System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting weather data, a means for constructing a model for predicting a wind direction by using the collected weather data, a means for collecting fire data, a means for predicting the spread of a fire by using the wind direction model, a means for calculating an optimum evacuation route for avoiding the spread of the fire, and a means for transmitting the calculated evacuation route to a terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, climate change has led to the frequent occurrence of large-scale fires around the world. These fires spread quickly and on a large scale, causing considerable property and human damage. Fires in urban areas in particular make it difficult to secure evacuation routes, requiring a rapid response. However, current technology lacks the means to accurately predict the direction and extent of fire spread in real time and calculate appropriate evacuation routes based on that prediction, making effective evacuation difficult. [Means for solving the problem]

[0005] This invention provides a means for collecting meteorological data and a means for constructing a model for predicting wind direction using the collected meteorological data. It also provides a means for collecting fire data and a means for predicting the spread of a fire using the fire data and the wind direction model. It also provides a means for calculating an optimal evacuation route that avoids the predicted spread of a fire. It also provides a means for transmitting the calculated evacuation route to a terminal, allowing users to confirm and use the evacuation route, thereby achieving a quick and safe evacuation. In this way, damage from fires is minimized and evacuation problems in urban areas are solved.

[0006] "Weather data" is a general term for information related to weather, such as wind speed, wind direction, humidity, and temperature.

[0007] A "wind direction prediction model" is an algorithm or system that predicts wind direction based on input meteorological data.

[0008] "Fire data" is a general term for information related to the occurrence of a fire, such as the coordinates of the location where the fire occurred and the scale of the fire.

[0009] "Fire spread forecasting" is the process of using wind direction forecasting models and fire data to predict in which direction and how far a fire will spread.

[0010] An "escape route" is the optimal route for a user to evacuate to a safe place to avoid the effects of a fire.

[0011] A "computing means" is a function that executes a process or algorithm that derives a specific result or answer based on specific information.

[0012] A "terminal" is an electronic device used by a user, and is a device that has the function of receiving and displaying information.

[0013] "User" refers to a person who uses this system to evacuate from a fire.

[0014] "Transmitting means" refers to the process or communication means for transferring the calculation results to other devices or terminals. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes. To implement this system, the following processes are performed.

[0037] Data Acquisition

[0038] The server communicates with external systems such as meteorological and fire departments to collect weather and fire data. Weather data includes wind speed, wind direction, humidity, temperature, etc. Fire data includes the coordinates of the fire's location and its scale.

[0039] Building the model

[0040] The server uses the acquired weather data to build a wind direction prediction model. Specifically, it trains a regression model that uses the collected weather data as input data and wind direction as output data. This makes it possible to predict which direction the wind will blow under specific weather conditions.

[0041] Fire spread prediction

[0042] The server uses the wind direction prediction model it has created to predict the spread of the fire. It predicts wind direction using meteorological data as input, and then calculates the direction and extent of the fire's spread based on that information. This prediction is made in real time, responding to the ever-changing situation of the fire.

[0043] Evacuation route calculation

[0044] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. This calculation uses an algorithm to find the shortest route from the user's current location to a safe evacuation site. The calculation takes into account the extent of the fire damage as an obstacle and determines the route to avoid it.

[0045] Notification of evacuation routes

[0046] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides the user with accurate evacuation instructions. Even after the user begins evacuation, the server recalculates the route in real time based on the latest weather and fire data, and re-notifies the device of the evacuation route as necessary.

[0047] Specific examples

[0048] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. To help the user evacuate safely, the server then calculates an evacuation route that avoids the spread of the fire and sends that route to the user's device. The device displays the route on a map and advises the user to "evacuate toward the west." Once the user begins evacuation, the server continues to monitor the weather and fire data, and calculates a new route if necessary and sends it to the device.

[0049] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0053] Step 2:

[0054] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0055] Step 3:

[0056] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0057] Step 4:

[0058] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0059] Step 5:

[0060] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0061] Step 6:

[0062] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[0063] Step 7:

[0064] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[0065] Step 8:

[0066] The device will notify the user of updated evacuation routes in real time, helping them to follow the new instructions and continue evacuating safely.

[0067] The above is the flow of specific processing steps of the system based on the present invention. This process can support quick and safe evacuation in the event of a fire.

[0068] Example 1

[0069] 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."

[0070] In recent years, there has been a growing demand for rapid and efficient evacuation in urban areas in the event of a fire. However, a system that predicts the spread of a fire and provides optimal evacuation routes based on that information has not yet been fully established. In particular, systems that integrate meteorological and fire data and have the ability to recalculate and update evacuation routes in real time are rare. As a result, many victims are unable to evacuate quickly and effectively, making it difficult to avoid serious damage. The present invention aims to solve these problems and provide a system that enables rapid and effective evacuation in the event of a fire.

[0071] 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.

[0072] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for preprocessing the collected weather data, means for predicting the spread of a fire using the wind direction model, means for simulating the extent of fire spread based on the weather data and the wind direction prediction model, means for calculating an optimal evacuation route that avoids the predicted spread of the fire, and means for transmitting the calculated evacuation route to the terminal. This makes it possible to construct a wind direction prediction model based on weather data and fire data at the time of a fire outbreak, simulate the spread of a fire using the prediction results, and calculate and notify evacuation routes in real time.

[0073] "Weather data" refers to information related to weather, such as wind speed, wind direction, humidity, and temperature.

[0074] "Means for collection" is a general term for hardware and software for obtaining necessary data from external systems.

[0075] "Means for constructing a model" refers to the algorithms and software used to generate predictive models based on acquired data.

[0076] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions.

[0077] "Fire data" is information related to a fire, such as the coordinates of the location where the fire occurred and the scale of the fire.

[0078] "Preprocessing" is the process of normalizing data and filling in missing values ​​in order to build a model.

[0079] "Means for simulating" refers to software or algorithms that virtually reproduce phenomena using predictive models and derive results.

[0080] "Means for calculating evacuation routes" refers to algorithms or methodologies for finding optimal evacuation routes.

[0081] A "terminal" is an electronic device that a user uses to receive information.

[0082] "Means for notifying" refers to the process or tool for transmitting calculated information to a user terminal.

[0083] This invention relates to a system that uses weather data and fire data in an integrated manner to predict the spread of a fire, calculate the optimal evacuation route, and notify the user. This system is composed of several main elements, each of which works together to realize the invention.

[0084] Data Acquisition

[0085] The server communicates with external systems such as meteorological and fire departments via APIs to collect the necessary weather and fire data. Weather data includes wind speed, direction, humidity, temperature, etc., and uses the OpenWeatherMap API, for example. Fire data includes the coordinates of the fire's location and its scale, and uses a dedicated API provided by the local fire department.

[0086] Data Preprocessing

[0087] The server preprocesses the collected weather data, which includes normalizing the data and filling in missing values. Preprocessing improves the quality of the data and increases the accuracy of the model.

[0088] Building a wind direction prediction model

[0089] The server builds a wind direction prediction model using machine learning libraries such as TENSORFLOW (registered trademark) and PyTorch. It trains a regression model that uses collected weather data as input and wind direction as output. This model is retrained overnight as a batch process.

[0090] Fire spread prediction

[0091] The server inputs the latest weather data into a wind direction prediction model to predict wind direction. Based on this, it simulates the spread of the fire in real time. By combining the predicted wind direction with fire data, it calculates the direction and extent of the fire's spread.

[0092] Evacuation route calculation

[0093] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. For example, it uses the A algorithm to search for the shortest route that avoids obstacles. It obtains the user's current location information and calculates the route to a safe evacuation location.

[0094] Notification of evacuation routes

[0095] The server sends the calculated evacuation route to the user's device. The device displays the received route information in a map application and notifies the user. The map display uses the Google (registered trademark) Maps API. Once the user begins evacuation, the server continues to monitor the data, calculates a new route as necessary, and sends it to the device.

[0096] Specific examples

[0097] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. Based on this data, the server builds a wind direction prediction model and predicts the wind direction to be north-northeast. It then predicts that the fire will spread north-northeast and calculates the optimal route for the user to evacuate. The calculated route is sent to the device, and the user is prompted to "Evacuate heading west." Once the user begins evacuation, the server continues to monitor weather and fire data and calculates new routes as needed.

[0098] Prompt Sentence Examples

[0099] "A fire has broken out near Tokyo Station. If the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, please predict the spread of the fire and the optimal evacuation route."

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1: Get the data

[0102] The server obtains weather and fire data through the APIs of the meteorological and fire departments. Specifically, it sends an HTTP request and receives data such as wind speed, wind direction, humidity, temperature, coordinates of the fire's location, and the scale of the fire. The data input is the response data from the API, and the output is the storage of the various collected data in a database.

[0103] Step 2: Preprocessing the data

[0104] The server preprocesses the collected weather data. The input is the raw data collected in step 1, and the output is weather data after normalization and missing value imputation. This includes unifying the data format, imputing missing values, and detecting and processing outliers. Specifically, it references historical data and executes an algorithm to impute missing data.

[0105] Step 3: Building a wind direction prediction model

[0106] The server builds a wind direction prediction model based on the preprocessed weather data. The input is normalized weather data, and the output is a trained wind direction prediction model. The regression model is trained using machine learning libraries such as TensorFlow and PyTorch. Specifically, weather data from each past month is input into the model training, and the accuracy of the model is also evaluated.

[0107] Step 4: Predict wind direction

[0108] The server inputs current weather data using the constructed forecast model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction. Specifically, the latest data is input into the model and the wind direction forecast result is obtained.

[0109] Step 5: Predicting the spread of the fire

[0110] The server simulates the spread of a fire based on predicted wind direction and fire data. The input is the predicted wind direction and initial fire data, and the output is the extent of the fire spread. Specifically, it applies a fire spread algorithm using a simulation grid.

[0111] Step 6: Calculate evacuation routes

[0112] The server calculates the optimal evacuation route to avoid the spread of the fire. The input is the extent of the fire spread and the user's current location data, and the output is the calculated evacuation route. For example, the server uses the A algorithm to search for an evacuation route and reflects the fire spread information in the route.

[0113] Step 7: Notify evacuation routes

[0114] The server sends the calculated evacuation route to the user's device. The input is the evacuation route data calculated in step 6, and the output is the route information displayed on the device. Specifically, the server sends the route data to the device in JSON format, and the device visualizes the route on a map using the Google Maps API.

[0115] Step 8: Real-time data updates and route recalculation

[0116] The server continuously monitors updates to weather and fire data and recalculates evacuation routes as needed. The input is newly acquired weather and fire data, and the output is updated evacuation routes. Specifically, the model is reevaluated each time new data is acquired, and route recalculation and notification are automatically performed.

[0117] (Application example 1)

[0118] 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."

[0119] Conventional fire evacuation systems can predict wind direction and the spread of fires based on meteorological and fire data, but they lack the ability to update data in real time or recalculate evacuation routes, making them insufficient for ensuring user safety. Furthermore, they lack a mechanism for visualizing evacuation routes and fire spread predictions on users' devices and providing appropriate evacuation instructions. Therefore, a system is needed that can efficiently predict the direction and extent of fire spread under specific weather conditions and provide quick and appropriate evacuation routes.

[0120] 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.

[0121] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, means for updating the weather data and fire data in real time to recalculate the evacuation route, and means for notifying the user of the latest evacuation route. This makes it possible to quickly and accurately recalculate an evacuation route based on the weather data and fire data updated in real time, and to provide the user with appropriate evacuation instructions.

[0122] "Weather data" is information about weather conditions such as wind speed, wind direction, humidity, and temperature.

[0123] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions based on collected weather data.

[0124] "Fire data" refers to information about a fire, including the coordinates of the location where the fire occurred and the scale of the fire.

[0125] "Fire spread prediction" is a process that uses a wind direction prediction model to predict in which direction and how far a fire will spread.

[0126] An "escape route" is the optimal route for a user to safely evacuate from a fire.

[0127] A "terminal" is a device used by a user, such as a smartphone or a personal computer.

[0128] "Real-time updates" means that weather and fire data are continuously updated with the latest information, and the system processes based on that information.

[0129] The "prompt generation function" is a function that creates automatically generated sentences to provide appropriate evacuation instructions to the user.

[0130] This invention provides a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes.

[0131] The server collects weather data and fire data from external systems (weather data providers and fire data providers). Weather data includes information such as wind speed, wind direction, humidity, and temperature. Fire data includes information such as the coordinates of the fire outbreak point and the scale of the fire.

[0132] The server then builds a wind direction prediction model based on the collected weather data. This model is trained using machine learning techniques (e.g., linear regression using scikit-learn). The prediction model can predict wind direction under specific weather conditions.

[0133] Using the constructed wind direction prediction model, the server inputs fire data and the latest weather data to predict the spread of the fire. Based on this prediction information, the server calculates a route that the user can safely evacuate. The server uses an algorithm to find the shortest route from the user's current location to a safe evacuation site, taking the fire damage area into account as an obstacle when determining the route.

[0134] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides accurate evacuation instructions to the user. In addition, the server continuously updates meteorological and fire data in real time, recalculates the evacuation route as needed, and notifies the device again of the latest evacuation route. It also has a prompt generation function that provides the user with appropriate evacuation instructions.

[0135] Specific examples

[0136] For example, suppose a fire breaks out while the user is near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then notifies the user's device, "Please evacuate heading west." Once the user begins evacuation, the server continues to monitor the weather and fire data, calculating a new route if necessary and re-notifying the device.

[0137] Prompt Sentence Examples

[0138] "When a user is near Tokyo Station, they launch the FireSafe app. The app retrieves real-time weather and fire data, and based on that data, uses a wind direction prediction model to predict the spread of the fire. The app then calculates a safe evacuation route from the user's current location and notifies them, saying, 'Please evacuate heading west.' Once the user begins to evacuate, the app continues to monitor weather and fire data, recalculating evacuation routes as necessary and notifying the user."

[0139] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[0140] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0141] Step 1: Collect weather and fire data

[0142] The server communicates with weather data providers and fire data providers to obtain real-time weather data (wind speed, wind direction, humidity, temperature, etc.) and fire data (coordinates of the outbreak point, scale of the fire, etc.). This data is sent to the server using an external API.

[0143] Input: Weather and fire data provided by external systems

[0144] Output: Weather and fire data stored on a server

[0145] Step 2: Building a wind direction prediction model

[0146] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a machine learning library (e.g., scikit-learn) to train a regression model that predicts wind direction from inputs such as wind speed, humidity, and temperature.

[0147] Input: Captured weather data

[0148] Output: A trained wind direction prediction model

[0149] Step 3: Predicting the spread of the fire

[0150] The server uses the constructed wind direction prediction model and the latest weather and fire data to predict the spread of the fire. The weather data is input into the wind direction prediction model, and the direction and speed of the fire spread are calculated from the prediction results.

[0151] Inputs: Latest weather and fire data, wind forecast model

[0152] Output: Fire spread prediction results (direction and speed)

[0153] Step 4: Calculate evacuation routes

[0154] The server calculates a safe evacuation route based on the fire spread prediction results and the user's current location. It uses an algorithm to find the shortest route to avoid the spread of the fire and determines the route from the user's current location to a safe evacuation location.

[0155] Input: Fire spread prediction results, user's current location

[0156] Output: Safe escape route

[0157] Step 5: Notify evacuation routes

[0158] The server then sends the calculated evacuation route to the user's device, which then visualizes the route on a map and provides accurate evacuation instructions to the user.

[0159] Input: Calculated evacuation route

[0160] Output: Display of evacuation route on user terminal

[0161] Step 6: Real-time updates of weather and fire data

[0162] The server monitors weather and fire data in real time, periodically acquiring new data, and repeats steps 2 through 5 based on the new data, recalculating evacuation routes as needed.

[0163] Input: Real-time updated weather and fire data

[0164] Output: Updated evacuation route

[0165] Step 7: Prompt generation provides evacuation instructions

[0166] The server uses a prompt generation function to provide appropriate evacuation instructions to the user. The generated prompts are displayed in a user-friendly format using natural language processing (NLP) technology.

[0167] Input: Calculated evacuation routes and current fire situation

[0168] Output: Appropriate evacuation instructions (prompt) provided to the user

[0169] The above steps result in a system that can quickly and accurately calculate evacuation routes based on meteorological and fire data and notify users of these routes. This system will be a powerful support tool for ensuring user safety in the event of a fire.

[0170] 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.

[0171] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[0172] Data Acquisition

[0173] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0174] Building the model

[0175] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0176] Fire spread prediction

[0177] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0178] Evacuation route calculation

[0179] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0180] Notification of evacuation routes

[0181] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0182] Emotion recognition and response

[0183] The device uses an emotion engine to recognize the user's emotions and adjusts the content and display of evacuation instructions depending on the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner.

[0184] Specific examples

[0185] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[0186] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and even send a short message advising them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculating the evacuation route as necessary and sending the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[0187] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0188] The processing flow will be explained below.

[0189] Step 1:

[0190] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0191] Step 2:

[0192] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0193] Step 3:

[0194] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0195] Step 4:

[0196] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0197] Step 5:

[0198] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0199] Step 6:

[0200] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[0201] Step 7:

[0202] The device uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice and facial expressions when confirming evacuation instructions on the device to determine the user's stress level and emotional state.

[0203] Step 8:

[0204] The device can adjust the content and display of evacuation instructions based on the user's perceived emotions. For example, if the user is experiencing high stress levels, the device will simplify the instructions and change the color of the evacuation route display to a more visible color.

[0205] Step 9:

[0206] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[0207] Step 10:

[0208] The device will notify the user of updated evacuation routes in real time, allowing them to continue evacuating safely by following the new instructions.

[0209] Examples:

[0210] For example, if a fire breaks out around Tokyo Station, the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, the system will operate as follows:

[0211] The server builds a wind direction prediction model based on this weather data and predicts wind direction.

[0212] The server predicts that the fire will spread to the north-northeast and calculates the optimal evacuation route to avoid the fire spreading.

[0213] The server sends the calculated evacuation route to the user's terminal.

[0214] The device displays the route on a map and instructs the user to "evacuate towards the west."

[0215] The device recognizes the user's emotions and, if it determines that the stress level is high, it will provide more concise instructions and make the display more noticeable.

[0216] The user follows the instructions and begins evacuation.

[0217] The server monitors weather and fire data, recalculates evacuation routes as needed, and sends updated routes to the device.

[0218] The device will notify the user of the updated route, allowing them to continue their evacuation safely.

[0219] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0220] Example 2

[0221] 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."

[0222] Accurate wind direction and fire spread forecasts are essential for swift and safe evacuation in the event of a fire. However, current systems have difficulty in doing this in real time, and evacuation routes are not optimized sufficiently. Furthermore, they do not provide flexible evacuation instructions that take into account the user's emotional state. This can lead to stress and confusion, making it difficult for users to take appropriate evacuation actions.

[0223] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, and means for recognizing the user's emotions and adjusting the content and display method of evacuation instructions. This enables quick and safe evacuation that takes the user's emotional state into consideration, and always provides an optimal evacuation route based on the latest information.

[0224] "Weather data" refers to information about weather conditions, such as wind speed, wind direction, humidity, and temperature.

[0225] A "wind direction prediction model" refers to a mathematical or machine learning model that uses input meteorological data such as wind speed, humidity, and temperature to predict wind direction.

[0226] "Fire data" refers to information about fires, such as the coordinates of the fire's location, the scale of the fire, and the progress of the fire.

[0227] "Methods for predicting fire spread" refers to algorithms and methods that use wind direction prediction models to calculate how far and in what direction a fire will spread.

[0228] "Means for calculating evacuation routes" refers to an algorithm for calculating the spread of fire and the optimal route from the user's current location to a safe evacuation location.

[0229] "Means for transmitting the calculated evacuation route to the terminal" refers to a communication means for transmitting information about the evacuation route from the server to the user's terminal.

[0230] "Means for recognizing user emotions" refers to sensors, software, and algorithms for detecting a user's emotional state.

[0231] "Means for adjusting the content and display of evacuation instructions" refers to algorithms and methods for changing and adjusting the evacuation route and message display depending on the recognized emotional state of the user.

[0232] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. Each process in this system is explained in detail below.

[0233] Data Acquisition

[0234] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. This allows you to always have the latest weather conditions in real time. It also obtains fire data such as the coordinates of the fire's location and its scale. Specifically, this data is obtained using an API.

[0235] Building the model

[0236] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. For example, the model is trained using the Python library Scikit-learn. This wind direction prediction model is then used to predict wind direction based on newly acquired weather data.

[0237] Fire spread prediction

[0238] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast. This makes it possible to determine the direction and extent of the fire's progress.

[0239] Evacuation route calculation

[0240] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses a path-finding algorithm such as Dijkstra's algorithm. The important thing here is to set the fire damage area as an obstacle and calculate a route that avoids it. For example, the route calculation is performed using the open-source library NetworkX.

[0241] Notification of evacuation routes

[0242] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the user's device of this list. This notification is usually done via the Internet.

[0243] Emotion recognition and response

[0244] The device uses an emotion engine to recognize the user's emotions. For example, it can use a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. Depending on the recognized emotion, the device can adjust the content and display of evacuation instructions. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display messages such as "Please remain calm and act calmly."

[0245] Specific examples

[0246] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[0247] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and advise them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[0248] Prompt Sentence Examples

[0249] "Given weather data and fire data for the area around Tokyo Station, with a wind speed of 10 m / s, a wind direction of north-northeast, humidity of 50%, and a temperature of 20 degrees, calculate the optimal evacuation route. Please also take into account the user's emotional state."

[0250] The above is a specific embodiment for carrying out the present invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0252] Step 1: Get the data

[0253] The server communicates with external systems such as the meteorological bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. The collected data is obtained through API requests. For example, the JSON data obtained as a response from the API is parsed to extract the necessary weather data. Fire data such as the coordinates of the fire's location and its scale is also obtained in a similar manner. The input is the API endpoint, and the output is data such as wind speed, wind direction, humidity, temperature, fire coordinates, and fire scale.

[0254] Step 2: Building a wind direction prediction model

[0255] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model that uses the collected wind speed, humidity, and temperature as input data and wind direction as output data. For example, it uses Python's Scikit-learn library to create a linear regression model and fit it with the training data. The input is weather data (wind speed, humidity, temperature), and the output is a wind direction prediction model.

[0256] Step 3: Predict wind direction

[0257] The server inputs the latest weather data into a wind direction prediction model to predict the current wind direction. It uses a trained linear regression model to input the latest wind speed, humidity, and temperature data to predict wind direction. For example, if the wind speed is 10 m / s, humidity is 50%, and the temperature is 20 degrees, these values ​​are input into the model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction.

[0258] Step 4: Predicting the spread of the fire

[0259] The server calculates how far and in what direction the fire will spread based on the predicted wind direction. For example, if the wind speed is 10 m / s and the wind is blowing north-northeast, the fire is predicted to spread north-northeast. An algorithm is implemented to calculate the distance the fire will spread based on the wind speed. The input is the predicted wind direction and wind speed, and the output is the direction and distance the fire will spread.

[0260] Step 5: Calculate evacuation routes

[0261] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses Dijkstra's algorithm. The fire damage area is set as an obstacle, and the route is calculated to avoid it. For example, an algorithm is run to find the shortest route using information on the user's current location and evacuation location. The input is information on the spread of the fire and the coordinates of the user's current location and evacuation location, and the output is the calculated evacuation route.

[0262] Step 6: Notify evacuation routes

[0263] The server sends the calculated evacuation route to the user's device. Specifically, it generates a list of evacuation route coordinates and notifies the user's device. The data is converted to JSON format and sent via the Internet. The input is the calculated evacuation route information, and the output is the evacuation route sent to the user's device.

[0264] Step 7: Emotion recognition and response

[0265] The device uses an emotion engine to recognize the user's emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. The device adjusts the content and display of evacuation instructions according to the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display a message such as "Please remain calm." The input is the user's facial expressions and voice information, and the output is the display of adjusted evacuation instructions.

[0266] (Application example 2)

[0267] 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."

[0268] In the event of a fire, quick and safe evacuation is required, but conventional systems have difficulty predicting the spread of fire or calculating evacuation routes in real time, and they have also been unable to provide appropriate evacuation guidance that takes into account the user's emotional state. As a result, there have been issues with reducing user stress during evacuation and providing reliable evacuation guidance.

[0269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0270] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of the fire, means for transmitting the calculated evacuation route to the terminal, means for recognizing a user's emotion, and means for adjusting the content and display method of evacuation instructions in accordance with the recognized user's emotion. This makes it possible to predict the spread of a fire and provide an optimal evacuation route in real time when a fire occurs, and further makes it possible to provide appropriate evacuation guidance based on the user's emotional state.

[0271] "Weather data" refers to data relating to weather conditions such as wind speed, wind direction, humidity, and temperature.

[0272] A "wind direction model" is a mathematical model for predicting wind direction based on specific meteorological data.

[0273] "Fire data" refers to data that includes information on the coordinates of the location of the fire and the scale of the fire.

[0274] A "means for predicting the spread of a fire" is a means for calculating the direction and extent of a fire's spread using a wind direction model.

[0275] "Means for calculating evacuation routes" refers to algorithms or procedures for calculating the optimal evacuation route that avoids the spread of fire.

[0276] "Means for recognizing user emotions" refers to technology for determining a user's emotional state by analyzing the user's facial expressions, voice, etc.

[0277] The "means for adjusting the content and display method of evacuation instructions" refers to a means for changing the display method of evacuation routes and guidance depending on the emotional state of the user.

[0278] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[0279] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[0280] Data Acquisition

[0281] To collect weather data, the server communicates with external systems such as meteorological and fire departments to obtain data on wind speed, wind direction, humidity, temperature, etc. It also collects fire data such as the coordinates of fire locations and information on the scale of fires.

[0282] Building the model

[0283] The server builds a wind direction prediction model based on the acquired weather data. Specifically, it uses a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model predicts wind direction based on weather conditions and estimates the direction of fire spread.

[0284] Fire spread prediction

[0285] The server inputs the latest weather data into the wind direction prediction model it has built to predict the current wind direction. For example, if the wind speed is 10 m / s and blowing north-northeast, it predicts that the fire will spread north-northeast.

[0286] Evacuation route calculation

[0287] The server calculates the optimal evacuation route to avoid the predicted direction of fire spread. It uses algorithms such as Dijkstra's algorithm to derive the shortest route from the user's current location to a safe evacuation site. It treats the predicted fire spread as an obstacle and optimizes the route to avoid it.

[0288] Notification of evacuation routes

[0289] The calculated evacuation route is sent from the server to the user's device. Specifically, a list of the evacuation route coordinates is generated and notified to the device.

[0290] Emotion recognition and response

[0291] The device uses an emotion engine to recognize the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine their stress level. Based on the recognized emotion, it adjusts the content and display method of evacuation instructions. For example, if the user is in a state of high stress, it will make the evacuation route display simpler and easier to understand.

[0292] Specific examples

[0293] For example, suppose a fire breaks out near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this data to build a wind direction prediction model and predicts the wind direction to be north-northeast. As the fire is predicted to spread north-northeast, the server calculates an evacuation route based on this information and sends it to the user's device. If the emotion engine recognizes that the user's stress level is high, the device will simplify the display of the evacuation route and display a message such as "Please remain calm and act accordingly."

[0294] Prompt Sentence Examples

[0295] "Your current location is 35.6895, 139.6917. Please calculate an evacuation route based on the latest wind speed of 10 m / s, wind direction north-northeast, humidity of 50%, and temperature of 20 degrees."

[0296] This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0297] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0298] Step 1:

[0299] The server collects meteorological data, specifically data such as wind speed, wind direction, humidity, and temperature, from the APIs of the weather bureau and fire department, allowing real-time weather information to be collected on the server.

[0300] Input: API of weather station and fire department

[0301] Output: Weather data such as wind speed, wind direction, humidity, and temperature

[0302] Step 2:

[0303] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a linear regression model to learn how to predict wind direction using wind speed, humidity, and temperature as inputs.

[0304] Input: Weather data such as wind speed, wind direction, humidity, and temperature

[0305] Output: Wind direction prediction model

[0306] Step 3:

[0307] The server collects fire data, specifically, obtaining information on the coordinates of the fire's location and its scale from the fire department's API.

[0308] Input: Fire Department API

[0309] Output: Coordinates of the fire location, data on the fire's scale

[0310] Step 4:

[0311] The server uses a wind direction prediction model to predict the spread of the fire. Collected weather data is input into the wind direction prediction model to predict the current wind direction. Next, based on the predicted wind direction and fire data, it calculates the direction and extent of the fire's spread.

[0312] Inputs: Wind direction prediction model, latest weather data, fire data

[0313] Output: Fire spread prediction results (direction and distance)

[0314] Step 5:

[0315] The server calculates the optimal evacuation route to avoid the spread of the fire. Specifically, it uses algorithms such as Dijkstra's algorithm to calculate the shortest route from the user's current location to a safe evacuation site. The predicted fire spread is treated as an obstacle, and the route is optimized to avoid it.

[0316] Input: User's current location, fire spread prediction results

[0317] Output: Evacuation route

[0318] Step 6:

[0319] The server sends the calculated evacuation route to the user's device, which then notifies the device of the coordinates of the evacuation route and displays it as a visual navigation system.

[0320] Input: List of evacuation route coordinates

[0321] Output: Evacuation route notification to user terminal

[0322] Step 7:

[0323] The device recognizes the user's emotions by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then uses an emotion engine to determine the user's stress level.

[0324] Input: Camera input, microphone input

[0325] Output: User's emotional state (stress level)

[0326] Step 8:

[0327] The device adjusts the content and display of evacuation instructions based on the user's emotions. For example, if the user's stress level is high, the device will change the display of evacuation routes to a simpler and easier-to-understand format and display the necessary messages.

[0328] Input: User's emotional state, evacuation route

[0329] Output: Coordinated evacuation instructions and messages

[0330] Step 9:

[0331] The user begins evacuation by following the evacuation route provided by the device, which continues to provide real-time notifications about the evacuation route and updates it as necessary.

[0332] Input: Coordinated evacuation orders and messages

[0333] Output: Evacuation, real-time notification

[0334] 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.

[0335] 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.

[0336] 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.

[0337] [Second embodiment]

[0338] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0339] 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.

[0340] 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).

[0341] 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.

[0342] 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.

[0343] 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).

[0344] 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.

[0345] 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.

[0346] 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.

[0347] 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.

[0348] 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.

[0349] 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."

[0350] This invention relates to a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes. To implement this system, the following processes are performed.

[0351] Data Acquisition

[0352] The server communicates with external systems such as meteorological and fire departments to collect weather and fire data. Weather data includes wind speed, wind direction, humidity, temperature, etc. Fire data includes the coordinates of the fire's location and its scale.

[0353] Building the model

[0354] The server uses the acquired weather data to build a wind direction prediction model. Specifically, it trains a regression model that uses the collected weather data as input data and wind direction as output data. This makes it possible to predict which direction the wind will blow under specific weather conditions.

[0355] Fire spread prediction

[0356] The server uses the wind direction prediction model it has created to predict the spread of the fire. It predicts wind direction using meteorological data as input, and then calculates the direction and extent of the fire's spread based on that information. This prediction is made in real time, responding to the ever-changing situation of the fire.

[0357] Evacuation route calculation

[0358] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. This calculation uses an algorithm to find the shortest route from the user's current location to a safe evacuation site. The calculation takes into account the extent of the fire damage as an obstacle and determines the route to avoid it.

[0359] Notification of evacuation routes

[0360] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides the user with accurate evacuation instructions. Even after the user begins evacuation, the server recalculates the route in real time based on the latest weather and fire data, and re-notifies the device of the evacuation route as necessary.

[0361] Specific examples

[0362] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. To help the user evacuate safely, the server then calculates an evacuation route that avoids the spread of the fire and sends that route to the user's device. The device displays the route on a map and advises the user to "evacuate toward the west." Once the user begins evacuation, the server continues to monitor the weather and fire data, and calculates a new route if necessary and sends it to the device.

[0363] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[0364] The processing flow will be explained below.

[0365] Step 1:

[0366] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0367] Step 2:

[0368] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0369] Step 3:

[0370] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0371] Step 4:

[0372] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0373] Step 5:

[0374] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0375] Step 6:

[0376] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[0377] Step 7:

[0378] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[0379] Step 8:

[0380] The device will notify the user of updated evacuation routes in real time, helping them to follow the new instructions and continue evacuating safely.

[0381] The above is the flow of specific processing steps of the system based on the present invention. This process can support quick and safe evacuation in the event of a fire.

[0382] Example 1

[0383] 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."

[0384] In recent years, there has been a growing demand for rapid and efficient evacuation in urban areas in the event of a fire. However, a system that predicts the spread of a fire and provides optimal evacuation routes based on that information has not yet been fully established. In particular, systems that integrate meteorological and fire data and have the ability to recalculate and update evacuation routes in real time are rare. As a result, many victims are unable to evacuate quickly and effectively, making it difficult to avoid serious damage. The present invention aims to solve these problems and provide a system that enables rapid and effective evacuation in the event of a fire.

[0385] 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.

[0386] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for preprocessing the collected weather data, means for predicting the spread of a fire using the wind direction model, means for simulating the extent of fire spread based on the weather data and the wind direction prediction model, means for calculating an optimal evacuation route that avoids the predicted spread of the fire, and means for transmitting the calculated evacuation route to the terminal. This makes it possible to construct a wind direction prediction model based on weather data and fire data at the time of a fire outbreak, simulate the spread of a fire using the prediction results, and calculate and notify evacuation routes in real time.

[0387] "Weather data" refers to information related to weather, such as wind speed, wind direction, humidity, and temperature.

[0388] "Means for collection" is a general term for hardware and software for obtaining necessary data from external systems.

[0389] "Means for constructing a model" refers to the algorithms and software used to generate predictive models based on acquired data.

[0390] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions.

[0391] "Fire data" is information related to a fire, such as the coordinates of the location where the fire occurred and the scale of the fire.

[0392] "Preprocessing" is the process of normalizing data and filling in missing values ​​in order to build a model.

[0393] "Means for simulating" refers to software or algorithms that virtually reproduce phenomena using predictive models and derive results.

[0394] "Means for calculating evacuation routes" refers to algorithms or methodologies for finding optimal evacuation routes.

[0395] A "terminal" is an electronic device that a user uses to receive information.

[0396] "Means for notifying" refers to the process or tool for transmitting calculated information to a user terminal.

[0397] This invention relates to a system that uses weather data and fire data in an integrated manner to predict the spread of a fire, calculate the optimal evacuation route, and notify the user. This system is composed of several main elements, each of which works together to realize the invention.

[0398] Data Acquisition

[0399] The server communicates with external systems such as meteorological and fire departments via APIs to collect the necessary weather and fire data. Weather data includes wind speed, direction, humidity, temperature, etc., and uses the OpenWeatherMap API, for example. Fire data includes the coordinates of the fire's location and its scale, and uses a dedicated API provided by the local fire department.

[0400] Data Preprocessing

[0401] The server preprocesses the collected weather data, which includes normalizing the data and filling in missing values. Preprocessing improves the quality of the data and increases the accuracy of the model.

[0402] Building a wind direction prediction model

[0403] The server builds a wind direction prediction model using machine learning libraries such as TensorFlow and PyTorch. It trains a regression model that uses collected weather data as input and wind direction as output. This model is retrained overnight as a batch process.

[0404] Fire spread prediction

[0405] The server inputs the latest weather data into a wind direction prediction model to predict wind direction. Based on this, it simulates the spread of the fire in real time. By combining the predicted wind direction with fire data, it calculates the direction and extent of the fire's spread.

[0406] Evacuation route calculation

[0407] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. For example, it uses the A algorithm to search for the shortest route that avoids obstacles. It obtains the user's current location information and calculates the route to a safe evacuation location.

[0408] Notification of evacuation routes

[0409] The server sends the calculated evacuation route to the user's device. The device displays the received route information in a map application and notifies the user. The map display uses the Google Maps API. Once the user begins evacuation, the server continues to monitor the data, calculates a new route as needed, and sends it to the device.

[0410] Specific examples

[0411] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. Based on this data, the server builds a wind direction prediction model and predicts the wind direction to be north-northeast. It then predicts that the fire will spread north-northeast and calculates the optimal route for the user to evacuate. The calculated route is sent to the device, and the user is prompted to "Evacuate heading west." Once the user begins evacuation, the server continues to monitor weather and fire data and calculates new routes as needed.

[0412] Prompt Sentence Examples

[0413] "A fire has broken out near Tokyo Station. If the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, please predict the spread of the fire and the optimal evacuation route."

[0414] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0415] Step 1: Get the data

[0416] The server obtains weather and fire data through the APIs of the meteorological and fire departments. Specifically, it sends an HTTP request and receives data such as wind speed, wind direction, humidity, temperature, coordinates of the fire's location, and the scale of the fire. The data input is the response data from the API, and the output is the storage of the various collected data in a database.

[0417] Step 2: Preprocessing the data

[0418] The server preprocesses the collected weather data. The input is the raw data collected in step 1, and the output is weather data after normalization and missing value imputation. This includes unifying the data format, imputing missing values, and detecting and processing outliers. Specifically, it references historical data and executes an algorithm to impute missing data.

[0419] Step 3: Building a wind direction prediction model

[0420] The server builds a wind direction prediction model based on the preprocessed weather data. The input is normalized weather data, and the output is a trained wind direction prediction model. The regression model is trained using machine learning libraries such as TensorFlow and PyTorch. Specifically, weather data from each past month is input into the model training, and the accuracy of the model is also evaluated.

[0421] Step 4: Predict wind direction

[0422] The server inputs current weather data using the constructed forecast model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction. Specifically, the latest data is input into the model and the wind direction forecast result is obtained.

[0423] Step 5: Predicting the spread of the fire

[0424] The server simulates the spread of a fire based on predicted wind direction and fire data. The input is the predicted wind direction and initial fire data, and the output is the extent of the fire spread. Specifically, it applies a fire spread algorithm using a simulation grid.

[0425] Step 6: Calculate evacuation routes

[0426] The server calculates the optimal evacuation route to avoid the spread of the fire. The input is the extent of the fire spread and the user's current location data, and the output is the calculated evacuation route. For example, the server uses the A algorithm to search for an evacuation route and reflects the fire spread information in the route.

[0427] Step 7: Notify evacuation routes

[0428] The server sends the calculated evacuation route to the user's device. The input is the evacuation route data calculated in step 6, and the output is the route information displayed on the device. Specifically, the server sends the route data to the device in JSON format, and the device visualizes the route on a map using the Google Maps API.

[0429] Step 8: Real-time data updates and route recalculation

[0430] The server continuously monitors updates to weather and fire data and recalculates evacuation routes as needed. The input is newly acquired weather and fire data, and the output is updated evacuation routes. Specifically, the model is reevaluated each time new data is acquired, and route recalculation and notification are automatically performed.

[0431] (Application example 1)

[0432] 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."

[0433] Conventional fire evacuation systems can predict wind direction and the spread of fires based on meteorological and fire data, but they lack the ability to update data in real time or recalculate evacuation routes, making them insufficient for ensuring user safety. Furthermore, they lack a mechanism for visualizing evacuation routes and fire spread predictions on users' devices and providing appropriate evacuation instructions. Therefore, a system is needed that can efficiently predict the direction and extent of fire spread under specific weather conditions and provide quick and appropriate evacuation routes.

[0434] 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.

[0435] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, means for updating the weather data and fire data in real time to recalculate the evacuation route, and means for notifying the user of the latest evacuation route. This makes it possible to quickly and accurately recalculate an evacuation route based on the weather data and fire data updated in real time, and to provide the user with appropriate evacuation instructions.

[0436] "Weather data" is information about weather conditions such as wind speed, wind direction, humidity, and temperature.

[0437] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions based on collected weather data.

[0438] "Fire data" refers to information about a fire, including the coordinates of the location where the fire occurred and the scale of the fire.

[0439] "Fire spread prediction" is a process that uses a wind direction prediction model to predict in which direction and how far a fire will spread.

[0440] An "escape route" is the optimal route for a user to safely evacuate from a fire.

[0441] A "terminal" is a device used by a user, such as a smartphone or a personal computer.

[0442] "Real-time updates" means that weather and fire data are continuously updated with the latest information, and the system processes based on that information.

[0443] The "prompt generation function" is a function that creates automatically generated sentences to provide appropriate evacuation instructions to the user.

[0444] This invention provides a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes.

[0445] The server collects weather data and fire data from external systems (weather data providers and fire data providers). Weather data includes information such as wind speed, wind direction, humidity, and temperature. Fire data includes information such as the coordinates of the fire outbreak point and the scale of the fire.

[0446] The server then builds a wind direction prediction model based on the collected weather data. This model is trained using machine learning techniques (e.g., linear regression using scikit-learn). The prediction model can predict wind direction under specific weather conditions.

[0447] Using the constructed wind direction prediction model, the server inputs fire data and the latest weather data to predict the spread of the fire. Based on this prediction information, the server calculates a route that the user can safely evacuate. The server uses an algorithm to find the shortest route from the user's current location to a safe evacuation site, taking the fire damage area into account as an obstacle when determining the route.

[0448] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides accurate evacuation instructions to the user. In addition, the server continuously updates meteorological and fire data in real time, recalculates the evacuation route as needed, and notifies the device again of the latest evacuation route. It also has a prompt generation function that provides the user with appropriate evacuation instructions.

[0449] Specific examples

[0450] For example, suppose a fire breaks out while the user is near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then notifies the user's device, "Please evacuate heading west." Once the user begins evacuation, the server continues to monitor the weather and fire data, calculating a new route if necessary and re-notifying the device.

[0451] Prompt Sentence Examples

[0452] "When a user is near Tokyo Station, they launch the FireSafe app. The app retrieves real-time weather and fire data, and based on that data, uses a wind direction prediction model to predict the spread of the fire. The app then calculates a safe evacuation route from the user's current location and notifies them, saying, 'Please evacuate heading west.' Once the user begins to evacuate, the app continues to monitor weather and fire data, recalculating evacuation routes as necessary and notifying the user."

[0453] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[0454] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0455] Step 1: Collect weather and fire data

[0456] The server communicates with weather data providers and fire data providers to obtain real-time weather data (wind speed, wind direction, humidity, temperature, etc.) and fire data (coordinates of the outbreak point, scale of the fire, etc.). This data is sent to the server using an external API.

[0457] Input: Weather and fire data provided by external systems

[0458] Output: Weather and fire data stored on a server

[0459] Step 2: Building a wind direction prediction model

[0460] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a machine learning library (e.g., scikit-learn) to train a regression model that predicts wind direction from inputs such as wind speed, humidity, and temperature.

[0461] Input: Captured weather data

[0462] Output: A trained wind direction prediction model

[0463] Step 3: Predicting the spread of the fire

[0464] The server uses the constructed wind direction prediction model and the latest weather and fire data to predict the spread of the fire. The weather data is input into the wind direction prediction model, and the direction and speed of the fire spread are calculated from the prediction results.

[0465] Inputs: Latest weather and fire data, wind forecast model

[0466] Output: Fire spread prediction results (direction and speed)

[0467] Step 4: Calculate evacuation routes

[0468] The server calculates a safe evacuation route based on the fire spread prediction results and the user's current location. It uses an algorithm to find the shortest route to avoid the spread of the fire and determines the route from the user's current location to a safe evacuation location.

[0469] Input: Fire spread prediction results, user's current location

[0470] Output: Safe escape route

[0471] Step 5: Notify evacuation routes

[0472] The server then sends the calculated evacuation route to the user's device, which then visualizes the route on a map and provides accurate evacuation instructions to the user.

[0473] Input: Calculated evacuation route

[0474] Output: Display of evacuation route on user terminal

[0475] Step 6: Real-time updates of weather and fire data

[0476] The server monitors weather and fire data in real time, periodically acquiring new data, and repeats steps 2 through 5 based on the new data, recalculating evacuation routes as needed.

[0477] Input: Real-time updated weather and fire data

[0478] Output: Updated evacuation route

[0479] Step 7: Prompt generation provides evacuation instructions

[0480] The server uses a prompt generation function to provide appropriate evacuation instructions to the user. The generated prompts are displayed in a user-friendly format using natural language processing (NLP) technology.

[0481] Input: Calculated evacuation routes and current fire situation

[0482] Output: Appropriate evacuation instructions (prompt) provided to the user

[0483] The above steps result in a system that can quickly and accurately calculate evacuation routes based on meteorological and fire data and notify users of these routes. This system will be a powerful support tool for ensuring user safety in the event of a fire.

[0484] 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.

[0485] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[0486] Data Acquisition

[0487] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0488] Building the model

[0489] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0490] Fire spread prediction

[0491] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0492] Evacuation route calculation

[0493] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0494] Notification of evacuation routes

[0495] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0496] Emotion recognition and response

[0497] The device uses an emotion engine to recognize the user's emotions and adjusts the content and display of evacuation instructions depending on the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner.

[0498] Specific examples

[0499] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[0500] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and even send a short message advising them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculating the evacuation route as necessary and sending the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[0501] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0505] Step 2:

[0506] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0507] Step 3:

[0508] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0509] Step 4:

[0510] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0511] Step 5:

[0512] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0513] Step 6:

[0514] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[0515] Step 7:

[0516] The device uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice and facial expressions when confirming evacuation instructions on the device to determine the user's stress level and emotional state.

[0517] Step 8:

[0518] The device can adjust the content and display of evacuation instructions based on the user's perceived emotions. For example, if the user is experiencing high stress levels, the device will simplify the instructions and change the color of the evacuation route display to a more visible color.

[0519] Step 9:

[0520] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[0521] Step 10:

[0522] The device will notify the user of updated evacuation routes in real time, allowing them to continue evacuating safely by following the new instructions.

[0523] Examples:

[0524] For example, if a fire breaks out around Tokyo Station, the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, the system will operate as follows:

[0525] The server builds a wind direction prediction model based on this weather data and predicts wind direction.

[0526] The server predicts that the fire will spread to the north-northeast and calculates the optimal evacuation route to avoid the fire spreading.

[0527] The server sends the calculated evacuation route to the user's terminal.

[0528] The device displays the route on a map and instructs the user to "evacuate towards the west."

[0529] The device recognizes the user's emotions and, if it determines that the stress level is high, it will provide more concise instructions and make the display more noticeable.

[0530] The user follows the instructions and begins evacuation.

[0531] The server monitors weather and fire data, recalculates evacuation routes as needed, and sends updated routes to the device.

[0532] The device will notify the user of the updated route, allowing them to continue their evacuation safely.

[0533] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0534] Example 2

[0535] 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."

[0536] Accurate wind direction and fire spread forecasts are essential for swift and safe evacuation in the event of a fire. However, current systems have difficulty in doing this in real time, and evacuation routes are not optimized sufficiently. Furthermore, they do not provide flexible evacuation instructions that take into account the user's emotional state. This can lead to stress and confusion, making it difficult for users to take appropriate evacuation actions.

[0537] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, and means for recognizing the user's emotions and adjusting the content and display method of evacuation instructions. This enables quick and safe evacuation that takes the user's emotional state into consideration, and always provides an optimal evacuation route based on the latest information.

[0538] "Weather data" refers to information about weather conditions, such as wind speed, wind direction, humidity, and temperature.

[0539] A "wind direction prediction model" refers to a mathematical or machine learning model that uses input meteorological data such as wind speed, humidity, and temperature to predict wind direction.

[0540] "Fire data" refers to information about fires, such as the coordinates of the fire's location, the scale of the fire, and the progress of the fire.

[0541] "Methods for predicting fire spread" refers to algorithms and methods that use wind direction prediction models to calculate how far and in what direction a fire will spread.

[0542] "Means for calculating evacuation routes" refers to an algorithm for calculating the spread of fire and the optimal route from the user's current location to a safe evacuation location.

[0543] "Means for transmitting the calculated evacuation route to the terminal" refers to a communication means for transmitting information about the evacuation route from the server to the user's terminal.

[0544] "Means for recognizing user emotions" refers to sensors, software, and algorithms for detecting a user's emotional state.

[0545] "Means for adjusting the content and display of evacuation instructions" refers to algorithms and methods for changing and adjusting the evacuation route and message display depending on the recognized emotional state of the user.

[0546] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. Each process in this system is explained in detail below.

[0547] Data Acquisition

[0548] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. This allows you to always have the latest weather conditions in real time. It also obtains fire data such as the coordinates of the fire's location and its scale. Specifically, this data is obtained using an API.

[0549] Building the model

[0550] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. For example, the model is trained using the Python library Scikit-learn. This wind direction prediction model is then used to predict wind direction based on newly acquired weather data.

[0551] Fire spread prediction

[0552] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast. This makes it possible to determine the direction and extent of the fire's progress.

[0553] Evacuation route calculation

[0554] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses a path-finding algorithm such as Dijkstra's algorithm. The important thing here is to set the fire damage area as an obstacle and calculate a route that avoids it. For example, the route calculation is performed using the open-source library NetworkX.

[0555] Notification of evacuation routes

[0556] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the user's device of this list. This notification is usually done via the Internet.

[0557] Emotion recognition and response

[0558] The device uses an emotion engine to recognize the user's emotions. For example, it can use a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. Depending on the recognized emotion, the device can adjust the content and display of evacuation instructions. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display messages such as "Please remain calm and act calmly."

[0559] Specific examples

[0560] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[0561] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and advise them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[0562] Prompt Sentence Examples

[0563] "Given weather data and fire data for the area around Tokyo Station, with a wind speed of 10 m / s, a wind direction of north-northeast, humidity of 50%, and a temperature of 20 degrees, calculate the optimal evacuation route. Please also take into account the user's emotional state."

[0564] The above is a specific embodiment for carrying out the present invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0565] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0566] Step 1: Get the data

[0567] The server communicates with external systems such as the meteorological bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. The collected data is obtained through API requests. For example, the JSON data obtained as a response from the API is parsed to extract the necessary weather data. Fire data such as the coordinates of the fire's location and its scale is also obtained in a similar manner. The input is the API endpoint, and the output is data such as wind speed, wind direction, humidity, temperature, fire coordinates, and fire scale.

[0568] Step 2: Building a wind direction prediction model

[0569] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model that uses the collected wind speed, humidity, and temperature as input data and wind direction as output data. For example, it uses Python's Scikit-learn library to create a linear regression model and fit it with the training data. The input is weather data (wind speed, humidity, temperature), and the output is a wind direction prediction model.

[0570] Step 3: Predict wind direction

[0571] The server inputs the latest weather data into a wind direction prediction model to predict the current wind direction. It uses a trained linear regression model to input the latest wind speed, humidity, and temperature data to predict wind direction. For example, if the wind speed is 10 m / s, humidity is 50%, and the temperature is 20 degrees, these values ​​are input into the model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction.

[0572] Step 4: Predicting the spread of the fire

[0573] The server calculates how far and in what direction the fire will spread based on the predicted wind direction. For example, if the wind speed is 10 m / s and the wind is blowing north-northeast, the fire is predicted to spread north-northeast. An algorithm is implemented to calculate the distance the fire will spread based on the wind speed. The input is the predicted wind direction and wind speed, and the output is the direction and distance the fire will spread.

[0574] Step 5: Calculate evacuation routes

[0575] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses Dijkstra's algorithm. The fire damage area is set as an obstacle, and the route is calculated to avoid it. For example, an algorithm is run to find the shortest route using information on the user's current location and evacuation location. The input is information on the spread of the fire and the coordinates of the user's current location and evacuation location, and the output is the calculated evacuation route.

[0576] Step 6: Notify evacuation routes

[0577] The server sends the calculated evacuation route to the user's device. Specifically, it generates a list of evacuation route coordinates and notifies the user's device. The data is converted to JSON format and sent via the Internet. The input is the calculated evacuation route information, and the output is the evacuation route sent to the user's device.

[0578] Step 7: Emotion recognition and response

[0579] The device uses an emotion engine to recognize the user's emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. The device adjusts the content and display of evacuation instructions according to the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display a message such as "Please remain calm." The input is the user's facial expressions and voice information, and the output is the display of adjusted evacuation instructions.

[0580] (Application example 2)

[0581] 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."

[0582] In the event of a fire, quick and safe evacuation is required, but conventional systems have difficulty predicting the spread of fire or calculating evacuation routes in real time, and they have also been unable to provide appropriate evacuation guidance that takes into account the user's emotional state. As a result, there have been issues with reducing user stress during evacuation and providing reliable evacuation guidance.

[0583] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0584] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of the fire, means for transmitting the calculated evacuation route to the terminal, means for recognizing a user's emotion, and means for adjusting the content and display method of evacuation instructions in accordance with the recognized user's emotion. This makes it possible to predict the spread of a fire and provide an optimal evacuation route in real time when a fire occurs, and further makes it possible to provide appropriate evacuation guidance based on the user's emotional state.

[0585] "Weather data" refers to data relating to weather conditions such as wind speed, wind direction, humidity, and temperature.

[0586] A "wind direction model" is a mathematical model for predicting wind direction based on specific meteorological data.

[0587] "Fire data" refers to data that includes information on the coordinates of the location of the fire and the scale of the fire.

[0588] A "means for predicting the spread of a fire" is a means for calculating the direction and extent of a fire's spread using a wind direction model.

[0589] "Means for calculating evacuation routes" refers to algorithms or procedures for calculating the optimal evacuation route that avoids the spread of fire.

[0590] "Means for recognizing user emotions" refers to technology for determining a user's emotional state by analyzing the user's facial expressions, voice, etc.

[0591] The "means for adjusting the content and display method of evacuation instructions" refers to a means for changing the display method of evacuation routes and guidance depending on the emotional state of the user.

[0592] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[0593] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[0594] Data Acquisition

[0595] To collect weather data, the server communicates with external systems such as meteorological and fire departments to obtain data on wind speed, wind direction, humidity, temperature, etc. It also collects fire data such as the coordinates of fire locations and information on the scale of fires.

[0596] Building the model

[0597] The server builds a wind direction prediction model based on the acquired weather data. Specifically, it uses a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model predicts wind direction based on weather conditions and estimates the direction of fire spread.

[0598] Fire spread prediction

[0599] The server inputs the latest weather data into the wind direction prediction model it has built to predict the current wind direction. For example, if the wind speed is 10 m / s and blowing north-northeast, it predicts that the fire will spread north-northeast.

[0600] Evacuation route calculation

[0601] The server calculates the optimal evacuation route to avoid the predicted direction of fire spread. It uses algorithms such as Dijkstra's algorithm to derive the shortest route from the user's current location to a safe evacuation site. It treats the predicted fire spread as an obstacle and optimizes the route to avoid it.

[0602] Notification of evacuation routes

[0603] The calculated evacuation route is sent from the server to the user's device. Specifically, a list of the evacuation route coordinates is generated and notified to the device.

[0604] Emotion recognition and response

[0605] The device uses an emotion engine to recognize the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine their stress level. Based on the recognized emotion, it adjusts the content and display method of evacuation instructions. For example, if the user is in a state of high stress, it will make the evacuation route display simpler and easier to understand.

[0606] Specific examples

[0607] For example, suppose a fire breaks out near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this data to build a wind direction prediction model and predicts the wind direction to be north-northeast. As the fire is predicted to spread north-northeast, the server calculates an evacuation route based on this information and sends it to the user's device. If the emotion engine recognizes that the user's stress level is high, the device will simplify the display of the evacuation route and display a message such as "Please remain calm and act accordingly."

[0608] Prompt Sentence Examples

[0609] "Your current location is 35.6895, 139.6917. Please calculate an evacuation route based on the latest wind speed of 10 m / s, wind direction north-northeast, humidity of 50%, and temperature of 20 degrees."

[0610] This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0611] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0612] Step 1:

[0613] The server collects meteorological data, specifically data such as wind speed, wind direction, humidity, and temperature, from the APIs of the weather bureau and fire department, allowing real-time weather information to be collected on the server.

[0614] Input: API of weather station and fire department

[0615] Output: Weather data such as wind speed, wind direction, humidity, and temperature

[0616] Step 2:

[0617] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a linear regression model to learn how to predict wind direction using wind speed, humidity, and temperature as inputs.

[0618] Input: Weather data such as wind speed, wind direction, humidity, and temperature

[0619] Output: Wind direction prediction model

[0620] Step 3:

[0621] The server collects fire data, specifically, obtaining information on the coordinates of the fire's location and its scale from the fire department's API.

[0622] Input: Fire Department API

[0623] Output: Coordinates of the fire location, data on the fire's scale

[0624] Step 4:

[0625] The server uses a wind direction prediction model to predict the spread of the fire. Collected weather data is input into the wind direction prediction model to predict the current wind direction. Next, based on the predicted wind direction and fire data, it calculates the direction and extent of the fire's spread.

[0626] Inputs: Wind direction prediction model, latest weather data, fire data

[0627] Output: Fire spread prediction results (direction and distance)

[0628] Step 5:

[0629] The server calculates the optimal evacuation route to avoid the spread of the fire. Specifically, it uses algorithms such as Dijkstra's algorithm to calculate the shortest route from the user's current location to a safe evacuation site. The predicted fire spread is treated as an obstacle, and the route is optimized to avoid it.

[0630] Input: User's current location, fire spread prediction results

[0631] Output: Evacuation route

[0632] Step 6:

[0633] The server sends the calculated evacuation route to the user's device, which then notifies the device of the coordinates of the evacuation route and displays it as a visual navigation system.

[0634] Input: List of evacuation route coordinates

[0635] Output: Evacuation route notification to user terminal

[0636] Step 7:

[0637] The device recognizes the user's emotions by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then uses an emotion engine to determine the user's stress level.

[0638] Input: Camera input, microphone input

[0639] Output: User's emotional state (stress level)

[0640] Step 8:

[0641] The device adjusts the content and display of evacuation instructions based on the user's emotions. For example, if the user's stress level is high, the device will change the display of evacuation routes to a simpler and easier-to-understand format and display the necessary messages.

[0642] Input: User's emotional state, evacuation route

[0643] Output: Coordinated evacuation instructions and messages

[0644] Step 9:

[0645] The user begins evacuation by following the evacuation route provided by the device, which continues to provide real-time notifications about the evacuation route and updates it as necessary.

[0646] Input: Coordinated evacuation orders and messages

[0647] Output: Evacuation, real-time notification

[0648] 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.

[0649] 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.

[0650] 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.

[0651] [Third embodiment]

[0652] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0653] 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.

[0654] 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).

[0655] 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.

[0656] 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.

[0657] 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).

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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."

[0664] This invention relates to a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes. To implement this system, the following processes are performed.

[0665] Data Acquisition

[0666] The server communicates with external systems such as meteorological and fire departments to collect weather and fire data. Weather data includes wind speed, wind direction, humidity, temperature, etc. Fire data includes the coordinates of the fire's location and its scale.

[0667] Building the model

[0668] The server uses the acquired weather data to build a wind direction prediction model. Specifically, it trains a regression model that uses the collected weather data as input data and wind direction as output data. This makes it possible to predict which direction the wind will blow under specific weather conditions.

[0669] Fire spread prediction

[0670] The server uses the wind direction prediction model it has created to predict the spread of the fire. It predicts wind direction using meteorological data as input, and then calculates the direction and extent of the fire's spread based on that information. This prediction is made in real time, responding to the ever-changing situation of the fire.

[0671] Evacuation route calculation

[0672] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. This calculation uses an algorithm to find the shortest route from the user's current location to a safe evacuation site. The calculation takes into account the extent of the fire damage as an obstacle and determines the route to avoid it.

[0673] Notification of evacuation routes

[0674] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides the user with accurate evacuation instructions. Even after the user begins evacuation, the server recalculates the route in real time based on the latest weather and fire data, and re-notifies the device of the evacuation route as necessary.

[0675] Specific examples

[0676] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. To help the user evacuate safely, the server then calculates an evacuation route that avoids the spread of the fire and sends that route to the user's device. The device displays the route on a map and advises the user to "evacuate toward the west." Once the user begins evacuation, the server continues to monitor the weather and fire data, and calculates a new route if necessary and sends it to the device.

[0677] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[0678] The processing flow will be explained below.

[0679] Step 1:

[0680] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0681] Step 2:

[0682] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0683] Step 3:

[0684] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0685] Step 4:

[0686] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0687] Step 5:

[0688] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0689] Step 6:

[0690] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[0691] Step 7:

[0692] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[0693] Step 8:

[0694] The device will notify the user of updated evacuation routes in real time, helping them to follow the new instructions and continue evacuating safely.

[0695] The above is the flow of specific processing steps of the system based on the present invention. This process can support quick and safe evacuation in the event of a fire.

[0696] Example 1

[0697] 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."

[0698] In recent years, there has been a growing demand for rapid and efficient evacuation in urban areas in the event of a fire. However, a system that predicts the spread of a fire and provides optimal evacuation routes based on that information has not yet been fully established. In particular, systems that integrate meteorological and fire data and have the ability to recalculate and update evacuation routes in real time are rare. As a result, many victims are unable to evacuate quickly and effectively, making it difficult to avoid serious damage. The present invention aims to solve these problems and provide a system that enables rapid and effective evacuation in the event of a fire.

[0699] 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.

[0700] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for preprocessing the collected weather data, means for predicting the spread of a fire using the wind direction model, means for simulating the extent of fire spread based on the weather data and the wind direction prediction model, means for calculating an optimal evacuation route that avoids the predicted spread of the fire, and means for transmitting the calculated evacuation route to the terminal. This makes it possible to construct a wind direction prediction model based on weather data and fire data at the time of a fire outbreak, simulate the spread of a fire using the prediction results, and calculate and notify evacuation routes in real time.

[0701] "Weather data" refers to information related to weather, such as wind speed, wind direction, humidity, and temperature.

[0702] "Means for collection" is a general term for hardware and software for obtaining necessary data from external systems.

[0703] "Means for constructing a model" refers to the algorithms and software used to generate predictive models based on acquired data.

[0704] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions.

[0705] "Fire data" is information related to a fire, such as the coordinates of the location where the fire occurred and the scale of the fire.

[0706] "Preprocessing" is the process of normalizing data and filling in missing values ​​in order to build a model.

[0707] "Means for simulating" refers to software or algorithms that virtually reproduce phenomena using predictive models and derive results.

[0708] "Means for calculating evacuation routes" refers to algorithms or methodologies for finding optimal evacuation routes.

[0709] A "terminal" is an electronic device that a user uses to receive information.

[0710] "Means for notifying" refers to the process or tool for transmitting calculated information to a user terminal.

[0711] This invention relates to a system that uses weather data and fire data in an integrated manner to predict the spread of a fire, calculate the optimal evacuation route, and notify the user. This system is composed of several main elements, each of which works together to realize the invention.

[0712] Data Acquisition

[0713] The server communicates with external systems such as meteorological and fire departments via APIs to collect the necessary weather and fire data. Weather data includes wind speed, direction, humidity, temperature, etc., and uses the OpenWeatherMap API, for example. Fire data includes the coordinates of the fire's location and its scale, and uses a dedicated API provided by the local fire department.

[0714] Data Preprocessing

[0715] The server preprocesses the collected weather data, which includes normalizing the data and filling in missing values. Preprocessing improves the quality of the data and increases the accuracy of the model.

[0716] Building a wind direction prediction model

[0717] The server builds a wind direction prediction model using machine learning libraries such as TensorFlow and PyTorch. It trains a regression model that uses collected weather data as input and wind direction as output. This model is retrained overnight as a batch process.

[0718] Fire spread prediction

[0719] The server inputs the latest weather data into a wind direction prediction model to predict wind direction. Based on this, it simulates the spread of the fire in real time. By combining the predicted wind direction with fire data, it calculates the direction and extent of the fire's spread.

[0720] Evacuation route calculation

[0721] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. For example, it uses the A algorithm to search for the shortest route that avoids obstacles. It obtains the user's current location information and calculates the route to a safe evacuation location.

[0722] Notification of evacuation routes

[0723] The server sends the calculated evacuation route to the user's device. The device displays the received route information in a map application and notifies the user. The map display uses the Google Maps API. Once the user begins evacuation, the server continues to monitor the data, calculates a new route as needed, and sends it to the device.

[0724] Specific examples

[0725] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. Based on this data, the server builds a wind direction prediction model and predicts the wind direction to be north-northeast. It then predicts that the fire will spread north-northeast and calculates the optimal route for the user to evacuate. The calculated route is sent to the device, and the user is prompted to "Evacuate heading west." Once the user begins evacuation, the server continues to monitor weather and fire data and calculates new routes as needed.

[0726] Prompt Sentence Examples

[0727] "A fire has broken out near Tokyo Station. If the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, please predict the spread of the fire and the optimal evacuation route."

[0728] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0729] Step 1: Get the data

[0730] The server obtains weather and fire data through the APIs of the meteorological and fire departments. Specifically, it sends an HTTP request and receives data such as wind speed, wind direction, humidity, temperature, coordinates of the fire's location, and the scale of the fire. The data input is the response data from the API, and the output is the storage of the various collected data in a database.

[0731] Step 2: Preprocessing the data

[0732] The server preprocesses the collected weather data. The input is the raw data collected in step 1, and the output is weather data after normalization and missing value imputation. This includes unifying the data format, imputing missing values, and detecting and processing outliers. Specifically, it references historical data and executes an algorithm to impute missing data.

[0733] Step 3: Building a wind direction prediction model

[0734] The server builds a wind direction prediction model based on the preprocessed weather data. The input is normalized weather data, and the output is a trained wind direction prediction model. The regression model is trained using machine learning libraries such as TensorFlow and PyTorch. Specifically, weather data from each past month is input into the model training, and the accuracy of the model is also evaluated.

[0735] Step 4: Predict wind direction

[0736] The server inputs current weather data using the constructed forecast model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction. Specifically, the latest data is input into the model and the wind direction forecast result is obtained.

[0737] Step 5: Predicting the spread of the fire

[0738] The server simulates the spread of a fire based on predicted wind direction and fire data. The input is the predicted wind direction and initial fire data, and the output is the extent of the fire spread. Specifically, it applies a fire spread algorithm using a simulation grid.

[0739] Step 6: Calculate evacuation routes

[0740] The server calculates the optimal evacuation route to avoid the spread of the fire. The input is the extent of the fire spread and the user's current location data, and the output is the calculated evacuation route. For example, the server uses the A algorithm to search for an evacuation route and reflects the fire spread information in the route.

[0741] Step 7: Notify evacuation routes

[0742] The server sends the calculated evacuation route to the user's device. The input is the evacuation route data calculated in step 6, and the output is the route information displayed on the device. Specifically, the server sends the route data to the device in JSON format, and the device visualizes the route on a map using the Google Maps API.

[0743] Step 8: Real-time data updates and route recalculation

[0744] The server continuously monitors updates to weather and fire data and recalculates evacuation routes as needed. The input is newly acquired weather and fire data, and the output is updated evacuation routes. Specifically, the model is reevaluated each time new data is acquired, and route recalculation and notification are automatically performed.

[0745] (Application example 1)

[0746] 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."

[0747] Conventional fire evacuation systems can predict wind direction and the spread of fires based on meteorological and fire data, but they lack the ability to update data in real time or recalculate evacuation routes, making them insufficient for ensuring user safety. Furthermore, they lack a mechanism for visualizing evacuation routes and fire spread predictions on users' devices and providing appropriate evacuation instructions. Therefore, a system is needed that can efficiently predict the direction and extent of fire spread under specific weather conditions and provide quick and appropriate evacuation routes.

[0748] 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.

[0749] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, means for updating the weather data and fire data in real time to recalculate the evacuation route, and means for notifying the user of the latest evacuation route. This makes it possible to quickly and accurately recalculate an evacuation route based on the weather data and fire data updated in real time, and to provide the user with appropriate evacuation instructions.

[0750] "Weather data" is information about weather conditions such as wind speed, wind direction, humidity, and temperature.

[0751] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions based on collected weather data.

[0752] "Fire data" refers to information about a fire, including the coordinates of the location where the fire occurred and the scale of the fire.

[0753] "Fire spread prediction" is a process that uses a wind direction prediction model to predict in which direction and how far a fire will spread.

[0754] An "escape route" is the optimal route for a user to safely evacuate from a fire.

[0755] A "terminal" is a device used by a user, such as a smartphone or a personal computer.

[0756] "Real-time updates" means that weather and fire data are continuously updated with the latest information, and the system processes based on that information.

[0757] The "prompt generation function" is a function that creates automatically generated sentences to provide appropriate evacuation instructions to the user.

[0758] This invention provides a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes.

[0759] The server collects weather data and fire data from external systems (weather data providers and fire data providers). Weather data includes information such as wind speed, wind direction, humidity, and temperature. Fire data includes information such as the coordinates of the fire outbreak point and the scale of the fire.

[0760] The server then builds a wind direction prediction model based on the collected weather data. This model is trained using machine learning techniques (e.g., linear regression using scikit-learn). The prediction model can predict wind direction under specific weather conditions.

[0761] Using the constructed wind direction prediction model, the server inputs fire data and the latest weather data to predict the spread of the fire. Based on this prediction information, the server calculates a route that the user can safely evacuate. The server uses an algorithm to find the shortest route from the user's current location to a safe evacuation site, taking the fire damage area into account as an obstacle when determining the route.

[0762] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides accurate evacuation instructions to the user. In addition, the server continuously updates meteorological and fire data in real time, recalculates the evacuation route as needed, and notifies the device again of the latest evacuation route. It also has a prompt generation function that provides the user with appropriate evacuation instructions.

[0763] Specific examples

[0764] For example, suppose a fire breaks out while the user is near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then notifies the user's device, "Please evacuate heading west." Once the user begins evacuation, the server continues to monitor the weather and fire data, calculating a new route if necessary and re-notifying the device.

[0765] Prompt Sentence Examples

[0766] "When a user is near Tokyo Station, they launch the FireSafe app. The app retrieves real-time weather and fire data, and based on that data, uses a wind direction prediction model to predict the spread of the fire. The app then calculates a safe evacuation route from the user's current location and notifies them, saying, 'Please evacuate heading west.' Once the user begins to evacuate, the app continues to monitor weather and fire data, recalculating evacuation routes as necessary and notifying the user."

[0767] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[0768] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0769] Step 1: Collect weather and fire data

[0770] The server communicates with weather data providers and fire data providers to obtain real-time weather data (wind speed, wind direction, humidity, temperature, etc.) and fire data (coordinates of the outbreak point, scale of the fire, etc.). This data is sent to the server using an external API.

[0771] Input: Weather and fire data provided by external systems

[0772] Output: Weather and fire data stored on a server

[0773] Step 2: Building a wind direction prediction model

[0774] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a machine learning library (e.g., scikit-learn) to train a regression model that predicts wind direction from inputs such as wind speed, humidity, and temperature.

[0775] Input: Captured weather data

[0776] Output: A trained wind direction prediction model

[0777] Step 3: Predicting the spread of the fire

[0778] The server uses the constructed wind direction prediction model and the latest weather and fire data to predict the spread of the fire. The weather data is input into the wind direction prediction model, and the direction and speed of the fire spread are calculated from the prediction results.

[0779] Inputs: Latest weather and fire data, wind forecast model

[0780] Output: Fire spread prediction results (direction and speed)

[0781] Step 4: Calculate evacuation routes

[0782] The server calculates a safe evacuation route based on the fire spread prediction results and the user's current location. It uses an algorithm to find the shortest route to avoid the spread of the fire and determines the route from the user's current location to a safe evacuation location.

[0783] Input: Fire spread prediction results, user's current location

[0784] Output: Safe escape route

[0785] Step 5: Notify evacuation routes

[0786] The server then sends the calculated evacuation route to the user's device, which then visualizes the route on a map and provides accurate evacuation instructions to the user.

[0787] Input: Calculated evacuation route

[0788] Output: Display of evacuation route on user terminal

[0789] Step 6: Real-time updates of weather and fire data

[0790] The server monitors weather and fire data in real time, periodically acquiring new data, and repeats steps 2 through 5 based on the new data, recalculating evacuation routes as needed.

[0791] Input: Real-time updated weather and fire data

[0792] Output: Updated evacuation route

[0793] Step 7: Prompt generation provides evacuation instructions

[0794] The server uses a prompt generation function to provide appropriate evacuation instructions to the user. The generated prompts are displayed in a user-friendly format using natural language processing (NLP) technology.

[0795] Input: Calculated evacuation routes and current fire situation

[0796] Output: Appropriate evacuation instructions (prompt) provided to the user

[0797] The above steps result in a system that can quickly and accurately calculate evacuation routes based on meteorological and fire data and notify users of these routes. This system will be a powerful support tool for ensuring user safety in the event of a fire.

[0798] 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.

[0799] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[0800] Data Acquisition

[0801] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0802] Building the model

[0803] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0804] Fire spread prediction

[0805] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0806] Evacuation route calculation

[0807] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0808] Notification of evacuation routes

[0809] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0810] Emotion recognition and response

[0811] The device uses an emotion engine to recognize the user's emotions and adjusts the content and display of evacuation instructions depending on the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner.

[0812] Specific examples

[0813] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[0814] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and even send a short message advising them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculating the evacuation route as necessary and sending the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[0815] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0816] The processing flow will be explained below.

[0817] Step 1:

[0818] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0819] Step 2:

[0820] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0821] Step 3:

[0822] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[0823] Step 4:

[0824] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[0825] Step 5:

[0826] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[0827] Step 6:

[0828] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[0829] Step 7:

[0830] The device uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice and facial expressions when confirming evacuation instructions on the device to determine the user's stress level and emotional state.

[0831] Step 8:

[0832] The device can adjust the content and display of evacuation instructions based on the user's perceived emotions. For example, if the user is experiencing high stress levels, the device will simplify the instructions and change the color of the evacuation route display to a more visible color.

[0833] Step 9:

[0834] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[0835] Step 10:

[0836] The device will notify the user of updated evacuation routes in real time, allowing them to continue evacuating safely by following the new instructions.

[0837] Examples:

[0838] For example, if a fire breaks out around Tokyo Station, the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, the system will operate as follows:

[0839] The server builds a wind direction prediction model based on this weather data and predicts wind direction.

[0840] The server predicts that the fire will spread to the north-northeast and calculates the optimal evacuation route to avoid the fire spreading.

[0841] The server sends the calculated evacuation route to the user's terminal.

[0842] The device displays the route on a map and instructs the user to "evacuate towards the west."

[0843] The device recognizes the user's emotions and, if it determines that the stress level is high, it will provide more concise instructions and make the display more noticeable.

[0844] The user follows the instructions and begins evacuation.

[0845] The server monitors weather and fire data, recalculates evacuation routes as needed, and sends updated routes to the device.

[0846] The device will notify the user of the updated route, allowing them to continue their evacuation safely.

[0847] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0848] Example 2

[0849] 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."

[0850] Accurate wind direction and fire spread forecasts are essential for swift and safe evacuation in the event of a fire. However, current systems have difficulty in doing this in real time, and evacuation routes are not optimized sufficiently. Furthermore, they do not provide flexible evacuation instructions that take into account the user's emotional state. This can lead to stress and confusion, making it difficult for users to take appropriate evacuation actions.

[0851] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, and means for recognizing the user's emotions and adjusting the content and display method of evacuation instructions. This enables quick and safe evacuation that takes the user's emotional state into consideration, and always provides an optimal evacuation route based on the latest information.

[0852] "Weather data" refers to information about weather conditions, such as wind speed, wind direction, humidity, and temperature.

[0853] A "wind direction prediction model" refers to a mathematical or machine learning model that uses input meteorological data such as wind speed, humidity, and temperature to predict wind direction.

[0854] "Fire data" refers to information about fires, such as the coordinates of the fire's location, the scale of the fire, and the progress of the fire.

[0855] "Methods for predicting fire spread" refers to algorithms and methods that use wind direction prediction models to calculate how far and in what direction a fire will spread.

[0856] "Means for calculating evacuation routes" refers to an algorithm for calculating the spread of fire and the optimal route from the user's current location to a safe evacuation location.

[0857] "Means for transmitting the calculated evacuation route to the terminal" refers to a communication means for transmitting information about the evacuation route from the server to the user's terminal.

[0858] "Means for recognizing user emotions" refers to sensors, software, and algorithms for detecting a user's emotional state.

[0859] "Means for adjusting the content and display of evacuation instructions" refers to algorithms and methods for changing and adjusting the evacuation route and message display depending on the recognized emotional state of the user.

[0860] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. Each process in this system is explained in detail below.

[0861] Data Acquisition

[0862] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. This allows you to always have the latest weather conditions in real time. It also obtains fire data such as the coordinates of the fire's location and its scale. Specifically, this data is obtained using an API.

[0863] Building the model

[0864] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. For example, the model is trained using the Python library Scikit-learn. This wind direction prediction model is then used to predict wind direction based on newly acquired weather data.

[0865] Fire spread prediction

[0866] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast. This makes it possible to determine the direction and extent of the fire's progress.

[0867] Evacuation route calculation

[0868] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses a path-finding algorithm such as Dijkstra's algorithm. The important thing here is to set the fire damage area as an obstacle and calculate a route that avoids it. For example, the route calculation is performed using the open-source library NetworkX.

[0869] Notification of evacuation routes

[0870] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the user's device of this list. This notification is usually done via the Internet.

[0871] Emotion recognition and response

[0872] The device uses an emotion engine to recognize the user's emotions. For example, it can use a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. Depending on the recognized emotion, the device can adjust the content and display of evacuation instructions. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display messages such as "Please remain calm and act calmly."

[0873] Specific examples

[0874] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[0875] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and advise them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[0876] Prompt Sentence Examples

[0877] "Given weather data and fire data for the area around Tokyo Station, with a wind speed of 10 m / s, a wind direction of north-northeast, humidity of 50%, and a temperature of 20 degrees, calculate the optimal evacuation route. Please also take into account the user's emotional state."

[0878] The above is a specific embodiment for carrying out the present invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0879] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0880] Step 1: Get the data

[0881] The server communicates with external systems such as the meteorological bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. The collected data is obtained through API requests. For example, the JSON data obtained as a response from the API is parsed to extract the necessary weather data. Fire data such as the coordinates of the fire's location and its scale is also obtained in a similar manner. The input is the API endpoint, and the output is data such as wind speed, wind direction, humidity, temperature, fire coordinates, and fire scale.

[0882] Step 2: Building a wind direction prediction model

[0883] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model that uses the collected wind speed, humidity, and temperature as input data and wind direction as output data. For example, it uses Python's Scikit-learn library to create a linear regression model and fit it with the training data. The input is weather data (wind speed, humidity, temperature), and the output is a wind direction prediction model.

[0884] Step 3: Predict wind direction

[0885] The server inputs the latest weather data into a wind direction prediction model to predict the current wind direction. It uses a trained linear regression model to input the latest wind speed, humidity, and temperature data to predict wind direction. For example, if the wind speed is 10 m / s, humidity is 50%, and the temperature is 20 degrees, these values ​​are input into the model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction.

[0886] Step 4: Predicting the spread of the fire

[0887] The server calculates how far and in what direction the fire will spread based on the predicted wind direction. For example, if the wind speed is 10 m / s and the wind is blowing north-northeast, the fire is predicted to spread north-northeast. An algorithm is implemented to calculate the distance the fire will spread based on the wind speed. The input is the predicted wind direction and wind speed, and the output is the direction and distance the fire will spread.

[0888] Step 5: Calculate evacuation routes

[0889] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses Dijkstra's algorithm. The fire damage area is set as an obstacle, and the route is calculated to avoid it. For example, an algorithm is run to find the shortest route using information on the user's current location and evacuation location. The input is information on the spread of the fire and the coordinates of the user's current location and evacuation location, and the output is the calculated evacuation route.

[0890] Step 6: Notify evacuation routes

[0891] The server sends the calculated evacuation route to the user's device. Specifically, it generates a list of evacuation route coordinates and notifies the user's device. The data is converted to JSON format and sent via the Internet. The input is the calculated evacuation route information, and the output is the evacuation route sent to the user's device.

[0892] Step 7: Emotion recognition and response

[0893] The device uses an emotion engine to recognize the user's emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. The device adjusts the content and display of evacuation instructions according to the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display a message such as "Please remain calm." The input is the user's facial expressions and voice information, and the output is the display of adjusted evacuation instructions.

[0894] (Application example 2)

[0895] 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."

[0896] In the event of a fire, quick and safe evacuation is required, but conventional systems have difficulty predicting the spread of fire or calculating evacuation routes in real time, and they have also been unable to provide appropriate evacuation guidance that takes into account the user's emotional state. As a result, there have been issues with reducing user stress during evacuation and providing reliable evacuation guidance.

[0897] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0898] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of the fire, means for transmitting the calculated evacuation route to the terminal, means for recognizing a user's emotion, and means for adjusting the content and display method of evacuation instructions in accordance with the recognized user's emotion. This makes it possible to predict the spread of a fire and provide an optimal evacuation route in real time when a fire occurs, and further makes it possible to provide appropriate evacuation guidance based on the user's emotional state.

[0899] "Weather data" refers to data relating to weather conditions such as wind speed, wind direction, humidity, and temperature.

[0900] A "wind direction model" is a mathematical model for predicting wind direction based on specific meteorological data.

[0901] "Fire data" refers to data that includes information on the coordinates of the location of the fire and the scale of the fire.

[0902] A "means for predicting the spread of a fire" is a means for calculating the direction and extent of a fire's spread using a wind direction model.

[0903] "Means for calculating evacuation routes" refers to algorithms or procedures for calculating the optimal evacuation route that avoids the spread of fire.

[0904] "Means for recognizing user emotions" refers to technology for determining a user's emotional state by analyzing the user's facial expressions, voice, etc.

[0905] The "means for adjusting the content and display method of evacuation instructions" refers to a means for changing the display method of evacuation routes and guidance depending on the emotional state of the user.

[0906] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[0907] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[0908] Data Acquisition

[0909] To collect weather data, the server communicates with external systems such as meteorological and fire departments to obtain data on wind speed, wind direction, humidity, temperature, etc. It also collects fire data such as the coordinates of fire locations and information on the scale of fires.

[0910] Building the model

[0911] The server builds a wind direction prediction model based on the acquired weather data. Specifically, it uses a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model predicts wind direction based on weather conditions and estimates the direction of fire spread.

[0912] Fire spread prediction

[0913] The server inputs the latest weather data into the wind direction prediction model it has built to predict the current wind direction. For example, if the wind speed is 10 m / s and blowing north-northeast, it predicts that the fire will spread north-northeast.

[0914] Evacuation route calculation

[0915] The server calculates the optimal evacuation route to avoid the predicted direction of fire spread. It uses algorithms such as Dijkstra's algorithm to derive the shortest route from the user's current location to a safe evacuation site. It treats the predicted fire spread as an obstacle and optimizes the route to avoid it.

[0916] Notification of evacuation routes

[0917] The calculated evacuation route is sent from the server to the user's device. Specifically, a list of the evacuation route coordinates is generated and notified to the device.

[0918] Emotion recognition and response

[0919] The device uses an emotion engine to recognize the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine their stress level. Based on the recognized emotion, it adjusts the content and display method of evacuation instructions. For example, if the user is in a state of high stress, it will make the evacuation route display simpler and easier to understand.

[0920] Specific examples

[0921] For example, suppose a fire breaks out near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this data to build a wind direction prediction model and predicts the wind direction to be north-northeast. As the fire is predicted to spread north-northeast, the server calculates an evacuation route based on this information and sends it to the user's device. If the emotion engine recognizes that the user's stress level is high, the device will simplify the display of the evacuation route and display a message such as "Please remain calm and act accordingly."

[0922] Prompt Sentence Examples

[0923] "Your current location is 35.6895, 139.6917. Please calculate an evacuation route based on the latest wind speed of 10 m / s, wind direction north-northeast, humidity of 50%, and temperature of 20 degrees."

[0924] This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[0925] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0926] Step 1:

[0927] The server collects meteorological data, specifically data such as wind speed, wind direction, humidity, and temperature, from the APIs of the weather bureau and fire department, allowing real-time weather information to be collected on the server.

[0928] Input: API of weather station and fire department

[0929] Output: Weather data such as wind speed, wind direction, humidity, and temperature

[0930] Step 2:

[0931] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a linear regression model to learn how to predict wind direction using wind speed, humidity, and temperature as inputs.

[0932] Input: Weather data such as wind speed, wind direction, humidity, and temperature

[0933] Output: Wind direction prediction model

[0934] Step 3:

[0935] The server collects fire data, specifically, obtaining information on the coordinates of the fire's location and its scale from the fire department's API.

[0936] Input: Fire Department API

[0937] Output: Coordinates of the fire location, data on the fire's scale

[0938] Step 4:

[0939] The server uses a wind direction prediction model to predict the spread of the fire. Collected weather data is input into the wind direction prediction model to predict the current wind direction. Next, based on the predicted wind direction and fire data, it calculates the direction and extent of the fire's spread.

[0940] Inputs: Wind direction prediction model, latest weather data, fire data

[0941] Output: Fire spread prediction results (direction and distance)

[0942] Step 5:

[0943] The server calculates the optimal evacuation route to avoid the spread of the fire. Specifically, it uses algorithms such as Dijkstra's algorithm to calculate the shortest route from the user's current location to a safe evacuation site. The predicted fire spread is treated as an obstacle, and the route is optimized to avoid it.

[0944] Input: User's current location, fire spread prediction results

[0945] Output: Evacuation route

[0946] Step 6:

[0947] The server sends the calculated evacuation route to the user's device, which then notifies the device of the coordinates of the evacuation route and displays it as a visual navigation system.

[0948] Input: List of evacuation route coordinates

[0949] Output: Evacuation route notification to user terminal

[0950] Step 7:

[0951] The device recognizes the user's emotions by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then uses an emotion engine to determine the user's stress level.

[0952] Input: Camera input, microphone input

[0953] Output: User's emotional state (stress level)

[0954] Step 8:

[0955] The device adjusts the content and display of evacuation instructions based on the user's emotions. For example, if the user's stress level is high, the device will change the display of evacuation routes to a simpler and easier-to-understand format and display the necessary messages.

[0956] Input: User's emotional state, evacuation route

[0957] Output: Coordinated evacuation instructions and messages

[0958] Step 9:

[0959] The user begins evacuation by following the evacuation route provided by the device, which continues to provide real-time notifications about the evacuation route and updates it as necessary.

[0960] Input: Coordinated evacuation orders and messages

[0961] Output: Evacuation, real-time notification

[0962] 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.

[0963] 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.

[0964] 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.

[0965] [Fourth embodiment]

[0966] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0967] 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.

[0968] 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).

[0969] 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.

[0970] 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.

[0971] 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).

[0972] 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.

[0973] 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.

[0974] 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.

[0975] 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.

[0976] 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.

[0977] 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.

[0978] 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."

[0979] This invention relates to a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes. To implement this system, the following processes are performed.

[0980] Data Acquisition

[0981] The server communicates with external systems such as meteorological and fire departments to collect weather and fire data. Weather data includes wind speed, wind direction, humidity, temperature, etc. Fire data includes the coordinates of the fire's location and its scale.

[0982] Building the model

[0983] The server uses the acquired weather data to build a wind direction prediction model. Specifically, it trains a regression model that uses the collected weather data as input data and wind direction as output data. This makes it possible to predict which direction the wind will blow under specific weather conditions.

[0984] Fire spread prediction

[0985] The server uses the wind direction prediction model it has created to predict the spread of the fire. It predicts wind direction using meteorological data as input, and then calculates the direction and extent of the fire's spread based on that information. This prediction is made in real time, responding to the ever-changing situation of the fire.

[0986] Evacuation route calculation

[0987] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. This calculation uses an algorithm to find the shortest route from the user's current location to a safe evacuation site. The calculation takes into account the extent of the fire damage as an obstacle and determines the route to avoid it.

[0988] Notification of evacuation routes

[0989] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides the user with accurate evacuation instructions. Even after the user begins evacuation, the server recalculates the route in real time based on the latest weather and fire data, and re-notifies the device of the evacuation route as necessary.

[0990] Specific examples

[0991] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. To help the user evacuate safely, the server then calculates an evacuation route that avoids the spread of the fire and sends that route to the user's device. The device displays the route on a map and advises the user to "evacuate toward the west." Once the user begins evacuation, the server continues to monitor the weather and fire data, and calculates a new route if necessary and sends it to the device.

[0992] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[0993] The processing flow will be explained below.

[0994] Step 1:

[0995] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[0996] Step 2:

[0997] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[0998] Step 3:

[0999] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[1000] Step 4:

[1001] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[1002] Step 5:

[1003] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[1004] Step 6:

[1005] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[1006] Step 7:

[1007] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[1008] Step 8:

[1009] The device will notify the user of updated evacuation routes in real time, helping them to follow the new instructions and continue evacuating safely.

[1010] The above is the flow of specific processing steps of the system based on the present invention. This process can support quick and safe evacuation in the event of a fire.

[1011] Example 1

[1012] 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."

[1013] In recent years, there has been a growing demand for rapid and efficient evacuation in urban areas in the event of a fire. However, a system that predicts the spread of a fire and provides optimal evacuation routes based on that information has not yet been fully established. In particular, systems that integrate meteorological and fire data and have the ability to recalculate and update evacuation routes in real time are rare. As a result, many victims are unable to evacuate quickly and effectively, making it difficult to avoid serious damage. The present invention aims to solve these problems and provide a system that enables rapid and effective evacuation in the event of a fire.

[1014] 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.

[1015] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for preprocessing the collected weather data, means for predicting the spread of a fire using the wind direction model, means for simulating the extent of fire spread based on the weather data and the wind direction prediction model, means for calculating an optimal evacuation route that avoids the predicted spread of the fire, and means for transmitting the calculated evacuation route to the terminal. This makes it possible to construct a wind direction prediction model based on weather data and fire data at the time of a fire outbreak, simulate the spread of a fire using the prediction results, and calculate and notify evacuation routes in real time.

[1016] "Weather data" refers to information related to weather, such as wind speed, wind direction, humidity, and temperature.

[1017] "Means for collection" is a general term for hardware and software for obtaining necessary data from external systems.

[1018] "Means for constructing a model" refers to the algorithms and software used to generate predictive models based on acquired data.

[1019] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions.

[1020] "Fire data" is information related to a fire, such as the coordinates of the location where the fire occurred and the scale of the fire.

[1021] "Preprocessing" is the process of normalizing data and filling in missing values ​​in order to build a model.

[1022] "Means for simulating" refers to software or algorithms that virtually reproduce phenomena using predictive models and derive results.

[1023] "Means for calculating evacuation routes" refers to algorithms or methodologies for finding optimal evacuation routes.

[1024] A "terminal" is an electronic device that a user uses to receive information.

[1025] "Means for notifying" refers to the process or tool for transmitting calculated information to a user terminal.

[1026] This invention relates to a system that uses weather data and fire data in an integrated manner to predict the spread of a fire, calculate the optimal evacuation route, and notify the user. This system is composed of several main elements, each of which works together to realize the invention.

[1027] Data Acquisition

[1028] The server communicates with external systems such as meteorological and fire departments via APIs to collect the necessary weather and fire data. Weather data includes wind speed, direction, humidity, temperature, etc., and uses the OpenWeatherMap API, for example. Fire data includes the coordinates of the fire's location and its scale, and uses a dedicated API provided by the local fire department.

[1029] Data Preprocessing

[1030] The server preprocesses the collected weather data, which includes normalizing the data and filling in missing values. Preprocessing improves the quality of the data and increases the accuracy of the model.

[1031] Building a wind direction prediction model

[1032] The server builds a wind direction prediction model using machine learning libraries such as TensorFlow and PyTorch. It trains a regression model that uses collected weather data as input and wind direction as output. This model is retrained overnight as a batch process.

[1033] Fire spread prediction

[1034] The server inputs the latest weather data into a wind direction prediction model to predict wind direction. Based on this, it simulates the spread of the fire in real time. By combining the predicted wind direction with fire data, it calculates the direction and extent of the fire's spread.

[1035] Evacuation route calculation

[1036] The server calculates the optimal evacuation route to avoid the predicted spread of the fire. For example, it uses the A algorithm to search for the shortest route that avoids obstacles. It obtains the user's current location information and calculates the route to a safe evacuation location.

[1037] Notification of evacuation routes

[1038] The server sends the calculated evacuation route to the user's device. The device displays the received route information in a map application and notifies the user. The map display uses the Google Maps API. Once the user begins evacuation, the server continues to monitor the data, calculates a new route as needed, and sends it to the device.

[1039] Specific examples

[1040] For example, consider a fire occurring near Tokyo Station. The wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20°C. Based on this data, the server builds a wind direction prediction model and predicts the wind direction to be north-northeast. It then predicts that the fire will spread north-northeast and calculates the optimal route for the user to evacuate. The calculated route is sent to the device, and the user is prompted to "Evacuate heading west." Once the user begins evacuation, the server continues to monitor weather and fire data and calculates new routes as needed.

[1041] Prompt Sentence Examples

[1042] "A fire has broken out near Tokyo Station. If the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, please predict the spread of the fire and the optimal evacuation route."

[1043] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1044] Step 1: Get the data

[1045] The server obtains weather and fire data through the APIs of the meteorological and fire departments. Specifically, it sends an HTTP request and receives data such as wind speed, wind direction, humidity, temperature, coordinates of the fire's location, and the scale of the fire. The data input is the response data from the API, and the output is the storage of the various collected data in a database.

[1046] Step 2: Preprocessing the data

[1047] The server preprocesses the collected weather data. The input is the raw data collected in step 1, and the output is weather data after normalization and missing value imputation. This includes unifying the data format, imputing missing values, and detecting and processing outliers. Specifically, it references historical data and executes an algorithm to impute missing data.

[1048] Step 3: Building a wind direction prediction model

[1049] The server builds a wind direction prediction model based on the preprocessed weather data. The input is normalized weather data, and the output is a trained wind direction prediction model. The regression model is trained using machine learning libraries such as TensorFlow and PyTorch. Specifically, weather data from each past month is input into the model training, and the accuracy of the model is also evaluated.

[1050] Step 4: Predict wind direction

[1051] The server inputs current weather data using the constructed forecast model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction. Specifically, the latest data is input into the model and the wind direction forecast result is obtained.

[1052] Step 5: Predicting the spread of the fire

[1053] The server simulates the spread of a fire based on predicted wind direction and fire data. The input is the predicted wind direction and initial fire data, and the output is the extent of the fire spread. Specifically, it applies a fire spread algorithm using a simulation grid.

[1054] Step 6: Calculate evacuation routes

[1055] The server calculates the optimal evacuation route to avoid the spread of the fire. The input is the extent of the fire spread and the user's current location data, and the output is the calculated evacuation route. For example, the server uses the A algorithm to search for an evacuation route and reflects the fire spread information in the route.

[1056] Step 7: Notify evacuation routes

[1057] The server sends the calculated evacuation route to the user's device. The input is the evacuation route data calculated in step 6, and the output is the route information displayed on the device. Specifically, the server sends the route data to the device in JSON format, and the device visualizes the route on a map using the Google Maps API.

[1058] Step 8: Real-time data updates and route recalculation

[1059] The server continuously monitors updates to weather and fire data and recalculates evacuation routes as needed. The input is newly acquired weather and fire data, and the output is updated evacuation routes. Specifically, the model is reevaluated each time new data is acquired, and route recalculation and notification are automatically performed.

[1060] (Application example 1)

[1061] 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."

[1062] Conventional fire evacuation systems can predict wind direction and the spread of fires based on meteorological and fire data, but they lack the ability to update data in real time or recalculate evacuation routes, making them insufficient for ensuring user safety. Furthermore, they lack a mechanism for visualizing evacuation routes and fire spread predictions on users' devices and providing appropriate evacuation instructions. Therefore, a system is needed that can efficiently predict the direction and extent of fire spread under specific weather conditions and provide quick and appropriate evacuation routes.

[1063] 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.

[1064] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, means for updating the weather data and fire data in real time to recalculate the evacuation route, and means for notifying the user of the latest evacuation route. This makes it possible to quickly and accurately recalculate an evacuation route based on the weather data and fire data updated in real time, and to provide the user with appropriate evacuation instructions.

[1065] "Weather data" is information about weather conditions such as wind speed, wind direction, humidity, and temperature.

[1066] A "wind direction prediction model" is a regression model for predicting wind direction under specific weather conditions based on collected weather data.

[1067] "Fire data" refers to information about a fire, including the coordinates of the location where the fire occurred and the scale of the fire.

[1068] "Fire spread prediction" is a process that uses a wind direction prediction model to predict in which direction and how far a fire will spread.

[1069] An "escape route" is the optimal route for a user to safely evacuate from a fire.

[1070] A "terminal" is a device used by a user, such as a smartphone or a personal computer.

[1071] "Real-time updates" means that weather and fire data are continuously updated with the latest information, and the system processes based on that information.

[1072] The "prompt generation function" is a function that creates automatically generated sentences to provide appropriate evacuation instructions to the user.

[1073] This invention provides a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of a fire, and calculates and notifies optimal evacuation routes.

[1074] The server collects weather data and fire data from external systems (weather data providers and fire data providers). Weather data includes information such as wind speed, wind direction, humidity, and temperature. Fire data includes information such as the coordinates of the fire outbreak point and the scale of the fire.

[1075] The server then builds a wind direction prediction model based on the collected weather data. This model is trained using machine learning techniques (e.g., linear regression using scikit-learn). The prediction model can predict wind direction under specific weather conditions.

[1076] Using the constructed wind direction prediction model, the server inputs fire data and the latest weather data to predict the spread of the fire. Based on this prediction information, the server calculates a route that the user can safely evacuate. The server uses an algorithm to find the shortest route from the user's current location to a safe evacuation site, taking the fire damage area into account as an obstacle when determining the route.

[1077] The server sends the calculated evacuation route to the user's device. The device visualizes the received evacuation route on a map and provides accurate evacuation instructions to the user. In addition, the server continuously updates meteorological and fire data in real time, recalculates the evacuation route as needed, and notifies the device again of the latest evacuation route. It also has a prompt generation function that provides the user with appropriate evacuation instructions.

[1078] Specific examples

[1079] For example, suppose a fire breaks out while the user is near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then notifies the user's device, "Please evacuate heading west." Once the user begins evacuation, the server continues to monitor the weather and fire data, calculating a new route if necessary and re-notifying the device.

[1080] Prompt Sentence Examples

[1081] "When a user is near Tokyo Station, they launch the FireSafe app. The app retrieves real-time weather and fire data, and based on that data, uses a wind direction prediction model to predict the spread of the fire. The app then calculates a safe evacuation route from the user's current location and notifies them, saying, 'Please evacuate heading west.' Once the user begins to evacuate, the app continues to monitor weather and fire data, recalculating evacuation routes as necessary and notifying the user."

[1082] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire.

[1083] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1084] Step 1: Collect weather and fire data

[1085] The server communicates with weather data providers and fire data providers to obtain real-time weather data (wind speed, wind direction, humidity, temperature, etc.) and fire data (coordinates of the outbreak point, scale of the fire, etc.). This data is sent to the server using an external API.

[1086] Input: Weather and fire data provided by external systems

[1087] Output: Weather and fire data stored on a server

[1088] Step 2: Building a wind direction prediction model

[1089] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a machine learning library (e.g., scikit-learn) to train a regression model that predicts wind direction from inputs such as wind speed, humidity, and temperature.

[1090] Input: Captured weather data

[1091] Output: A trained wind direction prediction model

[1092] Step 3: Predicting the spread of the fire

[1093] The server uses the constructed wind direction prediction model and the latest weather and fire data to predict the spread of the fire. The weather data is input into the wind direction prediction model, and the direction and speed of the fire spread are calculated from the prediction results.

[1094] Inputs: Latest weather and fire data, wind forecast model

[1095] Output: Fire spread prediction results (direction and speed)

[1096] Step 4: Calculate evacuation routes

[1097] The server calculates a safe evacuation route based on the fire spread prediction results and the user's current location. It uses an algorithm to find the shortest route to avoid the spread of the fire and determines the route from the user's current location to a safe evacuation location.

[1098] Input: Fire spread prediction results, user's current location

[1099] Output: Safe escape route

[1100] Step 5: Notify evacuation routes

[1101] The server then sends the calculated evacuation route to the user's device, which then visualizes the route on a map and provides accurate evacuation instructions to the user.

[1102] Input: Calculated evacuation route

[1103] Output: Display of evacuation route on user terminal

[1104] Step 6: Real-time updates of weather and fire data

[1105] The server monitors weather and fire data in real time, periodically acquiring new data, and repeats steps 2 through 5 based on the new data, recalculating evacuation routes as needed.

[1106] Input: Real-time updated weather and fire data

[1107] Output: Updated evacuation route

[1108] Step 7: Prompt generation provides evacuation instructions

[1109] The server uses a prompt generation function to provide appropriate evacuation instructions to the user. The generated prompts are displayed in a user-friendly format using natural language processing (NLP) technology.

[1110] Input: Calculated evacuation routes and current fire situation

[1111] Output: Appropriate evacuation instructions (prompt) provided to the user

[1112] The above steps result in a system that can quickly and accurately calculate evacuation routes based on meteorological and fire data and notify users of these routes. This system will be a powerful support tool for ensuring user safety in the event of a fire.

[1113] 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.

[1114] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[1115] Data Acquisition

[1116] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[1117] Building the model

[1118] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[1119] Fire spread prediction

[1120] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[1121] Evacuation route calculation

[1122] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[1123] Notification of evacuation routes

[1124] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[1125] Emotion recognition and response

[1126] The device uses an emotion engine to recognize the user's emotions and adjusts the content and display of evacuation instructions depending on the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner.

[1127] Specific examples

[1128] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[1129] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and even send a short message advising them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculating the evacuation route as necessary and sending the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[1130] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[1131] The processing flow will be explained below.

[1132] Step 1:

[1133] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature, as well as fire data such as the coordinates of the fire's location and its scale.

[1134] Step 2:

[1135] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model is used to predict wind direction based on weather conditions.

[1136] Step 3:

[1137] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast.

[1138] Step 4:

[1139] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses algorithms such as Dijkstra's algorithm to find the shortest route from the user's current location to a safe evacuation site. Based on the fire spread prediction, the fire damage area is set as an obstacle and the route is calculated to avoid it.

[1140] Step 5:

[1141] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the device of the list.

[1142] Step 6:

[1143] The device then visualizes the received evacuation route on a map, providing specific instructions such as "Follow this route to evacuate" to make it easier for users to evacuate.

[1144] Step 7:

[1145] The device uses an emotion engine to recognize the user's emotions, for example, by analyzing the user's voice and facial expressions when confirming evacuation instructions on the device to determine the user's stress level and emotional state.

[1146] Step 8:

[1147] The device can adjust the content and display of evacuation instructions based on the user's perceived emotions. For example, if the user is experiencing high stress levels, the device will simplify the instructions and change the color of the evacuation route display to a more visible color.

[1148] Step 9:

[1149] The user begins to move to a safe evacuation location by following the evacuation route displayed on the device. Even during the evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device.

[1150] Step 10:

[1151] The device will notify the user of updated evacuation routes in real time, allowing them to continue evacuating safely by following the new instructions.

[1152] Examples:

[1153] For example, if a fire breaks out around Tokyo Station, the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees, the system will operate as follows:

[1154] The server builds a wind direction prediction model based on this weather data and predicts wind direction.

[1155] The server predicts that the fire will spread to the north-northeast and calculates the optimal evacuation route to avoid the fire spreading.

[1156] The server sends the calculated evacuation route to the user's terminal.

[1157] The device displays the route on a map and instructs the user to "evacuate towards the west."

[1158] The device recognizes the user's emotions and, if it determines that the stress level is high, it will provide more concise instructions and make the display more noticeable.

[1159] The user follows the instructions and begins evacuation.

[1160] The server monitors weather and fire data, recalculates evacuation routes as needed, and sends updated routes to the device.

[1161] The device will notify the user of the updated route, allowing them to continue their evacuation safely.

[1162] The above is a specific embodiment for carrying out the invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[1163] Example 2

[1164] 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."

[1165] Accurate wind direction and fire spread forecasts are essential for swift and safe evacuation in the event of a fire. However, current systems have difficulty in doing this in real time, and evacuation routes are not optimized sufficiently. Furthermore, they do not provide flexible evacuation instructions that take into account the user's emotional state. This can lead to stress and confusion, making it difficult for users to take appropriate evacuation actions.

[1166] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of a fire, means for transmitting the calculated evacuation route to the terminal, and means for recognizing the user's emotions and adjusting the content and display method of evacuation instructions. This enables quick and safe evacuation that takes the user's emotional state into consideration, and always provides an optimal evacuation route based on the latest information.

[1167] "Weather data" refers to information about weather conditions, such as wind speed, wind direction, humidity, and temperature.

[1168] A "wind direction prediction model" refers to a mathematical or machine learning model that uses input meteorological data such as wind speed, humidity, and temperature to predict wind direction.

[1169] "Fire data" refers to information about fires, such as the coordinates of the fire's location, the scale of the fire, and the progress of the fire.

[1170] "Methods for predicting fire spread" refers to algorithms and methods that use wind direction prediction models to calculate how far and in what direction a fire will spread.

[1171] "Means for calculating evacuation routes" refers to an algorithm for calculating the spread of fire and the optimal route from the user's current location to a safe evacuation location.

[1172] "Means for transmitting the calculated evacuation route to the terminal" refers to a communication means for transmitting information about the evacuation route from the server to the user's terminal.

[1173] "Means for recognizing user emotions" refers to sensors, software, and algorithms for detecting a user's emotional state.

[1174] "Means for adjusting the content and display of evacuation instructions" refers to algorithms and methods for changing and adjusting the evacuation route and message display depending on the recognized emotional state of the user.

[1175] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. Each process in this system is explained in detail below.

[1176] Data Acquisition

[1177] The server communicates with external systems such as the weather bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. This allows you to always have the latest weather conditions in real time. It also obtains fire data such as the coordinates of the fire's location and its scale. Specifically, this data is obtained using an API.

[1178] Building the model

[1179] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. For example, the model is trained using the Python library Scikit-learn. This wind direction prediction model is then used to predict wind direction based on newly acquired weather data.

[1180] Fire spread prediction

[1181] The server inputs meteorological data into a wind direction prediction model to predict the current wind direction. Based on this predicted wind direction, it calculates the direction and extent of the fire's spread. For example, if the wind speed is 10 m / s and blowing north-northeast, the fire is predicted to spread north-northeast. This makes it possible to determine the direction and extent of the fire's progress.

[1182] Evacuation route calculation

[1183] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses a path-finding algorithm such as Dijkstra's algorithm. The important thing here is to set the fire damage area as an obstacle and calculate a route that avoids it. For example, the route calculation is performed using the open-source library NetworkX.

[1184] Notification of evacuation routes

[1185] The server then sends the calculated evacuation route to the user's device. Specifically, it generates a list of the evacuation route coordinates and notifies the user's device of this list. This notification is usually done via the Internet.

[1186] Emotion recognition and response

[1187] The device uses an emotion engine to recognize the user's emotions. For example, it can use a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. Depending on the recognized emotion, the device can adjust the content and display of evacuation instructions. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display messages such as "Please remain calm and act calmly."

[1188] Specific examples

[1189] For example, consider the case where a fire breaks out near Tokyo Station. Suppose the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this weather data to build a wind direction prediction model and predicts the wind direction to be north-northeast. The server then predicts which direction the fire will spread and determines that it will spread north-northeast. The server then calculates an evacuation route that avoids the spread of the fire so that the user can evacuate safely, and sends that route to the user's device.

[1190] If the emotion engine recognizes that the user's stress level is high, the device will display a simple and easy-to-understand evacuation route to the user and advise them to "stay calm." Even after the user begins evacuation, the server constantly monitors the latest weather and fire data, recalculates the evacuation route as needed, and sends the updated route to the device. The device then notifies the user of the updated evacuation route in real time, allowing them to continue evacuating safely by following the new instructions.

[1191] Prompt Sentence Examples

[1192] "Given weather data and fire data for the area around Tokyo Station, with a wind speed of 10 m / s, a wind direction of north-northeast, humidity of 50%, and a temperature of 20 degrees, calculate the optimal evacuation route. Please also take into account the user's emotional state."

[1193] The above is a specific embodiment for carrying out the present invention. This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[1194] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1195] Step 1: Get the data

[1196] The server communicates with external systems such as the meteorological bureau and fire department to collect weather data such as wind speed, wind direction, humidity, and temperature. The collected data is obtained through API requests. For example, the JSON data obtained as a response from the API is parsed to extract the necessary weather data. Fire data such as the coordinates of the fire's location and its scale is also obtained in a similar manner. The input is the API endpoint, and the output is data such as wind speed, wind direction, humidity, temperature, fire coordinates, and fire scale.

[1197] Step 2: Building a wind direction prediction model

[1198] The server uses the collected weather data to build a wind direction prediction model. Specifically, it trains a linear regression model that uses the collected wind speed, humidity, and temperature as input data and wind direction as output data. For example, it uses Python's Scikit-learn library to create a linear regression model and fit it with the training data. The input is weather data (wind speed, humidity, temperature), and the output is a wind direction prediction model.

[1199] Step 3: Predict wind direction

[1200] The server inputs the latest weather data into a wind direction prediction model to predict the current wind direction. It uses a trained linear regression model to input the latest wind speed, humidity, and temperature data to predict wind direction. For example, if the wind speed is 10 m / s, humidity is 50%, and the temperature is 20 degrees, these values ​​are input into the model to predict wind direction. The input is the latest weather data, and the output is the predicted wind direction.

[1201] Step 4: Predicting the spread of the fire

[1202] The server calculates how far and in what direction the fire will spread based on the predicted wind direction. For example, if the wind speed is 10 m / s and the wind is blowing north-northeast, the fire is predicted to spread north-northeast. An algorithm is implemented to calculate the distance the fire will spread based on the wind speed. The input is the predicted wind direction and wind speed, and the output is the direction and distance the fire will spread.

[1203] Step 5: Calculate evacuation routes

[1204] The server calculates the optimal evacuation route to avoid the spread of the fire. This calculation uses Dijkstra's algorithm. The fire damage area is set as an obstacle, and the route is calculated to avoid it. For example, an algorithm is run to find the shortest route using information on the user's current location and evacuation location. The input is information on the spread of the fire and the coordinates of the user's current location and evacuation location, and the output is the calculated evacuation route.

[1205] Step 6: Notify evacuation routes

[1206] The server sends the calculated evacuation route to the user's device. Specifically, it generates a list of evacuation route coordinates and notifies the user's device. The data is converted to JSON format and sent via the Internet. The input is the calculated evacuation route information, and the output is the evacuation route sent to the user's device.

[1207] Step 7: Emotion recognition and response

[1208] The device uses an emotion engine to recognize the user's emotions. For example, it uses a camera and microphone to analyze the user's facial expressions and voice to detect their emotional state. The device adjusts the content and display of evacuation instructions according to the recognized emotion. For example, if the user is experiencing high stress levels, the device will present evacuation routes in a more concise and easy-to-understand manner. It will also display a message such as "Please remain calm." The input is the user's facial expressions and voice information, and the output is the display of adjusted evacuation instructions.

[1209] (Application example 2)

[1210] 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."

[1211] In the event of a fire, quick and safe evacuation is required, but conventional systems have difficulty predicting the spread of fire or calculating evacuation routes in real time, and they have also been unable to provide appropriate evacuation guidance that takes into account the user's emotional state. As a result, there have been issues with reducing user stress during evacuation and providing reliable evacuation guidance.

[1212] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1213] In this invention, the server includes means for collecting weather data, means for constructing a model for predicting wind direction using the collected weather data, means for collecting fire data, means for predicting the spread of a fire using the wind direction model, means for calculating an optimal evacuation route that avoids the spread of the fire, means for transmitting the calculated evacuation route to the terminal, means for recognizing a user's emotion, and means for adjusting the content and display method of evacuation instructions in accordance with the recognized user's emotion. This makes it possible to predict the spread of a fire and provide an optimal evacuation route in real time when a fire occurs, and further makes it possible to provide appropriate evacuation guidance based on the user's emotional state.

[1214] "Weather data" refers to data relating to weather conditions such as wind speed, wind direction, humidity, and temperature.

[1215] A "wind direction model" is a mathematical model for predicting wind direction based on specific meteorological data.

[1216] "Fire data" refers to data that includes information on the coordinates of the location of the fire and the scale of the fire.

[1217] A "means for predicting the spread of a fire" is a means for calculating the direction and extent of a fire's spread using a wind direction model.

[1218] "Means for calculating evacuation routes" refers to algorithms or procedures for calculating the optimal evacuation route that avoids the spread of fire.

[1219] "Means for recognizing user emotions" refers to technology for determining a user's emotional state by analyzing the user's facial expressions, voice, etc.

[1220] The "means for adjusting the content and display method of evacuation instructions" refers to a means for changing the display method of evacuation routes and guidance depending on the emotional state of the user.

[1221] "Terminal" refers to a device used by a user, such as a smartphone or tablet.

[1222] This invention combines a system that builds a wind direction prediction model based on meteorological data and fire data, predicts the spread of fires, calculates and notifies optimal evacuation routes, and further combines it with an emotion engine that recognizes the user's emotions. To implement this system, the following processes are performed.

[1223] Data Acquisition

[1224] To collect weather data, the server communicates with external systems such as meteorological and fire departments to obtain data on wind speed, wind direction, humidity, temperature, etc. It also collects fire data such as the coordinates of fire locations and information on the scale of fires.

[1225] Building the model

[1226] The server builds a wind direction prediction model based on the acquired weather data. Specifically, it uses a linear regression model with wind speed, humidity, and temperature as input data and wind direction as output data. This model predicts wind direction based on weather conditions and estimates the direction of fire spread.

[1227] Fire spread prediction

[1228] The server inputs the latest weather data into the wind direction prediction model it has built to predict the current wind direction. For example, if the wind speed is 10 m / s and blowing north-northeast, it predicts that the fire will spread north-northeast.

[1229] Evacuation route calculation

[1230] The server calculates the optimal evacuation route to avoid the predicted direction of fire spread. It uses algorithms such as Dijkstra's algorithm to derive the shortest route from the user's current location to a safe evacuation site. It treats the predicted fire spread as an obstacle and optimizes the route to avoid it.

[1231] Notification of evacuation routes

[1232] The calculated evacuation route is sent from the server to the user's device. Specifically, a list of the evacuation route coordinates is generated and notified to the device.

[1233] Emotion recognition and response

[1234] The device uses an emotion engine to recognize the user's emotions. It uses a camera and microphone to analyze the user's facial expressions and voice to determine their stress level. Based on the recognized emotion, it adjusts the content and display method of evacuation instructions. For example, if the user is in a state of high stress, it will make the evacuation route display simpler and easier to understand.

[1235] Specific examples

[1236] For example, suppose a fire breaks out near Tokyo Station. Assume the wind speed is 10 m / s, the wind direction is north-northeast, the humidity is 50%, and the temperature is 20 degrees. The server uses this data to build a wind direction prediction model and predicts the wind direction to be north-northeast. As the fire is predicted to spread north-northeast, the server calculates an evacuation route based on this information and sends it to the user's device. If the emotion engine recognizes that the user's stress level is high, the device will simplify the display of the evacuation route and display a message such as "Please remain calm and act accordingly."

[1237] Prompt Sentence Examples

[1238] "Your current location is 35.6895, 139.6917. Please calculate an evacuation route based on the latest wind speed of 10 m / s, wind direction north-northeast, humidity of 50%, and temperature of 20 degrees."

[1239] This system enables quick and safe evacuation in the event of a fire, and also provides appropriate support according to the user's emotional state.

[1240] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1241] Step 1:

[1242] The server collects meteorological data, specifically data such as wind speed, wind direction, humidity, and temperature, from the APIs of the weather bureau and fire department, allowing real-time weather information to be collected on the server.

[1243] Input: API of weather station and fire department

[1244] Output: Weather data such as wind speed, wind direction, humidity, and temperature

[1245] Step 2:

[1246] The server uses the collected weather data to build a wind direction prediction model. Specifically, it uses a linear regression model to learn how to predict wind direction using wind speed, humidity, and temperature as inputs.

[1247] Input: Weather data such as wind speed, wind direction, humidity, and temperature

[1248] Output: Wind direction prediction model

[1249] Step 3:

[1250] The server collects fire data, specifically, obtaining information on the coordinates of the fire's location and its scale from the fire department's API.

[1251] Input: Fire Department API

[1252] Output: Coordinates of the fire location, data on the fire's scale

[1253] Step 4:

[1254] The server uses a wind direction prediction model to predict the spread of the fire. Collected weather data is input into the wind direction prediction model to predict the current wind direction. Next, based on the predicted wind direction and fire data, it calculates the direction and extent of the fire's spread.

[1255] Inputs: Wind direction prediction model, latest weather data, fire data

[1256] Output: Fire spread prediction results (direction and distance)

[1257] Step 5:

[1258] The server calculates the optimal evacuation route to avoid the spread of the fire. Specifically, it uses algorithms such as Dijkstra's algorithm to calculate the shortest route from the user's current location to a safe evacuation site. The predicted fire spread is treated as an obstacle, and the route is optimized to avoid it.

[1259] Input: User's current location, fire spread prediction results

[1260] Output: Evacuation route

[1261] Step 6:

[1262] The server sends the calculated evacuation route to the user's device, which then notifies the device of the coordinates of the evacuation route and displays it as a visual navigation system.

[1263] Input: List of evacuation route coordinates

[1264] Output: Evacuation route notification to user terminal

[1265] Step 7:

[1266] The device recognizes the user's emotions by analyzing the user's facial expressions and voice using the smartphone's camera and microphone, and then uses an emotion engine to determine the user's stress level.

[1267] Input: Camera input, microphone input

[1268] Output: User's emotional state (stress level)

[1269] Step 8:

[1270] The device adjusts the content and display of evacuation instructions based on the user's emotions. For example, if the user's stress level is high, the device will change the display of evacuation routes to a simpler and easier-to-understand format and display the necessary messages.

[1271] Input: User's emotional state, evacuation route

[1272] Output: Coordinated evacuation instructions and messages

[1273] Step 9:

[1274] The user begins evacuation by following the evacuation route provided by the device, which continues to provide real-time notifications about the evacuation route and updates it as necessary.

[1275] Input: Coordinated evacuation orders and messages

[1276] Output: Evacuation, real-time notification

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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).

[1284] 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.

[1285] 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."

[1286] 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.

[1287] 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).

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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.

[1292] 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.

[1293] 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.

[1294] 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.

[1295] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1296] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1297] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1298] The following is further disclosed regarding the above embodiment.

[1299] (Claim 1)

[1300] a means for collecting meteorological data;

[1301] a means for constructing a model for predicting wind direction using the collected weather data;

[1302] a means for collecting fire data;

[1303] a means of predicting the spread of fire using wind models;

[1304] A means of calculating the optimal escape route to avoid the spread of fire;

[1305] The system includes a means for transmitting the calculated evacuation route to a terminal.

[1306] (Claim 2)

[1307] 10. The system according to claim 1, further comprising means for visualizing the evacuation route on a user's terminal.

[1308] (Claim 3)

[1309] 10. The system of claim 1, further comprising means for recalculating an evacuation route based on updates to the fire data and weather data, and notifying the terminal of the updated evacuation route.

[1310] "Example 1"

[1311] (Claim 1)

[1312] a means for collecting meteorological data;

[1313] a means for constructing a model for predicting wind direction using the collected weather data;

[1314] a means for collecting fire data;

[1315] means for pre-processing the collected weather data;

[1316] a means of predicting the spread of fire using wind models;

[1317] a means for simulating the extent of fire spread based on meteorological data and a wind direction prediction model;

[1318] A means of calculating the optimal escape route to avoid the predicted spread of the fire;

[1319] means for transmitting the calculated evacuation route to the terminal;

[1320] A system including:

[1321] (Claim 2)

[1322] 10. The system of claim 1, further comprising means for visualizing the calculated evacuation route on a user's terminal.

[1323] (Claim 3)

[1324] 10. The system of claim 1, further comprising means for recalculating an evacuation route based on updates to the fire data and weather data, and notifying the terminal of the updated evacuation route.

[1325] "Application Example 1"

[1326] (Claim 1)

[1327] a means for collecting meteorological data;

[1328] a means for constructing a model for predicting wind direction using the collected weather data;

[1329] a means for collecting fire data;

[1330] a means of predicting the spread of fire using wind models;

[1331] A means of calculating the optimal escape route to avoid the spread of fire;

[1332] means for transmitting the calculated evacuation route to the terminal;

[1333] A means of updating weather and fire data in real time to recalculate evacuation routes;

[1334] A system that includes a means for notifying users of updated evacuation routes.

[1335] (Claim 2)

[1336] 2. The system according to claim 1, further comprising means for visualizing the evacuation route and the predicted fire spread on a user's terminal.

[1337] (Claim 3)

[1338] a means for recalculating an evacuation route based on updates of fire data and weather data and notifying the terminal of the updated evacuation route;

[1339] 10. The system of claim 1, further comprising means for generating prompts and providing appropriate evacuation instructions to the user.

[1340] "Example 2: Combining Emotion Engines"

[1341] (Claim 1)

[1342] a means for collecting meteorological data;

[1343] a means for constructing a model for predicting wind direction using the collected weather data;

[1344] a means for collecting fire data;

[1345] a means of predicting the spread of fire using wind models;

[1346] A means of calculating the optimal escape route to avoid the spread of fire;

[1347] means for transmitting the calculated evacuation route to the terminal;

[1348] A system that includes a means to recognize the user's emotions and adjust the content and display of evacuation instructions.

[1349] (Claim 2)

[1350] 10. The system according to claim 1, further comprising means for visualizing the evacuation route on a user's terminal.

[1351] (Claim 3)

[1352] 10. The system of claim 1, further comprising means for recalculating an evacuation route based on updates to the fire data and weather data, and notifying the terminal of the updated evacuation route.

[1353] "Application example 2 when combining emotion engines"

[1354] (Claim 1)

[1355] a means for collecting meteorological data;

[1356] a means for constructing a model for predicting wind direction using the collected weather data;

[1357] a means for collecting fire data;

[1358] a means of predicting the spread of fire using wind models;

[1359] A means of calculating the optimal escape route to avoid the spread of fire;

[1360] means for transmitting the calculated evacuation route to the terminal;

[1361] means for recognizing a user's emotion;

[1362] The system includes a means for adjusting the content and display of evacuation instructions depending on the recognized user emotion.

[1363] (Claim 2)

[1364] 10. The system according to claim 1, further comprising means for visualizing the evacuation route on a user's terminal.

[1365] (Claim 3)

[1366] 10. The system of claim 1, further comprising means for recalculating an evacuation route based on updates to the fire data and weather data, and notifying the terminal of the updated evacuation route. [Explanation of symbols]

[1367] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting meteorological data; a means for constructing a model for predicting wind direction using the collected weather data; a means for collecting fire data; a means of predicting the spread of fire using wind models; A means of calculating the optimal escape route to avoid the spread of fire; The system includes a means for transmitting the calculated evacuation route to a terminal.

2. The system of claim 1 , further comprising means for visualizing the evacuation route on a user's terminal.

3. The system according to claim 1 , further comprising means for recalculating an evacuation route based on updates to the fire data and weather data, and notifying the terminal of the updated evacuation route.

Images