying the generated distribution plan; an emotion analysis means for analyzing the user's emotional state; a means for adjusting the urgency of items taking the emotional state into consideration; and a means for integrating item request information with a geographic information system in real time and displaying it. This enables efficient and rapid delivery of needed items during a disaster while taking the emotional state of disaster victims into consideration.

[0683] A "user" is an individual or organization that uses the system to input items needed in the event of a disaster.

[0684] "Chat format" refers to a text-based communication format in which users input messages using a keyboard or touch screen.

[0685] The "voice input format" is a format in which information is input through voice using a microphone or the like.

[0686] "Necessary items" refers to the supplies and support items that disaster victims require in the event of a disaster.

[0687] "Terminal means" refers to a device, such as a smartphone or a personal computer, that transmits data entered by a user to a server.

[0688] "Audio data" refers to audio signals entered by a user using an audio input form.

[0689] "Text data" is voice data converted into character information.

[0690] "Natural language processing means" refers to a technical means for analyzing text data, understanding its meaning, and identifying the items needed and their urgency.

[0691] A "geographic information system" is a system that collects, displays, and analyzes geographic information.

[0692] "Disaster data" refers to data that includes various types of information related to disasters, such as weather information and earthquake information.

[0693] "Machine learning means" refers to technical means for learning data and improving the accuracy of predictive models based on the learning results.

[0694] A "distribution plan" is a plan that includes schedules and routes for optimally distributing necessary items to disaster victims.

[0695] "Emotion analysis means" is a technical means for analyzing the emotional state of a user from their voice or text and understanding the situation.

[0696] "Urgency" is an index that indicates the degree of need for an item.

[0697] "Means for integrating and displaying" refers to a technical means for integrating data obtained from multiple information sources and displaying it on a single display screen.

[0698] The "notification means" is a technical means for notifying the relevant parties of the generated product distribution plan.

[0699] This invention is a system for efficiently and quickly supplying items needed by disaster victims, and by combining it with an emotion engine, it provides support that takes into account the emotional state of the victims. Specific embodiments for carrying out the invention are described below.

[0700] System Overview

[0701] The system is made up of a server, terminals, and users working together. Users use terminals such as smartphones and PCs to input the items they need via chat or voice input. The terminals then send the input data to the server via the internet.

[0702] Voice Recognition

[0703] The device sends voice data to the server, which converts the voice data into text data using a speech recognition engine (e.g., Python's speech_recognition library). For example, if a user says "I need water" into their smartphone, this voice input is converted into the text data "I need water."

[0704] Emotion analysis

[0705] The server analyzes the text data using a natural language processing engine (e.g., sentiment analysis model from the transformers library) to identify the items needed and their urgency. The sentiment analysis engine also analyzes the user's emotional state (e.g., stress, anxiety).

[0706] Data aggregation and visualization

[0707] The analyzed data is stored in a database on the server. Next, using a geographic information system (e.g., the folium library), the necessary item information and the location information of each evacuation shelter are visualized on a map.

[0708] Collecting disaster data and predicting supply needs

[0709] The server uses an external disaster data API (e.g., API access with the requests library) to collect weather data, earthquake information, etc. This data is analyzed to predict future product needs.

[0710] Generate and notify material distribution plans

[0711] The server generates an optimal distribution plan based on the analysis results and disaster data (e.g., by processing the data using the pandas library). The generated distribution plan is notified to the support team and local governments via notification methods (e.g., email, app notification).

[0712] Specific examples

[0713] During a disaster, a user uses a device to voice-input the phrase "I need food." The device sends this voice data to a server, which then uses a speech recognition engine to generate text data saying "I need food." The text data is then analyzed using a natural language processing model to obtain information such as "Needed items: food, Urgency: high." A sentiment analysis engine is also used to extract information such as "Stress level: high." This information is integrated with a geographic information system and visualized on a map. The server checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0714] Prompt Sentence Examples

[0715] When a user says "I need water" into their smartphone, the application does the following:

[0716] 1. Convert audio data into text data.

[0717] 2. Conduct sentiment analysis to understand the user's emotional state.

[0718] 3. Collect disaster data and predict future needs.

[0719] 4. Integrate needed goods with geographic information to generate optimal distribution plans.

[0720] 5. Notify the logistics center of specific distribution instructions and provide support such as "send 50 liters of water to shelter A."

[0721] The above is a specific embodiment for carrying out the invention.

[0722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0723] Step 1:

[0724] The user inputs the items they need through voice input or chat. For example, the user speaks into their smartphone, saying, "I need water," and voice data is generated.

[0725] Step 2:

[0726] The device sends the user's voice data to the server, which then converts the data into a common audio format (e.g., WAV, MP3, etc.) and sends it to the server via the Internet.

[0727] Step 3:

[0728] The server converts the transmitted voice data into text data using a speech recognition engine. Specifically, it analyzes the voice signal using Python's speech_recognition library and generates the text data "I need water."

[0729] Step 4:

[0730] The server analyzes the text data using a natural language processing engine. The library used is transformers. The information extracted from the text is "Needed items: water, Urgency: high."

[0731] Step 5:

[0732] At the same time, the server uses an emotion analysis engine to analyze the user's emotional state. It analyzes "stress," "anxiety," etc. from the tone of voice and the content of the text. As a result, it obtains the data "Stress level: High."

[0733] Step 6:

[0734] The server integrates the text analysis results with the sentiment analysis results, generating integrated data such as "Needed items: water, Urgency: high, Stress level: high."

[0735] Step 7:

[0736] The server stores the integrated data in a database, and simultaneously visualizes the location of each evacuation center and necessary supplies on a map using a geographic information system (GIS). This is done using the folium library.

[0737] Step 8:

[0738] The server collects weather and earthquake data from external disaster data APIs using the requests library to obtain real-time disaster data.

[0739] Step 9:

[0740] The server analyzes the disaster data collected and predicts future needs for supplies. Based on past data, predictions are made using a machine learning model that uses a generative AI model.

[0741] Step 10:

[0742] The server generates an optimal distribution plan based on the analysis results and predicted data. Specifically, it processes the data using the pandas library and creates a specific distribution plan, such as "send 25 kg of food to shelter B."

[0743] Step 11:

[0744] The server notifies the support team and local governments of the generated distribution plan using methods such as email and app notifications to ensure information is transmitted quickly.

[0745] Through the above processing steps, it becomes possible to efficiently and quickly supply necessary items in the event of a disaster while taking into consideration the emotional state of the user.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] [Third embodiment]

[0750] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0751] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0752] 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).

[0753] 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.

[0754] 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.

[0755] 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).

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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."

[0762] Overview of the entire system

[0763] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0764] User input of items

[0765] Users can use devices such as smartphones or computers to input what items they need via chat or voice input. For example, users can input information such as "I need water" or "Please give me a blanket."

[0766] Data transmission by the terminal

[0767] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0768] Data preprocessing by the server

[0769] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0770] Data analysis using natural language processing

[0771] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0772] Aggregation and visualization of needs information

[0773] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0774] Disaster data collection and needs forecasting

[0775] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0776] Updating predictive models with machine learning

[0777] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[0778] Generate and notify material distribution plans

[0779] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0780] Specific examples

[0781] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model and obtains the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0782] This will enable the efficient and rapid supply of relief goods, and the system aims to provide faster and more accurate support in the event of a disaster.

[0783] The processing flow will be explained below.

[0784] Step 1:

[0785] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0786] Step 2:

[0787] The device sends the data entered by the user to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3. In the case of text input, the data is sent in its original format.

[0788] Step 3:

[0789] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[0790] Step 4:

[0791] The server uses a natural language processing model to analyze the text data, extracting information such as "Items needed: water, Urgency: high." The same analysis is done for text input in chat format.

[0792] Step 5:

[0793] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored.

[0794] Step 6:

[0795] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on the supplies needed. For example, an icon saying "Water needed" is displayed at the location of shelter A.

[0796] Step 7:

[0797] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[0798] Step 8:

[0799] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[0800] Step 9:

[0801] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[0802] Step 10:

[0803] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[0804] Step 11:

[0805] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[0806] These steps ensure efficient and rapid delivery of support items.

[0807] Example 1

[0808] 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."

[0809] In the event of a disaster, it is extremely important to provide necessary items to victims quickly and effectively, but current methods often result in insufficient information gathering and needs analysis, which delays appropriate assistance. Furthermore, the accuracy of predictive models is low, making it difficult to provide necessary items appropriately. The aim of this project is to solve these issues.

[0810] 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.

[0811] In this invention, the server includes a means for storing data generated from user input in a database, a means including a data analysis engine for extracting necessary information from the database, a means for analyzing past disaster data and identifying demand patterns for necessary items, a means for integrating multiple external data sources to predict future needs, and a means for optimizing item distribution plans using a machine learning predictive model, thereby enabling the prompt and appropriate distribution of relief items based on the needs of disaster victims.

[0812] A "user" is an individual or entity that uses the system to input required items.

[0813] A "terminal" is a device used by a user to send data entered by the user to a server via the Internet, and includes smartphones and personal computers.

[0814] A "server" is a central computer system that processes received data and analyzes user needs.

[0815] "Audio data" refers to digital data that represents an audio signal input by a user in the form of a voice input.

[0816] "Text data" is character-based data converted from voice data by a voice recognition engine.

[0817] "Natural language processing" refers to a set of technologies and methods for analyzing text data to identify needed items and their urgency.

[0818] "Geographic information" refers to location information of disaster areas and evacuation centers displayed using a geographic information system.

[0819] "Disaster data" refers to various types of data related to disasters, such as weather data and earthquake information.

[0820] A "predictive model" is a mathematical model for predicting future product needs based on collected data.

[0821] "Machine learning" is a collection of algorithms and techniques that improve the accuracy of predictive models based on data.

[0822] "Item distribution plan" refers to a specific item supply plan generated based on needs and forecasts.

[0823] A "database" is a collection of data collected, stored, and managed by a system.

[0824] A "data analysis engine" refers to a technology or system that analyzes information stored in a database and extracts the necessary information.

[0825] "External Data Source" means an external information source used by the system to gather data.

[0826] "Distribution plan optimization" refers to the process of formulating optimal distribution strategies to supply goods efficiently and effectively.

[0827] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0828] Hardware and Software Configuration

[0829] The user's terminal can be a smartphone, PC, or other general device. These terminals connect to the Internet and transmit user input to the server. Specific software includes a voice conversion module and a chat application.

[0830] The server is the central computing system for processing the received data. It is equipped with a speech recognition engine, natural language processing model, database management system, data analysis engine, and machine learning model. Specific software used includes Google Cloud Speech-to-Text, BERT, and GPT-3.

[0831] System Operation Overview

[0832] The user uses the terminal to input the items they need through chat or voice input. For example, the user inputs information such as "I need water" or "Please give me a blanket." This input data is sent by the terminal to the server via the Internet.

[0833] When a voice input is received, the server uses a voice recognition engine to convert the voice data into text data. Through this process, the voice data is converted into text data such as "I need water."

[0834] The server then uses a natural language processing model to analyze the text data. This process extracts information about the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0835] The analyzed information is stored in a database and visualized on a map using a geographic information system, allowing support teams to see at a glance what is needed at each evacuation shelter.

[0836] In addition, the server uses external APIs to collect weather data, earthquake information, and other disaster data. This data is analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0837] The server uses machine learning models to learn from past disaster data and improve its accuracy, which in turn makes forecasts of demand for goods more accurate.

[0838] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific plan might be created, such as "Send 50 liters of water to shelter A."

[0839] Specific examples

[0840] During a disaster, if a user uses a device to voice-input "I need food," the device sends this voice data to a server. The server uses a speech recognition engine to convert the voice data into text data, generating the text "I need food." Next, it analyzes the text data using a natural language processing model and extracts the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0841] Prompt Sentence Examples

[0842] 1. "Can you give me a Python code example for implementing an API for disaster data collection?"

[0843] 2. "How do I train a natural language processing model to extract supply needs during a disaster?"

[0844] 3. "Explain how TensorFlow can be used to predict demand for goods from disaster data."

[0845] 4. "How do I update a product demand forecast model using past disaster data?"

[0846] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0847] Step 1:

[0848] Users use devices such as smartphones or PCs to input the items they need through chat or voice input. Specifically, the user opens the application on their device and types "I need water" into the chat box, or presses the voice input button and speaks "I need a blanket." This input is received as the system's initial data.

[0849] Step 2:

[0850] The device receives user input, and if there is voice input, it uses the device's voice conversion module to convert the voice data into WAV or MP3 format. This converted data is then sent to the server via the Internet. Specifically, the device saves the voice input data as a WAV file and sends this data to the server via an HTTP request.

[0851] Step 3:

[0852] The server passes the received voice data to a speech recognition engine (for example, Google Cloud Speech-to-Text), which converts the voice data into text data. Specifically, the server sends the received wav file to the speech recognition engine, which receives the text data "I need a blanket." The output is the text data "I need a blanket."

[0853] Step 4:

[0854] The server uses a natural language processing model (e.g., BERT or GPT-3) to analyze the text data and extract the items needed and their urgency. The input is the text data "I need a blanket," and the output is "Item needed: Blanket, Urgency: High." Specifically, the server applies a natural language processing algorithm to analyze the text data.

[0855] Step 5:

[0856] The server stores the analysis results in a database. Specifically, it records information such as "Needed items: Blanket, Urgency: High" in the appropriate fields of the database. This process allows the server to accumulate information for subsequent processing.

[0857] Step 6:

[0858] The server uses a geographic information system (GIS) to visualize information about needed items on a map. For example, information such as "Shelter C: Necessary items = Blankets, Quantity = 10, Urgency = High" is displayed at a glance on the map. This allows support teams to instantly understand what is needed at each shelter.

[0859] Step 7:

[0860] The server uses external APIs (e.g., OpenWeatherMap and USGS Earthquake Data) to collect weather data, earthquake information, and other disaster data. An API request is sent as input, and weather data and earthquake information are returned as output. Specifically, the server sends a request to the API to obtain the latest disaster data.

[0861] Step 8:

[0862] The server analyzes the acquired disaster data and predicts future needs for supplies. The acquired disaster data is used as input, and the predicted information that "demand for water will increase" in the future is obtained as output. Specifically, the server runs a prediction algorithm and analyzes the disaster data.

[0863] Step 9:

[0864] The server trains a machine learning model using past disaster data to improve the accuracy of the predictive model. Past disaster data is given as input, and a machine learning algorithm is applied. A highly accurate predictive model is generated as output. Specifically, the server trains a new model using TensorFlow.

[0865] Step 10:

[0866] The server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific distribution plan may be created, such as "send 50 liters of water to shelter A." The output is a notification via the support team's dedicated app or email.

[0867] (Application example 1)

[0868] 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."

[0869] In the event of a disaster, it is extremely important to quickly and efficiently supply the necessary supplies to affected areas. However, conventional systems have had difficulty properly receiving and analyzing supply requests from affected areas and formulating and executing supply plans for relief supplies in real time. Furthermore, there was a lack of means to accurately predict future demand for supplies through the collection and analysis of disaster data. This limited the ability of logistics centers and relief organizations to respond appropriately, resulting in a high likelihood of delays in the supply of supplies to disaster victims and / or shortages and surpluses. Therefore, to solve these issues, a system is needed that can analyze and visualize requests from affected areas in real time and formulate appropriate supply plans.

[0870] 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.

[0871] In this invention, the server includes a means for users to input needed items via chat or voice input, a terminal means for transmitting the input data to the server, and a means for converting voice data into text data. This enables accurate and rapid receipt and analysis of requests for items from disaster-stricken areas. The server also includes a natural language processing means for analyzing the text data to identify needed items and their urgency, a means for visualizing needed items on a map based on the analysis results and geographic information, a means for collecting disaster data and predicting item needs, a machine learning means for training a prediction model to improve accuracy, a means for generating an item distribution plan based on the analysis results and predictions, a means for notifying the generated distribution plan, a means for optimizing the supply of relief items based on the item requests received by the logistics center, a means for visualizing user requests in real time, and a means for acquiring disaster data from an external data source and predicting item demand. This enables effective supply of items in line with the needs of disaster victims, thereby achieving rapid and accurate support for disaster-stricken areas.

[0872] The "chat format" is a form of communication in which users input text, and is an interface that allows messages to be sent and received in real time.

[0873] The "voice input format" is a format in which users input information using voice, and is an interface that receives and analyzes user requests by converting voice into text.

[0874] "Terminal means" refers to a device that allows a user to input information and send it to a server, and includes, for example, a smartphone, tablet, or PC.

[0875] The "server means" is a central computer system for performing data processing, and is a device that converts voice data into text data, performs natural language processing, and performs various data analyses.

[0876] "Natural language processing means" refers to technology for analyzing text data and identifying needed items and their urgency, and refers to the function of understanding and processing language data using machine learning models and algorithms.

[0877] "Visualization means" refers to technology that displays analyzed data on a map, allowing people to intuitively grasp the needs for goods.

[0878] "Disaster data" is a general term for disaster-related data such as meteorological information and earthquake information, and by collecting and analyzing this data, it can be used to forecast demand for goods.

[0879] "Prediction methods" are technologies and models for predicting future supply needs based on collected disaster data.

[0880] "Machine learning methods" are techniques that use past data to learn and improve the accuracy of predictive models, usually using algorithms or neural networks.

[0881] A "distribution plan" is a plan that specifically outlines how necessary items will be supplied to disaster-stricken areas, and determines the optimal distribution route and quantities.

[0882] "Notification methods" refer to technologies used to inform support teams and related organizations of the generated distribution plan, such as email, SMS, and notification apps.

[0883] A "logistics center" is a central facility for efficiently storing and managing goods and delivering them to disaster-stricken areas.

[0884] "Real-time visualization means" refers to technology that instantly displays user requests, enabling timely confirmation of needs for support items.

[0885] "External data sources" are external databases or APIs that provide disaster data and other relevant information that can be used to improve the accuracy of the predictive models.

[0886] This invention is a system for quickly and efficiently supplying necessary items to disaster victims in the event of a disaster. This system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[0887] User input of items

[0888] Users can input what items they need using chat or voice input on devices such as smartphones or computers. For example, users can input information such as "I need water" or "Please give me a blanket."

[0889] Data transmission by the terminal

[0890] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0891] Data preprocessing by the server

[0892] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0893] Data analysis using natural language processing

[0894] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[0895] Aggregation and visualization of needs information

[0896] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0897] Disaster data collection and needs forecasting

[0898] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[0899] Updating predictive models with machine learning

[0900] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[0901] Generate and notify material distribution plans

[0902] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0903] Addition of functions for logistics centers

[0904] This system also includes a function that enables logistics centers to optimize the supply of disaster relief supplies. The logistics center receives request data from users in real time and can create optimal supply plans based on needs information visualized on a map. In addition, by using disaster data obtained from external data sources, it is possible to accurately predict future demand for supplies and supply them accordingly.

[0905] Usage example

[0906] For example, if a user uses a device to say "I need food" during a disaster, this voice data is sent to a server and converted into text data by a speech recognition engine. Then, using a natural language processing model, the information "Needed items: food, Urgency: high" is extracted. This information is stored in a database and visualized on a map. Based on this information, the logistics center can create and execute a food supply plan for disaster-stricken areas. Furthermore, by collecting and analyzing weather data and other disaster data, future demand for goods can be predicted, enabling more effective support.

[0907] Prompt Sentence Examples

[0908] Here are some examples of prompts for generative AI models:

[0909] "We are developing an application that predicts the need for relief supplies during disasters and creates optimal distribution plans. It converts voice input into text, uses natural language processing to analyze the supplies needed and their urgency, and visualizes them on a map. It also obtains weather data from an external API to predict future needs. This will enable efficient supply of supplies."

[0910] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0911] Step 1:

[0912] The user inputs the items they need in chat or voice input format. Using a device such as a smartphone or PC, the user inputs information such as "I need water" or "Can I have a blanket?" This generates text data or voice data. Input: Text data or voice data from the user. Output: Text data or voice data.

[0913] Step 2:

[0914] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the voice data is converted on the device into a common audio format such as WAV or MP3, and then sent to the server along with the text data. Input: Text data or voice data. Output: Text data or voice data sent to the server.

[0915] Step 3:

[0916] When the server receives the voice data, it uses a voice recognition engine to convert the voice data into text data. As a result, voice data such as "I need water" is converted into text data. Input: Voice data. Output: Text data.

[0917] Step 4:

[0918] The server uses a natural language processing model to analyze the text data. This process extracts needed items and their urgency from the text data. For example, from the text "I need water," the information "Needed items: Water, Urgency: High" is obtained. Input: Text data. Output: Information on needed items and urgency.

[0919] Step 5:

[0920] The server stores the analyzed information in a database. Next, using a geographic information system, the location of each evacuation center and disaster victims, along with information on necessary items, are visualized on a map. Input: Information on necessary items and urgency. Output: Needs information displayed on a map.

[0921] Step 6:

[0922] The server uses an external API to collect disaster data such as weather data and earthquake information. It analyzes this disaster data and predicts future needs for goods. For example, it predicts future increases in demand for water based on rainfall data. Input: Disaster data obtained from the external API. Output: Predicted demand for goods.

[0923] Step 7:

[0924] The server uses past disaster data to train the predictive model and improve its accuracy. This makes demand forecasts for goods more accurate. Input: Past disaster data. Output: Improved predictive model.

[0925] Step 8:

[0926] The server generates an optimal distribution plan based on the analysis results and prediction data. For example, a specific plan such as "Send 50 liters of water to shelter A" is created. Input: Analysis results and prediction data. Output: Distribution plan.

[0927] Step 9:

[0928] The server notifies the support team and local governments of the generated item distribution plan, allowing support items to be supplied quickly and accurately. Input: Item distribution plan. Output: Notified distribution plan.

[0929] Step 10:

[0930] The logistics center optimizes the supply of relief goods based on the goods requests received from the server. It determines the optimal supply route and quantity of goods, taking into account congestion and logistics efficiency. Input: Goods requests from users and disaster data. Output: Optimized supply plan.

[0931] 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.

[0932] Overview of the entire system

[0933] This invention is a system for efficiently supplying disaster victims with necessary items. By combining it with an emotion engine, it provides support that takes into account the emotional state of the disaster victims. The system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[0934] User input of items

[0935] Users can input the items they need using chat or voice input using devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0936] Data transmission by the terminal

[0937] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[0938] Data preprocessing by the server

[0939] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[0940] Data analysis using natural language processing

[0941] The server uses natural language processing models to analyze text data, extracting information such as "Item needed: water, Urgency: high." Chat input is also analyzed.

[0942] Emotion analysis using an emotion engine

[0943] The server also uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from voice tone and text content.

[0944] Emotional information integration

[0945] Emotional information from the emotion engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[0946] Aggregation and visualization of needs information

[0947] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[0948] Disaster data collection and needs forecasting

[0949] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data and predicts future needs for supplies. For example, it predicts future increases in water demand based on rainfall data.

[0950] Updating predictive models with machine learning

[0951] The server uses past disaster data to train and improve the predictive model, which will lead to more accurate forecasts of future supply needs.

[0952] Generate and notify material distribution plans

[0953] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[0954] Specific examples

[0955] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model to obtain the information "Needed items: food, Urgency: high." Furthermore, it uses an emotion engine to extract the information "Stress level: high" from the voice data. This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[0956] This will enable the efficient and rapid supply of relief goods, while also enabling support that takes into consideration the emotional state of the victims.The system aims to provide faster and more accurate support during disasters.

[0957] The processing flow will be explained below.

[0958] Step 1:

[0959] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[0960] Step 2:

[0961] The device sends the user's input data to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3 before sending it. In the case of text input, the data is sent in its original format.

[0962] Step 3:

[0963] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[0964] Step 4:

[0965] The server uses a natural language processing model to analyze text data, extracting information such as "Items needed: water, Urgency: high." Chat input is also analyzed in the same way.

[0966] Step 5:

[0967] The server uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[0968] Step 6:

[0969] The server generates analysis results by integrating the emotion information from the emotion engine with natural language processing means. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotion information "Stress level: high."

[0970] Step 7:

[0971] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored along with emotional information.

[0972] Step 8:

[0973] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on necessary supplies. For example, the location of shelter A displays an icon that reads "Water needed" along with a "Stress level: High" icon.

[0974] Step 9:

[0975] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[0976] Step 10:

[0977] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[0978] Step 11:

[0979] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[0980] Step 12:

[0981] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[0982] Step 13:

[0983] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[0984] These steps will enable efficient and rapid delivery of relief supplies. In addition, by combining it with an emotion engine, it will be possible to provide support that takes into account the emotional state of the victims.

[0985] Example 2

[0986] 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."

[0987] Conventional disaster relief systems have difficulty quickly and accurately grasping the needs of disaster victims, resulting in delays in the supply of relief supplies and shortages and surpluses. Furthermore, relief efforts did not take into account the emotional state of disaster victims, resulting in a lack of psychological support. This resulted in issues that reduced the efficiency and accuracy of relief activities.

[0988] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0989] In this invention, the server includes a means for converting voice data into text data, a natural language processing means, and a sentiment analysis means, which enable the server to quickly and accurately grasp the material needs and emotional state of disaster victims, and to generate an optimal relief supply distribution plan by integrating the analysis results.

[0990] "User" refers to a disaster victim or a supporter who uses the system to input their needs for goods.

[0991] "Terminal means" refers to a device that allows a user to input product needs and transmit the data to the server, including a smartphone or PC.

[0992] "Central Processing Unit" refers to a server for processing and analyzing input data.

[0993] "Audio data" refers to the recorded data when the user inputs voice.

[0994] "Text data" refers to voice data or text entered in chat format.

[0995] "Natural language processing means" refers to algorithms and models that analyze input text data and extract information such as required items and urgency.

[0996] "Emotion analysis means" refers to algorithms or models that analyze a user's emotional state from their input and identify stress, anxiety, etc.

[0997] "Means for visualizing on a map" refers to a method for displaying analyzed information on a map using a geographic information system (GIS).

[0998] "Disaster data" refers to data related to disasters, such as weather information and earthquake information.

[0999] "Machine learning methods" refer to algorithms and technologies that use past disaster data to train predictive models and improve their accuracy.

[1000] "Item distribution plan" refers to an item supply plan created based on analysis results and forecast data.

[1001] "Means for notifying distribution plans" refers to methods and techniques for notifying support teams and local governments of the generated item distribution plans.

[1002] This invention is a system for efficiently providing necessary items to disaster victims in the event of a disaster, and provides support that takes into account the emotional state of the victims by combining it with emotion analysis. This system works by allowing users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[1003] Users can input the items they need using chat or voice input on devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone, or type "I don't have any blankets" into the chat window.

[1004] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it.

[1005] The server converts the transmitted voice data into text data using a speech recognition engine (for example, Google Cloud Speech-to-Text API). Specifically, the voice data is converted into text data such as "I need water."

[1006] Next, the server analyzes the text data using a natural language processing model (e.g., BERT or GPT). This analysis extracts information such as "Items needed: water, Urgency: high." The same analysis is performed even if the data is entered in chat format.

[1007] The server then uses an emotion analysis engine (e.g., IBM Watson Natural Language Understanding) to analyze the user's emotional state from the input data, for example, recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[1008] Emotional information from the emotion analysis engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[1009] The analyzed information is stored in a database on a server, and then a geographic information system is used to visualize the location of each evacuation shelter and disaster victims, along with information on the necessary supplies, on a map, allowing support teams to see at a glance what is needed at each shelter.

[1010] The server uses external APIs (e.g., OpenWeatherMap API or USGS Earthquake Hazards Program API) to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data to predict future needs for goods. For example, it can predict an increase in demand for water based on rainfall data.

[1011] Furthermore, the server uses past disaster data to train and improve the accuracy of predictive models using machine learning algorithms (such as Random Forest and XGBoost). This update enables highly accurate needs predictions.

[1012] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan to send 50 liters of water to shelter A and 25 kg of food to shelter B, and notifies the support team and local government in real time.

[1013] Specific examples

[1014] During a disaster, a user uses a device to voice input, "We need blankets." The device sends the voice data to a server, which converts it into text data using a voice recognition engine. The server analyzes the text data, "We need blankets," using a natural language processing model to obtain the information, "Needed items: blankets, Urgency: high." The server then uses an emotion analysis engine to extract the information, "Anxiety level: medium," from the voice data. This information is stored in a database and displayed on a map. The server checks current weather data and predicts that the demand for blankets will continue. Finally, it notifies the support team of a distribution plan, "Send 30 blankets to shelter C."

[1015] Example prompts to input to the generative AI model

[1016] "Please explain a system that efficiently supplies items needed by disaster victims in the event of a disaster. Please provide a detailed description, including the roles and specific processes of users, terminals, and servers."

[1017] This system will enable the rapid and accurate provision of relief supplies, and will also enable support that takes into consideration the emotional state of disaster victims.

[1018] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1019] Step 1:

[1020] Users use devices such as smartphones or PCs to input the items they need in chat or voice input format. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into a chat window. The input data is saved on the device as voice or text data.

[1021] Step 2:

[1022] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it, and in the case of text input, it sends the text data as is. This transfers the input data to the server.

[1023] Step 3:

[1024] The server converts the received voice data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, the voice data is converted into text data such as "I need water." This converted text data is used in the next analysis step.

[1025] Step 4:

[1026] The server analyzes the text data using a natural language processing model (e.g., BERT or GPT). In this step, information such as "needed items: water, urgency: high" is extracted from the text data. The input text is output as categorized information through the analysis process.

[1027] Step 5:

[1028] The server uses an emotion analysis engine (for example, IBM Watson Natural Language Understanding) to analyze the user's emotional state from the input data. Specifically, it recognizes emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content, and obtains information such as "stress level: high" as output.

[1029] Step 6:

[1030] The server integrates the results of natural language processing analysis and sentiment analysis. Specifically, it integrates the analysis results of the text data "Necessary items: water, urgency: high" with the emotional information "Stress level: high" into a single dataset. This generates data that comprehensively captures the necessary items, their urgency, and the user's emotional state.

[1031] Step 7:

[1032] The server stores the analyzed integrated information in a database and visualizes it on a map using a geographic information system (GIS). Information on the location of victims and the necessary supplies is displayed on the map. This allows support teams and other relevant parties to understand in real time what items are needed at each evacuation shelter.

[1033] Step 8:

[1034] The server uses external APIs (e.g., OpenWeatherMap API and USGS Earthquake Hazards Program API) to collect current weather data, earthquake information, and other disaster data. The collected data undergoes analysis and processing and is used as input data for predicting future product needs.

[1035] Step 9:

[1036] The server uses machine learning algorithms (such as Random Forest and XGBoost) to train and improve the accuracy of predictive models using past disaster data, which will lead to more accurate forecasts of future supply needs.

[1037] Step 10:

[1038] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, a specific plan may be created such as "send 50 liters of water to shelter A and 25 kg of food to shelter B." This plan is notified to relief teams and local governments in real time. This information serves as the basis for rapid relief activities.

[1039] (Application example 2)

[1040] 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."

[1041] While it is important to efficiently and quickly provide disaster victims with the supplies they need, conventional methods have difficulty providing support that takes into account the emotional state of the victims. Furthermore, it is difficult to integrate real-time geographic information and supply needs, which means it takes time to formulate an optimal supply distribution plan.

[1042] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input needed items in chat format or voice input format; a terminal means for transmitting the input data to the server; a means for converting voice data into text data; a natural language processing means for analyzing the text data and identifying needed items and their urgency; a means for visualizing needed items on a map based on the analysis results and geographic information; a means for collecting disaster data and predicting needs for items; a machine learning means for training a prediction model and improving accuracy; a means for generating an item distribution plan based on the analysis results and predictions; a means for notifying the generated distribution plan; an emotion analysis means for analyzing the user's emotional state; a means for adjusting the urgency of items taking the emotional state into consideration; and a means for integrating item request information with a geographic information system in real time and displaying it. This enables efficient and rapid delivery of needed items during a disaster while taking the emotional state of disaster victims into consideration.

[1043] A "user" is an individual or organization that uses the system to input items needed in the event of a disaster.

[1044] "Chat format" refers to a text-based communication format in which users input messages using a keyboard or touch screen.

[1045] The "voice input format" is a format in which information is input through voice using a microphone or the like.

[1046] "Necessary items" refers to the supplies and support items that disaster victims require in the event of a disaster.

[1047] "Terminal means" refers to a device, such as a smartphone or a personal computer, that transmits data entered by a user to a server.

[1048] "Audio data" refers to audio signals entered by a user using an audio input form.

[1049] "Text data" is voice data converted into character information.

[1050] "Natural language processing means" refers to a technical means for analyzing text data, understanding its meaning, and identifying the items needed and their urgency.

[1051] A "geographic information system" is a system that collects, displays, and analyzes geographic information.

[1052] "Disaster data" refers to data that includes various types of information related to disasters, such as weather information and earthquake information.

[1053] "Machine learning means" refers to technical means for learning data and improving the accuracy of predictive models based on the learning results.

[1054] A "distribution plan" is a plan that includes schedules and routes for optimally distributing necessary items to disaster victims.

[1055] "Emotion analysis means" is a technical means for analyzing the emotional state of a user from their voice or text and understanding the situation.

[1056] "Urgency" is an index that indicates the degree of need for an item.

[1057] "Means for integrating and displaying" refers to a technical means for integrating data obtained from multiple information sources and displaying it on a single display screen.

[1058] The "notification means" is a technical means for notifying the relevant parties of the generated product distribution plan.

[1059] This invention is a system for efficiently and quickly supplying items needed by disaster victims, and by combining it with an emotion engine, it provides support that takes into account the emotional state of the victims. Specific embodiments for carrying out the invention are described below.

[1060] System Overview

[1061] The system is made up of a server, terminals, and users working together. Users use terminals such as smartphones and PCs to input the items they need via chat or voice input. The terminals then send the input data to the server via the internet.

[1062] Voice Recognition

[1063] The device sends voice data to the server, which converts the voice data into text data using a speech recognition engine (e.g., Python's speech_recognition library). For example, if a user says "I need water" into their smartphone, this voice input is converted into the text data "I need water."

[1064] Emotion analysis

[1065] The server analyzes the text data using a natural language processing engine (e.g., sentiment analysis model from the transformers library) to identify the items needed and their urgency. The sentiment analysis engine also analyzes the user's emotional state (e.g., stress, anxiety).

[1066] Data aggregation and visualization

[1067] The analyzed data is stored in a database on the server. Next, using a geographic information system (e.g., the folium library), the necessary item information and the location information of each evacuation shelter are visualized on a map.

[1068] Collecting disaster data and predicting supply needs

[1069] The server uses an external disaster data API (e.g., API access with the requests library) to collect weather data, earthquake information, etc. This data is analyzed to predict future product needs.

[1070] Generate and notify material distribution plans

[1071] The server generates an optimal distribution plan based on the analysis results and disaster data (e.g., by processing the data using the pandas library). The generated distribution plan is notified to the support team and local governments via notification methods (e.g., email, app notification).

[1072] Specific examples

[1073] During a disaster, a user uses a device to voice-input the phrase "I need food." The device sends this voice data to a server, which then uses a speech recognition engine to generate text data saying "I need food." The text data is then analyzed using a natural language processing model to obtain information such as "Needed items: food, Urgency: high." A sentiment analysis engine is also used to extract information such as "Stress level: high." This information is integrated with a geographic information system and visualized on a map. The server checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[1074] Prompt Sentence Examples

[1075] When a user says "I need water" into their smartphone, the application does the following:

[1076] 1. Convert audio data into text data.

[1077] 2. Conduct sentiment analysis to understand the user's emotional state.

[1078] 3. Collect disaster data and predict future needs.

[1079] 4. Integrate needed goods with geographic information to generate optimal distribution plans.

[1080] 5. Notify the logistics center of specific distribution instructions and provide support such as "send 50 liters of water to shelter A."

[1081] The above is a specific embodiment for carrying out the invention.

[1082] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1083] Step 1:

[1084] The user inputs the items they need through voice input or chat. For example, the user speaks into their smartphone, saying, "I need water," and voice data is generated.

[1085] Step 2:

[1086] The device sends the user's voice data to the server, which then converts the data into a common audio format (e.g., WAV, MP3, etc.) and sends it to the server via the Internet.

[1087] Step 3:

[1088] The server converts the transmitted voice data into text data using a speech recognition engine. Specifically, it analyzes the voice signal using Python's speech_recognition library and generates the text data "I need water."

[1089] Step 4:

[1090] The server analyzes the text data using a natural language processing engine. The library used is transformers. The information extracted from the text is "Needed items: water, Urgency: high."

[1091] Step 5:

[1092] At the same time, the server uses an emotion analysis engine to analyze the user's emotional state. It analyzes "stress," "anxiety," etc. from the tone of voice and the content of the text. As a result, it obtains the data "Stress level: High."

[1093] Step 6:

[1094] The server integrates the text analysis results with the sentiment analysis results, generating integrated data such as "Needed items: water, Urgency: high, Stress level: high."

[1095] Step 7:

[1096] The server stores the integrated data in a database, and simultaneously visualizes the location of each evacuation center and necessary supplies on a map using a geographic information system (GIS). This is done using the folium library.

[1097] Step 8:

[1098] The server collects weather and earthquake data from external disaster data APIs using the requests library to obtain real-time disaster data.

[1099] Step 9:

[1100] The server analyzes the disaster data collected and predicts future needs for supplies. Based on past data, predictions are made using a machine learning model that uses a generative AI model.

[1101] Step 10:

[1102] The server generates an optimal distribution plan based on the analysis results and predicted data. Specifically, it processes the data using the pandas library and creates a specific distribution plan, such as "send 25 kg of food to shelter B."

[1103] Step 11:

[1104] The server notifies the support team and local governments of the generated distribution plan using methods such as email and app notifications to ensure information is transmitted quickly.

[1105] Through the above processing steps, it becomes possible to efficiently and quickly supply necessary items in the event of a disaster while taking into consideration the emotional state of the user.

[1106] 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.

[1107] 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.

[1108] 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.

[1109] [Fourth embodiment]

[1110] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1111] 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.

[1112] 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).

[1113] 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.

[1114] 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.

[1115] 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).

[1116] 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.

[1117] 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.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] 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.

[1122] 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."

[1123] Overview of the entire system

[1124] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[1125] User input of items

[1126] Users can use devices such as smartphones or computers to input what items they need via chat or voice input. For example, users can input information such as "I need water" or "Please give me a blanket."

[1127] Data transmission by the terminal

[1128] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[1129] Data preprocessing by the server

[1130] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[1131] Data analysis using natural language processing

[1132] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[1133] Aggregation and visualization of needs information

[1134] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[1135] Disaster data collection and needs forecasting

[1136] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[1137] Updating predictive models with machine learning

[1138] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[1139] Generate and notify material distribution plans

[1140] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[1141] Specific examples

[1142] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model and obtains the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[1143] This will enable the efficient and rapid supply of relief goods, and the system aims to provide faster and more accurate support in the event of a disaster.

[1144] The processing flow will be explained below.

[1145] Step 1:

[1146] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[1147] Step 2:

[1148] The device sends the data entered by the user to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3. In the case of text input, the data is sent in its original format.

[1149] Step 3:

[1150] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[1151] Step 4:

[1152] The server uses a natural language processing model to analyze the text data, extracting information such as "Items needed: water, Urgency: high." The same analysis is done for text input in chat format.

[1153] Step 5:

[1154] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored.

[1155] Step 6:

[1156] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on the supplies needed. For example, an icon saying "Water needed" is displayed at the location of shelter A.

[1157] Step 7:

[1158] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[1159] Step 8:

[1160] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[1161] Step 9:

[1162] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[1163] Step 10:

[1164] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[1165] Step 11:

[1166] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[1167] These steps ensure efficient and rapid delivery of support items.

[1168] Example 1

[1169] 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."

[1170] In the event of a disaster, it is extremely important to provide necessary items to victims quickly and effectively, but current methods often result in insufficient information gathering and needs analysis, which delays appropriate assistance. Furthermore, the accuracy of predictive models is low, making it difficult to provide necessary items appropriately. The aim of this project is to solve these issues.

[1171] 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.

[1172] In this invention, the server includes a means for storing data generated from user input in a database, a means including a data analysis engine for extracting necessary information from the database, a means for analyzing past disaster data and identifying demand patterns for necessary items, a means for integrating multiple external data sources to predict future needs, and a means for optimizing item distribution plans using a machine learning predictive model, thereby enabling the prompt and appropriate distribution of relief items based on the needs of disaster victims.

[1173] A "user" is an individual or entity that uses the system to input required items.

[1174] A "terminal" is a device used by a user to send data entered by the user to a server via the Internet, and includes smartphones and personal computers.

[1175] A "server" is a central computer system that processes received data and analyzes user needs.

[1176] "Audio data" refers to digital data that represents an audio signal input by a user in the form of a voice input.

[1177] "Text data" is character-based data converted from voice data by a voice recognition engine.

[1178] "Natural language processing" refers to a set of technologies and methods for analyzing text data to identify needed items and their urgency.

[1179] "Geographic information" refers to location information of disaster areas and evacuation centers displayed using a geographic information system.

[1180] "Disaster data" refers to various types of data related to disasters, such as weather data and earthquake information.

[1181] A "predictive model" is a mathematical model for predicting future product needs based on collected data.

[1182] "Machine learning" is a collection of algorithms and techniques that improve the accuracy of predictive models based on data.

[1183] "Item distribution plan" refers to a specific item supply plan generated based on needs and forecasts.

[1184] A "database" is a collection of data collected, stored, and managed by a system.

[1185] A "data analysis engine" refers to a technology or system that analyzes information stored in a database and extracts the necessary information.

[1186] "External Data Source" means an external information source used by the system to gather data.

[1187] "Distribution plan optimization" refers to the process of formulating optimal distribution strategies to supply goods efficiently and effectively.

[1188] This invention is a system for efficiently supplying necessary items to disaster victims in the event of a disaster. In this system, users input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[1189] Hardware and Software Configuration

[1190] The user's terminal can be a smartphone, PC, or other general device. These terminals connect to the Internet and transmit user input to the server. Specific software includes a voice conversion module and a chat application.

[1191] The server is the central computing system for processing the received data. It is equipped with a speech recognition engine, natural language processing model, database management system, data analysis engine, and machine learning model. Specific software used includes Google Cloud Speech-to-Text, BERT, and GPT-3.

[1192] System Operation Overview

[1193] The user uses the terminal to input the items they need through chat or voice input. For example, the user inputs information such as "I need water" or "Please give me a blanket." This input data is sent by the terminal to the server via the Internet.

[1194] When a voice input is received, the server uses a voice recognition engine to convert the voice data into text data. Through this process, the voice data is converted into text data such as "I need water."

[1195] The server then uses a natural language processing model to analyze the text data. This process extracts information about the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[1196] The analyzed information is stored in a database and visualized on a map using a geographic information system, allowing support teams to see at a glance what is needed at each evacuation shelter.

[1197] In addition, the server uses external APIs to collect weather data, earthquake information, and other disaster data. This data is analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[1198] The server uses machine learning models to learn from past disaster data and improve its accuracy, which in turn makes forecasts of demand for goods more accurate.

[1199] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific plan might be created, such as "Send 50 liters of water to shelter A."

[1200] Specific examples

[1201] During a disaster, if a user uses a device to voice-input "I need food," the device sends this voice data to a server. The server uses a speech recognition engine to convert the voice data into text data, generating the text "I need food." Next, it analyzes the text data using a natural language processing model and extracts the information "Needed items: food, Urgency: high." This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[1202] Prompt Sentence Examples

[1203] 1. "Can you give me a Python code example for implementing an API for disaster data collection?"

[1204] 2. "How do I train a natural language processing model to extract supply needs during a disaster?"

[1205] 3. "Explain how TensorFlow can be used to predict demand for goods from disaster data."

[1206] 4. "How do I update a product demand forecast model using past disaster data?"

[1207] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1208] Step 1:

[1209] Users use devices such as smartphones or PCs to input the items they need through chat or voice input. Specifically, the user opens the application on their device and types "I need water" into the chat box, or presses the voice input button and speaks "I need a blanket." This input is received as the system's initial data.

[1210] Step 2:

[1211] The device receives user input, and if there is voice input, it uses the device's voice conversion module to convert the voice data into WAV or MP3 format. This converted data is then sent to the server via the Internet. Specifically, the device saves the voice input data as a WAV file and sends this data to the server via an HTTP request.

[1212] Step 3:

[1213] The server passes the received voice data to a speech recognition engine (for example, Google Cloud Speech-to-Text), which converts the voice data into text data. Specifically, the server sends the received wav file to the speech recognition engine, which receives the text data "I need a blanket." The output is the text data "I need a blanket."

[1214] Step 4:

[1215] The server uses a natural language processing model (e.g., BERT or GPT-3) to analyze the text data and extract the items needed and their urgency. The input is the text data "I need a blanket," and the output is "Item needed: Blanket, Urgency: High." Specifically, the server applies a natural language processing algorithm to analyze the text data.

[1216] Step 5:

[1217] The server stores the analysis results in a database. Specifically, it records information such as "Needed items: Blanket, Urgency: High" in the appropriate fields of the database. This process allows the server to accumulate information for subsequent processing.

[1218] Step 6:

[1219] The server uses a geographic information system (GIS) to visualize information about needed items on a map. For example, information such as "Shelter C: Necessary items = Blankets, Quantity = 10, Urgency = High" is displayed at a glance on the map. This allows support teams to instantly understand what is needed at each shelter.

[1220] Step 7:

[1221] The server uses external APIs (e.g., OpenWeatherMap and USGS Earthquake Data) to collect weather data, earthquake information, and other disaster data. An API request is sent as input, and weather data and earthquake information are returned as output. Specifically, the server sends a request to the API to obtain the latest disaster data.

[1222] Step 8:

[1223] The server analyzes the acquired disaster data and predicts future needs for supplies. The acquired disaster data is used as input, and the predicted information that "demand for water will increase" in the future is obtained as output. Specifically, the server runs a prediction algorithm and analyzes the disaster data.

[1224] Step 9:

[1225] The server trains a machine learning model using past disaster data to improve the accuracy of the predictive model. Past disaster data is given as input, and a machine learning algorithm is applied. A highly accurate predictive model is generated as output. Specifically, the server trains a new model using TensorFlow.

[1226] Step 10:

[1227] The server generates an optimal distribution plan based on the analysis results and forecast data, and notifies the support team and local government. For example, a specific distribution plan may be created, such as "send 50 liters of water to shelter A." The output is a notification via the support team's dedicated app or email.

[1228] (Application example 1)

[1229] 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."

[1230] In the event of a disaster, it is extremely important to quickly and efficiently supply the necessary supplies to affected areas. However, conventional systems have had difficulty properly receiving and analyzing supply requests from affected areas and formulating and executing supply plans for relief supplies in real time. Furthermore, there was a lack of means to accurately predict future demand for supplies through the collection and analysis of disaster data. This limited the ability of logistics centers and relief organizations to respond appropriately, resulting in a high likelihood of delays in the supply of supplies to disaster victims and / or shortages and surpluses. Therefore, to solve these issues, a system is needed that can analyze and visualize requests from affected areas in real time and formulate appropriate supply plans.

[1231] 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.

[1232] In this invention, the server includes a means for users to input needed items via chat or voice input, a terminal means for transmitting the input data to the server, and a means for converting voice data into text data. This enables accurate and rapid receipt and analysis of requests for items from disaster-stricken areas. The server also includes a natural language processing means for analyzing the text data to identify needed items and their urgency, a means for visualizing needed items on a map based on the analysis results and geographic information, a means for collecting disaster data and predicting item needs, a machine learning means for training a prediction model to improve accuracy, a means for generating an item distribution plan based on the analysis results and predictions, a means for notifying the generated distribution plan, a means for optimizing the supply of relief items based on the item requests received by the logistics center, a means for visualizing user requests in real time, and a means for acquiring disaster data from an external data source and predicting item demand. This enables effective supply of items in line with the needs of disaster victims, thereby achieving rapid and accurate support for disaster-stricken areas.

[1233] The "chat format" is a form of communication in which users input text, and is an interface that allows messages to be sent and received in real time.

[1234] The "voice input format" is a format in which users input information using voice, and is an interface that receives and analyzes user requests by converting voice into text.

[1235] "Terminal means" refers to a device that allows a user to input information and send it to a server, and includes, for example, a smartphone, tablet, or PC.

[1236] The "server means" is a central computer system for performing data processing, and is a device that converts voice data into text data, performs natural language processing, and performs various data analyses.

[1237] "Natural language processing means" refers to technology for analyzing text data and identifying needed items and their urgency, and refers to the function of understanding and processing language data using machine learning models and algorithms.

[1238] "Visualization means" refers to technology that displays analyzed data on a map, allowing people to intuitively grasp the needs for goods.

[1239] "Disaster data" is a general term for disaster-related data such as meteorological information and earthquake information, and by collecting and analyzing this data, it can be used to forecast demand for goods.

[1240] "Prediction methods" are technologies and models for predicting future supply needs based on collected disaster data.

[1241] "Machine learning methods" are techniques that use past data to learn and improve the accuracy of predictive models, usually using algorithms or neural networks.

[1242] A "distribution plan" is a plan that specifically outlines how necessary items will be supplied to disaster-stricken areas, and determines the optimal distribution route and quantities.

[1243] "Notification methods" refer to technologies used to inform support teams and related organizations of the generated distribution plan, such as email, SMS, and notification apps.

[1244] A "logistics center" is a central facility for efficiently storing and managing goods and delivering them to disaster-stricken areas.

[1245] "Real-time visualization means" refers to technology that instantly displays user requests, enabling timely confirmation of needs for support items.

[1246] "External data sources" are external databases or APIs that provide disaster data and other relevant information that can be used to improve the accuracy of the predictive models.

[1247] This invention is a system for quickly and efficiently supplying necessary items to disaster victims in the event of a disaster. This system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, the system includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[1248] User input of items

[1249] Users can input what items they need using chat or voice input on devices such as smartphones or computers. For example, users can input information such as "I need water" or "Please give me a blanket."

[1250] Data transmission by the terminal

[1251] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[1252] Data preprocessing by the server

[1253] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[1254] Data analysis using natural language processing

[1255] The server uses a natural language processing model to analyze the text data. This process extracts information such as the items needed and their urgency. For example, the text "I need water" yields the information "Item needed: Water, Urgency: High."

[1256] Aggregation and visualization of needs information

[1257] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[1258] Disaster data collection and needs forecasting

[1259] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This data can be analyzed to predict future needs for goods. For example, rainfall data can be used to predict future increases in water demand.

[1260] Updating predictive models with machine learning

[1261] The server uses past disaster data to train and improve the predictive model, which in turn leads to more accurate forecasts of demand for goods.

[1262] Generate and notify material distribution plans

[1263] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it may create a specific plan to "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[1264] Addition of functions for logistics centers

[1265] This system also includes a function that enables logistics centers to optimize the supply of disaster relief supplies. The logistics center receives request data from users in real time and can create optimal supply plans based on needs information visualized on a map. In addition, by using disaster data obtained from external data sources, it is possible to accurately predict future demand for supplies and supply them accordingly.

[1266] Usage example

[1267] For example, if a user uses a device to say "I need food" during a disaster, this voice data is sent to a server and converted into text data by a speech recognition engine. Then, using a natural language processing model, the information "Needed items: food, Urgency: high" is extracted. This information is stored in a database and visualized on a map. Based on this information, the logistics center can create and execute a food supply plan for disaster-stricken areas. Furthermore, by collecting and analyzing weather data and other disaster data, future demand for goods can be predicted, enabling more effective support.

[1268] Prompt Sentence Examples

[1269] Here are some examples of prompts for generative AI models:

[1270] "We are developing an application that predicts the need for relief supplies during disasters and creates optimal distribution plans. It converts voice input into text, uses natural language processing to analyze the supplies needed and their urgency, and visualizes them on a map. It also obtains weather data from an external API to predict future needs. This will enable efficient supply of supplies."

[1271] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1272] Step 1:

[1273] The user inputs the items they need in chat or voice input format. Using a device such as a smartphone or PC, the user inputs information such as "I need water" or "Can I have a blanket?" This generates text data or voice data. Input: Text data or voice data from the user. Output: Text data or voice data.

[1274] Step 2:

[1275] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the voice data is converted on the device into a common audio format such as WAV or MP3, and then sent to the server along with the text data. Input: Text data or voice data. Output: Text data or voice data sent to the server.

[1276] Step 3:

[1277] When the server receives the voice data, it uses a voice recognition engine to convert the voice data into text data. As a result, voice data such as "I need water" is converted into text data. Input: Voice data. Output: Text data.

[1278] Step 4:

[1279] The server uses a natural language processing model to analyze the text data. This process extracts needed items and their urgency from the text data. For example, from the text "I need water," the information "Needed items: Water, Urgency: High" is obtained. Input: Text data. Output: Information on needed items and urgency.

[1280] Step 5:

[1281] The server stores the analyzed information in a database. Next, using a geographic information system, the location of each evacuation center and disaster victims, along with information on necessary items, are visualized on a map. Input: Information on necessary items and urgency. Output: Needs information displayed on a map.

[1282] Step 6:

[1283] The server uses an external API to collect disaster data such as weather data and earthquake information. It analyzes this disaster data and predicts future needs for goods. For example, it predicts future increases in demand for water based on rainfall data. Input: Disaster data obtained from the external API. Output: Predicted demand for goods.

[1284] Step 7:

[1285] The server uses past disaster data to train the predictive model and improve its accuracy. This makes demand forecasts for goods more accurate. Input: Past disaster data. Output: Improved predictive model.

[1286] Step 8:

[1287] The server generates an optimal distribution plan based on the analysis results and prediction data. For example, a specific plan such as "Send 50 liters of water to shelter A" is created. Input: Analysis results and prediction data. Output: Distribution plan.

[1288] Step 9:

[1289] The server notifies the support team and local governments of the generated item distribution plan, allowing support items to be supplied quickly and accurately. Input: Item distribution plan. Output: Notified distribution plan.

[1290] Step 10:

[1291] The logistics center optimizes the supply of relief goods based on the goods requests received from the server. It determines the optimal supply route and quantity of goods, taking into account congestion and logistics efficiency. Input: Goods requests from users and disaster data. Output: Optimized supply plan.

[1292] 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.

[1293] Overview of the entire system

[1294] This invention is a system for efficiently supplying disaster victims with necessary items. By combining it with an emotion engine, it provides support that takes into account the emotional state of the disaster victims. The system allows users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict the need for items from disaster data and generate and notify optimal item distribution plans.

[1295] User input of items

[1296] Users can input the items they need using chat or voice input using devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[1297] Data transmission by the terminal

[1298] The device sends the data entered by the user to a server via the Internet. In the case of voice input, the voice data is converted to a common audio format such as WAV or MP3 on the device before being sent.

[1299] Data preprocessing by the server

[1300] When the voice data is sent, the server uses a voice recognition engine to convert the voice data into text data, which results in the voice data being converted into text data such as "I need water."

[1301] Data analysis using natural language processing

[1302] The server uses natural language processing models to analyze text data, extracting information such as "Item needed: water, Urgency: high." Chat input is also analyzed.

[1303] Emotion analysis using an emotion engine

[1304] The server also uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from voice tone and text content.

[1305] Emotional information integration

[1306] Emotional information from the emotion engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[1307] Aggregation and visualization of needs information

[1308] The analyzed information is stored in a database on a server. Next, using a geographic information system, the location of each evacuation shelter and the location of the disaster victims is visualized on a map along with the necessary supplies, allowing the support team to see at a glance what is needed at each shelter.

[1309] Disaster data collection and needs forecasting

[1310] The server uses external APIs to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data and predicts future needs for supplies. For example, it predicts future increases in water demand based on rainfall data.

[1311] Updating predictive models with machine learning

[1312] The server uses past disaster data to train and improve the predictive model, which will lead to more accurate forecasts of future supply needs.

[1313] Generate and notify material distribution plans

[1314] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A." This plan is then notified to the support team and local government.

[1315] Specific examples

[1316] Consider the case where a user uses a device to voice-input "I need food" during a disaster. First, the device sends this voice input data to the server. The server uses a speech recognition engine to convert the voice data into text data, generating the text data "I need food." Next, it analyzes the text data using a natural language processing model to obtain the information "Needed items: food, Urgency: high." Furthermore, it uses an emotion engine to extract the information "Stress level: high" from the voice data. This information is stored in a database and visualized on a map. The server then checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[1317] This will enable the efficient and rapid supply of relief goods, while also enabling support that takes into consideration the emotional state of the victims.The system aims to provide faster and more accurate support during disasters.

[1318] The processing flow will be explained below.

[1319] Step 1:

[1320] The user inputs the items they need using a chat or voice input method. For example, the user might say "I need water" into their smartphone or type "I don't have any blankets" into the chat window.

[1321] Step 2:

[1322] The device sends the user's input data to the server. In the case of voice input, the device converts the voice data into a common audio format such as WAV or MP3 before sending it. In the case of text input, the data is sent in its original format.

[1323] Step 3:

[1324] The server receives the voice data and converts the voice data into text data using a voice recognition engine. For example, the voice data "I need water" is converted into text data "I need water."

[1325] Step 4:

[1326] The server uses a natural language processing model to analyze text data, extracting information such as "Items needed: water, Urgency: high." Chat input is also analyzed in the same way.

[1327] Step 5:

[1328] The server uses an emotion engine to analyze emotions from the user's input data, for example recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[1329] Step 6:

[1330] The server generates analysis results by integrating the emotion information from the emotion engine with natural language processing means. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotion information "Stress level: high."

[1331] Step 7:

[1332] The server stores the analysis results in a database. For example, information such as "water" is needed at shelter A is stored along with emotional information.

[1333] Step 8:

[1334] The server uses a geographic information system to visualize the analysis results on a map. The map displays the location of each evacuation shelter along with information on necessary supplies. For example, the location of shelter A displays an icon that reads "Water needed" along with a "Stress level: High" icon.

[1335] Step 9:

[1336] The server uses external APIs to collect weather data, earthquake information, and other disaster data, including current rainfall, temperature, and earthquake magnitude.

[1337] Step 10:

[1338] The server analyzes the disaster data collected and predicts future needs for goods, for example, predicting that demand for water will increase in the future based on current rainfall data.

[1339] Step 11:

[1340] The server uses past disaster data to train the machine learning model and improve the accuracy of the predictive model, which will lead to more accurate forecasts of future supply needs.

[1341] Step 12:

[1342] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan such as "send 50 liters of water to shelter A."

[1343] Step 13:

[1344] The server generates a distribution plan and notifies the relief team and local government, allowing relief activities to be carried out quickly.

[1345] These steps will enable efficient and rapid delivery of relief supplies. In addition, by combining it with an emotion engine, it will be possible to provide support that takes into account the emotional state of the victims.

[1346] Example 2

[1347] 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."

[1348] Conventional disaster relief systems have difficulty quickly and accurately grasping the needs of disaster victims, resulting in delays in the supply of relief supplies and shortages and surpluses. Furthermore, relief efforts did not take into account the emotional state of disaster victims, resulting in a lack of psychological support. This resulted in issues that reduced the efficiency and accuracy of relief activities.

[1349] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1350] In this invention, the server includes a means for converting voice data into text data, a natural language processing means, and a sentiment analysis means, which enable the server to quickly and accurately grasp the material needs and emotional state of disaster victims, and to generate an optimal relief supply distribution plan by integrating the analysis results.

[1351] "User" refers to a disaster victim or a supporter who uses the system to input their needs for goods.

[1352] "Terminal means" refers to a device that allows a user to input product needs and transmit the data to the server, including a smartphone or PC.

[1353] "Central Processing Unit" refers to a server for processing and analyzing input data.

[1354] "Audio data" refers to the recorded data when the user inputs voice.

[1355] "Text data" refers to voice data or text entered in chat format.

[1356] "Natural language processing means" refers to algorithms and models that analyze input text data and extract information such as required items and urgency.

[1357] "Emotion analysis means" refers to algorithms or models that analyze a user's emotional state from their input and identify stress, anxiety, etc.

[1358] "Means for visualizing on a map" refers to a method for displaying analyzed information on a map using a geographic information system (GIS).

[1359] "Disaster data" refers to data related to disasters, such as weather information and earthquake information.

[1360] "Machine learning methods" refer to algorithms and technologies that use past disaster data to train predictive models and improve their accuracy.

[1361] "Item distribution plan" refers to an item supply plan created based on analysis results and forecast data.

[1362] "Means for notifying distribution plans" refers to methods and techniques for notifying support teams and local governments of the generated item distribution plans.

[1363] This invention is a system for efficiently providing necessary items to disaster victims in the event of a disaster, and provides support that takes into account the emotional state of the victims by combining it with emotion analysis. This system works by allowing users to input the items they need using chat or voice input, and the server analyzes the data to determine the needs for the items. Furthermore, it also includes a function to predict needs for items from disaster data and generate and notify optimal item distribution plans.

[1364] Users can input the items they need using chat or voice input on devices such as smartphones or PCs. For example, a user might say "I need water" into their smartphone, or type "I don't have any blankets" into the chat window.

[1365] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it.

[1366] The server converts the transmitted voice data into text data using a speech recognition engine (for example, Google Cloud Speech-to-Text API). Specifically, the voice data is converted into text data such as "I need water."

[1367] Next, the server analyzes the text data using a natural language processing model (e.g., BERT or GPT). This analysis extracts information such as "Items needed: water, Urgency: high." The same analysis is performed even if the data is entered in chat format.

[1368] The server then uses an emotion analysis engine (e.g., IBM Watson Natural Language Understanding) to analyze the user's emotional state from the input data, for example, recognizing emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content.

[1369] Emotional information from the emotion analysis engine is integrated with the analysis results of natural language processing. For example, from the text data "I need water," the information "Needed item: water, Urgency: high" is integrated with the emotional information "Stress level: high."

[1370] The analyzed information is stored in a database on a server, and then a geographic information system is used to visualize the location of each evacuation shelter and disaster victims, along with information on the necessary supplies, on a map, allowing support teams to see at a glance what is needed at each shelter.

[1371] The server uses external APIs (e.g., OpenWeatherMap API or USGS Earthquake Hazards Program API) to collect weather data, earthquake information, and other disaster data. This includes current rainfall, temperature, and earthquake magnitude. The server analyzes this data to predict future needs for goods. For example, it can predict an increase in demand for water based on rainfall data.

[1372] Furthermore, the server uses past disaster data to train and improve the accuracy of predictive models using machine learning algorithms (such as Random Forest and XGBoost). This update enables highly accurate needs predictions.

[1373] Finally, the server generates an optimal distribution plan based on the analysis results and forecast data. For example, it creates a specific plan to send 50 liters of water to shelter A and 25 kg of food to shelter B, and notifies the support team and local government in real time.

[1374] Specific examples

[1375] During a disaster, a user uses a device to voice input, "We need blankets." The device sends the voice data to a server, which converts it into text data using a voice recognition engine. The server analyzes the text data, "We need blankets," using a natural language processing model to obtain the information, "Needed items: blankets, Urgency: high." The server then uses an emotion analysis engine to extract the information, "Anxiety level: medium," from the voice data. This information is stored in a database and displayed on a map. The server checks current weather data and predicts that the demand for blankets will continue. Finally, it notifies the support team of a distribution plan, "Send 30 blankets to shelter C."

[1376] Example prompts to input to the generative AI model

[1377] "Please explain a system that efficiently supplies items needed by disaster victims in the event of a disaster. Please provide a detailed description, including the roles and specific processes of users, terminals, and servers."

[1378] This system will enable the rapid and accurate provision of relief supplies, and will also enable support that takes into consideration the emotional state of disaster victims.

[1379] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1380] Step 1:

[1381] Users use devices such as smartphones or PCs to input the items they need in chat or voice input format. For example, a user might say "I need water" into their smartphone or type "I don't have any blankets" into a chat window. The input data is saved on the device as voice or text data.

[1382] Step 2:

[1383] The device sends the data entered by the user to the server via the Internet. In the case of voice input, the device converts the voice data into WAV or MP3 format before sending it, and in the case of text input, it sends the text data as is. This transfers the input data to the server.

[1384] Step 3:

[1385] The server converts the received voice data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, the voice data is converted into text data such as "I need water." This converted text data is used in the next analysis step.

[1386] Step 4:

[1387] The server analyzes the text data using a natural language processing model (e.g., BERT or GPT). In this step, information such as "needed items: water, urgency: high" is extracted from the text data. The input text is output as categorized information through the analysis process.

[1388] Step 5:

[1389] The server uses an emotion analysis engine (for example, IBM Watson Natural Language Understanding) to analyze the user's emotional state from the input data. Specifically, it recognizes emotions such as "stress," "anxiety," and "urgency" from the tone of voice and text content, and obtains information such as "stress level: high" as output.

[1390] Step 6:

[1391] The server integrates the results of natural language processing analysis and sentiment analysis. Specifically, it integrates the analysis results of the text data "Necessary items: water, urgency: high" with the emotional information "Stress level: high" into a single dataset. This generates data that comprehensively captures the necessary items, their urgency, and the user's emotional state.

[1392] Step 7:

[1393] The server stores the analyzed integrated information in a database and visualizes it on a map using a geographic information system (GIS). Information on the location of victims and the necessary supplies is displayed on the map. This allows support teams and other relevant parties to understand in real time what items are needed at each evacuation shelter.

[1394] Step 8:

[1395] The server uses external APIs (e.g., OpenWeatherMap API and USGS Earthquake Hazards Program API) to collect current weather data, earthquake information, and other disaster data. The collected data undergoes analysis and processing and is used as input data for predicting future product needs.

[1396] Step 9:

[1397] The server uses machine learning algorithms (such as Random Forest and XGBoost) to train and improve the accuracy of predictive models using past disaster data, which will lead to more accurate forecasts of future supply needs.

[1398] Step 10:

[1399] The server generates an optimal distribution plan based on the analysis results and forecast data. For example, a specific plan may be created such as "send 50 liters of water to shelter A and 25 kg of food to shelter B." This plan is notified to relief teams and local governments in real time. This information serves as the basis for rapid relief activities.

[1400] (Application example 2)

[1401] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1402] While it is important to efficiently and quickly provide disaster victims with the supplies they need, conventional methods have difficulty providing support that takes into account the emotional state of the victims. Furthermore, it is difficult to integrate real-time geographic information and supply needs, which means it takes time to formulate an optimal supply distribution plan.

[1403] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to input needed items in chat format or voice input format; a terminal means for transmitting the input data to the server; a means for converting voice data into text data; a natural language processing means for analyzing the text data and identifying needed items and their urgency; a means for visualizing needed items on a map based on the analysis results and geographic information; a means for collecting disaster data and predicting needs for items; a machine learning means for training a prediction model and improving accuracy; a means for generating an item distribution plan based on the analysis results and predictions; a means for notifying the generated distribution plan; an emotion analysis means for analyzing the user's emotional state; a means for adjusting the urgency of items taking the emotional state into consideration; and a means for integrating item request information with a geographic information system in real time and displaying it. This enables efficient and rapid delivery of needed items during a disaster while taking the emotional state of disaster victims into consideration.

[1404] A "user" is an individual or organization that uses the system to input items needed in the event of a disaster.

[1405] "Chat format" refers to a text-based communication format in which users input messages using a keyboard or touch screen.

[1406] The "voice input format" is a format in which information is input through voice using a microphone or the like.

[1407] "Necessary items" refers to the supplies and support items that disaster victims require in the event of a disaster.

[1408] "Terminal means" refers to a device, such as a smartphone or a personal computer, that transmits data entered by a user to a server.

[1409] "Audio data" refers to audio signals entered by a user using an audio input form.

[1410] "Text data" is voice data converted into character information.

[1411] "Natural language processing means" refers to a technical means for analyzing text data, understanding its meaning, and identifying the items needed and their urgency.

[1412] A "geographic information system" is a system that collects, displays, and analyzes geographic information.

[1413] "Disaster data" refers to data that includes various types of information related to disasters, such as weather information and earthquake information.

[1414] "Machine learning means" refers to technical means for learning data and improving the accuracy of predictive models based on the learning results.

[1415] A "distribution plan" is a plan that includes schedules and routes for optimally distributing necessary items to disaster victims.

[1416] "Emotion analysis means" is a technical means for analyzing the emotional state of a user from their voice or text and understanding the situation.

[1417] "Urgency" is an index that indicates the degree of need for an item.

[1418] "Means for integrating and displaying" refers to a technical means for integrating data obtained from multiple information sources and displaying it on a single display screen.

[1419] The "notification means" is a technical means for notifying the relevant parties of the generated product distribution plan.

[1420] This invention is a system for efficiently and quickly supplying items needed by disaster victims, and by combining it with an emotion engine, it provides support that takes into account the emotional state of the victims. Specific embodiments for carrying out the invention are described below.

[1421] System Overview

[1422] The system is made up of a server, terminals, and users working together. Users use terminals such as smartphones and PCs to input the items they need via chat or voice input. The terminals then send the input data to the server via the internet.

[1423] Voice Recognition

[1424] The device sends voice data to the server, which converts the voice data into text data using a speech recognition engine (e.g., Python's speech_recognition library). For example, if a user says "I need water" into their smartphone, this voice input is converted into the text data "I need water."

[1425] Emotion analysis

[1426] The server analyzes the text data using a natural language processing engine (e.g., sentiment analysis model from the transformers library) to identify the items needed and their urgency. The sentiment analysis engine also analyzes the user's emotional state (e.g., stress, anxiety).

[1427] Data aggregation and visualization

[1428] The analyzed data is stored in a database on the server. Next, using a geographic information system (e.g., the folium library), the necessary item information and the location information of each evacuation shelter are visualized on a map.

[1429] Collecting disaster data and predicting supply needs

[1430] The server uses an external disaster data API (e.g., API access with the requests library) to collect weather data, earthquake information, etc. This data is analyzed to predict future product needs.

[1431] Generate and notify material distribution plans

[1432] The server generates an optimal distribution plan based on the analysis results and disaster data (e.g., by processing the data using the pandas library). The generated distribution plan is notified to the support team and local governments via notification methods (e.g., email, app notification).

[1433] Specific examples

[1434] During a disaster, a user uses a device to voice-input the phrase "I need food." The device sends this voice data to a server, which then uses a speech recognition engine to generate text data saying "I need food." The text data is then analyzed using a natural language processing model to obtain information such as "Needed items: food, Urgency: high." A sentiment analysis engine is also used to extract information such as "Stress level: high." This information is integrated with a geographic information system and visualized on a map. The server checks current disaster data and predicts that the demand for food will continue. Finally, it notifies the support team of a distribution plan, such as "Send 25 kg of food to shelter B."

[1435] Prompt Sentence Examples

[1436] When a user says "I need water" into their smartphone, the application does the following:

[1437] 1. Convert audio data into text data.

[1438] 2. Conduct sentiment analysis to understand the user's emotional state.

[1439] 3. Collect disaster data and predict future needs.

[1440] 4. Integrate needed goods with geographic information to generate optimal distribution plans.

[1441] 5. Notify the logistics center of specific distribution instructions and provide support such as "send 50 liters of water to shelter A."

[1442] The above is a specific embodiment for carrying out the invention.

[1443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1444] Step 1:

[1445] The user inputs the items they need through voice input or chat. For example, the user speaks into their smartphone, saying, "I need water," and voice data is generated.

[1446] Step 2:

[1447] The device sends the user's voice data to the server, which then converts the data into a common audio format (e.g., WAV, MP3, etc.) and sends it to the server via the Internet.

[1448] Step 3:

[1449] The server converts the transmitted voice data into text data using a speech recognition engine. Specifically, it analyzes the voice signal using Python's speech_recognition library and generates the text data "I need water."

[1450] Step 4:

[1451] The server analyzes the text data using a natural language processing engine. The library used is transformers. The information extracted from the text is "Needed items: water, Urgency: high."

[1452] Step 5:

[1453] At the same time, the server uses an emotion analysis engine to analyze the user's emotional state. It analyzes "stress," "anxiety," etc. from the tone of voice and the content of the text. As a result, it obtains the data "Stress level: High."

[1454] Step 6:

[1455] The server integrates the text analysis results with the sentiment analysis results, generating integrated data such as "Needed items: water, Urgency: high, Stress level: high."

[1456] Step 7:

[1457] The server stores the integrated data in a database, and simultaneously visualizes the location of each evacuation center and necessary supplies on a map using a geographic information system (GIS). This is done using the folium library.

[1458] Step 8:

[1459] The server collects weather and earthquake data from external disaster data APIs using the requests library to obtain real-time disaster data.

[1460] Step 9:

[1461] The server analyzes the disaster data collected and predicts future needs for supplies. Based on past data, predictions are made using a machine learning model that uses a generative AI model.

[1462] Step 10:

[1463] The server generates an optimal distribution plan based on the analysis results and predicted data. Specifically, it processes the data using the pandas library and creates a specific distribution plan, such as "send 25 kg of food to shelter B."

[1464] Step 11:

[1465] The server notifies the support team and local governments of the generated distribution plan using methods such as email and app notifications to ensure information is transmitted quickly.

[1466] Through the above processing steps, it becomes possible to efficiently and quickly supply necessary items in the event of a disaster while taking into consideration the emotional state of the user.

[1467] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1468] 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.

[1469] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1470] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1471] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1472] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1473] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1474] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1475] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1476] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1477] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1478] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1479] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1480] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1481] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1482] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1483] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1484] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1485] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1486] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1487] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1488] The following is further disclosed regarding the above embodiment.

[1489] (Claim 1)

[1490] A means for the user to input the required items in chat or voice input format;

[1491] a terminal means for transmitting input data to a server;

[1492] a server means including a means for converting voice data into text data;

[1493] natural language processing means for analyzing text data and identifying necessary items and their urgency;

[1494] A means for visualizing necessary items on a map based on the analysis results and geographic information;

[1495] A means of collecting disaster data and forecasting supply needs;

[1496] Machine learning methods to train and improve the accuracy of predictive models;

[1497] A means for generating an item distribution plan based on the analysis results and predictions;

[1498] means for notifying the generated distribution plan;

[1499] A system including:

[1500] (Claim 2)

[1501] 2. The system according to claim 1, further comprising means for providing a chat format in addition to voice input as an interface when a user inputs a required item.

[1502] (Claim 3)

[1503] The system according to claim 1, wherein the machine learning means performs processing to improve the accuracy of the prediction model using past disaster data.

[1504] "Example 1"

[1505] (Claim 1)

[1506] A means for the user to input the required items in chat or voice input format;

[1507] a terminal means for transmitting input data to a server;

[1508] a server means including a means for converting voice data into text data;

[1509] natural language processing means for analyzing text data and identifying necessary items and their urgency;

[1510] A means for visualizing necessary items on a map based on the analysis results and geographic information;

[1511] A means of collecting disaster data and forecasting supply needs;

[1512] Machine learning methods to train and improve the accuracy of predictive models;

[1513] A means for generating an item distribution plan based on the analysis results and predictions;

[1514] means for notifying the generated distribution plan;

[1515] means for storing data generated from user input in a database;

[1516] means including a data analysis engine for extracting required information from the database;

[1517] A means of analyzing past disaster data to identify demand patterns for needed goods;

[1518] A means of integrating multiple external data sources to forecast future needs; and

[1519] A system that uses machine learning predictive models to optimize product distribution plans.

[1520] (Claim 2)

[1521] 2. The system according to claim 1, further comprising means for providing a chat format in addition to voice input as an interface when a user inputs a required item.

[1522] (Claim 3)

[1523] The system according to claim 1, wherein the machine learning means performs processing to improve the accuracy of the prediction model using past disaster data.

[1524] "Application Example 1"

[1525] (Claim 1)

[1526] A means for the user to input the required items in chat or voice input format;

[1527] a terminal means for transmitting input data to a server;

[1528] a server means including a means for converting voice data into text data;

[1529] natural language processing means for analyzing text data and identifying necessary items and their urgency;

[1530] A means for visualizing necessary items on a map based on the analysis results and geographic information;

[1531] A means of collecting disaster data and forecasting supply needs;

[1532] Machine learning methods to train and improve the accuracy of predictive models;

[1533] A means for generating an item distribution plan based on the analysis results and predictions;

[1534] means for notifying the generated distribution plan;

[1535] means for optimizing support item supply based on item requests received by the logistics center;

[1536] A means of visualizing user requirements in real time,

[1537] A means for acquiring disaster data from external data sources and forecasting demand for goods;

[1538] A system including:

[1539] (Claim 2)

[1540] 2. The system according to claim 1, further comprising means for providing a chat format in addition to voice input as an interface when a user inputs a required item.

[1541] (Claim 3)

[1542] The system according to claim 1, wherein the machine learning means performs processing to improve the accuracy of the prediction model using past disaster data.

[1543] "Example 2: Combining Emotion Engines"

[1544] (Claim 1)

[1545] A means for the user to input the required items in chat or voice input format;

[1546] terminal means for transmitting input data to a central processing unit;

[1547] a central processing unit means including means for converting voice data into text data;

[1548] natural language processing means for analyzing text data and identifying necessary items and their urgency;

[1549] A means for visualizing necessary items on a map based on the analysis results and geographic information;

[1550] A means of collecting disaster data and forecasting supply needs;

[1551] Machine learning methods to train and improve the accuracy of predictive models;

[1552] A means for generating an item distribution plan based on the analysis results and predictions;

[1553] means for analyzing the emotional state of a user from input data and integrating the analysis results;

[1554] means for notifying the generated distribution plan;

[1555] A system including:

[1556] (Claim 2)

[1557] 2. The system according to claim 1, further comprising means for providing a chat format in addition to voice input as an interface when a user inputs a required item.

[1558] (Claim 3)

[1559] The system according to claim 1, wherein the machine learning means performs processing to improve the accuracy of the prediction model using past disaster data.

[1560] "Application example 2 when combining emotion engines"

[1561] (Claim 1)

[1562] A means for the user to input the required items in chat or voice input format;

[1563] a terminal means for transmitting input data to a server;

[1564] a server means including a means for converting voice data into text data;

[1565] natural language processing means for analyzing text data and identifying necessary items and their urgency;

[1566] A means for visualizing necessary items on a map based on the analysis results and geographic information;

[1567] A means of collecting disaster data and forecasting supply needs;

[1568] Machine learning methods to train and improve the accuracy of predictive models;

[1569] A means for generating an item distribution plan based on the analysis results and predictions;

[1570] means for notifying the generated distribution plan;

[1571] emotion analysis means for analyzing the emotional state of a user;

[1572] a means for adjusting the urgency of the item in consideration of the emotional state;

[1573] means for integrating and displaying real-time item request information with a geographic information system;

[1574] A system including:

[1575] (Claim 2)

[1576] 2. The system according to claim 1, further comprising means for providing a chat format in addition to voice input as an interface when a user inputs a required item.

[1577] (Claim 3)

[1578] The system according to claim 1, wherein the machine learning means performs processing to improve the accuracy of the prediction model using past disaster data. [Explanation of symbols]

[1579] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for the user to input the required items in chat or voice input format; a terminal means for transmitting input data to a server; a server means including a means for converting voice data into text data; natural language processing means for analyzing text data and identifying necessary items and their urgency; A means for visualizing necessary items on a map based on the analysis results and geographic information; A means of collecting disaster data and forecasting supply needs; Machine learning methods to train and improve the accuracy of predictive models; A means for generating an item distribution plan based on the analysis results and predictions; means for notifying the generated distribution plan; A system including:

2. 2. The system according to claim 1, further comprising means for providing a chat format in addition to voice input as an interface when a user inputs a required item.

3. The system according to claim 1 , wherein the machine learning means performs processing to improve the accuracy of the prediction model using past disaster data.

Images