System

Abstract

A system is provided.SOLUTION: A system includes a means for collecting real-time data such as weather data and traffic information, a means for analyzing the collected real-time data and generating a model for predicting a congestion situation of an evacuation route, a means for generating an evacuation route suitable for each user based on the prediction, a means for providing the generated evacuation route information to a user terminal, and a means for receiving feedback from the user through the user terminal and updating the evacuation route information.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] Conventional evacuation systems have the problem of congested evacuation routes during disasters, making efficient evacuation difficult. Specifically, because they cannot reflect real-time conditions, information about predicted congestion and impassable routes is not properly communicated to evacuees, making it difficult to achieve a safe evacuation. This creates the risk that evacuation will take longer or that people will be exposed to secondary dangers during evacuation. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: means for collecting real-time data such as weather data and traffic information; means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes; means for generating evacuation routes tailored to individual users based on the predictions; means for providing the generated evacuation route information to a user terminal; and means for receiving feedback from users via the user terminal and updating the evacuation route information. This system enables users to obtain the optimal evacuation route in real time, enabling them to evacuate quickly and safely based on that information. Furthermore, by reflecting feedback received during evacuation in real time, the system always provides the optimal route.

[0006] "Weather data" refers to information about weather, such as weather, temperature, precipitation, wind speed, and air pressure, obtained from the Japan Meteorological Agency or other weather observation organizations.

[0007] "Traffic information" refers to data related to traffic, such as road congestion, traffic congestion information, traffic volume and speed, accident information, and road closure information.

[0008] "Real-time data" refers to information that instantly reflects current phenomena and conditions, and is provided without any time delay.

[0009] "Means of collection" refers to the methods and processes for obtaining information, and is the technology used to collect data using APIs, sensors, databases, etc.

[0010] "Analysis" is the process of understanding useful information and patterns based on collected data, and breaking it down, evaluating, and judging it for specific purposes.

[0011] A "model" is an algorithm or design that represents real-world phenomena mathematically, through machine learning, or through simulation, and is used to make predictions and judgments.

[0012] "Prediction" is the act of predicting future events or conditions based on past data and current circumstances.

[0013] An "evacuation route" refers to a recommended route or path that a user should take to evacuate in the event of a disaster.

[0014] A "means of generation" is a mechanism for creating new data or information through a specific process or method.

[0015] "Means for providing" refers to the methods and technologies for transmitting the generated information to users or terminals and making it accessible.

[0016] A "user terminal" is a device for displaying and receiving information, and includes smartphones, tablets, personal computers, etc.

[0017] "Feedback" refers to information such as status reports, opinions, and observations provided by users.

[0018] "Updating" is the process of changing existing data or information to new ones based on the feedback received. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] System Overview

[0041] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather and traffic information to predict congestion on evacuation routes and provides appropriate evacuation routes to individual users. It also has a function to reflect user feedback and update evacuation route information.

[0042] System configuration

[0043] This system is mainly composed of three elements: the server, the terminal, and the user. The role of each will be explained in detail below.

[0044] server

[0045] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems. For example, weather data includes precipitation, wind speed, and earthquake information, and traffic information includes road congestion and road closure information.

[0046] Data analysis and predictive model generation: Collected data is analyzed and an AI model is used to predict congestion along evacuation routes. Machine learning algorithms are used to make highly accurate predictions based on past data and the current situation.

[0047] Evacuation route generation: Based on the analysis results, the system generates the optimal route from the user's current location to the evacuation shelter. It evaluates multiple route candidates and selects the least congested and safest route.

[0048] Providing information: The generated evacuation route information is sent to the user's device.

[0049] Feedback analysis: Route information is updated in real time based on user feedback.

[0050] Terminal

[0051] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and is also provided with audio guidance.

[0052] Feedback transmission: Provides an interface for users to input local information and congestion status, and sends this to the server.

[0053] User

[0054] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[0055] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation is sent via the device.

[0056] Specific examples

[0057] Evacuation scenario in the event of an earthquake

[0058] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0059] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[0060] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[0061] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user feeds that information back to the server via their device.

[0062] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[0063] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[0064] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[0065] The processing flow will be explained below.

[0066] Step 1: Getting real-time data

[0067] The server obtains real-time data such as weather data and traffic information. It calls the APIs of meteorological agencies and traffic management systems to collect data such as weather information for each region, earthquake information, traffic congestion information, and the availability of evacuation shelters.

[0068] Step 2: Data analysis and model generation

[0069] The server analyzes real-time data acquired and uses AI models to predict congestion along evacuation routes. The data is preprocessed and congestion predictions are made using machine learning algorithms and simulation models. The accuracy of the generated models is also evaluated, and the models are adjusted as necessary.

[0070] Step 3: Generate evacuation routes

[0071] The server generates an evacuation route suited to each individual user based on the analysis results. It obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[0072] Step 4: Provide evacuation route information

[0073] The server generates evacuation route information and sends it to the user's device. The data format is converted to JSON or XML and sent to the device via an API. During this process, the data is encrypted to ensure security.

[0074] Step 5: Evacuation route notification and guidance

[0075] The device notifies the user of the evacuation route information it has received. It uses pop-up notifications and sound alerts to encourage the user to begin evacuation. It visually displays the route on a map and provides route guidance through audio guidance.

[0076] Step 6: Provide feedback

[0077] Users provide feedback through their devices. They report congested or impassable areas during evacuation using an input form or voice input. The devices then send this feedback information to the server.

[0078] Step 7: Analyze feedback and update route

[0079] The server analyzes the received feedback and updates evacuation route information in real time, recalculating routes to reflect new information about obstacles and congestion, and generating the latest optimal routes.

[0080] Step 8: Re-informing and re-guiding

[0081] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on a map and re-guided by voice guidance. The user continues evacuating according to the new route information.

[0082] This series of processing steps enables the server, terminals, and users to work together to achieve efficient and safe evacuation in real time.

[0083] Example 1

[0084] 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."

[0085] In modern society, rapid and safe evacuation in the event of a disaster is extremely important. However, there are many challenges in collecting and analyzing real-time weather and traffic data and providing optimal evacuation routes. In particular, complex data analysis, rapid information provision, and the ability to incorporate user feedback in real time are required. Conventional systems have difficulty integrating and effectively executing these elements, resulting in issues such as reduced evacuation efficiency and a compromised safety.

[0086] 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.

[0087] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating evacuation routes suitable for each user based on the prediction and evaluating multiple route candidates to select the optimal route, means for providing the generated evacuation route information to a user terminal and notifying the user using audio guidance and a visual map display, and means for receiving feedback from the user via the user terminal and reanalyzing and updating the route information in real time, thereby enabling the provision of evacuation routes with high speed and accuracy and optimization that reflects user feedback in real time.

[0088] "Weather data" refers to various information related to meteorological phenomena such as temperature, precipitation, wind speed, air pressure, earthquake intensity and epicenter.

[0089] "Traffic information" refers to various information related to traffic flow and road usage, such as road congestion, road closures, traffic accident occurrences, and congestion information.

[0090] "Real-time data" refers to up-to-date data that reflects current conditions, including weather and traffic information.

[0091] A "machine learning algorithm" refers to a computational method that learns patterns from past data and makes predictions and decisions when new data is given.

[0092] An "evacuation route" refers to the route a user takes to travel from their current location to a specific evacuation shelter or safe location.

[0093] "Congestion" refers to the amount of traffic and concentration of people on a particular road or route.

[0094] "Predictive model" refers to a mathematical or computational method used to predict specific future conditions based on collected data.

[0095] "Route update" refers to the process of recalculating existing evacuation route information and re-providing optimal routes based on user feedback and newly collected data.

[0096] "Voice guidance" refers to a method of giving instructions and guidance to a user through voice.

[0097] "Visual map display" refers to a method of providing route information to a user using a graphical map.

[0098] "Feedback" refers to reports provided by users regarding local information and congestion during evacuation.

[0099] "User terminal" refers to an electronic device, such as a smartphone or tablet, that a user uses to receive and send information.

[0100] This invention is a system that supports efficient and safe evacuation in the event of a disaster. It consists of three elements: a server, a terminal, and a user, and realizes advanced evacuation support using real-time data.

[0101] System Overview

[0102] The main features of the system are as follows:

[0103] 1. Real-time data collection

[0104] 2. Data analysis and predictive model generation

[0105] 3. Generating optimal evacuation routes

[0106] 4. Providing evacuation route information

[0107] 5. Receiving user feedback and updating route information

[0108] Hardware and software used

[0109] server

[0110] Hardware: Server computer

[0111] Software: API for data collection (e.g., OpenWeatherMap API, Google® Maps API), programming libraries for data analysis (e.g., Python, pandas, scikit-learn, TENSORFLOW®), algorithms for path generation (e.g., Dijkstra algorithm, A algorithm)

[0112] Terminal

[0113] Hardware: Smartphones, tablets

[0114] Software: Map display apps (e.g., Google Maps), TTS (text-to-speech) engine for voice guidance

[0115] User

[0116] Hardware: Smartphones, tablets

[0117] Software: Evacuation route display app, feedback input interface

[0118] Specific processing

[0119] server

[0120] The server collects weather and traffic data in real time. It periodically retrieves the data using an API and stores it in a database. The collected data is then cleaned (by filling in missing values ​​and removing outliers) and a machine learning model is trained. Specifically, a random forest and LSTM model are used to predict the congestion status of evacuation routes.

[0121] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. This uses the Dijkstra algorithm and the A algorithm. The generated routes are evaluated for congestion and safety to select the most suitable one. The selected route information is sent to the user's device in JSON format.

[0122] Terminal

[0123] The device receives evacuation route information sent from the server and notifies the user. It uses a map display application to visually display the route and a TTS engine to provide voice guidance. It provides an interface that allows the user to input feedback information (e.g., congestion status and impassable areas) during evacuation. The input feedback information is sent to the server.

[0124] User

[0125] The user begins evacuation based on the evacuation route information. For example, if an earthquake occurs, the user will follow the route information displayed on the device and head to the most suitable evacuation shelter. If the user encounters congestion or impassable conditions along the way, the user will provide this information via the device. This allows the server to reanalyze the data and receive updated route information.

[0126] Specific examples

[0127] Evacuation scenario in the event of an earthquake

[0128] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0129] 2. Analysis and model generation: The collected information is analyzed and congestion predictions are made for the affected areas. An LSTM model is used for this analysis.

[0130] 3. Providing evacuation routes: The server generates the optimal evacuation route and sends it to the user's device. The device receives it and notifies the user using a map display app and a TTS engine.

[0131] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, that information is fed back to the user via the device.

[0132] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[0133] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[0134] Example prompts to input to the generative AI model

[0135] "Based on the latest earthquake information, please tell me the best evacuation route from point A to point B."

[0136] "Enter your current location and destination and we'll predict and provide you with the least congested evacuation route."

[0137] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1:

[0140] Real-time data collection

[0141] server

[0142] The server calls the APIs of meteorological agencies and traffic management systems to collect the latest weather and traffic information. Specifically, it sends an HTTP request to the API endpoint and receives a JSON-formatted response. This data includes precipitation, wind speed, temperature, earthquake intensity, epicenter information, road congestion status, and road closure information. The collected data is stored in an internal database.

[0143] Input: Weather and traffic data retrieved from API endpoints

[0144] Output: Real-time data stored in an internal database

[0145] Step 2:

[0146] Data preprocessing and analysis

[0147] server

[0148] The server preprocesses the collected data. Specifically, it complements missing values, removes outliers, and formats the data. This process uses the Python pandas library. After preprocessing is complete, the server analyzes the data using a machine learning algorithm (e.g., random forest or LSTM model) to generate a model for predicting the congestion status of evacuation routes.

[0149] Input: Stored real-time data

[0150] Output: Preprocessed data and predictive model

[0151] Step 3:

[0152] Evacuation route generation and evaluation

[0153] server

[0154] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. To do this, it uses road network data and calculates the shortest or optimal route using the Dijkstra algorithm or the A algorithm. The generated routes are evaluated taking into account congestion and safety, and the optimal route is selected.

[0155] Input: Prediction model, user's current location, location of evacuation shelter

[0156] Output: Evaluated optimal evacuation route

[0157] Step 4:

[0158] Providing evacuation route information

[0159] server

[0160] The server sends optimal evacuation route information to the user's device in JSON format.

[0161] Terminal

[0162] The device analyzes the received evacuation route information and notifies the user. Specifically, it uses a map display application (e.g., Google Maps) to visually display the route and uses a TTS engine to provide voice guidance.

[0163] Input: Evacuation route information in JSON format sent from the server

[0164] Output: Map display and evacuation route notification with voice guidance

[0165] Step 5:

[0166] Receiving feedback from users

[0167] User

[0168] During evacuation, users report impassable areas and congestion via their devices.

[0169] Terminal

[0170] The terminal collects feedback information from the user and transmits it to the server.

[0171] Input: User-entered feedback information

[0172] Output: Feedback information sent to the server

[0173] Step 6:

[0174] Analyzing feedback and updating routes

[0175] server

[0176] The server analyzes the received feedback information and recalculates and updates evacuation route information as necessary, again using the predictive model and route generation algorithm.

[0177] Input: User feedback information

[0178] Output: Updated evacuation route information

[0179] Step 7:

[0180] Providing updated route information

[0181] server

[0182] The server then transmits the updated evacuation route information to the user's terminal again.

[0183] Terminal

[0184] The device receives the new evacuation route information and notifies the user again, updating the map display and voice guidance.

[0185] Input: Updated evacuation route information

[0186] Output: New evacuation route information notified to the user

[0187] Through these seven steps, the system of this invention realizes efficient and safe evacuation support. By collecting and analyzing data in real time and dynamically updating routes based on user feedback, it is possible to provide optimal evacuation routes at all times.

[0188] (Application example 1)

[0189] 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."

[0190] Conventional evacuation support systems are unable to fully utilize real-time data, making it difficult to provide rapid evacuation routes that respond to changes in congestion. Furthermore, they are unable to flexibly recalculate routes using user feedback, which means they are unable to respond to dynamic environmental changes. Furthermore, the means of notifying users of evacuation routes are limited, and there is a need for information to be provided in a format that is intuitively easy for users to understand. There is a need for a system that can solve these problems and support safe and efficient evacuation during disasters.

[0191] 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.

[0192] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes, means for generating evacuation routes suitable for individual users based on the prediction, means for providing the generated evacuation route information to a user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for notifying the user of the evacuation route information based on the user's current location by voice and map using a smart device. This enables real-time data analysis and route provision, thereby realizing intuitive and immediate evacuation support for users.

[0193] "Weather data" refers to information about weather and weather conditions, including precipitation, wind speed, temperature, humidity, and air pressure.

[0194] "Traffic information" refers to information relating to road traffic conditions, including congestion, road closures, accident information, and the like.

[0195] "Real-time data" refers to the latest information at the current time, and is data that is collected and processed immediately.

[0196] A "model" is an algorithm or mathematical framework for predicting congestion along evacuation routes based on collected data.

[0197] A "user terminal" is an information communication device used by a user, and includes a smartphone, a tablet, smart glasses, etc.

[0198] "Feedback" is information provided by users based on local conditions and experiences.

[0199] "Evacuation routes" refer to recommended roads and routes for safe evacuation in the event of a disaster.

[0200] A "smart device" is an electronic device with advanced functionality that can connect to the Internet.

[0201] "Audio guidance" refers to a means of providing information to a user through audio.

[0202] "Visual map display" is a function that visually displays a map and provides route information and the like to the user.

[0203] An "evacuation support system" is an overall system for supporting users' evacuation in the event of a disaster.

[0204] MODE FOR CARRYING OUT THE INVENTION

[0205] System Overview

[0206] The system of this invention is designed to support efficient and safe evacuation in the event of a disaster. It collects real-time data, such as weather and traffic information, and analyzes that data to predict congestion along evacuation routes. Based on user feedback, it updates evacuation route information in real time and provides optimal evacuation routes.

[0207] Server Features

[0208] The server has the following features:

[0209] Real-time data collection: The server collects weather and traffic data in real time using external APIs (e.g., weather agencies and traffic information services).

[0210] Data analysis and model generation: Analyze the collected data and generate a model to predict the congestion status of evacuation routes. This modeling is performed using machine learning libraries such as TensorFlow.

[0211] Evacuation route generation: Based on the results of data analysis, an evacuation route appropriate for each individual user is generated. Multiple route candidates are evaluated and the least congested and safest route is selected.

[0212] Information provision: The generated evacuation route information is sent to the user's device.

[0213] Feedback analysis: Evacuation route information is updated in real time based on user feedback.

[0214] User device functions

[0215] The user terminal has the following features:

[0216] Receiving and displaying information: Receives evacuation route information sent from the server and notifies the user on the smart device with a visual map display and voice guidance.

[0217] Feedback submission: Provides an interface for users to input feedback and sends it to the server. Users can report traffic conditions, congestion, impassable areas, etc. in real time.

[0218] User Behavior

[0219] A user interacts with the system in the following way:

[0220] 1. Checking evacuation routes: When a disaster occurs, the user launches the application and receives notification of evacuation routes.

[0221] 2. Begin evacuation: Follow the map display and voice guidance on your smart device to proceed along the evacuation route.

[0222] 3. Providing feedback: Enter feedback about obstacles and congestion encountered during evacuation and send it to the server.

[0223] Specific examples

[0224] Let's take the example of a large-scale earthquake and a user evacuating. The server obtains real-time data from meteorological agencies and traffic information services. This data is analyzed using TensorFlow to generate an optimal evacuation route. The generated evacuation route information is sent to the user's smartphone, where the user receives a map display and voice guidance through the application. If the user encounters an impassable road or a congested area along the way, they enter that information in the application and send feedback to the server. The server reanalyzes the evacuation route based on this feedback and sends the new route information to the user's smartphone.

[0225] Prompt Sentence Examples

[0226] The user's current location is "35.6895, 139.6917" (center of the city). Please predict the best evacuation route for this user based on real-time weather and traffic information. Please take into account the following feedback ("Road impassable due to traffic jam", "Location: In front of Shibuya Station").

[0227] This example uses prompt sentences to demonstrate how a generative AI model can predict optimal evacuation routes and update them in real time based on feedback information.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] The server collects real-time data such as weather data and traffic information. It uses external APIs (for example, APIs of meteorological agencies or APIs of traffic information services) to obtain data such as precipitation, wind speed, road congestion, and road closure information. It processes the data obtained from the external APIs as input, converts it into an appropriate format, and saves it in an internal data store. The output is the collected real-time data.

[0231] Step 2:

[0232] The server analyzes the collected real-time data and generates a model that predicts the congestion status of evacuation routes. It uses TensorFlow, a machine learning library, to create a predictive model based on past and current data. It uses the collected real-time data and past evacuation data as input and performs data analysis. The output is a model that predicts the congestion status of evacuation routes.

[0233] Step 3:

[0234] The server generates an evacuation route suited to each individual user based on the generated model. It analyzes the model's prediction results, evaluates multiple route candidates, and selects the safest route. The inputs are the user's current location, real-time data, and the output of the predictive model. The output is evacuation route information optimized for each user.

[0235] Step 4:

[0236] The server sends the generated evacuation route information to the user's device. The notification is sent via the Internet in a format that corresponds to the type of device used (smartphone, tablet, etc.). The input is the generated evacuation route information, and the output is the route information received by the user's device.

[0237] Step 5:

[0238] The user device notifies the user of the received evacuation route information using a visual map display and voice guidance. The user checks the route information through the application and begins evacuation. The input is the evacuation route information sent from the server, and the output is a notification to the user.

[0239] Step 6:

[0240] Users provide feedback on the congestion and impassable areas they encounter during evacuation via their terminals. The application has an interface for inputting feedback, and the information entered by the user is sent to the server. The input is feedback data from the user, and the output is the transmission of the feedback data to the server.

[0241] Step 7:

[0242] The server reanalyzes the evacuation route information based on the received feedback information and generates a new optimal route. The reanalysis uses real-time data and feedback information, and the generated new route information is sent back to the user terminal. The input is user feedback and real-time data, and the output is updated evacuation route information.

[0243] Step 8:

[0244] The user device receives the updated evacuation route information and notifies the user again. This allows the user to continue evacuating safely according to the latest evacuation route. The input is the updated route information sent from the server, and the output is the notification to the user.

[0245] 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.

[0246] System Overview

[0247] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather data and traffic information to predict congestion on evacuation routes and provides evacuation routes that are suitable for each individual user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides evacuation route guidance that is appropriate for the user's condition.

[0248] System configuration

[0249] This system consists of three elements: a server, a terminal, and a user. By adding an emotion engine, it can be customized based on the user's emotional state.

[0250] server

[0251] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems, such as precipitation, wind speed, earthquake information, road congestion, and road closure information.

[0252] Data analysis and model generation: Analyze collected data and use AI models to predict congestion along evacuation routes. Use machine learning algorithms to make highly accurate predictions based on past data and current conditions.

[0253] Evacuation route generation: The system obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[0254] Information provision: The generated evacuation route information is sent to the user's device. The data format is converted to JSON or XML and sent to the device via API.

[0255] Feedback analysis: Update route information in real time based on user feedback.

[0256] Terminal

[0257] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and guided by audio guidance.

[0258] Emotion engine: Analyzes voice, facial expressions, heart rate, etc. to recognize the user's emotions and assess their stress level. Based on the recognition results, the system adjusts evacuation route guidance methods.

[0259] Feedback transmission: Local information and congestion status are provided by the user through an input interface and sent to the server.

[0260] User

[0261] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[0262] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation will be provided via the terminal.

[0263] Specific examples

[0264] Evacuation scenario in the event of an earthquake

[0265] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0266] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[0267] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[0268] 4. Adjustment by emotion engine: The emotion engine of the device evaluates the user's stress level and adjusts evacuation route guidance. For example, if the user is in a high stress state, the instructions will be simplified and a reassuring voice guidance will be provided.

[0269] 5. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user will provide feedback on this information to the server via their device.

[0270] 6. Reanalysis and route update: The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it to the terminal again.

[0271] 7. Re-notification to the user: The device receives the new route information and notifies the user. The user continues evacuation along the new route.

[0272] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state. By always providing optimal route information and guidance, evacuation can be carried out quickly and reliably in the event of a disaster.

[0273] The processing flow will be explained below.

[0274] Step 1: Getting real-time data

[0275] The server obtains real-time data such as weather data and traffic information. It collects earthquake information, precipitation, wind speed, etc. from meteorological agencies' APIs, and obtains road congestion, traffic accident information, and road closure information from traffic management systems.

[0276] Step 2: Data analysis and model generation

[0277] The server analyzes the real-time data it acquires and generates a model to predict congestion along evacuation routes. Specifically, it preprocesses the data and applies machine learning algorithms to train a congestion prediction model based on past data and current conditions. The generated model can predict congestion in each area with high accuracy.

[0278] Step 3: Generate evacuation routes

[0279] The server generates an evacuation route suited to each individual user based on the analysis results. The user's current location is identified using GPS data, and multiple route candidates are generated. Congestion predictions and risk assessments are performed for each route candidate, and the safest and most efficient route is selected.

[0280] Step 4: Provide evacuation route information

[0281] The server provides the generated evacuation route information to the user's device. The generated route information is converted into an appropriate data format (JSON or XML) and sent to the device via API with end-to-end encrypted communication.

[0282] Step 5: Evacuation route notification and guidance

[0283] The device notifies the user of the evacuation route information it receives. Specifically, it uses pop-up notifications and alert sounds to prompt the user to begin evacuation. Furthermore, it uses a map display function to visually display the route and a voice guidance function to guide the user.

[0284] Step 6: Emotion Recognition with the Emotion Engine

[0285] The device's emotion engine recognizes the user's emotional state. The emotion engine evaluates the user's stress level and tension by analyzing the user's voice, facial expressions, heart rate, etc. As a specific example, it analyzes the tone of the user's voice from voice input to determine the stress level.

[0286] Step 7: Emotion-Based Guidance Adjustments

[0287] The device adjusts evacuation route guidance based on the results of the emotion engine. If the user is judged to be in a high-stress state, it simplifies the instructions and provides reassuring voice guidance. If the user is calm, it provides detailed instructions.

[0288] Step 8: Provide feedback

[0289] During evacuation, users provide feedback using their devices, reporting congested areas and impassable locations using a simple input form or voice input, and the devices then send this information to the server.

[0290] Step 9: Analyze feedback and update route in real time

[0291] The server analyzes the received feedback and updates evacuation route information in real time. It recalculates routes based on new obstacle and congestion information and generates the latest optimal route. The updated route information is then sent back to the device.

[0292] Step 10: Re-informing and re-guiding

[0293] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on the map and voice guidance is provided again. The user follows the instructions to continue evacuating safely.

[0294] This series of processing steps not only enables the server, terminal, and user to work together to achieve efficient and safe evacuation in real time, but also provides more appropriate evacuation support by providing customized guidance based on the user's emotional state.

[0295] Example 2

[0296] 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."

[0297] Conventional evacuation systems have had problems with difficulty in predicting congestion in real time and providing optimal evacuation routes for individual users, and they were unable to provide evacuation guidance that took into account the user's emotional state. This prevented efficient and safe evacuation, potentially increasing user stress and confusion. Furthermore, there was a lack of a mechanism for utilizing feedback to update route information in real time, which posed a risk of reducing the effectiveness of evacuation routes.

[0298] 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.

[0299] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating multiple evacuation route candidates suitable for each user based on the prediction and evaluating them to select the optimal evacuation route, means for converting the generated evacuation route information into a data format and providing it to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information in real time, and means for analyzing voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting the evacuation route guidance method based on the user's stress level. This enables accurate congestion prediction in real time, provision of evacuation routes tailored to each individual user, and appropriate evacuation guidance based on the user's emotional state.

[0300] "Weather data" refers to data related to weather elements such as precipitation, wind speed, and earthquake information.

[0301] "Traffic information" refers to data related to traffic, such as road congestion and road closure information.

[0302] "Real-time data" means the most up-to-date data about current conditions or status.

[0303] A "machine learning algorithm" is an algorithm that analyzes collected data to find patterns and trends and make predictions and classifications.

[0304] An "evacuation route" is a route that a user uses to safely evacuate in the event of a disaster.

[0305] "Congestion status" refers to the degree of concentration of people and vehicles in a particular location or route.

[0306] "Means for generating a model" refers to the means for creating a machine learning model for making predictions and classifications based on collected data.

[0307] "Feedback" refers to local information, opinions, impressions, etc. obtained from users.

[0308] A "data format" is a standard way of storing, displaying, or transmitting data.

[0309] "Emotional state" refers to the user's current emotional or mental state.

[0310] The "stress level" is a value that indicates the degree of stress that the user is feeling.

[0311] The "means for adjusting the evacuation route guidance method" is a means for optimizing the evacuation route guidance method based on the user's emotional state and stress level.

[0312] The system of the present invention is designed to support users in evacuating safely and efficiently in the event of a disaster. The system is mainly composed of three elements: a server, a terminal, and a user. By further integrating an emotion engine, the system is customized based on the user's emotional state. Specific embodiments of each element are shown below.

[0313] Server Processing

[0314] The server is responsible for a series of processes: collection, analysis, generation, provision, and updating. First, to collect real-time data such as weather data and traffic information, the server connects to the API of each data source (for example, the API of a weather information service or the API of a traffic information service) and obtains the real-time data.

[0315] The server then analyzes the acquired data and uses machine learning algorithms (for example, frameworks such as TensorFlow or PyTorch) to predict congestion along evacuation routes. The model generated by this analysis makes highly accurate congestion predictions based on past and real-time data.

[0316] The server generates multiple evacuation route candidates based on this forecast data and evaluates the congestion and risk of each candidate. After selecting the optimal evacuation route, it converts the information into JSON or XML format and sends it to the user's device via an API. It also receives feedback from users in real time and updates the evacuation route information.

[0317] Terminal handling

[0318] The device receives the evacuation route information sent from the server and notifies the user. Notifications are made visually using a map display (for example, using Google Maps API) and through voice guidance.

[0319] The device is also equipped with an emotion engine that analyzes the user's voice, facial expressions, heart rate, and other data to recognize the user's emotional state. This analysis uses emotion recognition APIs such as AWS® Rekognition and IBM Watson®. Based on the user's emotional state and stress level, the device can adjust evacuation route guidance methods (such as simplified instructions or reassuring voice guidance).

[0320] The device also provides an interface for users to input local information and congestion status, and has the function of sending user feedback to the server, which keeps the evacuation route information always up-to-date.

[0321] User operations

[0322] Users check the evacuation route information displayed on their device, select a safe route, and begin evacuation. Information about congestion and impassable areas encountered during evacuation can be provided to the server as feedback via the device. This improves the effectiveness of evacuation routes and also helps support other evacuees.

[0323] Specific examples

[0324] For example, if a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API, analyzes the data, and predicts congestion in the affected area. Based on this, it generates an optimal evacuation route model and sends it to the user's device. The device receives this information and notifies the user through a map display and voice guidance. The emotion engine also evaluates the user's stress level and provides appropriate guidance.

[0325] Example prompt sentence:

[0326] "We are designing a system to generate appropriate AI models and assist in safe evacuation. How can we improve efficiency and safety by incorporating user emotion recognition into evacuation route guidance?"

[0327] This allows users to quickly identify safe and efficient evacuation routes, enabling them to evacuate while reducing stress.

[0328] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0329] Step 1:

[0330] Real-time data collection

[0331] The server connects to the APIs of meteorological agencies and traffic management systems to collect real-time data. This process obtains data such as precipitation, wind speed, earthquake information, road congestion, and road closure information. Specifically, the server sends a data request to the API, receives a response in JSON format, and analyzes it. The input is the request from the API, and the output is the analyzed weather data and traffic information.

[0332] Step 2:

[0333] Data Preprocessing

[0334] The real-time data acquired by the server is integrated into a single dataset, and data normalization and missing value imputation are performed. This process is performed using the Python Pandas library. The input is raw real-time data, and the output is a preprocessed integrated dataset in a format suitable for analysis.

[0335] Step 3:

[0336] Training a machine learning model

[0337] The server trains machine learning models using the preprocessed dataset. It uses TensorFlow or PyTorch to build regression and time series forecasting models. The input is the preprocessed integrated dataset, and the output is a trained predictive model. Specific operations include splitting the dataset, defining the model, training it, and evaluating it.

[0338] Step 4:

[0339] Running a prediction

[0340] The server uses the trained model to predict the congestion status of evacuation routes based on current data. The input is current real-time data, and the output is the congestion prediction results for each route. Specific operations include inputting data into the model, obtaining prediction results, and evaluating the results.

[0341] Step 5:

[0342] Generate evacuation routes

[0343] The server obtains the user's current location (GPS data) and generates multiple candidate evacuation routes. Routes are calculated using map databases such as OpenStreetMap, and a model is used to predict congestion and assess risk for each route. The input is the user's current location and the congestion prediction results, and the output is multiple evaluated evacuation routes. Specific operations include generating candidate routes, assessing congestion, and selecting the optimal route.

[0344] Step 6:

[0345] Providing route information

[0346] The server converts the generated evacuation route information into JSON or XML format and sends it to the user's device via API. The input is the evaluated evacuation route, and the output is the route information sent to the user's device. Specific operations include converting the data format and sending an HTTP request.

[0347] Step 7:

[0348] Receiving information and notifications via device

[0349] The terminal receives evacuation route information sent from the server and notifies the user. Visually, it uses a map display and voice guidance. The input is route information from the server, and the output is a notification to the user. Specific operations include parsing data, displaying a map, and starting voice guidance.

[0350] Step 8:

[0351] Running the Emotion Engine

[0352] The device collects data from sensors, such as the user's voice, facial expressions, and heart rate, and analyzes their emotional state. AWS Rekognition and IBM Watson APIs are used to identify the user's stress level and emotional state. The input is sensor data, and the output is the emotional assessment result. The specific operations are data collection and emotion analysis.

[0353] Step 9:

[0354] Emotion-based guidance adjustment

[0355] The device adjusts the evacuation route guidance method based on the results of emotion analysis. For example, if the user is in a high-stress state, it simplifies the instructions and selects a voice guidance that provides a sense of security. The input is the emotion evaluation result, and the output is the adjusted guidance method. The specific operation is to select the guidance and display / execute the voice guidance.

[0356] Step 10:

[0357] Send Feedback

[0358] The user inputs the local situation they encountered during evacuation into the terminal and sends the information to the server. The input is the feedback from the user, and the output is the feedback data sent to the server. The specific operation is to provide a data input form and send an HTTP request.

[0359] Step 11:

[0360] Feedback analysis and route updates

[0361] The server receives feedback from users and updates evacuation route information in real time. It then reapplies the machine learning model to generate a new optimal route and sends it back to the user's device. The input is the feedback data, and the output is the updated evacuation route information. The specific operations are data analysis, route recalculation, and information retransmission.

[0362] (Application example 2)

[0363] 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."

[0364] In modern society, there is a demand for rapid and safe evacuation in the event of sudden disasters such as meteorological disasters, fires, and earthquakes. However, conventional evacuation support systems lack the ability to collect and analyze data in real time, and are unable to provide evacuation guidance that takes into account the user's emotional state, which can increase confusion and stress. The present invention aims to solve these problems and achieve safe and efficient evacuation.

[0365] 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 means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting the congestion status of evacuation routes, means for generating an evacuation route appropriate for each user based on the prediction, means for providing the generated evacuation route information to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for analyzing the user's voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting evacuation route guidance. This makes it possible to provide an appropriate evacuation route in real time taking the user's emotional state into consideration.

[0366] "Weather data" refers to information relating to weather, such as weather, precipitation, wind speed, and temperature.

[0367] "Traffic information" refers to information relating to traffic, such as road traffic conditions, congestion information, and road closures.

[0368] "Real-time data" is information data that is collected in the present and can be used immediately.

[0369] "Analysis" means examining collected data in detail to understand its meaning and characteristics.

[0370] An "evacuation route" is a route used to move to a safe location in the event of a disaster.

[0371] "Crowding status" is information indicating the degree or density of congestion within a certain range.

[0372] A "model" is a mathematical or computational representation used to understand and predict a system or phenomenon.

[0373] A "user terminal" is an electronic device such as a computer or smartphone used by a user.

[0374] "Feedback" is information or opinions provided by users.

[0375] "Emotional state" refers to an individual's psychological state, such as stress, relief, or tension.

[0376] "Audio guidance" is a method of providing guidance information to a user using voice.

[0377] "Visual map display" is a method of presenting information visually by displaying a map on a screen.

[0378] A "collection means" is a device or method for acquiring data.

[0379] "Providing means" refers to the device or method used to deliver information to users.

[0380] An "update means" is a device or method for updating content based on the latest information or data.

[0381] An "emotion recognition means" is a device or method for analyzing and recognizing a user's emotional state.

[0382] System Overview

[0383] This invention is a system that uses real-time data to support efficient and safe evacuation during disasters. The main components are a server, a terminal, and a user, and an emotion engine is added to these to provide evacuation guidance according to the user's emotional state.

[0384] server

[0385] The server collects real-time data such as weather and traffic information and generates a model to predict congestion on evacuation routes. Specifically, the server uses the following software and hardware:

[0386] Real-time data collection

[0387] The server collects data using APIs of meteorological agencies and traffic management systems. For example, it obtains precipitation, wind speed, earthquake information, road congestion status, etc. from the OpenWeatherMap API and Google Maps API.

[0388] Data analysis and model generation

[0389] Analyze the collected data and use a generative AI model (e.g., TensorFlow) to predict congestion along evacuation routes. Build a highly accurate predictive model based on past data and the current situation.

[0390] Generate and provide evacuation routes

[0391] The system obtains the user's current location information from GPS data and generates route candidates to the optimal evacuation shelter. The generated route candidates are provided to the device in JSON or XML format.

[0392] Feedback Analysis

[0393] It also includes a function to analyze user feedback in real time and update evacuation route information.

[0394] Terminal

[0395] The terminal is a user device such as a smartphone or tablet, which receives evacuation route information sent from the server and provides it to the user. It also uses an emotion engine to recognize the user's emotional state and adjust evacuation route guidance accordingly.

[0396] Information Reception and Notification

[0397] The device receives the data sent from the server and notifies the user through a visual map display and voice guidance. Applications using Flutter (registered trademark) and React Native can be used for this.

[0398] Emotion Engine

[0399] It uses Azure® Cognitive Services and Google Cloud Vision API to analyze data such as voice, facial expressions, and heart rate. The emotion engine assesses the user's stress level and adjusts evacuation route guidance.

[0400] Send Feedback

[0401] It has an interface to collect feedback from users and sends the collected data to a server, which allows for real-time optimization of evacuation route information.

[0402] User

[0403] Users can check evacuation route information through their devices and take evacuation actions, while also providing feedback on the situations they encounter during evacuation.

[0404] Checking evacuation routes and taking evacuation actions

[0405] Based on the evacuation route information displayed on the device, users can confirm a safe route and begin evacuation procedures.

[0406] Providing Feedback

[0407] The device reports to the server any congestion or impassable areas encountered during evacuation.

[0408] Specific examples

[0409] Evacuation scenario in the event of an earthquake

[0410] 1. The server acquires earthquake information

[0411] The server obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API.

[0412] 2. Analysis and Model Generation

[0413] The collected information is analyzed, and generative AI models such as TensorFlow are used to predict congestion on evacuation routes and generate an optimal evacuation route model.

[0414] 3. Providing evacuation routes

[0415] The server provides evacuation route information to the terminal, which receives it and notifies the user through voice guidance and visual map display.

[0416] 4. Emotional Engine Adjustment

[0417] The device's emotion engine assesses the user's stress level and adjusts evacuation route guidance accordingly. For example, if the user is in a high stress state, the device will simplify instructions and provide reassuring voice guidance.

[0418] 5. Evacuation behavior and feedback

[0419] The user begins evacuation by following the provided evacuation route. If the user encounters a road that has been severely damaged and is impassable along the way, the user's device will provide feedback to the server.

[0420] 6. Reanalysis and Route Updates

[0421] The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it back to the terminal.

[0422] 7. Re-notifying the user

[0423] The terminal receives the new route information again and notifies the user.

[0424] Prompt Sentence Examples

[0425] "predict_evacuations_route(current_weather, traffic_data, user_location)"

[0426] "analyze_emotion(user_voice, user_facial_expression, user_heart_rate)"

[0427] "traffic_conditions.update({"location": "X", "status": "closed"})"

[0428] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state.

[0429] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0430] Step 1:

[0431] The server collects weather and traffic information. The server obtains real-time data from the APIs of meteorological agencies (e.g., OpenWeatherMap API) and traffic information systems (e.g., Google Maps API). Input data includes precipitation, wind speed, earthquake information, road congestion status, etc., and stores this data in a database.

[0432] Step 2:

[0433] The server analyzes the collected data and uses a generative AI model (e.g., TensorFlow) to predict the congestion status of evacuation routes. The input is the weather data and traffic information collected in Step 1, and based on this, a machine learning algorithm processes and calculates the data. The output is a congestion prediction for each evacuation route.

[0434] Step 3:

[0435] The server generates an evacuation route suitable for each user based on congestion predictions. The user's current location information (GPS data) is also used as input. The server generates multiple evacuation route candidates and evaluates the efficiency and safety of each route. The optimal evacuation route information is generated in JSON format.

[0436] Step 4:

[0437] The server provides the generated evacuation route information to the user terminal. The input is the optimal evacuation route information generated in step 3, which is sent to the terminal via API. The terminal receives this information and starts visual map display and audio guidance.

[0438] Step 5:

[0439] The device collects the user's voice, facial expressions, heart rate, etc. and analyzes them using an emotion engine. The input is the user's voice data, facial images, heart rate data, etc., and this data is analyzed using Azure Cognitive Services and Google Cloud Vision API. The output is the user's stress level and emotional state.

[0440] Step 6:

[0441] The device adjusts evacuation route guidance based on the user's emotional state. The inputs are the emotion analysis results from step 5 and the evacuation route information from step 4. For example, if the user is in a high-stress state, the device simplifies instructions and provides reassuring voice guidance.

[0442] Step 7:

[0443] The user begins evacuation by following the evacuation route. If the user encounters an impassable road or a crowded situation along the way, the user sends feedback to the server via the device. The input is the user's feedback information, which is then sent to the server.

[0444] Step 8:

[0445] The server receives feedback from users and updates the evacuation route information. The input is the on-site feedback data obtained in step 7, and based on this, it analyzes the data again using a machine learning algorithm to generate a new evacuation route model. The output is the updated evacuation route information.

[0446] Step 9:

[0447] The server again sends the new evacuation route information to the terminal. The input is the new evacuation route information generated in step 8, and sends this to the terminal via the API. The terminal receives the new route information and notifies the user.

[0448] In this way, real-time data and an emotion engine are combined to support efficient and safe evacuation according to the user's emotional state.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] [Second embodiment]

[0453] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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."

[0465] System Overview

[0466] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather and traffic information to predict congestion on evacuation routes and provides appropriate evacuation routes to individual users. It also has a function to reflect user feedback and update evacuation route information.

[0467] System configuration

[0468] This system is mainly composed of three elements: the server, the terminal, and the user. The role of each will be explained in detail below.

[0469] server

[0470] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems. For example, weather data includes precipitation, wind speed, and earthquake information, and traffic information includes road congestion and road closure information.

[0471] Data analysis and predictive model generation: Collected data is analyzed and an AI model is used to predict congestion along evacuation routes. Machine learning algorithms are used to make highly accurate predictions based on past data and the current situation.

[0472] Evacuation route generation: Based on the analysis results, the system generates the optimal route from the user's current location to the evacuation shelter. It evaluates multiple route candidates and selects the least congested and safest route.

[0473] Providing information: The generated evacuation route information is sent to the user's device.

[0474] Feedback analysis: Route information is updated in real time based on user feedback.

[0475] Terminal

[0476] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and is also provided with audio guidance.

[0477] Feedback transmission: Provides an interface for users to input local information and congestion status, and sends this to the server.

[0478] User

[0479] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[0480] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation is sent via the device.

[0481] Specific examples

[0482] Evacuation scenario in the event of an earthquake

[0483] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0484] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[0485] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[0486] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user feeds that information back to the server via their device.

[0487] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[0488] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[0489] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[0490] The processing flow will be explained below.

[0491] Step 1: Getting real-time data

[0492] The server obtains real-time data such as weather data and traffic information. It calls the APIs of meteorological agencies and traffic management systems to collect data such as weather information for each region, earthquake information, traffic congestion information, and the availability of evacuation shelters.

[0493] Step 2: Data analysis and model generation

[0494] The server analyzes real-time data acquired and uses AI models to predict congestion along evacuation routes. The data is preprocessed and congestion predictions are made using machine learning algorithms and simulation models. The accuracy of the generated models is also evaluated, and the models are adjusted as necessary.

[0495] Step 3: Generate evacuation routes

[0496] The server generates an evacuation route suited to each individual user based on the analysis results. It obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[0497] Step 4: Provide evacuation route information

[0498] The server generates evacuation route information and sends it to the user's device. The data format is converted to JSON or XML and sent to the device via an API. During this process, the data is encrypted to ensure security.

[0499] Step 5: Evacuation route notification and guidance

[0500] The device notifies the user of the evacuation route information it has received. It uses pop-up notifications and sound alerts to encourage the user to begin evacuation. It visually displays the route on a map and provides route guidance through audio guidance.

[0501] Step 6: Provide feedback

[0502] Users provide feedback through their devices. They report congested or impassable areas during evacuation using an input form or voice input. The devices then send this feedback information to the server.

[0503] Step 7: Analyze feedback and update route

[0504] The server analyzes the received feedback and updates evacuation route information in real time, recalculating routes to reflect new information about obstacles and congestion, and generating the latest optimal routes.

[0505] Step 8: Re-informing and re-guiding

[0506] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on a map and re-guided by voice guidance. The user continues evacuating according to the new route information.

[0507] This series of processing steps enables the server, terminals, and users to work together to achieve efficient and safe evacuation in real time.

[0508] Example 1

[0509] 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."

[0510] In modern society, rapid and safe evacuation in the event of a disaster is extremely important. However, there are many challenges in collecting and analyzing real-time weather and traffic data and providing optimal evacuation routes. In particular, complex data analysis, rapid information provision, and the ability to incorporate user feedback in real time are required. Conventional systems have difficulty integrating and effectively executing these elements, resulting in issues such as reduced evacuation efficiency and a compromised safety.

[0511] 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.

[0512] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating evacuation routes suitable for each user based on the prediction and evaluating multiple route candidates to select the optimal route, means for providing the generated evacuation route information to a user terminal and notifying the user using audio guidance and a visual map display, and means for receiving feedback from the user via the user terminal and reanalyzing and updating the route information in real time, thereby enabling the provision of evacuation routes with high speed and accuracy and optimization that reflects user feedback in real time.

[0513] "Weather data" refers to various information related to meteorological phenomena such as temperature, precipitation, wind speed, air pressure, earthquake intensity and epicenter.

[0514] "Traffic information" refers to various information related to traffic flow and road usage, such as road congestion, road closures, traffic accident occurrences, and congestion information.

[0515] "Real-time data" refers to up-to-date data that reflects current conditions, including weather and traffic information.

[0516] A "machine learning algorithm" refers to a computational method that learns patterns from past data and makes predictions and decisions when new data is given.

[0517] An "evacuation route" refers to the route a user takes to travel from their current location to a specific evacuation shelter or safe location.

[0518] "Congestion" refers to the amount of traffic and concentration of people on a particular road or route.

[0519] "Predictive model" refers to a mathematical or computational method used to predict specific future conditions based on collected data.

[0520] "Route update" refers to the process of recalculating existing evacuation route information and re-providing optimal routes based on user feedback and newly collected data.

[0521] "Voice guidance" refers to a method of giving instructions and guidance to a user through voice.

[0522] "Visual map display" refers to a method of providing route information to a user using a graphical map.

[0523] "Feedback" refers to reports provided by users regarding local information and congestion during evacuation.

[0524] "User terminal" refers to an electronic device, such as a smartphone or tablet, that a user uses to receive and send information.

[0525] This invention is a system that supports efficient and safe evacuation in the event of a disaster. It consists of three elements: a server, a terminal, and a user, and realizes advanced evacuation support using real-time data.

[0526] System Overview

[0527] The main features of the system are as follows:

[0528] 1. Real-time data collection

[0529] 2. Data analysis and predictive model generation

[0530] 3. Generating optimal evacuation routes

[0531] 4. Providing evacuation route information

[0532] 5. Receiving user feedback and updating route information

[0533] Hardware and software used

[0534] server

[0535] Hardware: Server computer

[0536] Software: APIs for data collection (e.g., OpenWeatherMap API, Google Maps API), programming libraries for data analysis (e.g., Python, pandas, scikit-learn, TensorFlow), algorithms for path generation (e.g., Dijkstra algorithm, A algorithm)

[0537] Terminal

[0538] Hardware: Smartphones, tablets

[0539] Software: Map display apps (e.g., Google Maps), TTS (text-to-speech) engine for voice guidance

[0540] User

[0541] Hardware: Smartphones, tablets

[0542] Software: Evacuation route display app, feedback input interface

[0543] Specific processing

[0544] server

[0545] The server collects weather and traffic data in real time. It periodically retrieves the data using an API and stores it in a database. The collected data is then cleaned (by filling in missing values ​​and removing outliers) and a machine learning model is trained. Specifically, a random forest and LSTM model are used to predict the congestion status of evacuation routes.

[0546] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. This uses the Dijkstra algorithm and the A algorithm. The generated routes are evaluated for congestion and safety to select the most suitable one. The selected route information is sent to the user's device in JSON format.

[0547] Terminal

[0548] The device receives evacuation route information sent from the server and notifies the user. It uses a map display application to visually display the route and a TTS engine to provide voice guidance. It provides an interface that allows the user to input feedback information (e.g., congestion status and impassable areas) during evacuation. The input feedback information is sent to the server.

[0549] User

[0550] The user begins evacuation based on the evacuation route information. For example, if an earthquake occurs, the user will follow the route information displayed on the device and head to the most suitable evacuation shelter. If the user encounters congestion or impassable conditions along the way, the user will provide this information via the device. This allows the server to reanalyze the data and receive updated route information.

[0551] Specific examples

[0552] Evacuation scenario in the event of an earthquake

[0553] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0554] 2. Analysis and model generation: The collected information is analyzed and congestion predictions are made for the affected areas. An LSTM model is used for this analysis.

[0555] 3. Providing evacuation routes: The server generates the optimal evacuation route and sends it to the user's device. The device receives it and notifies the user using a map display app and a TTS engine.

[0556] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, that information is fed back to the user via the device.

[0557] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[0558] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[0559] Example prompts to input to the generative AI model

[0560] "Based on the latest earthquake information, please tell me the best evacuation route from point A to point B."

[0561] "Enter your current location and destination and we'll predict and provide you with the least congested evacuation route."

[0562] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[0563] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0564] Step 1:

[0565] Real-time data collection

[0566] server

[0567] The server calls the APIs of meteorological agencies and traffic management systems to collect the latest weather and traffic information. Specifically, it sends an HTTP request to the API endpoint and receives a JSON-formatted response. This data includes precipitation, wind speed, temperature, earthquake intensity, epicenter information, road congestion status, and road closure information. The collected data is stored in an internal database.

[0568] Input: Weather and traffic data retrieved from API endpoints

[0569] Output: Real-time data stored in an internal database

[0570] Step 2:

[0571] Data preprocessing and analysis

[0572] server

[0573] The server preprocesses the collected data. Specifically, it complements missing values, removes outliers, and formats the data. This process uses the Python pandas library. After preprocessing is complete, the server analyzes the data using a machine learning algorithm (e.g., random forest or LSTM model) to generate a model for predicting the congestion status of evacuation routes.

[0574] Input: Stored real-time data

[0575] Output: Preprocessed data and predictive model

[0576] Step 3:

[0577] Evacuation route generation and evaluation

[0578] server

[0579] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. To do this, it uses road network data and calculates the shortest or optimal route using the Dijkstra algorithm or the A algorithm. The generated routes are evaluated taking into account congestion and safety, and the optimal route is selected.

[0580] Input: Prediction model, user's current location, location of evacuation shelter

[0581] Output: Evaluated optimal evacuation route

[0582] Step 4:

[0583] Providing evacuation route information

[0584] server

[0585] The server sends optimal evacuation route information to the user's device in JSON format.

[0586] Terminal

[0587] The device analyzes the received evacuation route information and notifies the user. Specifically, it uses a map display application (e.g., Google Maps) to visually display the route and uses a TTS engine to provide voice guidance.

[0588] Input: Evacuation route information in JSON format sent from the server

[0589] Output: Map display and evacuation route notification with voice guidance

[0590] Step 5:

[0591] Receiving feedback from users

[0592] User

[0593] During evacuation, users report impassable areas and congestion via their devices.

[0594] Terminal

[0595] The terminal collects feedback information from the user and transmits it to the server.

[0596] Input: User-entered feedback information

[0597] Output: Feedback information sent to the server

[0598] Step 6:

[0599] Analyzing feedback and updating routes

[0600] server

[0601] The server analyzes the received feedback information and recalculates and updates evacuation route information as necessary, again using the predictive model and route generation algorithm.

[0602] Input: User feedback information

[0603] Output: Updated evacuation route information

[0604] Step 7:

[0605] Providing updated route information

[0606] server

[0607] The server then transmits the updated evacuation route information to the user's terminal again.

[0608] Terminal

[0609] The device receives the new evacuation route information and notifies the user again, updating the map display and voice guidance.

[0610] Input: Updated evacuation route information

[0611] Output: New evacuation route information notified to the user

[0612] Through these seven steps, the system of this invention realizes efficient and safe evacuation support. By collecting and analyzing data in real time and dynamically updating routes based on user feedback, it is possible to provide optimal evacuation routes at all times.

[0613] (Application example 1)

[0614] 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."

[0615] Conventional evacuation support systems are unable to fully utilize real-time data, making it difficult to provide rapid evacuation routes that respond to changes in congestion. Furthermore, they are unable to flexibly recalculate routes using user feedback, which means they are unable to respond to dynamic environmental changes. Furthermore, the means of notifying users of evacuation routes are limited, and there is a need for information to be provided in a format that is intuitively easy for users to understand. There is a need for a system that can solve these problems and support safe and efficient evacuation during disasters.

[0616] 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.

[0617] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes, means for generating evacuation routes suitable for individual users based on the prediction, means for providing the generated evacuation route information to a user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for notifying the user of the evacuation route information based on the user's current location by voice and map using a smart device. This enables real-time data analysis and route provision, thereby realizing intuitive and immediate evacuation support for users.

[0618] "Weather data" refers to information about weather and weather conditions, including precipitation, wind speed, temperature, humidity, and air pressure.

[0619] "Traffic information" refers to information relating to road traffic conditions, including congestion, road closures, accident information, and the like.

[0620] "Real-time data" refers to the latest information at the current time, and is data that is collected and processed immediately.

[0621] A "model" is an algorithm or mathematical framework for predicting congestion along evacuation routes based on collected data.

[0622] A "user terminal" is an information communication device used by a user, and includes a smartphone, a tablet, smart glasses, etc.

[0623] "Feedback" is information provided by users based on local conditions and experiences.

[0624] "Evacuation routes" refer to recommended roads and routes for safe evacuation in the event of a disaster.

[0625] A "smart device" is an electronic device with advanced functionality that can connect to the Internet.

[0626] "Audio guidance" refers to a means of providing information to a user through audio.

[0627] "Visual map display" is a function that visually displays a map and provides route information and the like to the user.

[0628] An "evacuation support system" is an overall system for supporting users' evacuation in the event of a disaster.

[0629] MODE FOR CARRYING OUT THE INVENTION

[0630] System Overview

[0631] The system of this invention is designed to support efficient and safe evacuation in the event of a disaster. It collects real-time data, such as weather and traffic information, and analyzes that data to predict congestion along evacuation routes. Based on user feedback, it updates evacuation route information in real time and provides optimal evacuation routes.

[0632] Server Features

[0633] The server has the following features:

[0634] Real-time data collection: The server collects weather and traffic data in real time using external APIs (e.g., weather agencies and traffic information services).

[0635] Data analysis and model generation: Analyze the collected data and generate a model to predict the congestion status of evacuation routes. This modeling is performed using machine learning libraries such as TensorFlow.

[0636] Evacuation route generation: Based on the results of data analysis, an evacuation route appropriate for each individual user is generated. Multiple route candidates are evaluated and the least congested and safest route is selected.

[0637] Information provision: The generated evacuation route information is sent to the user's device.

[0638] Feedback analysis: Evacuation route information is updated in real time based on user feedback.

[0639] User device functions

[0640] The user terminal has the following features:

[0641] Receiving and displaying information: Receives evacuation route information sent from the server and notifies the user on the smart device with a visual map display and voice guidance.

[0642] Feedback submission: Provides an interface for users to input feedback and sends it to the server. Users can report traffic conditions, congestion, impassable areas, etc. in real time.

[0643] User Behavior

[0644] A user interacts with the system in the following way:

[0645] 1. Checking evacuation routes: When a disaster occurs, the user launches the application and receives notification of evacuation routes.

[0646] 2. Begin evacuation: Follow the map display and voice guidance on your smart device to proceed along the evacuation route.

[0647] 3. Providing feedback: Enter feedback about obstacles and congestion encountered during evacuation and send it to the server.

[0648] Specific examples

[0649] Let's take the example of a large-scale earthquake and a user evacuating. The server obtains real-time data from meteorological agencies and traffic information services. This data is analyzed using TensorFlow to generate an optimal evacuation route. The generated evacuation route information is sent to the user's smartphone, where the user receives a map display and voice guidance through the application. If the user encounters an impassable road or a congested area along the way, they enter that information in the application and send feedback to the server. The server reanalyzes the evacuation route based on this feedback and sends the new route information to the user's smartphone.

[0650] Prompt Sentence Examples

[0651] The user's current location is "35.6895, 139.6917" (center of the city). Please predict the best evacuation route for this user based on real-time weather and traffic information. Please take into account the following feedback ("Road impassable due to traffic jam", "Location: In front of Shibuya Station").

[0652] This example uses prompt sentences to demonstrate how a generative AI model can predict optimal evacuation routes and update them in real time based on feedback information.

[0653] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0654] Step 1:

[0655] The server collects real-time data such as weather data and traffic information. It uses external APIs (for example, APIs of meteorological agencies or APIs of traffic information services) to obtain data such as precipitation, wind speed, road congestion, and road closure information. It processes the data obtained from the external APIs as input, converts it into an appropriate format, and saves it in an internal data store. The output is the collected real-time data.

[0656] Step 2:

[0657] The server analyzes the collected real-time data and generates a model that predicts the congestion status of evacuation routes. It uses TensorFlow, a machine learning library, to create a predictive model based on past and current data. It uses the collected real-time data and past evacuation data as input and performs data analysis. The output is a model that predicts the congestion status of evacuation routes.

[0658] Step 3:

[0659] The server generates an evacuation route suited to each individual user based on the generated model. It analyzes the model's prediction results, evaluates multiple route candidates, and selects the safest route. The inputs are the user's current location, real-time data, and the output of the predictive model. The output is evacuation route information optimized for each user.

[0660] Step 4:

[0661] The server sends the generated evacuation route information to the user's device. The notification is sent via the Internet in a format that corresponds to the type of device used (smartphone, tablet, etc.). The input is the generated evacuation route information, and the output is the route information received by the user's device.

[0662] Step 5:

[0663] The user device notifies the user of the received evacuation route information using a visual map display and voice guidance. The user checks the route information through the application and begins evacuation. The input is the evacuation route information sent from the server, and the output is a notification to the user.

[0664] Step 6:

[0665] Users provide feedback on the congestion and impassable areas they encounter during evacuation via their terminals. The application has an interface for inputting feedback, and the information entered by the user is sent to the server. The input is feedback data from the user, and the output is the transmission of the feedback data to the server.

[0666] Step 7:

[0667] The server reanalyzes the evacuation route information based on the received feedback information and generates a new optimal route. The reanalysis uses real-time data and feedback information, and the generated new route information is sent back to the user terminal. The input is user feedback and real-time data, and the output is updated evacuation route information.

[0668] Step 8:

[0669] The user device receives the updated evacuation route information and notifies the user again. This allows the user to continue evacuating safely according to the latest evacuation route. The input is the updated route information sent from the server, and the output is the notification to the user.

[0670] 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.

[0671] System Overview

[0672] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather data and traffic information to predict congestion on evacuation routes and provides evacuation routes that are suitable for each individual user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides evacuation route guidance that is appropriate for the user's condition.

[0673] System configuration

[0674] This system consists of three elements: a server, a terminal, and a user. By adding an emotion engine, it can be customized based on the user's emotional state.

[0675] server

[0676] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems, such as precipitation, wind speed, earthquake information, road congestion, and road closure information.

[0677] Data analysis and model generation: Analyze collected data and use AI models to predict congestion along evacuation routes. Use machine learning algorithms to make highly accurate predictions based on past data and current conditions.

[0678] Evacuation route generation: The system obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[0679] Information provision: The generated evacuation route information is sent to the user's device. The data format is converted to JSON or XML and sent to the device via API.

[0680] Feedback analysis: Update route information in real time based on user feedback.

[0681] Terminal

[0682] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and guided by audio guidance.

[0683] Emotion engine: Analyzes voice, facial expressions, heart rate, etc. to recognize the user's emotions and assess their stress level. Based on the recognition results, the system adjusts evacuation route guidance methods.

[0684] Feedback transmission: Local information and congestion status are provided by the user through an input interface and sent to the server.

[0685] User

[0686] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[0687] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation will be provided via the terminal.

[0688] Specific examples

[0689] Evacuation scenario in the event of an earthquake

[0690] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0691] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[0692] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[0693] 4. Adjustment by emotion engine: The emotion engine of the device evaluates the user's stress level and adjusts evacuation route guidance. For example, if the user is in a high stress state, the instructions will be simplified and a reassuring voice guidance will be provided.

[0694] 5. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user will provide feedback on this information to the server via their device.

[0695] 6. Reanalysis and route update: The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it to the terminal again.

[0696] 7. Re-notification to the user: The device receives the new route information and notifies the user. The user continues evacuation along the new route.

[0697] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state. By always providing optimal route information and guidance, evacuation can be carried out quickly and reliably in the event of a disaster.

[0698] The processing flow will be explained below.

[0699] Step 1: Getting real-time data

[0700] The server obtains real-time data such as weather data and traffic information. It collects earthquake information, precipitation, wind speed, etc. from meteorological agencies' APIs, and obtains road congestion, traffic accident information, and road closure information from traffic management systems.

[0701] Step 2: Data analysis and model generation

[0702] The server analyzes the real-time data it acquires and generates a model to predict congestion along evacuation routes. Specifically, it preprocesses the data and applies machine learning algorithms to train a congestion prediction model based on past data and current conditions. The generated model can predict congestion in each area with high accuracy.

[0703] Step 3: Generate evacuation routes

[0704] The server generates an evacuation route suited to each individual user based on the analysis results. The user's current location is identified using GPS data, and multiple route candidates are generated. Congestion predictions and risk assessments are performed for each route candidate, and the safest and most efficient route is selected.

[0705] Step 4: Provide evacuation route information

[0706] The server provides the generated evacuation route information to the user's device. The generated route information is converted into an appropriate data format (JSON or XML) and sent to the device via API with end-to-end encrypted communication.

[0707] Step 5: Evacuation route notification and guidance

[0708] The device notifies the user of the evacuation route information it receives. Specifically, it uses pop-up notifications and alert sounds to prompt the user to begin evacuation. Furthermore, it uses a map display function to visually display the route and a voice guidance function to guide the user.

[0709] Step 6: Emotion Recognition with the Emotion Engine

[0710] The device's emotion engine recognizes the user's emotional state. The emotion engine evaluates the user's stress level and tension by analyzing the user's voice, facial expressions, heart rate, etc. As a specific example, it analyzes the tone of the user's voice from voice input to determine the stress level.

[0711] Step 7: Emotion-Based Guidance Adjustments

[0712] The device adjusts evacuation route guidance based on the results of the emotion engine. If the user is judged to be in a high-stress state, it simplifies the instructions and provides reassuring voice guidance. If the user is calm, it provides detailed instructions.

[0713] Step 8: Provide feedback

[0714] During evacuation, users provide feedback using their devices, reporting congested areas and impassable locations using a simple input form or voice input, and the devices then send this information to the server.

[0715] Step 9: Analyze feedback and update route in real time

[0716] The server analyzes the received feedback and updates evacuation route information in real time. It recalculates routes based on new obstacle and congestion information and generates the latest optimal route. The updated route information is then sent back to the device.

[0717] Step 10: Re-informing and re-guiding

[0718] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on the map and voice guidance is provided again. The user follows the instructions to continue evacuating safely.

[0719] This series of processing steps not only enables the server, terminal, and user to work together to achieve efficient and safe evacuation in real time, but also provides more appropriate evacuation support by providing customized guidance based on the user's emotional state.

[0720] Example 2

[0721] 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."

[0722] Conventional evacuation systems have had problems with difficulty in predicting congestion in real time and providing optimal evacuation routes for individual users, and they were unable to provide evacuation guidance that took into account the user's emotional state. This prevented efficient and safe evacuation, potentially increasing user stress and confusion. Furthermore, there was a lack of a mechanism for utilizing feedback to update route information in real time, which posed a risk of reducing the effectiveness of evacuation routes.

[0723] 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.

[0724] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating multiple evacuation route candidates suitable for each user based on the prediction and evaluating them to select the optimal evacuation route, means for converting the generated evacuation route information into a data format and providing it to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information in real time, and means for analyzing voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting the evacuation route guidance method based on the user's stress level. This enables accurate congestion prediction in real time, provision of evacuation routes tailored to each individual user, and appropriate evacuation guidance based on the user's emotional state.

[0725] "Weather data" refers to data related to weather elements such as precipitation, wind speed, and earthquake information.

[0726] "Traffic information" refers to data related to traffic, such as road congestion and road closure information.

[0727] "Real-time data" means the most up-to-date data about current conditions or status.

[0728] A "machine learning algorithm" is an algorithm that analyzes collected data to find patterns and trends and make predictions and classifications.

[0729] An "evacuation route" is a route that a user uses to safely evacuate in the event of a disaster.

[0730] "Congestion status" refers to the degree of concentration of people and vehicles in a particular location or route.

[0731] "Means for generating a model" refers to the means for creating a machine learning model for making predictions and classifications based on collected data.

[0732] "Feedback" refers to local information, opinions, impressions, etc. obtained from users.

[0733] A "data format" is a standard way of storing, displaying, or transmitting data.

[0734] "Emotional state" refers to the user's current emotional or mental state.

[0735] The "stress level" is a value that indicates the degree of stress that the user is feeling.

[0736] The "means for adjusting the evacuation route guidance method" is a means for optimizing the evacuation route guidance method based on the user's emotional state and stress level.

[0737] The system of the present invention is designed to support users in evacuating safely and efficiently in the event of a disaster. The system is mainly composed of three elements: a server, a terminal, and a user. By further integrating an emotion engine, the system is customized based on the user's emotional state. Specific embodiments of each element are shown below.

[0738] Server Processing

[0739] The server is responsible for a series of processes: collection, analysis, generation, provision, and updating. First, to collect real-time data such as weather data and traffic information, the server connects to the API of each data source (for example, the API of a weather information service or the API of a traffic information service) and obtains the real-time data.

[0740] The server then analyzes the acquired data and uses machine learning algorithms (for example, frameworks such as TensorFlow or PyTorch) to predict congestion along evacuation routes. The model generated by this analysis makes highly accurate congestion predictions based on past and real-time data.

[0741] The server generates multiple evacuation route candidates based on this forecast data and evaluates the congestion and risk of each candidate. After selecting the optimal evacuation route, it converts the information into JSON or XML format and sends it to the user's device via an API. It also receives feedback from users in real time and updates the evacuation route information.

[0742] Terminal handling

[0743] The device receives the evacuation route information sent from the server and notifies the user. Notifications are made visually using a map display (for example, using Google Maps API) and through voice guidance.

[0744] The device is also equipped with an emotion engine that recognizes the user's emotional state by analyzing voice, facial expressions, heart rate, etc. This analysis uses emotion recognition APIs such as AWS Rekognition and IBM Watson. Based on the user's emotional state and stress level, it is possible to adjust evacuation route guidance methods (such as simplified instructions or reassuring voice guidance).

[0745] The device also provides an interface for users to input local information and congestion status, and has the function of sending user feedback to the server, which keeps the evacuation route information always up-to-date.

[0746] User operations

[0747] Users check the evacuation route information displayed on their device, select a safe route, and begin evacuation. Information about congestion and impassable areas encountered during evacuation can be provided to the server as feedback via the device. This improves the effectiveness of evacuation routes and also helps support other evacuees.

[0748] Specific examples

[0749] For example, if a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API, analyzes the data, and predicts congestion in the affected area. Based on this, it generates an optimal evacuation route model and sends it to the user's device. The device receives this information and notifies the user through a map display and voice guidance. The emotion engine also evaluates the user's stress level and provides appropriate guidance.

[0750] Example prompt sentence:

[0751] "We are designing a system to generate appropriate AI models and assist in safe evacuation. How can we improve efficiency and safety by incorporating user emotion recognition into evacuation route guidance?"

[0752] This allows users to quickly identify safe and efficient evacuation routes, enabling them to evacuate while reducing stress.

[0753] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0754] Step 1:

[0755] Real-time data collection

[0756] The server connects to the APIs of meteorological agencies and traffic management systems to collect real-time data. This process obtains data such as precipitation, wind speed, earthquake information, road congestion, and road closure information. Specifically, the server sends a data request to the API, receives a response in JSON format, and analyzes it. The input is the request from the API, and the output is the analyzed weather data and traffic information.

[0757] Step 2:

[0758] Data Preprocessing

[0759] The real-time data acquired by the server is integrated into a single dataset, and data normalization and missing value imputation are performed. This process is performed using the Python Pandas library. The input is raw real-time data, and the output is a preprocessed integrated dataset in a format suitable for analysis.

[0760] Step 3:

[0761] Training a machine learning model

[0762] The server trains machine learning models using the preprocessed dataset. It uses TensorFlow or PyTorch to build regression and time series forecasting models. The input is the preprocessed integrated dataset, and the output is a trained predictive model. Specific operations include splitting the dataset, defining the model, training it, and evaluating it.

[0763] Step 4:

[0764] Running a prediction

[0765] The server uses the trained model to predict the congestion status of evacuation routes based on current data. The input is current real-time data, and the output is the congestion prediction results for each route. Specific operations include inputting data into the model, obtaining prediction results, and evaluating the results.

[0766] Step 5:

[0767] Generate evacuation routes

[0768] The server obtains the user's current location (GPS data) and generates multiple candidate evacuation routes. Routes are calculated using map databases such as OpenStreetMap, and a model is used to predict congestion and assess risk for each route. The input is the user's current location and the congestion prediction results, and the output is multiple evaluated evacuation routes. Specific operations include generating candidate routes, assessing congestion, and selecting the optimal route.

[0769] Step 6:

[0770] Providing route information

[0771] The server converts the generated evacuation route information into JSON or XML format and sends it to the user's device via API. The input is the evaluated evacuation route, and the output is the route information sent to the user's device. Specific operations include converting the data format and sending an HTTP request.

[0772] Step 7:

[0773] Receiving information and notifications via device

[0774] The terminal receives evacuation route information sent from the server and notifies the user. Visually, it uses a map display and voice guidance. The input is route information from the server, and the output is a notification to the user. Specific operations include parsing data, displaying a map, and starting voice guidance.

[0775] Step 8:

[0776] Running the Emotion Engine

[0777] The device collects data from sensors, such as the user's voice, facial expressions, and heart rate, and analyzes their emotional state. AWS Rekognition and IBM Watson APIs are used to identify the user's stress level and emotional state. The input is sensor data, and the output is the emotional assessment result. The specific operations are data collection and emotion analysis.

[0778] Step 9:

[0779] Emotion-based guidance adjustment

[0780] The device adjusts the evacuation route guidance method based on the results of emotion analysis. For example, if the user is in a high-stress state, it simplifies the instructions and selects a voice guidance that provides a sense of security. The input is the emotion evaluation result, and the output is the adjusted guidance method. The specific operation is to select the guidance and display / execute the voice guidance.

[0781] Step 10:

[0782] Send Feedback

[0783] The user inputs the local situation they encountered during evacuation into the terminal and sends the information to the server. The input is the feedback from the user, and the output is the feedback data sent to the server. The specific operation is to provide a data input form and send an HTTP request.

[0784] Step 11:

[0785] Feedback analysis and route updates

[0786] The server receives feedback from users and updates evacuation route information in real time. It then reapplies the machine learning model to generate a new optimal route and sends it back to the user's device. The input is the feedback data, and the output is the updated evacuation route information. The specific operations are data analysis, route recalculation, and information retransmission.

[0787] (Application example 2)

[0788] 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."

[0789] In modern society, there is a demand for rapid and safe evacuation in the event of sudden disasters such as meteorological disasters, fires, and earthquakes. However, conventional evacuation support systems lack the ability to collect and analyze data in real time, and are unable to provide evacuation guidance that takes into account the user's emotional state, which can increase confusion and stress. The present invention aims to solve these problems and achieve safe and efficient evacuation.

[0790] 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 means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting the congestion status of evacuation routes, means for generating an evacuation route appropriate for each user based on the prediction, means for providing the generated evacuation route information to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for analyzing the user's voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting evacuation route guidance. This makes it possible to provide an appropriate evacuation route in real time taking the user's emotional state into consideration.

[0791] "Weather data" refers to information relating to weather, such as weather, precipitation, wind speed, and temperature.

[0792] "Traffic information" refers to information relating to traffic, such as road traffic conditions, congestion information, and road closures.

[0793] "Real-time data" is information data that is collected in the present and can be used immediately.

[0794] "Analysis" means examining collected data in detail to understand its meaning and characteristics.

[0795] An "evacuation route" is a route used to move to a safe location in the event of a disaster.

[0796] "Crowding status" is information indicating the degree or density of congestion within a certain range.

[0797] A "model" is a mathematical or computational representation used to understand and predict a system or phenomenon.

[0798] A "user terminal" is an electronic device such as a computer or smartphone used by a user.

[0799] "Feedback" is information or opinions provided by users.

[0800] "Emotional state" refers to an individual's psychological state, such as stress, relief, or tension.

[0801] "Audio guidance" is a method of providing guidance information to a user using voice.

[0802] "Visual map display" is a method of presenting information visually by displaying a map on a screen.

[0803] A "collection means" is a device or method for acquiring data.

[0804] "Providing means" refers to the device or method used to deliver information to users.

[0805] An "update means" is a device or method for updating content based on the latest information or data.

[0806] An "emotion recognition means" is a device or method for analyzing and recognizing a user's emotional state.

[0807] System Overview

[0808] This invention is a system that uses real-time data to support efficient and safe evacuation during disasters. The main components are a server, a terminal, and a user, and an emotion engine is added to these to provide evacuation guidance according to the user's emotional state.

[0809] server

[0810] The server collects real-time data such as weather and traffic information and generates a model to predict congestion on evacuation routes. Specifically, the server uses the following software and hardware:

[0811] Real-time data collection

[0812] The server collects data using APIs of meteorological agencies and traffic management systems. For example, it obtains precipitation, wind speed, earthquake information, road congestion status, etc. from the OpenWeatherMap API and Google Maps API.

[0813] Data analysis and model generation

[0814] Analyze the collected data and use a generative AI model (e.g., TensorFlow) to predict congestion along evacuation routes. Build a highly accurate predictive model based on past data and the current situation.

[0815] Generate and provide evacuation routes

[0816] The system obtains the user's current location information from GPS data and generates route candidates to the optimal evacuation shelter. The generated route candidates are provided to the device in JSON or XML format.

[0817] Feedback Analysis

[0818] It also includes a function to analyze user feedback in real time and update evacuation route information.

[0819] Terminal

[0820] The terminal is a user device such as a smartphone or tablet, which receives evacuation route information sent from the server and provides it to the user. It also uses an emotion engine to recognize the user's emotional state and adjust evacuation route guidance accordingly.

[0821] Information Reception and Notification

[0822] The device receives the data sent from the server and notifies the user through a visual map display and voice guidance, using applications written in Flutter and React Native.

[0823] Emotion Engine

[0824] It uses Azure Cognitive Services and Google Cloud Vision API to analyze data such as voice, facial expressions, and heart rate, and its emotion engine assesses the user's stress level and adjusts evacuation route guidance.

[0825] Send Feedback

[0826] It has an interface to collect feedback from users and sends the collected data to a server, which allows for real-time optimization of evacuation route information.

[0827] User

[0828] Users can check evacuation route information through their devices and take evacuation actions, while also providing feedback on the situations they encounter during evacuation.

[0829] Checking evacuation routes and taking evacuation actions

[0830] Based on the evacuation route information displayed on the device, users can confirm a safe route and begin evacuation procedures.

[0831] Providing Feedback

[0832] The device reports to the server any congestion or impassable areas encountered during evacuation.

[0833] Specific examples

[0834] Evacuation scenario in the event of an earthquake

[0835] 1. The server acquires earthquake information

[0836] The server obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API.

[0837] 2. Analysis and Model Generation

[0838] The collected information is analyzed, and generative AI models such as TensorFlow are used to predict congestion on evacuation routes and generate an optimal evacuation route model.

[0839] 3. Providing evacuation routes

[0840] The server provides evacuation route information to the terminal, which receives it and notifies the user through voice guidance and visual map display.

[0841] 4. Emotional Engine Adjustment

[0842] The device's emotion engine assesses the user's stress level and adjusts evacuation route guidance accordingly. For example, if the user is in a high stress state, the device will simplify instructions and provide reassuring voice guidance.

[0843] 5. Evacuation behavior and feedback

[0844] The user begins evacuation by following the provided evacuation route. If the user encounters a road that has been severely damaged and is impassable along the way, the user's device will provide feedback to the server.

[0845] 6. Reanalysis and Route Updates

[0846] The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it back to the terminal.

[0847] 7. Re-notifying the user

[0848] The terminal receives the new route information again and notifies the user.

[0849] Prompt Sentence Examples

[0850] "predict_evacuations_route(current_weather, traffic_data, user_location)"

[0851] "analyze_emotion(user_voice, user_facial_expression, user_heart_rate)"

[0852] "traffic_conditions.update({"location": "X", "status": "closed"})"

[0853] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state.

[0854] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0855] Step 1:

[0856] The server collects weather and traffic information. The server obtains real-time data from the APIs of meteorological agencies (e.g., OpenWeatherMap API) and traffic information systems (e.g., Google Maps API). Input data includes precipitation, wind speed, earthquake information, road congestion status, etc., and stores this data in a database.

[0857] Step 2:

[0858] The server analyzes the collected data and uses a generative AI model (e.g., TensorFlow) to predict the congestion status of evacuation routes. The input is the weather data and traffic information collected in Step 1, and based on this, a machine learning algorithm processes and calculates the data. The output is a congestion prediction for each evacuation route.

[0859] Step 3:

[0860] The server generates an evacuation route suitable for each user based on congestion predictions. The user's current location information (GPS data) is also used as input. The server generates multiple evacuation route candidates and evaluates the efficiency and safety of each route. The optimal evacuation route information is generated in JSON format.

[0861] Step 4:

[0862] The server provides the generated evacuation route information to the user terminal. The input is the optimal evacuation route information generated in step 3, which is sent to the terminal via API. The terminal receives this information and starts visual map display and audio guidance.

[0863] Step 5:

[0864] The device collects the user's voice, facial expressions, heart rate, etc. and analyzes them using an emotion engine. The input is the user's voice data, facial images, heart rate data, etc., and this data is analyzed using Azure Cognitive Services and Google Cloud Vision API. The output is the user's stress level and emotional state.

[0865] Step 6:

[0866] The device adjusts evacuation route guidance based on the user's emotional state. The inputs are the emotion analysis results from step 5 and the evacuation route information from step 4. For example, if the user is in a high-stress state, the device simplifies instructions and provides reassuring voice guidance.

[0867] Step 7:

[0868] The user begins evacuation by following the evacuation route. If the user encounters an impassable road or a crowded situation along the way, the user sends feedback to the server via the device. The input is the user's feedback information, which is then sent to the server.

[0869] Step 8:

[0870] The server receives feedback from users and updates the evacuation route information. The input is the on-site feedback data obtained in step 7, and based on this, it analyzes the data again using a machine learning algorithm to generate a new evacuation route model. The output is the updated evacuation route information.

[0871] Step 9:

[0872] The server again sends the new evacuation route information to the terminal. The input is the new evacuation route information generated in step 8, and sends this to the terminal via the API. The terminal receives the new route information and notifies the user.

[0873] In this way, real-time data and an emotion engine are combined to support efficient and safe evacuation according to the user's emotional state.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] [Third embodiment]

[0878] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0879] 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.

[0880] 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).

[0881] 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.

[0882] 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.

[0883] 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).

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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."

[0890] System Overview

[0891] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather and traffic information to predict congestion on evacuation routes and provides appropriate evacuation routes to individual users. It also has a function to reflect user feedback and update evacuation route information.

[0892] System configuration

[0893] This system is mainly composed of three elements: the server, the terminal, and the user. The role of each will be explained in detail below.

[0894] server

[0895] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems. For example, weather data includes precipitation, wind speed, and earthquake information, and traffic information includes road congestion and road closure information.

[0896] Data analysis and predictive model generation: Collected data is analyzed and an AI model is used to predict congestion along evacuation routes. Machine learning algorithms are used to make highly accurate predictions based on past data and the current situation.

[0897] Evacuation route generation: Based on the analysis results, the system generates the optimal route from the user's current location to the evacuation shelter. It evaluates multiple route candidates and selects the least congested and safest route.

[0898] Providing information: The generated evacuation route information is sent to the user's device.

[0899] Feedback analysis: Route information is updated in real time based on user feedback.

[0900] Terminal

[0901] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and is also provided with audio guidance.

[0902] Feedback transmission: Provides an interface for users to input local information and congestion status, and sends this to the server.

[0903] User

[0904] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[0905] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation is sent via the device.

[0906] Specific examples

[0907] Evacuation scenario in the event of an earthquake

[0908] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0909] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[0910] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[0911] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user feeds that information back to the server via their device.

[0912] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[0913] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[0914] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[0915] The processing flow will be explained below.

[0916] Step 1: Getting real-time data

[0917] The server obtains real-time data such as weather data and traffic information. It calls the APIs of meteorological agencies and traffic management systems to collect data such as weather information for each region, earthquake information, traffic congestion information, and the availability of evacuation shelters.

[0918] Step 2: Data analysis and model generation

[0919] The server analyzes real-time data acquired and uses AI models to predict congestion along evacuation routes. The data is preprocessed and congestion predictions are made using machine learning algorithms and simulation models. The accuracy of the generated models is also evaluated, and the models are adjusted as necessary.

[0920] Step 3: Generate evacuation routes

[0921] The server generates an evacuation route suited to each individual user based on the analysis results. It obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[0922] Step 4: Provide evacuation route information

[0923] The server generates evacuation route information and sends it to the user's device. The data format is converted to JSON or XML and sent to the device via an API. During this process, the data is encrypted to ensure security.

[0924] Step 5: Evacuation route notification and guidance

[0925] The device notifies the user of the evacuation route information it has received. It uses pop-up notifications and sound alerts to encourage the user to begin evacuation. It visually displays the route on a map and provides route guidance through audio guidance.

[0926] Step 6: Provide feedback

[0927] Users provide feedback through their devices. They report congested or impassable areas during evacuation using an input form or voice input. The devices then send this feedback information to the server.

[0928] Step 7: Analyze feedback and update route

[0929] The server analyzes the received feedback and updates evacuation route information in real time, recalculating routes to reflect new information about obstacles and congestion, and generating the latest optimal routes.

[0930] Step 8: Re-informing and re-guiding

[0931] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on a map and re-guided by voice guidance. The user continues evacuating according to the new route information.

[0932] This series of processing steps enables the server, terminals, and users to work together to achieve efficient and safe evacuation in real time.

[0933] Example 1

[0934] 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."

[0935] In modern society, rapid and safe evacuation in the event of a disaster is extremely important. However, there are many challenges in collecting and analyzing real-time weather and traffic data and providing optimal evacuation routes. In particular, complex data analysis, rapid information provision, and the ability to incorporate user feedback in real time are required. Conventional systems have difficulty integrating and effectively executing these elements, resulting in issues such as reduced evacuation efficiency and a compromised safety.

[0936] 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.

[0937] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating evacuation routes suitable for each user based on the prediction and evaluating multiple route candidates to select the optimal route, means for providing the generated evacuation route information to a user terminal and notifying the user using audio guidance and a visual map display, and means for receiving feedback from the user via the user terminal and reanalyzing and updating the route information in real time, thereby enabling the provision of evacuation routes with high speed and accuracy and optimization that reflects user feedback in real time.

[0938] "Weather data" refers to various information related to meteorological phenomena such as temperature, precipitation, wind speed, air pressure, earthquake intensity and epicenter.

[0939] "Traffic information" refers to various information related to traffic flow and road usage, such as road congestion, road closures, traffic accident occurrences, and congestion information.

[0940] "Real-time data" refers to up-to-date data that reflects current conditions, including weather and traffic information.

[0941] A "machine learning algorithm" refers to a computational method that learns patterns from past data and makes predictions and decisions when new data is given.

[0942] An "evacuation route" refers to the route a user takes to travel from their current location to a specific evacuation shelter or safe location.

[0943] "Congestion" refers to the amount of traffic and concentration of people on a particular road or route.

[0944] "Predictive model" refers to a mathematical or computational method used to predict specific future conditions based on collected data.

[0945] "Route update" refers to the process of recalculating existing evacuation route information and re-providing optimal routes based on user feedback and newly collected data.

[0946] "Voice guidance" refers to a method of giving instructions and guidance to a user through voice.

[0947] "Visual map display" refers to a method of providing route information to a user using a graphical map.

[0948] "Feedback" refers to reports provided by users regarding local information and congestion during evacuation.

[0949] "User terminal" refers to an electronic device, such as a smartphone or tablet, that a user uses to receive and send information.

[0950] This invention is a system that supports efficient and safe evacuation in the event of a disaster. It consists of three elements: a server, a terminal, and a user, and realizes advanced evacuation support using real-time data.

[0951] System Overview

[0952] The main features of the system are as follows:

[0953] 1. Real-time data collection

[0954] 2. Data analysis and predictive model generation

[0955] 3. Generating optimal evacuation routes

[0956] 4. Providing evacuation route information

[0957] 5. Receiving user feedback and updating route information

[0958] Hardware and software used

[0959] server

[0960] Hardware: Server computer

[0961] Software: APIs for data collection (e.g., OpenWeatherMap API, Google Maps API), programming libraries for data analysis (e.g., Python, pandas, scikit-learn, TensorFlow), algorithms for path generation (e.g., Dijkstra algorithm, A algorithm)

[0962] Terminal

[0963] Hardware: Smartphones, tablets

[0964] Software: Map display apps (e.g., Google Maps), TTS (text-to-speech) engine for voice guidance

[0965] User

[0966] Hardware: Smartphones, tablets

[0967] Software: Evacuation route display app, feedback input interface

[0968] Specific processing

[0969] server

[0970] The server collects weather and traffic data in real time. It periodically retrieves the data using an API and stores it in a database. The collected data is then cleaned (by filling in missing values ​​and removing outliers) and a machine learning model is trained. Specifically, a random forest and LSTM model are used to predict the congestion status of evacuation routes.

[0971] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. This uses the Dijkstra algorithm and the A algorithm. The generated routes are evaluated for congestion and safety to select the most suitable one. The selected route information is sent to the user's device in JSON format.

[0972] Terminal

[0973] The device receives evacuation route information sent from the server and notifies the user. It uses a map display application to visually display the route and a TTS engine to provide voice guidance. It provides an interface that allows the user to input feedback information (e.g., congestion status and impassable areas) during evacuation. The input feedback information is sent to the server.

[0974] User

[0975] The user begins evacuation based on the evacuation route information. For example, if an earthquake occurs, the user will follow the route information displayed on the device and head to the most suitable evacuation shelter. If the user encounters congestion or impassable conditions along the way, the user will provide this information via the device. This allows the server to reanalyze the data and receive updated route information.

[0976] Specific examples

[0977] Evacuation scenario in the event of an earthquake

[0978] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[0979] 2. Analysis and model generation: The collected information is analyzed and congestion predictions are made for the affected areas. An LSTM model is used for this analysis.

[0980] 3. Providing evacuation routes: The server generates the optimal evacuation route and sends it to the user's device. The device receives it and notifies the user using a map display app and a TTS engine.

[0981] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, that information is fed back to the user via the device.

[0982] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[0983] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[0984] Example prompts to input to the generative AI model

[0985] "Based on the latest earthquake information, please tell me the best evacuation route from point A to point B."

[0986] "Enter your current location and destination and we'll predict and provide you with the least congested evacuation route."

[0987] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[0988] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0989] Step 1:

[0990] Real-time data collection

[0991] server

[0992] The server calls the APIs of meteorological agencies and traffic management systems to collect the latest weather and traffic information. Specifically, it sends an HTTP request to the API endpoint and receives a JSON-formatted response. This data includes precipitation, wind speed, temperature, earthquake intensity, epicenter information, road congestion status, and road closure information. The collected data is stored in an internal database.

[0993] Input: Weather and traffic data retrieved from API endpoints

[0994] Output: Real-time data stored in an internal database

[0995] Step 2:

[0996] Data preprocessing and analysis

[0997] server

[0998] The server preprocesses the collected data. Specifically, it complements missing values, removes outliers, and formats the data. This process uses the Python pandas library. After preprocessing is complete, the server analyzes the data using a machine learning algorithm (e.g., random forest or LSTM model) to generate a model for predicting the congestion status of evacuation routes.

[0999] Input: Stored real-time data

[1000] Output: Preprocessed data and predictive model

[1001] Step 3:

[1002] Evacuation route generation and evaluation

[1003] server

[1004] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. To do this, it uses road network data and calculates the shortest or optimal route using the Dijkstra algorithm or the A algorithm. The generated routes are evaluated taking into account congestion and safety, and the optimal route is selected.

[1005] Input: Prediction model, user's current location, location of evacuation shelter

[1006] Output: Evaluated optimal evacuation route

[1007] Step 4:

[1008] Providing evacuation route information

[1009] server

[1010] The server sends optimal evacuation route information to the user's device in JSON format.

[1011] Terminal

[1012] The device analyzes the received evacuation route information and notifies the user. Specifically, it uses a map display application (e.g., Google Maps) to visually display the route and uses a TTS engine to provide voice guidance.

[1013] Input: Evacuation route information in JSON format sent from the server

[1014] Output: Map display and evacuation route notification with voice guidance

[1015] Step 5:

[1016] Receiving feedback from users

[1017] User

[1018] During evacuation, users report impassable areas and congestion via their devices.

[1019] Terminal

[1020] The terminal collects feedback information from the user and transmits it to the server.

[1021] Input: User-entered feedback information

[1022] Output: Feedback information sent to the server

[1023] Step 6:

[1024] Analyzing feedback and updating routes

[1025] server

[1026] The server analyzes the received feedback information and recalculates and updates evacuation route information as necessary, again using the predictive model and route generation algorithm.

[1027] Input: User feedback information

[1028] Output: Updated evacuation route information

[1029] Step 7:

[1030] Providing updated route information

[1031] server

[1032] The server then transmits the updated evacuation route information to the user's terminal again.

[1033] Terminal

[1034] The device receives the new evacuation route information and notifies the user again, updating the map display and voice guidance.

[1035] Input: Updated evacuation route information

[1036] Output: New evacuation route information notified to the user

[1037] Through these seven steps, the system of this invention realizes efficient and safe evacuation support. By collecting and analyzing data in real time and dynamically updating routes based on user feedback, it is possible to provide optimal evacuation routes at all times.

[1038] (Application example 1)

[1039] 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."

[1040] Conventional evacuation support systems are unable to fully utilize real-time data, making it difficult to provide rapid evacuation routes that respond to changes in congestion. Furthermore, they are unable to flexibly recalculate routes using user feedback, which means they are unable to respond to dynamic environmental changes. Furthermore, the means of notifying users of evacuation routes are limited, and there is a need for information to be provided in a format that is intuitively easy for users to understand. There is a need for a system that can solve these problems and support safe and efficient evacuation during disasters.

[1041] 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.

[1042] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes, means for generating evacuation routes suitable for individual users based on the prediction, means for providing the generated evacuation route information to a user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for notifying the user of the evacuation route information based on the user's current location by voice and map using a smart device. This enables real-time data analysis and route provision, thereby realizing intuitive and immediate evacuation support for users.

[1043] "Weather data" refers to information about weather and weather conditions, including precipitation, wind speed, temperature, humidity, and air pressure.

[1044] "Traffic information" refers to information relating to road traffic conditions, including congestion, road closures, accident information, and the like.

[1045] "Real-time data" refers to the latest information at the current time, and is data that is collected and processed immediately.

[1046] A "model" is an algorithm or mathematical framework for predicting congestion along evacuation routes based on collected data.

[1047] A "user terminal" is an information communication device used by a user, and includes a smartphone, a tablet, smart glasses, etc.

[1048] "Feedback" is information provided by users based on local conditions and experiences.

[1049] "Evacuation routes" refer to recommended roads and routes for safe evacuation in the event of a disaster.

[1050] A "smart device" is an electronic device with advanced functionality that can connect to the Internet.

[1051] "Audio guidance" refers to a means of providing information to a user through audio.

[1052] "Visual map display" is a function that visually displays a map and provides route information and the like to the user.

[1053] An "evacuation support system" is an overall system for supporting users' evacuation in the event of a disaster.

[1054] MODE FOR CARRYING OUT THE INVENTION

[1055] System Overview

[1056] The system of this invention is designed to support efficient and safe evacuation in the event of a disaster. It collects real-time data, such as weather and traffic information, and analyzes that data to predict congestion along evacuation routes. Based on user feedback, it updates evacuation route information in real time and provides optimal evacuation routes.

[1057] Server Features

[1058] The server has the following features:

[1059] Real-time data collection: The server collects weather and traffic data in real time using external APIs (e.g., weather agencies and traffic information services).

[1060] Data analysis and model generation: Analyze the collected data and generate a model to predict the congestion status of evacuation routes. This modeling is performed using machine learning libraries such as TensorFlow.

[1061] Evacuation route generation: Based on the results of data analysis, an evacuation route appropriate for each individual user is generated. Multiple route candidates are evaluated and the least congested and safest route is selected.

[1062] Information provision: The generated evacuation route information is sent to the user's device.

[1063] Feedback analysis: Evacuation route information is updated in real time based on user feedback.

[1064] User device functions

[1065] The user terminal has the following features:

[1066] Receiving and displaying information: Receives evacuation route information sent from the server and notifies the user on the smart device with a visual map display and voice guidance.

[1067] Feedback submission: Provides an interface for users to input feedback and sends it to the server. Users can report traffic conditions, congestion, impassable areas, etc. in real time.

[1068] User Behavior

[1069] A user interacts with the system in the following way:

[1070] 1. Checking evacuation routes: When a disaster occurs, the user launches the application and receives notification of evacuation routes.

[1071] 2. Begin evacuation: Follow the map display and voice guidance on your smart device to proceed along the evacuation route.

[1072] 3. Providing feedback: Enter feedback about obstacles and congestion encountered during evacuation and send it to the server.

[1073] Specific examples

[1074] Let's take the example of a large-scale earthquake and a user evacuating. The server obtains real-time data from meteorological agencies and traffic information services. This data is analyzed using TensorFlow to generate an optimal evacuation route. The generated evacuation route information is sent to the user's smartphone, where the user receives a map display and voice guidance through the application. If the user encounters an impassable road or a congested area along the way, they enter that information in the application and send feedback to the server. The server reanalyzes the evacuation route based on this feedback and sends the new route information to the user's smartphone.

[1075] Prompt Sentence Examples

[1076] The user's current location is "35.6895, 139.6917" (center of the city). Please predict the best evacuation route for this user based on real-time weather and traffic information. Please take into account the following feedback ("Road impassable due to traffic jam", "Location: In front of Shibuya Station").

[1077] This example uses prompt sentences to demonstrate how a generative AI model can predict optimal evacuation routes and update them in real time based on feedback information.

[1078] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1079] Step 1:

[1080] The server collects real-time data such as weather data and traffic information. It uses external APIs (for example, APIs of meteorological agencies or APIs of traffic information services) to obtain data such as precipitation, wind speed, road congestion, and road closure information. It processes the data obtained from the external APIs as input, converts it into an appropriate format, and saves it in an internal data store. The output is the collected real-time data.

[1081] Step 2:

[1082] The server analyzes the collected real-time data and generates a model that predicts the congestion status of evacuation routes. It uses TensorFlow, a machine learning library, to create a predictive model based on past and current data. It uses the collected real-time data and past evacuation data as input and performs data analysis. The output is a model that predicts the congestion status of evacuation routes.

[1083] Step 3:

[1084] The server generates an evacuation route suited to each individual user based on the generated model. It analyzes the model's prediction results, evaluates multiple route candidates, and selects the safest route. The inputs are the user's current location, real-time data, and the output of the predictive model. The output is evacuation route information optimized for each user.

[1085] Step 4:

[1086] The server sends the generated evacuation route information to the user's device. The notification is sent via the Internet in a format that corresponds to the type of device used (smartphone, tablet, etc.). The input is the generated evacuation route information, and the output is the route information received by the user's device.

[1087] Step 5:

[1088] The user device notifies the user of the received evacuation route information using a visual map display and voice guidance. The user checks the route information through the application and begins evacuation. The input is the evacuation route information sent from the server, and the output is a notification to the user.

[1089] Step 6:

[1090] Users provide feedback on the congestion and impassable areas they encounter during evacuation via their terminals. The application has an interface for inputting feedback, and the information entered by the user is sent to the server. The input is feedback data from the user, and the output is the transmission of the feedback data to the server.

[1091] Step 7:

[1092] The server reanalyzes the evacuation route information based on the received feedback information and generates a new optimal route. The reanalysis uses real-time data and feedback information, and the generated new route information is sent back to the user terminal. The input is user feedback and real-time data, and the output is updated evacuation route information.

[1093] Step 8:

[1094] The user device receives the updated evacuation route information and notifies the user again. This allows the user to continue evacuating safely according to the latest evacuation route. The input is the updated route information sent from the server, and the output is the notification to the user.

[1095] 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.

[1096] System Overview

[1097] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather data and traffic information to predict congestion on evacuation routes and provides evacuation routes that are suitable for each individual user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides evacuation route guidance that is appropriate for the user's condition.

[1098] System configuration

[1099] This system consists of three elements: a server, a terminal, and a user. By adding an emotion engine, it can be customized based on the user's emotional state.

[1100] server

[1101] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems, such as precipitation, wind speed, earthquake information, road congestion, and road closure information.

[1102] Data analysis and model generation: Analyze collected data and use AI models to predict congestion along evacuation routes. Use machine learning algorithms to make highly accurate predictions based on past data and current conditions.

[1103] Evacuation route generation: The system obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[1104] Information provision: The generated evacuation route information is sent to the user's device. The data format is converted to JSON or XML and sent to the device via API.

[1105] Feedback analysis: Update route information in real time based on user feedback.

[1106] Terminal

[1107] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and guided by audio guidance.

[1108] Emotion engine: Analyzes voice, facial expressions, heart rate, etc. to recognize the user's emotions and assess their stress level. Based on the recognition results, the system adjusts evacuation route guidance methods.

[1109] Feedback transmission: Local information and congestion status are provided by the user through an input interface and sent to the server.

[1110] User

[1111] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[1112] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation will be provided via the terminal.

[1113] Specific examples

[1114] Evacuation scenario in the event of an earthquake

[1115] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[1116] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[1117] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[1118] 4. Adjustment by emotion engine: The emotion engine of the device evaluates the user's stress level and adjusts evacuation route guidance. For example, if the user is in a high stress state, the instructions will be simplified and a reassuring voice guidance will be provided.

[1119] 5. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user will provide feedback on this information to the server via their device.

[1120] 6. Reanalysis and route update: The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it to the terminal again.

[1121] 7. Re-notification to the user: The device receives the new route information and notifies the user. The user continues evacuation along the new route.

[1122] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state. By always providing optimal route information and guidance, evacuation can be carried out quickly and reliably in the event of a disaster.

[1123] The processing flow will be explained below.

[1124] Step 1: Getting real-time data

[1125] The server obtains real-time data such as weather data and traffic information. It collects earthquake information, precipitation, wind speed, etc. from meteorological agencies' APIs, and obtains road congestion, traffic accident information, and road closure information from traffic management systems.

[1126] Step 2: Data analysis and model generation

[1127] The server analyzes the real-time data it acquires and generates a model to predict congestion along evacuation routes. Specifically, it preprocesses the data and applies machine learning algorithms to train a congestion prediction model based on past data and current conditions. The generated model can predict congestion in each area with high accuracy.

[1128] Step 3: Generate evacuation routes

[1129] The server generates an evacuation route suited to each individual user based on the analysis results. The user's current location is identified using GPS data, and multiple route candidates are generated. Congestion predictions and risk assessments are performed for each route candidate, and the safest and most efficient route is selected.

[1130] Step 4: Provide evacuation route information

[1131] The server provides the generated evacuation route information to the user's device. The generated route information is converted into an appropriate data format (JSON or XML) and sent to the device via API with end-to-end encrypted communication.

[1132] Step 5: Evacuation route notification and guidance

[1133] The device notifies the user of the evacuation route information it receives. Specifically, it uses pop-up notifications and alert sounds to prompt the user to begin evacuation. Furthermore, it uses a map display function to visually display the route and a voice guidance function to guide the user.

[1134] Step 6: Emotion Recognition with the Emotion Engine

[1135] The device's emotion engine recognizes the user's emotional state. The emotion engine evaluates the user's stress level and tension by analyzing the user's voice, facial expressions, heart rate, etc. As a specific example, it analyzes the tone of the user's voice from voice input to determine the stress level.

[1136] Step 7: Emotion-Based Guidance Adjustments

[1137] The device adjusts evacuation route guidance based on the results of the emotion engine. If the user is judged to be in a high-stress state, it simplifies the instructions and provides reassuring voice guidance. If the user is calm, it provides detailed instructions.

[1138] Step 8: Provide feedback

[1139] During evacuation, users provide feedback using their devices, reporting congested areas and impassable locations using a simple input form or voice input, and the devices then send this information to the server.

[1140] Step 9: Analyze feedback and update route in real time

[1141] The server analyzes the received feedback and updates evacuation route information in real time. It recalculates routes based on new obstacle and congestion information and generates the latest optimal route. The updated route information is then sent back to the device.

[1142] Step 10: Re-informing and re-guiding

[1143] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on the map and voice guidance is provided again. The user follows the instructions to continue evacuating safely.

[1144] This series of processing steps not only enables the server, terminal, and user to work together to achieve efficient and safe evacuation in real time, but also provides more appropriate evacuation support by providing customized guidance based on the user's emotional state.

[1145] Example 2

[1146] 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."

[1147] Conventional evacuation systems have had problems with difficulty in predicting congestion in real time and providing optimal evacuation routes for individual users, and they were unable to provide evacuation guidance that took into account the user's emotional state. This prevented efficient and safe evacuation, potentially increasing user stress and confusion. Furthermore, there was a lack of a mechanism for utilizing feedback to update route information in real time, which posed a risk of reducing the effectiveness of evacuation routes.

[1148] 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.

[1149] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating multiple evacuation route candidates suitable for each user based on the prediction and evaluating them to select the optimal evacuation route, means for converting the generated evacuation route information into a data format and providing it to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information in real time, and means for analyzing voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting the evacuation route guidance method based on the user's stress level. This enables accurate congestion prediction in real time, provision of evacuation routes tailored to each individual user, and appropriate evacuation guidance based on the user's emotional state.

[1150] "Weather data" refers to data related to weather elements such as precipitation, wind speed, and earthquake information.

[1151] "Traffic information" refers to data related to traffic, such as road congestion and road closure information.

[1152] "Real-time data" means the most up-to-date data about current conditions or status.

[1153] A "machine learning algorithm" is an algorithm that analyzes collected data to find patterns and trends and make predictions and classifications.

[1154] An "evacuation route" is a route that a user uses to safely evacuate in the event of a disaster.

[1155] "Congestion status" refers to the degree of concentration of people and vehicles in a particular location or route.

[1156] "Means for generating a model" refers to the means for creating a machine learning model for making predictions and classifications based on collected data.

[1157] "Feedback" refers to local information, opinions, impressions, etc. obtained from users.

[1158] A "data format" is a standard way of storing, displaying, or transmitting data.

[1159] "Emotional state" refers to the user's current emotional or mental state.

[1160] The "stress level" is a value that indicates the degree of stress that the user is feeling.

[1161] The "means for adjusting the evacuation route guidance method" is a means for optimizing the evacuation route guidance method based on the user's emotional state and stress level.

[1162] The system of the present invention is designed to support users in evacuating safely and efficiently in the event of a disaster. The system is mainly composed of three elements: a server, a terminal, and a user. By further integrating an emotion engine, the system is customized based on the user's emotional state. Specific embodiments of each element are shown below.

[1163] Server Processing

[1164] The server is responsible for a series of processes: collection, analysis, generation, provision, and updating. First, to collect real-time data such as weather data and traffic information, the server connects to the API of each data source (for example, the API of a weather information service or the API of a traffic information service) and obtains the real-time data.

[1165] The server then analyzes the acquired data and uses machine learning algorithms (for example, frameworks such as TensorFlow or PyTorch) to predict congestion along evacuation routes. The model generated by this analysis makes highly accurate congestion predictions based on past and real-time data.

[1166] The server generates multiple evacuation route candidates based on this forecast data and evaluates the congestion and risk of each candidate. After selecting the optimal evacuation route, it converts the information into JSON or XML format and sends it to the user's device via an API. It also receives feedback from users in real time and updates the evacuation route information.

[1167] Terminal handling

[1168] The device receives the evacuation route information sent from the server and notifies the user. Notifications are made visually using a map display (for example, using Google Maps API) and through voice guidance.

[1169] The device is also equipped with an emotion engine that recognizes the user's emotional state by analyzing voice, facial expressions, heart rate, etc. This analysis uses emotion recognition APIs such as AWS Rekognition and IBM Watson. Based on the user's emotional state and stress level, it is possible to adjust evacuation route guidance methods (such as simplified instructions or reassuring voice guidance).

[1170] The device also provides an interface for users to input local information and congestion status, and has the function of sending user feedback to the server, which keeps the evacuation route information always up-to-date.

[1171] User operations

[1172] Users check the evacuation route information displayed on their device, select a safe route, and begin evacuation. Information about congestion and impassable areas encountered during evacuation can be provided to the server as feedback via the device. This improves the effectiveness of evacuation routes and also helps support other evacuees.

[1173] Specific examples

[1174] For example, if a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API, analyzes the data, and predicts congestion in the affected area. Based on this, it generates an optimal evacuation route model and sends it to the user's device. The device receives this information and notifies the user through a map display and voice guidance. The emotion engine also evaluates the user's stress level and provides appropriate guidance.

[1175] Example prompt sentence:

[1176] "We are designing a system to generate appropriate AI models and assist in safe evacuation. How can we improve efficiency and safety by incorporating user emotion recognition into evacuation route guidance?"

[1177] This allows users to quickly identify safe and efficient evacuation routes, enabling them to evacuate while reducing stress.

[1178] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1179] Step 1:

[1180] Real-time data collection

[1181] The server connects to the APIs of meteorological agencies and traffic management systems to collect real-time data. This process obtains data such as precipitation, wind speed, earthquake information, road congestion, and road closure information. Specifically, the server sends a data request to the API, receives a response in JSON format, and analyzes it. The input is the request from the API, and the output is the analyzed weather data and traffic information.

[1182] Step 2:

[1183] Data Preprocessing

[1184] The real-time data acquired by the server is integrated into a single dataset, and data normalization and missing value imputation are performed. This process is performed using the Python Pandas library. The input is raw real-time data, and the output is a preprocessed integrated dataset in a format suitable for analysis.

[1185] Step 3:

[1186] Training a machine learning model

[1187] The server trains machine learning models using the preprocessed dataset. It uses TensorFlow or PyTorch to build regression and time series forecasting models. The input is the preprocessed integrated dataset, and the output is a trained predictive model. Specific operations include splitting the dataset, defining the model, training it, and evaluating it.

[1188] Step 4:

[1189] Running a prediction

[1190] The server uses the trained model to predict the congestion status of evacuation routes based on current data. The input is current real-time data, and the output is the congestion prediction results for each route. Specific operations include inputting data into the model, obtaining prediction results, and evaluating the results.

[1191] Step 5:

[1192] Generate evacuation routes

[1193] The server obtains the user's current location (GPS data) and generates multiple candidate evacuation routes. Routes are calculated using map databases such as OpenStreetMap, and a model is used to predict congestion and assess risk for each route. The input is the user's current location and the congestion prediction results, and the output is multiple evaluated evacuation routes. Specific operations include generating candidate routes, assessing congestion, and selecting the optimal route.

[1194] Step 6:

[1195] Providing route information

[1196] The server converts the generated evacuation route information into JSON or XML format and sends it to the user's device via API. The input is the evaluated evacuation route, and the output is the route information sent to the user's device. Specific operations include converting the data format and sending an HTTP request.

[1197] Step 7:

[1198] Receiving information and notifications via device

[1199] The terminal receives evacuation route information sent from the server and notifies the user. Visually, it uses a map display and voice guidance. The input is route information from the server, and the output is a notification to the user. Specific operations include parsing data, displaying a map, and starting voice guidance.

[1200] Step 8:

[1201] Running the Emotion Engine

[1202] The device collects data from sensors, such as the user's voice, facial expressions, and heart rate, and analyzes their emotional state. AWS Rekognition and IBM Watson APIs are used to identify the user's stress level and emotional state. The input is sensor data, and the output is the emotional assessment result. The specific operations are data collection and emotion analysis.

[1203] Step 9:

[1204] Emotion-based guidance adjustment

[1205] The device adjusts the evacuation route guidance method based on the results of emotion analysis. For example, if the user is in a high-stress state, it simplifies the instructions and selects a voice guidance that provides a sense of security. The input is the emotion evaluation result, and the output is the adjusted guidance method. The specific operation is to select the guidance and display / execute the voice guidance.

[1206] Step 10:

[1207] Send Feedback

[1208] The user inputs the local situation they encountered during evacuation into the terminal and sends the information to the server. The input is the feedback from the user, and the output is the feedback data sent to the server. The specific operation is to provide a data input form and send an HTTP request.

[1209] Step 11:

[1210] Feedback analysis and route updates

[1211] The server receives feedback from users and updates evacuation route information in real time. It then reapplies the machine learning model to generate a new optimal route and sends it back to the user's device. The input is the feedback data, and the output is the updated evacuation route information. The specific operations are data analysis, route recalculation, and information retransmission.

[1212] (Application example 2)

[1213] 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."

[1214] In modern society, there is a demand for rapid and safe evacuation in the event of sudden disasters such as meteorological disasters, fires, and earthquakes. However, conventional evacuation support systems lack the ability to collect and analyze data in real time, and are unable to provide evacuation guidance that takes into account the user's emotional state, which can increase confusion and stress. The present invention aims to solve these problems and achieve safe and efficient evacuation.

[1215] 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 means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting the congestion status of evacuation routes, means for generating an evacuation route appropriate for each user based on the prediction, means for providing the generated evacuation route information to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for analyzing the user's voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting evacuation route guidance. This makes it possible to provide an appropriate evacuation route in real time taking the user's emotional state into consideration.

[1216] "Weather data" refers to information relating to weather, such as weather, precipitation, wind speed, and temperature.

[1217] "Traffic information" refers to information relating to traffic, such as road traffic conditions, congestion information, and road closures.

[1218] "Real-time data" is information data that is collected in the present and can be used immediately.

[1219] "Analysis" means examining collected data in detail to understand its meaning and characteristics.

[1220] An "evacuation route" is a route used to move to a safe location in the event of a disaster.

[1221] "Crowding status" is information indicating the degree or density of congestion within a certain range.

[1222] A "model" is a mathematical or computational representation used to understand and predict a system or phenomenon.

[1223] A "user terminal" is an electronic device such as a computer or smartphone used by a user.

[1224] "Feedback" is information or opinions provided by users.

[1225] "Emotional state" refers to an individual's psychological state, such as stress, relief, or tension.

[1226] "Audio guidance" is a method of providing guidance information to a user using voice.

[1227] "Visual map display" is a method of presenting information visually by displaying a map on a screen.

[1228] A "collection means" is a device or method for acquiring data.

[1229] "Providing means" refers to the device or method used to deliver information to users.

[1230] An "update means" is a device or method for updating content based on the latest information or data.

[1231] An "emotion recognition means" is a device or method for analyzing and recognizing a user's emotional state.

[1232] System Overview

[1233] This invention is a system that uses real-time data to support efficient and safe evacuation during disasters. The main components are a server, a terminal, and a user, and an emotion engine is added to these to provide evacuation guidance according to the user's emotional state.

[1234] server

[1235] The server collects real-time data such as weather and traffic information and generates a model to predict congestion on evacuation routes. Specifically, the server uses the following software and hardware:

[1236] Real-time data collection

[1237] The server collects data using APIs of meteorological agencies and traffic management systems. For example, it obtains precipitation, wind speed, earthquake information, road congestion status, etc. from the OpenWeatherMap API and Google Maps API.

[1238] Data analysis and model generation

[1239] Analyze the collected data and use a generative AI model (e.g., TensorFlow) to predict congestion along evacuation routes. Build a highly accurate predictive model based on past data and the current situation.

[1240] Generate and provide evacuation routes

[1241] The system obtains the user's current location information from GPS data and generates route candidates to the optimal evacuation shelter. The generated route candidates are provided to the device in JSON or XML format.

[1242] Feedback Analysis

[1243] It also includes a function to analyze user feedback in real time and update evacuation route information.

[1244] Terminal

[1245] The terminal is a user device such as a smartphone or tablet, which receives evacuation route information sent from the server and provides it to the user. It also uses an emotion engine to recognize the user's emotional state and adjust evacuation route guidance accordingly.

[1246] Information Reception and Notification

[1247] The device receives the data sent from the server and notifies the user through a visual map display and voice guidance, using applications written in Flutter and React Native.

[1248] Emotion Engine

[1249] It uses Azure Cognitive Services and Google Cloud Vision API to analyze data such as voice, facial expressions, and heart rate, and its emotion engine assesses the user's stress level and adjusts evacuation route guidance.

[1250] Send Feedback

[1251] It has an interface to collect feedback from users and sends the collected data to a server, which allows for real-time optimization of evacuation route information.

[1252] User

[1253] Users can check evacuation route information through their devices and take evacuation actions, while also providing feedback on the situations they encounter during evacuation.

[1254] Checking evacuation routes and taking evacuation actions

[1255] Based on the evacuation route information displayed on the device, users can confirm a safe route and begin evacuation procedures.

[1256] Providing Feedback

[1257] The device reports to the server any congestion or impassable areas encountered during evacuation.

[1258] Specific examples

[1259] Evacuation scenario in the event of an earthquake

[1260] 1. The server acquires earthquake information

[1261] The server obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API.

[1262] 2. Analysis and Model Generation

[1263] The collected information is analyzed, and generative AI models such as TensorFlow are used to predict congestion on evacuation routes and generate an optimal evacuation route model.

[1264] 3. Providing evacuation routes

[1265] The server provides evacuation route information to the terminal, which receives it and notifies the user through voice guidance and visual map display.

[1266] 4. Emotional Engine Adjustment

[1267] The device's emotion engine assesses the user's stress level and adjusts evacuation route guidance accordingly. For example, if the user is in a high stress state, the device will simplify instructions and provide reassuring voice guidance.

[1268] 5. Evacuation behavior and feedback

[1269] The user begins evacuation by following the provided evacuation route. If the user encounters a road that has been severely damaged and is impassable along the way, the user's device will provide feedback to the server.

[1270] 6. Reanalysis and Route Updates

[1271] The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it back to the terminal.

[1272] 7. Re-notifying the user

[1273] The terminal receives the new route information again and notifies the user.

[1274] Prompt Sentence Examples

[1275] "predict_evacuations_route(current_weather, traffic_data, user_location)"

[1276] "analyze_emotion(user_voice, user_facial_expression, user_heart_rate)"

[1277] "traffic_conditions.update({"location": "X", "status": "closed"})"

[1278] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state.

[1279] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1280] Step 1:

[1281] The server collects weather and traffic information. The server obtains real-time data from the APIs of meteorological agencies (e.g., OpenWeatherMap API) and traffic information systems (e.g., Google Maps API). Input data includes precipitation, wind speed, earthquake information, road congestion status, etc., and stores this data in a database.

[1282] Step 2:

[1283] The server analyzes the collected data and uses a generative AI model (e.g., TensorFlow) to predict the congestion status of evacuation routes. The input is the weather data and traffic information collected in Step 1, and based on this, a machine learning algorithm processes and calculates the data. The output is a congestion prediction for each evacuation route.

[1284] Step 3:

[1285] The server generates an evacuation route suitable for each user based on congestion predictions. The user's current location information (GPS data) is also used as input. The server generates multiple evacuation route candidates and evaluates the efficiency and safety of each route. The optimal evacuation route information is generated in JSON format.

[1286] Step 4:

[1287] The server provides the generated evacuation route information to the user terminal. The input is the optimal evacuation route information generated in step 3, which is sent to the terminal via API. The terminal receives this information and starts visual map display and audio guidance.

[1288] Step 5:

[1289] The device collects the user's voice, facial expressions, heart rate, etc. and analyzes them using an emotion engine. The input is the user's voice data, facial images, heart rate data, etc., and this data is analyzed using Azure Cognitive Services and Google Cloud Vision API. The output is the user's stress level and emotional state.

[1290] Step 6:

[1291] The device adjusts evacuation route guidance based on the user's emotional state. The inputs are the emotion analysis results from step 5 and the evacuation route information from step 4. For example, if the user is in a high-stress state, the device simplifies instructions and provides reassuring voice guidance.

[1292] Step 7:

[1293] The user begins evacuation by following the evacuation route. If the user encounters an impassable road or a crowded situation along the way, the user sends feedback to the server via the device. The input is the user's feedback information, which is then sent to the server.

[1294] Step 8:

[1295] The server receives feedback from users and updates the evacuation route information. The input is the on-site feedback data obtained in step 7, and based on this, it analyzes the data again using a machine learning algorithm to generate a new evacuation route model. The output is the updated evacuation route information.

[1296] Step 9:

[1297] The server again sends the new evacuation route information to the terminal. The input is the new evacuation route information generated in step 8, and sends this to the terminal via the API. The terminal receives the new route information and notifies the user.

[1298] In this way, real-time data and an emotion engine are combined to support efficient and safe evacuation according to the user's emotional state.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] [Fourth embodiment]

[1303] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1304] 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.

[1305] 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).

[1306] 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.

[1307] 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.

[1308] 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).

[1309] 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.

[1310] 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.

[1311] 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.

[1312] 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.

[1313] 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.

[1314] 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.

[1315] 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."

[1316] System Overview

[1317] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather and traffic information to predict congestion on evacuation routes and provides appropriate evacuation routes to individual users. It also has a function to reflect user feedback and update evacuation route information.

[1318] System configuration

[1319] This system is mainly composed of three elements: the server, the terminal, and the user. The role of each will be explained in detail below.

[1320] server

[1321] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems. For example, weather data includes precipitation, wind speed, and earthquake information, and traffic information includes road congestion and road closure information.

[1322] Data analysis and predictive model generation: Collected data is analyzed and an AI model is used to predict congestion along evacuation routes. Machine learning algorithms are used to make highly accurate predictions based on past data and the current situation.

[1323] Evacuation route generation: Based on the analysis results, the system generates the optimal route from the user's current location to the evacuation shelter. It evaluates multiple route candidates and selects the least congested and safest route.

[1324] Providing information: The generated evacuation route information is sent to the user's device.

[1325] Feedback analysis: Route information is updated in real time based on user feedback.

[1326] Terminal

[1327] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and is also provided with audio guidance.

[1328] Feedback transmission: Provides an interface for users to input local information and congestion status, and sends this to the server.

[1329] User

[1330] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[1331] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation is sent via the device.

[1332] Specific examples

[1333] Evacuation scenario in the event of an earthquake

[1334] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[1335] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[1336] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[1337] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user feeds that information back to the server via their device.

[1338] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[1339] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[1340] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[1341] The processing flow will be explained below.

[1342] Step 1: Getting real-time data

[1343] The server obtains real-time data such as weather data and traffic information. It calls the APIs of meteorological agencies and traffic management systems to collect data such as weather information for each region, earthquake information, traffic congestion information, and the availability of evacuation shelters.

[1344] Step 2: Data analysis and model generation

[1345] The server analyzes real-time data acquired and uses AI models to predict congestion along evacuation routes. The data is preprocessed and congestion predictions are made using machine learning algorithms and simulation models. The accuracy of the generated models is also evaluated, and the models are adjusted as necessary.

[1346] Step 3: Generate evacuation routes

[1347] The server generates an evacuation route suited to each individual user based on the analysis results. It obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[1348] Step 4: Provide evacuation route information

[1349] The server generates evacuation route information and sends it to the user's device. The data format is converted to JSON or XML and sent to the device via an API. During this process, the data is encrypted to ensure security.

[1350] Step 5: Evacuation route notification and guidance

[1351] The device notifies the user of the evacuation route information it has received. It uses pop-up notifications and sound alerts to encourage the user to begin evacuation. It visually displays the route on a map and provides route guidance through audio guidance.

[1352] Step 6: Provide feedback

[1353] Users provide feedback through their devices. They report congested or impassable areas during evacuation using an input form or voice input. The devices then send this feedback information to the server.

[1354] Step 7: Analyze feedback and update route

[1355] The server analyzes the received feedback and updates evacuation route information in real time, recalculating routes to reflect new information about obstacles and congestion, and generating the latest optimal routes.

[1356] Step 8: Re-informing and re-guiding

[1357] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on a map and re-guided by voice guidance. The user continues evacuating according to the new route information.

[1358] This series of processing steps enables the server, terminals, and users to work together to achieve efficient and safe evacuation in real time.

[1359] Example 1

[1360] 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."

[1361] In modern society, rapid and safe evacuation in the event of a disaster is extremely important. However, there are many challenges in collecting and analyzing real-time weather and traffic data and providing optimal evacuation routes. In particular, complex data analysis, rapid information provision, and the ability to incorporate user feedback in real time are required. Conventional systems have difficulty integrating and effectively executing these elements, resulting in issues such as reduced evacuation efficiency and a compromised safety.

[1362] 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.

[1363] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating evacuation routes suitable for each user based on the prediction and evaluating multiple route candidates to select the optimal route, means for providing the generated evacuation route information to a user terminal and notifying the user using audio guidance and a visual map display, and means for receiving feedback from the user via the user terminal and reanalyzing and updating the route information in real time, thereby enabling the provision of evacuation routes with high speed and accuracy and optimization that reflects user feedback in real time.

[1364] "Weather data" refers to various information related to meteorological phenomena such as temperature, precipitation, wind speed, air pressure, earthquake intensity and epicenter.

[1365] "Traffic information" refers to various information related to traffic flow and road usage, such as road congestion, road closures, traffic accident occurrences, and congestion information.

[1366] "Real-time data" refers to up-to-date data that reflects current conditions, including weather and traffic information.

[1367] A "machine learning algorithm" refers to a computational method that learns patterns from past data and makes predictions and decisions when new data is given.

[1368] An "evacuation route" refers to the route a user takes to travel from their current location to a specific evacuation shelter or safe location.

[1369] "Congestion" refers to the amount of traffic and concentration of people on a particular road or route.

[1370] "Predictive model" refers to a mathematical or computational method used to predict specific future conditions based on collected data.

[1371] "Route update" refers to the process of recalculating existing evacuation route information and re-providing optimal routes based on user feedback and newly collected data.

[1372] "Voice guidance" refers to a method of giving instructions and guidance to a user through voice.

[1373] "Visual map display" refers to a method of providing route information to a user using a graphical map.

[1374] "Feedback" refers to reports provided by users regarding local information and congestion during evacuation.

[1375] "User terminal" refers to an electronic device, such as a smartphone or tablet, that a user uses to receive and send information.

[1376] This invention is a system that supports efficient and safe evacuation in the event of a disaster. It consists of three elements: a server, a terminal, and a user, and realizes advanced evacuation support using real-time data.

[1377] System Overview

[1378] The main features of the system are as follows:

[1379] 1. Real-time data collection

[1380] 2. Data analysis and predictive model generation

[1381] 3. Generating optimal evacuation routes

[1382] 4. Providing evacuation route information

[1383] 5. Receiving user feedback and updating route information

[1384] Hardware and software used

[1385] server

[1386] Hardware: Server computer

[1387] Software: APIs for data collection (e.g., OpenWeatherMap API, Google Maps API), programming libraries for data analysis (e.g., Python, pandas, scikit-learn, TensorFlow), algorithms for path generation (e.g., Dijkstra algorithm, A algorithm)

[1388] Terminal

[1389] Hardware: Smartphones, tablets

[1390] Software: Map display apps (e.g., Google Maps), TTS (text-to-speech) engine for voice guidance

[1391] User

[1392] Hardware: Smartphones, tablets

[1393] Software: Evacuation route display app, feedback input interface

[1394] Specific processing

[1395] server

[1396] The server collects weather and traffic data in real time. It periodically retrieves the data using an API and stores it in a database. The collected data is then cleaned (by filling in missing values ​​and removing outliers) and a machine learning model is trained. Specifically, a random forest and LSTM model are used to predict the congestion status of evacuation routes.

[1397] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. This uses the Dijkstra algorithm and the A algorithm. The generated routes are evaluated for congestion and safety to select the most suitable one. The selected route information is sent to the user's device in JSON format.

[1398] Terminal

[1399] The device receives evacuation route information sent from the server and notifies the user. It uses a map display application to visually display the route and a TTS engine to provide voice guidance. It provides an interface that allows the user to input feedback information (e.g., congestion status and impassable areas) during evacuation. The input feedback information is sent to the server.

[1400] User

[1401] The user begins evacuation based on the evacuation route information. For example, if an earthquake occurs, the user will follow the route information displayed on the device and head to the most suitable evacuation shelter. If the user encounters congestion or impassable conditions along the way, the user will provide this information via the device. This allows the server to reanalyze the data and receive updated route information.

[1402] Specific examples

[1403] Evacuation scenario in the event of an earthquake

[1404] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[1405] 2. Analysis and model generation: The collected information is analyzed and congestion predictions are made for the affected areas. An LSTM model is used for this analysis.

[1406] 3. Providing evacuation routes: The server generates the optimal evacuation route and sends it to the user's device. The device receives it and notifies the user using a map display app and a TTS engine.

[1407] 4. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, that information is fed back to the user via the device.

[1408] 5. Reanalysis and route update: Based on the received feedback, the server reanalyzes the evacuation route, generates a new optimal route, and sends it again to the terminal.

[1409] 6. Re-notification to the user: The device receives the new route information and notifies the user. The user continues to evacuate safely by following the new route.

[1410] Example prompts to input to the generative AI model

[1411] "Based on the latest earthquake information, please tell me the best evacuation route from point A to point B."

[1412] "Enter your current location and destination and we'll predict and provide you with the least congested evacuation route."

[1413] In this way, the system of the present invention utilizes real-time data to support efficient and safe evacuation. By updating route information based on dynamic user feedback, evacuation can be carried out more quickly and reliably in the event of a disaster.

[1414] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1415] Step 1:

[1416] Real-time data collection

[1417] server

[1418] The server calls the APIs of meteorological agencies and traffic management systems to collect the latest weather and traffic information. Specifically, it sends an HTTP request to the API endpoint and receives a JSON-formatted response. This data includes precipitation, wind speed, temperature, earthquake intensity, epicenter information, road congestion status, and road closure information. The collected data is stored in an internal database.

[1419] Input: Weather and traffic data retrieved from API endpoints

[1420] Output: Real-time data stored in an internal database

[1421] Step 2:

[1422] Data preprocessing and analysis

[1423] server

[1424] The server preprocesses the collected data. Specifically, it complements missing values, removes outliers, and formats the data. This process uses the Python pandas library. After preprocessing is complete, the server analyzes the data using a machine learning algorithm (e.g., random forest or LSTM model) to generate a model for predicting the congestion status of evacuation routes.

[1425] Input: Stored real-time data

[1426] Output: Preprocessed data and predictive model

[1427] Step 3:

[1428] Evacuation route generation and evaluation

[1429] server

[1430] Based on the analysis results, the server generates multiple routes from the user's current location to the evacuation shelter. To do this, it uses road network data and calculates the shortest or optimal route using the Dijkstra algorithm or the A algorithm. The generated routes are evaluated taking into account congestion and safety, and the optimal route is selected.

[1431] Input: Prediction model, user's current location, location of evacuation shelter

[1432] Output: Evaluated optimal evacuation route

[1433] Step 4:

[1434] Providing evacuation route information

[1435] server

[1436] The server sends optimal evacuation route information to the user's device in JSON format.

[1437] Terminal

[1438] The device analyzes the received evacuation route information and notifies the user. Specifically, it uses a map display application (e.g., Google Maps) to visually display the route and uses a TTS engine to provide voice guidance.

[1439] Input: Evacuation route information in JSON format sent from the server

[1440] Output: Map display and evacuation route notification with voice guidance

[1441] Step 5:

[1442] Receiving feedback from users

[1443] User

[1444] During evacuation, users report impassable areas and congestion via their devices.

[1445] Terminal

[1446] The terminal collects feedback information from the user and transmits it to the server.

[1447] Input: User-entered feedback information

[1448] Output: Feedback information sent to the server

[1449] Step 6:

[1450] Analyzing feedback and updating routes

[1451] server

[1452] The server analyzes the received feedback information and recalculates and updates evacuation route information as necessary, again using the predictive model and route generation algorithm.

[1453] Input: User feedback information

[1454] Output: Updated evacuation route information

[1455] Step 7:

[1456] Providing updated route information

[1457] server

[1458] The server then transmits the updated evacuation route information to the user's terminal again.

[1459] Terminal

[1460] The device receives the new evacuation route information and notifies the user again, updating the map display and voice guidance.

[1461] Input: Updated evacuation route information

[1462] Output: New evacuation route information notified to the user

[1463] Through these seven steps, the system of this invention realizes efficient and safe evacuation support. By collecting and analyzing data in real time and dynamically updating routes based on user feedback, it is possible to provide optimal evacuation routes at all times.

[1464] (Application example 1)

[1465] 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."

[1466] Conventional evacuation support systems are unable to fully utilize real-time data, making it difficult to provide rapid evacuation routes that respond to changes in congestion. Furthermore, they are unable to flexibly recalculate routes using user feedback, which means they are unable to respond to dynamic environmental changes. Furthermore, the means of notifying users of evacuation routes are limited, and there is a need for information to be provided in a format that is intuitively easy for users to understand. There is a need for a system that can solve these problems and support safe and efficient evacuation during disasters.

[1467] 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.

[1468] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes, means for generating evacuation routes suitable for individual users based on the prediction, means for providing the generated evacuation route information to a user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for notifying the user of the evacuation route information based on the user's current location by voice and map using a smart device. This enables real-time data analysis and route provision, thereby realizing intuitive and immediate evacuation support for users.

[1469] "Weather data" refers to information about weather and weather conditions, including precipitation, wind speed, temperature, humidity, and air pressure.

[1470] "Traffic information" refers to information relating to road traffic conditions, including congestion, road closures, accident information, and the like.

[1471] "Real-time data" refers to the latest information at the current time, and is data that is collected and processed immediately.

[1472] A "model" is an algorithm or mathematical framework for predicting congestion along evacuation routes based on collected data.

[1473] A "user terminal" is an information communication device used by a user, and includes a smartphone, a tablet, smart glasses, etc.

[1474] "Feedback" is information provided by users based on local conditions and experiences.

[1475] "Evacuation routes" refer to recommended roads and routes for safe evacuation in the event of a disaster.

[1476] A "smart device" is an electronic device with advanced functionality that can connect to the Internet.

[1477] "Audio guidance" refers to a means of providing information to a user through audio.

[1478] "Visual map display" is a function that visually displays a map and provides route information and the like to the user.

[1479] An "evacuation support system" is an overall system for supporting users' evacuation in the event of a disaster.

[1480] MODE FOR CARRYING OUT THE INVENTION

[1481] System Overview

[1482] The system of this invention is designed to support efficient and safe evacuation in the event of a disaster. It collects real-time data, such as weather and traffic information, and analyzes that data to predict congestion along evacuation routes. Based on user feedback, it updates evacuation route information in real time and provides optimal evacuation routes.

[1483] Server Features

[1484] The server has the following features:

[1485] Real-time data collection: The server collects weather and traffic data in real time using external APIs (e.g., weather agencies and traffic information services).

[1486] Data analysis and model generation: Analyze the collected data and generate a model to predict the congestion status of evacuation routes. This modeling is performed using machine learning libraries such as TensorFlow.

[1487] Evacuation route generation: Based on the results of data analysis, an evacuation route appropriate for each individual user is generated. Multiple route candidates are evaluated and the least congested and safest route is selected.

[1488] Information provision: The generated evacuation route information is sent to the user's device.

[1489] Feedback analysis: Evacuation route information is updated in real time based on user feedback.

[1490] User device functions

[1491] The user terminal has the following features:

[1492] Receiving and displaying information: Receives evacuation route information sent from the server and notifies the user on the smart device with a visual map display and voice guidance.

[1493] Feedback submission: Provides an interface for users to input feedback and sends it to the server. Users can report traffic conditions, congestion, impassable areas, etc. in real time.

[1494] User Behavior

[1495] A user interacts with the system in the following way:

[1496] 1. Checking evacuation routes: When a disaster occurs, the user launches the application and receives notification of evacuation routes.

[1497] 2. Begin evacuation: Follow the map display and voice guidance on your smart device to proceed along the evacuation route.

[1498] 3. Providing feedback: Enter feedback about obstacles and congestion encountered during evacuation and send it to the server.

[1499] Specific examples

[1500] Let's take the example of a large-scale earthquake and a user evacuating. The server obtains real-time data from meteorological agencies and traffic information services. This data is analyzed using TensorFlow to generate an optimal evacuation route. The generated evacuation route information is sent to the user's smartphone, where the user receives a map display and voice guidance through the application. If the user encounters an impassable road or a congested area along the way, they enter that information in the application and send feedback to the server. The server reanalyzes the evacuation route based on this feedback and sends the new route information to the user's smartphone.

[1501] Prompt Sentence Examples

[1502] The user's current location is "35.6895, 139.6917" (center of the city). Please predict the best evacuation route for this user based on real-time weather and traffic information. Please take into account the following feedback ("Road impassable due to traffic jam", "Location: In front of Shibuya Station").

[1503] This example uses prompt sentences to demonstrate how a generative AI model can predict optimal evacuation routes and update them in real time based on feedback information.

[1504] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1505] Step 1:

[1506] The server collects real-time data such as weather data and traffic information. It uses external APIs (for example, APIs of meteorological agencies or APIs of traffic information services) to obtain data such as precipitation, wind speed, road congestion, and road closure information. It processes the data obtained from the external APIs as input, converts it into an appropriate format, and saves it in an internal data store. The output is the collected real-time data.

[1507] Step 2:

[1508] The server analyzes the collected real-time data and generates a model that predicts the congestion status of evacuation routes. It uses TensorFlow, a machine learning library, to create a predictive model based on past and current data. It uses the collected real-time data and past evacuation data as input and performs data analysis. The output is a model that predicts the congestion status of evacuation routes.

[1509] Step 3:

[1510] The server generates an evacuation route suited to each individual user based on the generated model. It analyzes the model's prediction results, evaluates multiple route candidates, and selects the safest route. The inputs are the user's current location, real-time data, and the output of the predictive model. The output is evacuation route information optimized for each user.

[1511] Step 4:

[1512] The server sends the generated evacuation route information to the user's device. The notification is sent via the Internet in a format that corresponds to the type of device used (smartphone, tablet, etc.). The input is the generated evacuation route information, and the output is the route information received by the user's device.

[1513] Step 5:

[1514] The user device notifies the user of the received evacuation route information using a visual map display and voice guidance. The user checks the route information through the application and begins evacuation. The input is the evacuation route information sent from the server, and the output is a notification to the user.

[1515] Step 6:

[1516] Users provide feedback on the congestion and impassable areas they encounter during evacuation via their terminals. The application has an interface for inputting feedback, and the information entered by the user is sent to the server. The input is feedback data from the user, and the output is the transmission of the feedback data to the server.

[1517] Step 7:

[1518] The server reanalyzes the evacuation route information based on the received feedback information and generates a new optimal route. The reanalysis uses real-time data and feedback information, and the generated new route information is sent back to the user terminal. The input is user feedback and real-time data, and the output is updated evacuation route information.

[1519] Step 8:

[1520] The user device receives the updated evacuation route information and notifies the user again. This allows the user to continue evacuating safely according to the latest evacuation route. The input is the updated route information sent from the server, and the output is the notification to the user.

[1521] 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.

[1522] System Overview

[1523] The system of the present invention is designed to support efficient and safe evacuation in the event of a disaster. It uses real-time data such as weather data and traffic information to predict congestion on evacuation routes and provides evacuation routes that are suitable for each individual user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it provides evacuation route guidance that is appropriate for the user's condition.

[1524] System configuration

[1525] This system consists of three elements: a server, a terminal, and a user. By adding an emotion engine, it can be customized based on the user's emotional state.

[1526] server

[1527] Real-time data collection: The server collects weather and traffic information from the APIs of meteorological agencies and traffic management systems, such as precipitation, wind speed, earthquake information, road congestion, and road closure information.

[1528] Data analysis and model generation: Analyze collected data and use AI models to predict congestion along evacuation routes. Use machine learning algorithms to make highly accurate predictions based on past data and current conditions.

[1529] Evacuation route generation: The system obtains the user's current location from GPS data and generates multiple route candidates to the optimal evacuation shelter. It then predicts congestion and assesses risks for each route candidate to select the safest and most efficient route.

[1530] Information provision: The generated evacuation route information is sent to the user's device. The data format is converted to JSON or XML and sent to the device via API.

[1531] Feedback analysis: Update route information in real time based on user feedback.

[1532] Terminal

[1533] Information reception and notification: Receives evacuation route information sent from the server and notifies the user. The notification is displayed visually on a map and guided by audio guidance.

[1534] Emotion engine: Analyzes voice, facial expressions, heart rate, etc. to recognize the user's emotions and assess their stress level. Based on the recognition results, the system adjusts evacuation route guidance methods.

[1535] Feedback transmission: Local information and congestion status are provided by the user through an input interface and sent to the server.

[1536] User

[1537] Confirming evacuation routes and taking evacuation action: Based on the evacuation route information displayed on the device, confirm the safe route and begin evacuation action.

[1538] Providing feedback: Feedback such as congestion and impassable areas encountered during evacuation will be provided via the terminal.

[1539] Specific examples

[1540] Evacuation scenario in the event of an earthquake

[1541] 1. The server obtains earthquake information: When a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and intensity from the meteorological agency's API.

[1542] 2. Analysis and model generation: The collected information is analyzed to predict congestion in the affected area. Based on this, an optimal evacuation route model is generated.

[1543] 3. Providing evacuation routes: When a user starts to evacuate, the server sends evacuation route information to the user's device. The device receives this information and notifies the user with voice and a map.

[1544] 4. Adjustment by emotion engine: The emotion engine of the device evaluates the user's stress level and adjusts evacuation route guidance. For example, if the user is in a high stress state, the instructions will be simplified and a reassuring voice guidance will be provided.

[1545] 5. Evacuation behavior and feedback: The user begins evacuation according to the provided evacuation route. If the user encounters a road that is severely damaged and impassable along the way, the user will provide feedback on this information to the server via their device.

[1546] 6. Reanalysis and route update: The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it to the terminal again.

[1547] 7. Re-notification to the user: The device receives the new route information and notifies the user. The user continues evacuation along the new route.

[1548] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state. By always providing optimal route information and guidance, evacuation can be carried out quickly and reliably in the event of a disaster.

[1549] The processing flow will be explained below.

[1550] Step 1: Getting real-time data

[1551] The server obtains real-time data such as weather data and traffic information. It collects earthquake information, precipitation, wind speed, etc. from meteorological agencies' APIs, and obtains road congestion, traffic accident information, and road closure information from traffic management systems.

[1552] Step 2: Data analysis and model generation

[1553] The server analyzes the real-time data it acquires and generates a model to predict congestion along evacuation routes. Specifically, it preprocesses the data and applies machine learning algorithms to train a congestion prediction model based on past data and current conditions. The generated model can predict congestion in each area with high accuracy.

[1554] Step 3: Generate evacuation routes

[1555] The server generates an evacuation route suited to each individual user based on the analysis results. The user's current location is identified using GPS data, and multiple route candidates are generated. Congestion predictions and risk assessments are performed for each route candidate, and the safest and most efficient route is selected.

[1556] Step 4: Provide evacuation route information

[1557] The server provides the generated evacuation route information to the user's device. The generated route information is converted into an appropriate data format (JSON or XML) and sent to the device via API with end-to-end encrypted communication.

[1558] Step 5: Evacuation route notification and guidance

[1559] The device notifies the user of the evacuation route information it receives. Specifically, it uses pop-up notifications and alert sounds to prompt the user to begin evacuation. Furthermore, it uses a map display function to visually display the route and a voice guidance function to guide the user.

[1560] Step 6: Emotion Recognition with the Emotion Engine

[1561] The device's emotion engine recognizes the user's emotional state. The emotion engine evaluates the user's stress level and tension by analyzing the user's voice, facial expressions, heart rate, etc. As a specific example, it analyzes the tone of the user's voice from voice input to determine the stress level.

[1562] Step 7: Emotion-Based Guidance Adjustments

[1563] The device adjusts evacuation route guidance based on the results of the emotion engine. If the user is judged to be in a high-stress state, it simplifies the instructions and provides reassuring voice guidance. If the user is calm, it provides detailed instructions.

[1564] Step 8: Provide feedback

[1565] During evacuation, users provide feedback using their devices, reporting congested areas and impassable locations using a simple input form or voice input, and the devices then send this information to the server.

[1566] Step 9: Analyze feedback and update route in real time

[1567] The server analyzes the received feedback and updates evacuation route information in real time. It recalculates routes based on new obstacle and congestion information and generates the latest optimal route. The updated route information is then sent back to the device.

[1568] Step 10: Re-informing and re-guiding

[1569] The device receives the updated evacuation route information and notifies the user again. The new route information is displayed on the map and voice guidance is provided again. The user follows the instructions to continue evacuating safely.

[1570] This series of processing steps not only enables the server, terminal, and user to work together to achieve efficient and safe evacuation in real time, but also provides more appropriate evacuation support by providing customized guidance based on the user's emotional state.

[1571] Example 2

[1572] 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."

[1573] Conventional evacuation systems have had problems with difficulty in predicting congestion in real time and providing optimal evacuation routes for individual users, and they were unable to provide evacuation guidance that took into account the user's emotional state. This prevented efficient and safe evacuation, potentially increasing user stress and confusion. Furthermore, there was a lack of a mechanism for utilizing feedback to update route information in real time, which posed a risk of reducing the effectiveness of evacuation routes.

[1574] 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.

[1575] In this invention, the server includes means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes using a machine learning algorithm, means for generating multiple evacuation route candidates suitable for each user based on the prediction and evaluating them to select the optimal evacuation route, means for converting the generated evacuation route information into a data format and providing it to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information in real time, and means for analyzing voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting the evacuation route guidance method based on the user's stress level. This enables accurate congestion prediction in real time, provision of evacuation routes tailored to each individual user, and appropriate evacuation guidance based on the user's emotional state.

[1576] "Weather data" refers to data related to weather elements such as precipitation, wind speed, and earthquake information.

[1577] "Traffic information" refers to data related to traffic, such as road congestion and road closure information.

[1578] "Real-time data" means the most up-to-date data about current conditions or status.

[1579] A "machine learning algorithm" is an algorithm that analyzes collected data to find patterns and trends and make predictions and classifications.

[1580] An "evacuation route" is a route that a user uses to safely evacuate in the event of a disaster.

[1581] "Congestion status" refers to the degree of concentration of people and vehicles in a particular location or route.

[1582] "Means for generating a model" refers to the means for creating a machine learning model for making predictions and classifications based on collected data.

[1583] "Feedback" refers to local information, opinions, impressions, etc. obtained from users.

[1584] A "data format" is a standard way of storing, displaying, or transmitting data.

[1585] "Emotional state" refers to the user's current emotional or mental state.

[1586] The "stress level" is a value that indicates the degree of stress that the user is feeling.

[1587] The "means for adjusting the evacuation route guidance method" is a means for optimizing the evacuation route guidance method based on the user's emotional state and stress level.

[1588] The system of the present invention is designed to support users in evacuating safely and efficiently in the event of a disaster. The system is mainly composed of three elements: a server, a terminal, and a user. By further integrating an emotion engine, the system is customized based on the user's emotional state. Specific embodiments of each element are shown below.

[1589] Server Processing

[1590] The server is responsible for a series of processes: collection, analysis, generation, provision, and updating. First, to collect real-time data such as weather data and traffic information, the server connects to the API of each data source (for example, the API of a weather information service or the API of a traffic information service) and obtains the real-time data.

[1591] The server then analyzes the acquired data and uses machine learning algorithms (for example, frameworks such as TensorFlow or PyTorch) to predict congestion along evacuation routes. The model generated by this analysis makes highly accurate congestion predictions based on past and real-time data.

[1592] The server generates multiple evacuation route candidates based on this forecast data and evaluates the congestion and risk of each candidate. After selecting the optimal evacuation route, it converts the information into JSON or XML format and sends it to the user's device via an API. It also receives feedback from users in real time and updates the evacuation route information.

[1593] Terminal handling

[1594] The device receives the evacuation route information sent from the server and notifies the user. Notifications are made visually using a map display (for example, using Google Maps API) and through voice guidance.

[1595] The device is also equipped with an emotion engine that recognizes the user's emotional state by analyzing voice, facial expressions, heart rate, etc. This analysis uses emotion recognition APIs such as AWS Rekognition and IBM Watson. Based on the user's emotional state and stress level, it is possible to adjust evacuation route guidance methods (such as simplified instructions or reassuring voice guidance).

[1596] The device also provides an interface for users to input local information and congestion status, and has the function of sending user feedback to the server, which keeps the evacuation route information always up-to-date.

[1597] User operations

[1598] Users check the evacuation route information displayed on their device, select a safe route, and begin evacuation. Information about congestion and impassable areas encountered during evacuation can be provided to the server as feedback via the device. This improves the effectiveness of evacuation routes and also helps support other evacuees.

[1599] Specific examples

[1600] For example, if a large earthquake occurs, the server immediately obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API, analyzes the data, and predicts congestion in the affected area. Based on this, it generates an optimal evacuation route model and sends it to the user's device. The device receives this information and notifies the user through a map display and voice guidance. The emotion engine also evaluates the user's stress level and provides appropriate guidance.

[1601] Example prompt sentence:

[1602] "We are designing a system to generate appropriate AI models and assist in safe evacuation. How can we improve efficiency and safety by incorporating user emotion recognition into evacuation route guidance?"

[1603] This allows users to quickly identify safe and efficient evacuation routes, enabling them to evacuate while reducing stress.

[1604] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1605] Step 1:

[1606] Real-time data collection

[1607] The server connects to the APIs of meteorological agencies and traffic management systems to collect real-time data. This process obtains data such as precipitation, wind speed, earthquake information, road congestion, and road closure information. Specifically, the server sends a data request to the API, receives a response in JSON format, and analyzes it. The input is the request from the API, and the output is the analyzed weather data and traffic information.

[1608] Step 2:

[1609] Data Preprocessing

[1610] The real-time data acquired by the server is integrated into a single dataset, and data normalization and missing value imputation are performed. This process is performed using the Python Pandas library. The input is raw real-time data, and the output is a preprocessed integrated dataset in a format suitable for analysis.

[1611] Step 3:

[1612] Training a machine learning model

[1613] The server trains machine learning models using the preprocessed dataset. It uses TensorFlow or PyTorch to build regression and time series forecasting models. The input is the preprocessed integrated dataset, and the output is a trained predictive model. Specific operations include splitting the dataset, defining the model, training it, and evaluating it.

[1614] Step 4:

[1615] Running a prediction

[1616] The server uses the trained model to predict the congestion status of evacuation routes based on current data. The input is current real-time data, and the output is the congestion prediction results for each route. Specific operations include inputting data into the model, obtaining prediction results, and evaluating the results.

[1617] Step 5:

[1618] Generate evacuation routes

[1619] The server obtains the user's current location (GPS data) and generates multiple candidate evacuation routes. Routes are calculated using map databases such as OpenStreetMap, and a model is used to predict congestion and assess risk for each route. The input is the user's current location and the congestion prediction results, and the output is multiple evaluated evacuation routes. Specific operations include generating candidate routes, assessing congestion, and selecting the optimal route.

[1620] Step 6:

[1621] Providing route information

[1622] The server converts the generated evacuation route information into JSON or XML format and sends it to the user's device via API. The input is the evaluated evacuation route, and the output is the route information sent to the user's device. Specific operations include converting the data format and sending an HTTP request.

[1623] Step 7:

[1624] Receiving information and notifications via device

[1625] The terminal receives evacuation route information sent from the server and notifies the user. Visually, it uses a map display and voice guidance. The input is route information from the server, and the output is a notification to the user. Specific operations include parsing data, displaying a map, and starting voice guidance.

[1626] Step 8:

[1627] Running the Emotion Engine

[1628] The device collects data from sensors, such as the user's voice, facial expressions, and heart rate, and analyzes their emotional state. AWS Rekognition and IBM Watson APIs are used to identify the user's stress level and emotional state. The input is sensor data, and the output is the emotional assessment result. The specific operations are data collection and emotion analysis.

[1629] Step 9:

[1630] Emotion-based guidance adjustment

[1631] The device adjusts the evacuation route guidance method based on the results of emotion analysis. For example, if the user is in a high-stress state, it simplifies the instructions and selects a voice guidance that provides a sense of security. The input is the emotion evaluation result, and the output is the adjusted guidance method. The specific operation is to select the guidance and display / execute the voice guidance.

[1632] Step 10:

[1633] Send Feedback

[1634] The user inputs the local situation they encountered during evacuation into the terminal and sends the information to the server. The input is the feedback from the user, and the output is the feedback data sent to the server. The specific operation is to provide a data input form and send an HTTP request.

[1635] Step 11:

[1636] Feedback analysis and route updates

[1637] The server receives feedback from users and updates evacuation route information in real time. It then reapplies the machine learning model to generate a new optimal route and sends it back to the user's device. The input is the feedback data, and the output is the updated evacuation route information. The specific operations are data analysis, route recalculation, and information retransmission.

[1638] (Application example 2)

[1639] 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."

[1640] In modern society, there is a demand for rapid and safe evacuation in the event of sudden disasters such as meteorological disasters, fires, and earthquakes. However, conventional evacuation support systems lack the ability to collect and analyze data in real time, and are unable to provide evacuation guidance that takes into account the user's emotional state, which can increase confusion and stress. The present invention aims to solve these problems and achieve safe and efficient evacuation.

[1641] 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 means for collecting real-time data such as weather data and traffic information, means for analyzing the collected real-time data and generating a model for predicting the congestion status of evacuation routes, means for generating an evacuation route appropriate for each user based on the prediction, means for providing the generated evacuation route information to the user terminal, means for receiving feedback from the user via the user terminal and updating the evacuation route information, and means for analyzing the user's voice, facial expression, heart rate, etc. to recognize the user's emotional state and adjusting evacuation route guidance. This makes it possible to provide an appropriate evacuation route in real time taking the user's emotional state into consideration.

[1642] "Weather data" refers to information relating to weather, such as weather, precipitation, wind speed, and temperature.

[1643] "Traffic information" refers to information relating to traffic, such as road traffic conditions, congestion information, and road closures.

[1644] "Real-time data" is information data that is collected in the present and can be used immediately.

[1645] "Analysis" means examining collected data in detail to understand its meaning and characteristics.

[1646] An "evacuation route" is a route used to move to a safe location in the event of a disaster.

[1647] "Crowding status" is information indicating the degree or density of congestion within a certain range.

[1648] A "model" is a mathematical or computational representation used to understand and predict a system or phenomenon.

[1649] A "user terminal" is an electronic device such as a computer or smartphone used by a user.

[1650] "Feedback" is information or opinions provided by users.

[1651] "Emotional state" refers to an individual's psychological state, such as stress, relief, or tension.

[1652] "Audio guidance" is a method of providing guidance information to a user using voice.

[1653] "Visual map display" is a method of presenting information visually by displaying a map on a screen.

[1654] A "collection means" is a device or method for acquiring data.

[1655] "Providing means" refers to the device or method used to deliver information to users.

[1656] An "update means" is a device or method for updating content based on the latest information or data.

[1657] An "emotion recognition means" is a device or method for analyzing and recognizing a user's emotional state.

[1658] System Overview

[1659] This invention is a system that uses real-time data to support efficient and safe evacuation during disasters. The main components are a server, a terminal, and a user, and an emotion engine is added to these to provide evacuation guidance according to the user's emotional state.

[1660] server

[1661] The server collects real-time data such as weather and traffic information and generates a model to predict congestion on evacuation routes. Specifically, the server uses the following software and hardware:

[1662] Real-time data collection

[1663] The server collects data using APIs of meteorological agencies and traffic management systems. For example, it obtains precipitation, wind speed, earthquake information, road congestion status, etc. from the OpenWeatherMap API and Google Maps API.

[1664] Data analysis and model generation

[1665] Analyze the collected data and use a generative AI model (e.g., TensorFlow) to predict congestion along evacuation routes. Build a highly accurate predictive model based on past data and the current situation.

[1666] Generate and provide evacuation routes

[1667] The system obtains the user's current location information from GPS data and generates route candidates to the optimal evacuation shelter. The generated route candidates are provided to the device in JSON or XML format.

[1668] Feedback Analysis

[1669] It also includes a function to analyze user feedback in real time and update evacuation route information.

[1670] Terminal

[1671] The terminal is a user device such as a smartphone or tablet, which receives evacuation route information sent from the server and provides it to the user. It also uses an emotion engine to recognize the user's emotional state and adjust evacuation route guidance accordingly.

[1672] Information Reception and Notification

[1673] The device receives the data sent from the server and notifies the user through a visual map display and voice guidance, using applications written in Flutter and React Native.

[1674] Emotion Engine

[1675] It uses Azure Cognitive Services and Google Cloud Vision API to analyze data such as voice, facial expressions, and heart rate, and its emotion engine assesses the user's stress level and adjusts evacuation route guidance.

[1676] Send Feedback

[1677] It has an interface to collect feedback from users and sends the collected data to a server, which allows for real-time optimization of evacuation route information.

[1678] User

[1679] Users can check evacuation route information through their devices and take evacuation actions, while also providing feedback on the situations they encounter during evacuation.

[1680] Checking evacuation routes and taking evacuation actions

[1681] Based on the evacuation route information displayed on the device, users can confirm a safe route and begin evacuation procedures.

[1682] Providing Feedback

[1683] The device reports to the server any congestion or impassable areas encountered during evacuation.

[1684] Specific examples

[1685] Evacuation scenario in the event of an earthquake

[1686] 1. The server acquires earthquake information

[1687] The server obtains information on the earthquake's epicenter and seismic intensity from the meteorological agency's API.

[1688] 2. Analysis and Model Generation

[1689] The collected information is analyzed, and generative AI models such as TensorFlow are used to predict congestion on evacuation routes and generate an optimal evacuation route model.

[1690] 3. Providing evacuation routes

[1691] The server provides evacuation route information to the terminal, which receives it and notifies the user through voice guidance and visual map display.

[1692] 4. Emotional Engine Adjustment

[1693] The device's emotion engine assesses the user's stress level and adjusts evacuation route guidance accordingly. For example, if the user is in a high stress state, the device will simplify instructions and provide reassuring voice guidance.

[1694] 5. Evacuation behavior and feedback

[1695] The user begins evacuation by following the provided evacuation route. If the user encounters a road that has been severely damaged and is impassable along the way, the user's device will provide feedback to the server.

[1696] 6. Reanalysis and Route Updates

[1697] The server reanalyzes the evacuation route based on the received feedback, generates a new optimal route, and sends it back to the terminal.

[1698] 7. Re-notifying the user

[1699] The terminal receives the new route information again and notifies the user.

[1700] Prompt Sentence Examples

[1701] "predict_evacuations_route(current_weather, traffic_data, user_location)"

[1702] "analyze_emotion(user_voice, user_facial_expression, user_heart_rate)"

[1703] "traffic_conditions.update({"location": "X", "status": "closed"})"

[1704] In this way, the system of the present invention combines real-time data with an emotion engine to support efficient and safe evacuation according to the user's emotional state.

[1705] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1706] Step 1:

[1707] The server collects weather and traffic information. The server obtains real-time data from the APIs of meteorological agencies (e.g., OpenWeatherMap API) and traffic information systems (e.g., Google Maps API). Input data includes precipitation, wind speed, earthquake information, road congestion status, etc., and stores this data in a database.

[1708] Step 2:

[1709] The server analyzes the collected data and uses a generative AI model (e.g., TensorFlow) to predict the congestion status of evacuation routes. The input is the weather data and traffic information collected in Step 1, and based on this, a machine learning algorithm processes and calculates the data. The output is a congestion prediction for each evacuation route.

[1710] Step 3:

[1711] The server generates an evacuation route suitable for each user based on congestion predictions. The user's current location information (GPS data) is also used as input. The server generates multiple evacuation route candidates and evaluates the efficiency and safety of each route. The optimal evacuation route information is generated in JSON format.

[1712] Step 4:

[1713] The server provides the generated evacuation route information to the user terminal. The input is the optimal evacuation route information generated in step 3, which is sent to the terminal via API. The terminal receives this information and starts visual map display and audio guidance.

[1714] Step 5:

[1715] The device collects the user's voice, facial expressions, heart rate, etc. and analyzes them using an emotion engine. The input is the user's voice data, facial images, heart rate data, etc., and this data is analyzed using Azure Cognitive Services and Google Cloud Vision API. The output is the user's stress level and emotional state.

[1716] Step 6:

[1717] The device adjusts evacuation route guidance based on the user's emotional state. The inputs are the emotion analysis results from step 5 and the evacuation route information from step 4. For example, if the user is in a high-stress state, the device simplifies instructions and provides reassuring voice guidance.

[1718] Step 7:

[1719] The user begins evacuation by following the evacuation route. If the user encounters an impassable road or a crowded situation along the way, the user sends feedback to the server via the device. The input is the user's feedback information, which is then sent to the server.

[1720] Step 8:

[1721] The server receives feedback from users and updates the evacuation route information. The input is the on-site feedback data obtained in step 7, and based on this, it analyzes the data again using a machine learning algorithm to generate a new evacuation route model. The output is the updated evacuation route information.

[1722] Step 9:

[1723] The server again sends the new evacuation route information to the terminal. The input is the new evacuation route information generated in step 8, and sends this to the terminal via the API. The terminal receives the new route information and notifies the user.

[1724] In this way, real-time data and an emotion engine are combined to support efficient and safe evacuation according to the user's emotional state.

[1725] 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.

[1726] 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.

[1727] 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.

[1728] 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.

[1729] 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.

[1730] 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.

[1731] 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).

[1732] 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.

[1733] 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."

[1734] 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.

[1735] 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).

[1736] 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.

[1737] 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.

[1738] 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.

[1739] 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.

[1740] 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.

[1741] 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.

[1742] 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.

[1743] Furthermore, the hardware structure of these v...

Claims

1. means for collecting real-time data such as weather data and traffic information; a means for analyzing the collected real-time data and generating a model for predicting congestion on evacuation routes; means for generating an evacuation route suited to each individual user based on the prediction; means for providing the generated evacuation route information to a user terminal; a means for receiving feedback from a user via a user terminal and updating evacuation route information; A system including:

2. 10. The system of claim 1, wherein the means for providing evacuation route information uses audio guidance and a visual map display.

3. 10. The system of claim 1, wherein the system uses the feedback to recalculate evacuation routes in real time and retransmits updated information to the terminal.

Images