System

Abstract

A system is provided.SOLUTION: A data collection unit that collects position information and a movement history acquired in real time from a plurality of mobile objects when a disaster occurs; a data preprocessing unit that preprocesses the data collected by the data collection unit, deletes an abnormal value, and normalizes the data; A system comprising: a data-analyzing means for predicting a non-passable place and a traffic jam risk by using a generated AI model; a route-optimizing means for calculating an optimum route while avoiding the non-passable place and the traffic jam risk predicted by the data-analyzing means; a route-information-distributing means for distributing optimum route information calculated by the route-optimizing means to terminals; and a real-time route-updating means for recalculating a route by using recollected information based on the optimum route information distributed by the route-information-distributing means.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When a disaster occurs, many ordinary vehicles rush to the affected area, making it difficult for emergency vehicles to reach their destinations, resulting in a serious problem of delays in rescue operations. This can result in the loss of lives that could have been saved. This invention aims to solve this problem by providing an efficient system that enables emergency vehicles to quickly reach their destinations during a disaster without getting caught in traffic jams with ordinary vehicles. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by a system including the following means: when a disaster occurs, the system includes a data collection means that collects location information and movement histories obtained in real time from multiple mobile objects, a data preprocessing means that preprocesses the data collected by the data collection means to remove outliers and normalize the data, a data analysis means that analyzes the data preprocessed by the data preprocessing means and predicts impassable locations and congestion risks using a generative AI model, a route optimization means that calculates an optimal route that avoids the impassable locations and congestion risks predicted by the data analysis means, a route information distribution means that distributes optimal route information calculated by the route optimization means to a terminal, and a real-time route update means that recalculate the route using data recollected based on the optimal route information distributed by the route information distribution means, thereby enabling emergency vehicles to quickly reach their destination without getting caught in traffic jams caused by general vehicles.

[0006] The "data collection means" is a device or system that acquires location information and movement history from multiple mobile objects in real time when a disaster occurs.

[0007] The "data preprocessing means" is a device or system that preprocesses the data collected by the data collection means, removes outliers, and normalizes the data.

[0008] "Data analysis means" refers to a device or system that analyzes pre-processed data and uses a generative AI model to predict impassable areas and congestion risks.

[0009] A "generative AI model" is an algorithm or model that uses deep learning and machine learning to analyze and predict people's behavior and traffic flow.

[0010] The "route optimization means" is a device or system that calculates the optimal route while avoiding impassable areas and congestion risks predicted by the data analysis means.

[0011] The "route information distribution means" is a device or system that distributes the calculated optimum route information to the terminal.

[0012] The "real-time route update means" is a device or system that recalculates and updates the route using data that is recollected based on the distributed optimum route information. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[0035] System Overview

[0036] This system provides an optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[0037] Data collection

[0038] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[0039] Data Preprocessing

[0040] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[0041] Data Analysis and Prediction

[0042] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[0043] Route Optimization

[0044] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[0045] Route information distribution

[0046] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0047] Real-time updates

[0048] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is then redistributed to the device, and the emergency vehicle adjusts its actions based on the latest optimal route.

[0049] Specific examples

[0050] Example 1: Dispatch of emergency vehicles during floods

[0051] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0052] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0053] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0054] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0055] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[0056] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[0057] Example 2: Transporting relief supplies after an earthquake

[0058] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[0059] 2. The server removes outliers and normalizes the data.

[0060] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[0061] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[0062] 5. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[0063] In this way, emergency vehicles can act quickly and rescue operations can be carried out smoothly in the event of a disaster.

[0064] The processing flow will be explained below.

[0065] Step 1: Data collection

[0066] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it obtains current location and speed information from multiple mobile devices. It also integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[0067] Step 2: Data Preprocessing

[0068] The server preprocesses the collected data. First, it detects and removes outliers from the collected data. Next, it standardizes the formats of GPS data and traffic data and performs normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[0069] Step 3: Data analysis

[0070] The server then analyzes the preprocessed data using a generative AI model. For example, the underlying deep learning model learns general traffic patterns based on past data, and then uses newly collected data to predict impassable areas and congestion risks in specific areas.

[0071] Step 4: Identify impassable areas

[0072] The server analyzes the data and determines that a particular road is impassable due to a flood or earthquake. For example, a road at a particular latitude and longitude is predicted to be impassable based on the latest weather and traffic data.

[0073] Step 5: Predict congestion risk

[0074] Based on the results of the data analysis, the server determines that there is a high possibility of traffic congestion in a particular area. For example, congestion is predicted based on a temporary increase in traffic flow around an evacuation shelter.

[0075] Step 6: Route optimization

[0076] The server calculates the optimal route that avoids identified impassable areas and predicted congestion risks. For example, Algorithm A calculates a route for emergency vehicles to use the expressway, generating a route that will allow them to reach their destination safely and quickly.

[0077] Step 7: Route Distribution

[0078] The server distributes optimal route information to the terminals of local governments and rescue teams in real time. For example, the optimal route is displayed on the screen of a terminal at a local government emergency response center, and the person in charge conveys it to the driver of the emergency vehicle providing assistance.

[0079] Step 8: Real-time updates

[0080] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. When new road impassability or congestion occurs, the route is recalculated based on the new collected data and updated optimal route information is distributed. For example, if a new congestion occurs along the way, a new route reflecting that information is recalculated in real time and distributed to the rescue team's terminal.

[0081] In this way, the system always provides the best route based on the latest conditions, enabling emergency vehicles to provide assistance efficiently and quickly.

[0082] Example 1

[0083] 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."

[0084] In the event of a disaster, it is important for emergency vehicles to obtain real-time information on traffic conditions and passable routes and select an appropriate route in order to reach their destination quickly. However, conventional systems do not perform this process efficiently enough, and emergency vehicles may get caught in traffic jams or impassable areas. In addition, a system that can quickly respond to new changes in the situation is required.

[0085] 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.

[0086] In this invention, the server includes a data collection means for collecting location information and movement histories acquired in real time from multiple mobile objects in the event of a disaster, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to terminals, a real-time route update means for recalculating a route using recollected data based on the optimal route information distributed by the route information distribution means, and a means for distributing the recalculated route to each terminal in real time when new data is collected. This enables emergency vehicles to quickly obtain an optimal route and reach their destination quickly even in the event of a disaster.

[0087] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or tsunami occurs, or a man-made disaster such as a fire or accident occurs.

[0088] "Mobile objects" refers to all moving objects, such as cars, motorbikes, and pedestrians, that can provide location information in real time.

[0089] "Real-time" refers to a timeframe in which data collection, processing, and delivery occur almost instantly, with little or no specific delay.

[0090] "Location Information" refers to latitude, longitude and altitude data obtained through location information systems such as GPS.

[0091] "Movement history" refers to data that records the routes and stopping points taken by a moving object over a certain period of time.

[0092] "Data collection means" refers to a device or system for acquiring location information and movement history from a mobile object in real time.

[0093] "Data preprocessing means" refers to a device or program that performs processing to remove outliers from collected data and normalize the data.

[0094] An "outlier" is an inaccurate or unnatural value in the collected data that falls outside the normal range.

[0095] "Data normalization" refers to the process of converting data collected in different formats or units into a consistent format.

[0096] "Generative AI model" refers to an artificial intelligence model that learns patterns from data and is used to make predictions or classifications. Examples include deep learning models.

[0097] "Data analysis means" refers to a device or program that uses preprocessed data to perform processing for a specific purpose, such as predicting impassable areas or congestion risks.

[0098] An "impassable area" refers to a location where vehicles and pedestrians are temporarily or permanently unable to pass due to a disaster, traffic accident, or other cause.

[0099] "Congestion risk" refers to the prediction of situations and locations that may cause traffic flow to slow down.

[0100] "Route optimization means" refers to a device or program for calculating the optimal route based on given conditions and analysis results.

[0101] "Route information distribution means" refers to a device or system for transmitting calculated optimal route information to a terminal in real time.

[0102] "Terminal" refers to mobile terminals and fixed computer systems used by emergency vehicles and local governments.

[0103] "Real-time route update means" refers to a device or program that updates a route in real time by recalculating it based on new data collected.

[0104] The system of the present invention is designed to support efficient rescue operations by emergency vehicles in the event of a disaster. This system uses data collected from mobile objects in real time to calculate and provide optimal routes. Specific embodiments of the system are described below.

[0105] Data collection

[0106] The server collects real-time GPS data from mobile devices, traffic sensor data, and weather data using high-performance data collection equipment and dedicated software. The collected data is used to track the location and movement history of emergency vehicles and general vehicles.

[0107] Data Preprocessing

[0108] The server preprocesses the collected data with high accuracy. Specifically, it removes outliers and normalizes the data. The software used is a program that implements data cleaning tools and normalization algorithms. For example, if GPS data contains abnormal values, it removes them and converts the data into data that is consistent with other formats.

[0109] Data Analysis and Prediction

[0110] The server uses the preprocessed data to train and analyze generative AI models (e.g., deep learning models). This allows for highly accurate prediction of impassable areas and congestion risks. The AI ​​models used are built using architectures such as TensorFlow and PyTorch. For example, they can identify roads and bridges that have become impassable due to floods or earthquakes, and also predict the risk of future traffic congestion.

[0111] Route Optimization

[0112] The server uses the results of the data analysis to calculate the optimal route. In this process, the A algorithm and Dijkstra algorithm are applied. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible. For example, a specific route is calculated to bypass certain impassable areas.

[0113] Route information distribution

[0114] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time using technologies such as HTTP and WebSocket communication, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0115] Real-time updates

[0116] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server automatically detects this, collects new data, and recalculates the route. The updated route information is quickly delivered to the device, allowing the emergency vehicle to adjust its activities based on the latest information.

[0117] Specific examples

[0118] Dispatch of emergency vehicles during floods

[0119] 1. The server collects GPS data, traffic data, and weather data from mobile devices and traffic sensors in real time.

[0120] 2. The server preprocesses the acquired data, removes outliers, and normalizes the data.

[0121] 3. The server uses the generative AI model to identify the locations of bridges that have become impassable due to flooding.

[0122] 4. The server uses the A algorithm to calculate a fast and safe route.

[0123] 5. The server distributes the optimal route to local government and emergency vehicle terminals in real time.

[0124] 6. Emergency vehicles will use this information to quickly reach the affected area.

[0125] Transporting relief supplies in the event of an earthquake

[0126] 1. The server collects traffic and weather data and analyzes impassable areas and congestion risks due to earthquakes.

[0127] 2. The server removes outliers and normalizes the data.

[0128] 3. The server uses the generated AI model to predict future congestion risks.

[0129] 4. The server calculates the optimal route for delivering relief supplies using the Dijkstra algorithm.

[0130] 5. The server distributes the calculated route information to the Self-Defense Forces' terminals in real time.

[0131] 6. The Self-Defense Forces will use this information to effectively transport relief supplies.

[0132] Prompt Sentence Examples

[0133] "Show the best route for emergency vehicles to quickly reach a particular area in the event of flooding."

[0134] "What is the best route to transport relief supplies effectively in the event of an earthquake?"

[0135] In this way, it is possible to realize rapid action by emergency vehicles and smooth rescue operations in the event of a disaster.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1: Data collection

[0138] The server acquires GPS data from mobile devices, traffic sensor data, weather data, and other data in real time. The server connects to each data source and periodically acquires data. The input is raw data acquired from each data source, and the output is a set of collected real-time data. Specifically, the server updates GPS data every 5 seconds and collects data from traffic sensors every 10 seconds.

[0139] Step 2: Data Preprocessing

[0140] The server preprocesses the collected data. Specifically, it fills in missing data, removes outliers, and normalizes the data. The input is the raw data collected in step 1, and the output is the preprocessed clean data. For example, if the GPS data contains abnormal location information, it deletes that data, fills in the missing parts, and standardizes the data format.

[0141] Step 3: Data analysis and prediction

[0142] The server uses the preprocessed data to train a generative AI model and perform analysis. During this process, deep learning models are used to predict impassable areas and congestion risks. The input is preprocessed clean data, and the output is analysis and prediction results. Specifically, it identifies impassable areas due to floods or earthquakes and analyzes past data sets against real-time data to predict future congestion risks.

[0143] Step 4: Route optimization

[0144] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is the analysis results and prediction results, and the output is the optimal route information. For example, it performs specific operations such as avoiding multiple impassable areas and traffic jams and calculating the quickest and safest route.

[0145] Step 5: Route information distribution

[0146] The server distributes the calculated optimal route information to the terminal in real time. This is done using HTTP or WebSocket communication. The input is the optimal route information, and the output is the route information distributed in real time. For example, the server has a list of mobile terminals and fixed computer systems to which it should distribute, and performs the specific operation of sending the latest route information to each terminal in real time.

[0147] Step 6: Real-time updates

[0148] The server collects new data and recalculates the route. When new information about impassable areas or traffic congestion is acquired, it automatically recalculates and redistributes the updated route information. The input is newly collected real-time data, and the output is the latest recalculated route information. Specifically, after new data is collected, it immediately recalculates, generates a new route, and instantly distributes it to each device.

[0149] (Application example 1)

[0150] 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."

[0151] When a disaster occurs, it is important for emergency vehicles to reach their destination quickly and efficiently. However, in reality, emergency vehicle movement is often hindered by ever-changing road conditions and newly emerging obstacles. Furthermore, conventional navigation systems lack the ability to adapt in real time, which can delay the optimization of emergency routes. This can delay rescue efforts and exacerbate disaster damage.

[0152] 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.

[0153] In this invention, the server includes a data collection means for collecting location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to a terminal, a real-time route update means for recalculating a route using re-collected data based on the optimal route information distributed by the route information distribution means, and a means for notifying a smartphone of the route information recalculated by the real-time route update means, thereby enabling rapid and efficient movement of emergency vehicles.

[0154] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or typhoon occurs.

[0155] "Multiple moving objects" refers to various means of transportation such as emergency vehicles, regular vehicles, and drones.

[0156] "Real-time" refers to data acquired continuously in ongoing time.

[0157] "Location information" refers to information about your current location, such as GPS data obtained from a mobile device or vehicle.

[0158] "Movement history" refers to a record of movement based on past location information.

[0159] "Data collection means" refers to the devices and systems used to collect the necessary data.

[0160] "Data preprocessing means" refers to means for preprocessing collected data, such as removing outliers and normalizing data.

[0161] An "outlier" is data that falls outside the normal range.

[0162] "Normalization" refers to the process of standardizing data formats so that they can be handled according to common standards.

[0163] "Data analysis means" refers to a device or system for analyzing collected and pre-processed data.

[0164] A "generative AI model" refers to a machine learning model that uses artificial intelligence to perform data analysis, etc.

[0165] "Impassable areas" refer to areas that are impassable due to disasters or other reasons.

[0166] "Congestion risk" refers to the possibility of traffic flow slowing down.

[0167] "Route optimizer" refers to a device or system for calculating the most efficient route.

[0168] The "route information distribution means" refers to a device or system for distributing calculated route information to a terminal.

[0169] "Real-time route update means" refers to a device or system for recalculating and updating route information based on the latest data.

[0170] "Terminal" refers to a device for receiving and displaying information.

[0171] A "smartphone" refers to a mobile phone with advanced computing power and internet connectivity.

[0172] A "prompt sentence" refers to an instruction sentence input to a generative AI model to obtain an appropriate output result.

[0173] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[0174] System Overview

[0175] This system provides the optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[0176] Data collection

[0177] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[0178] Data Preprocessing

[0179] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[0180] Data Analysis and Prediction

[0181] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[0182] Route Optimization

[0183] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[0184] Route information distribution

[0185] The server then delivers the calculated optimal route information to smartphones and other devices in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0186] Real-time updates

[0187] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is again sent to the smartphone, and the emergency vehicle adjusts its actions based on the latest optimal route.

[0188] Specific examples

[0189] Dispatch of emergency vehicles during floods

[0190] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0191] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0192] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0193] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0194] 5. The server distributes optimal route information to smartphones and other devices.

[0195] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[0196] Example prompts for generative AI models

[0197] "Identify areas that have become impassable due to flooding and generate safe routes."

[0198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0199] Step 1:

[0200] The server collects data in real time from mobile devices, traffic sensors, and weather data collection devices. The input data includes the location information of each mobile object and its movement history. This data consists of GPS data, traffic condition data, weather data, etc. The server initially collects this data and prepares it for subsequent processing.

[0201] Step 2:

[0202] The server preprocesses the collected data. Specifically, if there are any outliers in the data, they are removed. The data format is also standardized and normalized. For example, if there are any outliers in the GPS data (such as extremely distant location information), they are removed. The preprocessed data is then passed to the subsequent analysis step.

[0203] Step 3:

[0204] The server analyzes the preprocessed data. A generative AI model (e.g., a deep learning model) is used to predict impassable areas and congestion risks. The input data includes location information, movement history, and traffic condition data preprocessed in the previous step. This data is analyzed using a generative AI model to predict impassable areas and future congestion risks. The output includes location information of impassable areas and congestion risks.

[0205] Step 4:

[0206] The server calculates the optimal route based on the results of the data analysis. It uses route search algorithms such as the A algorithm and Dijkstra algorithm to calculate a route that avoids impassable areas and congestion risks. The input data includes information on impassable areas and congestion risks predicted in the previous step. The server calculates the optimal route based on this data and provides it as output.

[0207] Step 5:

[0208] The server delivers the calculated optimal route information to smartphones and other devices in real time. The input data includes the optimal route information. The server sends this information to the device in real time and notifies the emergency vehicle driver.

[0209] Step 6:

[0210] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server collects data again and updates the route. The input data includes newly collected location information and traffic condition data. The server recalculates the route based on this data and notifies the smartphone of the updated optimal route information. The emergency vehicle driver continues traveling according to the new route notified again.

[0211] These steps will enable the rapid and efficient movement of emergency vehicles in the event of a disaster.

[0212] 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.

[0213] A specific embodiment of a system that supports efficient rescue operations by emergency vehicles in the event of a disaster by combining an emotion engine will be described below.

[0214] System Overview

[0215] This system includes a data collection means, data preprocessing means, data analysis means, route optimization means, route information distribution means, real-time route update means, and an emotion engine that recognizes the user's emotions. This not only enables emergency vehicles to reach their destinations quickly, but also reduces the stress of users (such as emergency vehicle drivers).

[0216] Data collection

[0217] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it acquires current location and speed information from multiple mobile devices, and integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[0218] Data Preprocessing

[0219] The server preprocesses the collected data, detecting and removing outliers from the collected data, standardizing the formats of GPS data and traffic data, and performing normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[0220] Data Analysis and Prediction

[0221] The server then analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks. For example, it can identify roads and bridges that have become impassable due to floods or earthquakes and predict the risk of future traffic congestion.

[0222] Route Optimization

[0223] The server calculates the optimal route based on the results of data analysis. It uses the A algorithm and Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly.

[0224] Route information distribution

[0225] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0226] Real-time updates

[0227] The server continuously collects real-time data and monitors changes in road closures and congestion risks. If new road closures or congestion occur, the server recalculates the route based on the new data collected and distributes updated optimal route information.

[0228] Recognizing user emotions with an emotion engine

[0229] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions. For example, if an emergency vehicle driver is nervous, the emotion engine will quantify the level of nervousness based on the driver's facial expression and voice data.

[0230] Reassessing your route based on emotions

[0231] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, it recalculates an easier and less stressful route.

[0232] Specific examples

[0233] Example 1: Dispatch of emergency vehicles during floods

[0234] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0235] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0236] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0237] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0238] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[0239] 6. The emotion engine analyzes the voice and facial expressions of emergency vehicle drivers and reevaluates routes to reduce stress if the driver is feeling stressed.

[0240] 7. Emergency vehicles will follow this information to quickly reach the affected area.

[0241] Example 2: Transporting relief supplies after an earthquake

[0242] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[0243] 2. The server removes outliers and normalizes the data.

[0244] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[0245] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[0246] 5. An emotion engine assesses the driver's level of tension and stress and adjusts routes as needed.

[0247] 6. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[0248] In this way, the system not only supports the rapid action of emergency vehicles in the event of a disaster, but also takes into account the emotions and stress of emergency vehicle drivers, enabling more effective rescue operations.

[0249] The processing flow will be explained below.

[0250] Step 1: Data collection

[0251] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. For example, it obtains GPS data from each mobile device, vehicle flow and speed data from traffic sensors, and the latest weather information from weather data collectors.

[0252] Step 2: Data Preprocessing

[0253] The server preprocesses the collected data. First, it detects and removes outliers, then standardizes the data format and performs normalization. For example, it converts GPS data into a common coordinate system and standardizes time information to improve data accuracy.

[0254] Step 3: Data analysis

[0255] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts impassable areas and congestion risks. For example, it identifies roads that have become impassable due to floods or earthquakes, and time periods and areas where congestion is likely to occur.

[0256] Step 4: Identify impassable areas

[0257] The server analyzes the data and identifies impassable areas, for example, roads and bridges damaged by floods.

[0258] Step 5: Predict congestion risk

[0259] The server uses the results of data analysis to predict future congestion risks. For example, it predicts a sudden increase in traffic flow around evacuation shelters and determines that there is a high possibility of congestion occurring as a result.

[0260] Step 6: Route optimization

[0261] The server calculates the optimal route that avoids identified impassable areas and congestion risks, for example using the A algorithm or Dijkstra algorithm to determine the fastest and safest route for emergency vehicles to reach their destination.

[0262] Step 7: Route Distribution

[0263] The server distributes the generated optimal route information to the terminals of local governments and rescue teams, for example by sending the route information in real time to the navigation systems of emergency vehicles.

[0264] Step 8: Collect emotion data

[0265] The terminal collects the user's voice data, facial expression data, or biometric data. For example, real-time biometric information is collected from a wearable device worn by an emergency vehicle driver.

[0266] Step 9: Sentiment Analysis

[0267] The emotion engine analyzes the collected data and recognizes the user's emotions (level of tension and stress). For example, it quantifies how tense the user is based on the tone of their voice data and changes in their facial expressions.

[0268] Step 10: Reassess your route based on your emotions

[0269] The server takes into account the user's emotional data recognized by the emotion engine and reevaluates the route. For example, if the driver is extremely nervous, it will recalculate a straighter and easier route.

[0270] Step 11: Distributing recalculated route information

[0271] The server then redistributes the recalculated optimal route information to the emergency vehicle's terminal, allowing the driver to head to their destination with less stress based on the latest information.

[0272] In this way, the system can grasp the user's emotional state in real time and provide the optimal route accordingly, helping emergency vehicles reach their destination efficiently and safely.

[0273] Example 2

[0274] 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."

[0275] Conventional disaster response systems, even if capable of collecting information and quickly preprocessing data in real time, do not take into account the influence of driver emotions and stress when operating emergency vehicles. As a result, even if an emergency vehicle selects the optimal route, if the driver is overly nervous or stressed, it may be difficult to operate quickly and safely. Furthermore, even if the route is updated in real time, it may not always be optimal for the driver. A solution to these issues is needed.

[0276] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0277] In this invention, the server includes a data collection means for collecting location information and movement history acquired in real time from multiple mobile objects, a data preprocessing means for preprocessing the collected data, removing outliers, and normalizing the data, a data analysis means for analyzing the preprocessed data and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the predicted impassable areas and congestion risks, a route information distribution means for distributing the calculated optimal route information to the terminal, a real-time route update means for recalculating the route using recollected data based on the distributed optimal route information, an emotion engine means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotion, and an emotion-based route reevaluation means for reevaluating and recalculating the route based on the recognized user emotion data. This enables emergency vehicles to not only select the optimal route but also operate while taking into account the driver's emotion and stress level.

[0278] The "data collection means" is a means for collecting location information and movement history in real time from multiple mobile objects when a disaster occurs.

[0279] The "data preprocessing means" is a means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data.

[0280] A "generative AI model" is an artificial intelligence model that analyzes preprocessed data and predicts impassable areas and congestion risks.

[0281] The "data analysis means" is a means for analyzing data preprocessed by the data preprocessing means using a generative AI model to predict impassable areas and congestion risks.

[0282] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[0283] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[0284] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[0285] The "emotion engine means" is a means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotions.

[0286] The "route re-evaluation means based on emotion" is a means for re-evaluating and re-calculating the route based on the emotion data of the user recognized by the emotion engine means.

[0287] This invention relates to a system that supports efficient rescue operations by emergency vehicles when a disaster occurs, and specifically, the system includes data collection, data preprocessing, data analysis, route optimization, route information distribution, real-time route update, and user emotion recognition and route reevaluation based on that emotion. Each element of this system is described in detail below.

[0288] Data collection

[0289] When a disaster occurs, the server collects real-time location information and movement history from multiple mobile devices (e.g., emergency vehicles, personal devices). Specifically, it integrates GPS data from mobile devices, vehicle flow data from traffic sensors, and weather observation data from weather data collection devices. The hardware used for this data collection includes GPS modules, traffic sensors, and weather observation devices.

[0290] Data Preprocessing

[0291] The server preprocesses the data acquired by the data collection means. This preprocessing involves detecting and removing outliers and normalizing data provided in different formats. For example, abnormal values ​​for altitude and position in GPS data are removed. Furthermore, different time formats are unified to standardize the data.

[0292] Data analysis

[0293] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts potential road impassability and congestion risks. Specifically, a deep learning model is trained using past and current traffic data as input to predict future road impassability and congestion. For example, it can identify areas where roads and bridges will be impassable due to floods or earthquakes.

[0294] Route Optimization

[0295] The server calculates the optimal route based on the prediction results from the data analysis method. It uses the A algorithm or Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly. For example, it proposes the shortest route that avoids impassable areas.

[0296] Route information distribution

[0297] The server then distributes the calculated optimal route information in real time to the devices of local governments and rescue teams, allowing emergency vehicle drivers to instantly obtain the latest route information and take swift and safe action.

[0298] Real-time updates

[0299] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. If new road impassability or congestion occurs, the server immediately updates the data, recalculates the optimal route, and distributes the latest route information.

[0300] Recognizing user emotions with an emotion engine

[0301] The server or a dedicated emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotion. For example, if an emergency vehicle driver is nervous, the emotion engine can analyze the voice tone and facial expression to quantify the level of nervousness.

[0302] Emotion-based route reassessment

[0303] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, the server recalculates the route to select safer and wider roads, thereby reducing the driver's burden.

[0304] Specific examples

[0305] One example is the dispatch of emergency vehicles during floods. The server collects data from mobile devices and traffic sensors, including data on bridges that are impassable due to flooding. After preprocessing the data and removing outliers, a generative AI model is used to identify impassable areas. Route optimization is performed to generate a route that uses highways and distributes it to the local government's terminal and the emergency vehicle's terminal. In addition, an emotion engine evaluates the driver's level of stress and reevaluates the route if necessary.

[0306] An example prompt for using a generative AI model is:

[0307] "Predict expected road impassability and congestion risk within the next hour based on current traffic and weather data."

[0308] As a result, the system can support the swift and safe operation of emergency vehicles in the event of a disaster, reducing stress and tension for drivers.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Program processing flow

[0311] Step 1: Data collection

[0312] The server collects GPS data from mobile devices, data from traffic sensors, and weather data in real time.

[0313] (Input) Location information from mobile devices, flow rate and velocity data from traffic sensors, and observation data from the Meteorological Agency.

[0314] (Output) A consolidated real-time dataset.

[0315] Specifically, the server periodically retrieves information from each data source and stores the data in different formats in a single database.

[0316] Step 2: Data Preprocessing

[0317] The server pre-processes the collected data.

[0318] (Input) Integrated real-time dataset.

[0319] (Output) The normalized dataset with outliers removed.

[0320] Detect and remove outliers in collected data, and standardize the formats of GPS and traffic data, for example by standardizing the coordinate system for location information and standardizing time information.

[0321] Step 3: Data analysis and prediction

[0322] The server analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[0323] (Input) The preprocessed dataset.

[0324] (Output) Predicted impassable areas and congestion risk data.

[0325] Specifically, the server performs analysis based on deep learning models to predict future risks based on past and current traffic conditions.

[0326] Step 4: Route optimization

[0327] The server calculates the optimal route based on the results of data analysis.

[0328] (Input) Predicted impassable areas and congestion risk data.

[0329] (Output) Optimal route information.

[0330] The A algorithm and Dijkstra algorithm are used to calculate the shortest and safest route. Specifically, it searches for a route with the objectives of minimizing time and avoiding risk.

[0331] Step 5: Route information distribution

[0332] The server distributes the calculated optimal route information to the terminals of local governments and rescue teams in real time.

[0333] (Input) Optimal route information.

[0334] (Output) Notification of delivery completion to each device.

[0335] Specifically, the server transmits route information to each terminal via the communication module and records the transmission log.

[0336] Step 6: Real-time updates

[0337] The server continuously collects real-time data and monitors changes in impassable areas and congestion risks.

[0338] (Input) Newly collected real-time data.

[0339] (Output) Updated optimal route information.

[0340] If a new road closure or congestion occurs, the server immediately recalculates the route and delivers the latest route information again.

[0341] Step 7: Recognizing user emotions with the emotion engine

[0342] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions.

[0343] (Input) Voice data, facial expression data, biometric data.

[0344] (Output) User emotion data.

[0345] Specifically, the server or emotion engine uses voice activity detection (VAD) and facial expression recognition algorithms to assess and quantify the user's emotional state.

[0346] Step 8: Emotion-Based Route Reassessment

[0347] The server receives the user's emotion data recognized by the emotion engine and reevaluates the route if necessary.

[0348] (Input) User emotion data.

[0349] (Output) The reevaluated optimal route information.

[0350] For example, if the driver is overly nervous, the server will recalculate the route to select safer, wider roads, and the reevaluated route information will be sent to the device again.

[0351] The above is the specific flow of program processing for this system.

[0352] (Application example 2)

[0353] 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."

[0354] In order for emergency vehicles to carry out rescue operations quickly and safely in the event of a disaster, it is essential to obtain accurate traffic and weather information in real time and provide optimal routes. However, current systems do not reevaluate routes taking into account the driver's emotions and stress, which creates the risk that emergency vehicle drivers will become overly nervous and make incorrect decisions. Therefore, a system is needed that can recognize the driver's emotional state in real time and reevaluate routes based on that information.

[0355] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a data collection means that collects location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs; a data preprocessing means that preprocesses the data collected by the data collection means, removes outliers, and normalizes the data; a data analysis means that analyzes the data preprocessed by the data preprocessing means and predicts impassable areas and congestion risks using a generative AI model; a route optimization means that calculates an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means; a route information distribution means that distributes optimal route information calculated by the route optimization means to a terminal; a real-time route update means that recalculates a route using re-collected data based on the optimal route information distributed by the route information distribution means; and an emotion engine means that collects user emotion data using the real-time route update means and re-evaluates the route based on the data. This enables fast and safe rescue operations that take into account the emotions and stress of emergency vehicle drivers.

[0356] The "data collection means" is a means for acquiring location information and movement history from multiple mobile objects in real time when a disaster occurs.

[0357] The "data preprocessing means" is a means for removing outliers in the data collected by the data collection means and for normalizing the data.

[0358] "Data analysis means" refers to a means of predicting impassable areas and congestion risks using an AI model generated from preprocessed data.

[0359] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[0360] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[0361] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[0362] The "emotion engine means" is a means for collecting user emotion data and re-evaluating the route based on that data.

[0363] A "generative AI model" is an algorithm that uses machine learning technology to learn patterns from large amounts of data and predict impassable areas and congestion risks.

[0364] The "A algorithm" is a type of graph search algorithm used to calculate the shortest route.

[0365] The "Dijkstra algorithm" is an algorithm for finding the shortest path on a graph with non-negative weights.

[0366] "Device" means a computer or mobile device used by an emergency vehicle driver or local government.

[0367] An "impassable area" is an area where vehicles cannot pass due to a disaster or other reason.

[0368] "Congestion risk" indicates the possibility of traffic congestion occurring on a particular road or area.

[0369] The present invention is a system for supporting efficient rescue operations by emergency vehicles when a disaster occurs, and specific embodiments thereof will be described below.

[0370] System Overview

[0371] The system includes a data collection means, a data pre-processing means, a data analysis means, a route optimization means, a route information distribution means, a real-time route update means, and an emotion engine means.

[0372] The server collects GPS data from mobile devices, traffic sensor data, and weather data in real time. A data preprocessing means detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. Furthermore, a data analysis means analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[0373] The route optimization means calculates the optimal route using the A algorithm or the Dijkstra algorithm based on the analysis results obtained from the data analysis means. The route information distribution means distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The real-time route update means recalculates the route based on new data and distributes the updated optimal route information. In addition, the emotion engine means collects emotion data from the user (emergency vehicle driver) and reevaluates the route based on that data.

[0374] Hardware and Software

[0375] The system requires hardware such as GPS sensors, traffic sensors, weather data collection devices, and computers installed in autonomous vehicles. The software includes Python, machine learning libraries (e.g., Scikit-learn), Dijkstra's algorithm, A algorithm, generative AI models, and emotion engines. Specific examples of Python libraries include Numpy, Pandas, Scikit-learn, and PyTorch.

[0376] Specific examples

[0377] The server collects GPS data, traffic sensor data, and weather data in real time as emergency vehicles head toward flood-prone areas. The collected data is subjected to a data pre-processing means, which removes outliers and normalizes them. Then, a data analysis means using a generative AI model predicts impassable areas and congestion risks. Next, a route optimization means calculates the optimal route based on the analysis results, and the route information distribution means distributes it to the emergency vehicle's terminal. The driver's emotional state is analyzed in real time by an emotion engine means, and the route is reevaluated as necessary.

[0378] Prompt Sentence Examples

[0379] Suggest the optimal route based on traffic and weather data from the designated emergency vehicle's current location to its destination. Calculate routes to avoid impassable areas or potential congestion. Also, choose a route that minimizes stress for drivers who are under stress.

[0380] This concrete example demonstrates how the system can achieve fast and safe rescue operations while taking into account the emotions and stress of emergency vehicle drivers.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1: Data collection

[0383] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. The inputs are location information, speed information, traffic sensor data, and weather data. The server receives these data and outputs them as an integrated dataset.

[0384] Step 2: Data Preprocessing

[0385] The server detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. The input is the data collected in step 1, and the output is a preprocessed dataset. The server uses libraries such as Numpy and Pandas for this processing.

[0386] Step 3: Data analysis

[0387] The server uses the preprocessed data to predict road impassability and congestion risk using a generative AI model. The input is the preprocessed dataset, and the output is predicted road impassability and congestion risk information. At this stage, the server performs data analysis using machine learning libraries (e.g., Scikit-learn and PyTorch).

[0388] Step 4: Route optimization

[0389] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is information on predicted impassable areas and congestion risks, and the output is optimal route information. The server runs programs that implement these algorithms.

[0390] Step 5: Route information distribution

[0391] The server distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The input is the optimal route information, and the output is the route information distributed to the terminal. The server distributes the information using a communication protocol.

[0392] Step 6: Real-time route updates

[0393] The server recalculates routes based on newly collected data in real time and distributes updated optimal route information. The input is newly collected data, and the output is recalculated route information. The server performs this process periodically to adapt to the latest traffic conditions.

[0394] Step 7: Collect emotional data

[0395] The server collects emotional data from the user (emergency vehicle driver) through voice and facial expressions. The input is the user's voice data and facial expression data, and the output is analyzed emotional state information. The emotion engine performs this analysis.

[0396] Step 8: Route reevaluation

[0397] The server reevaluates the route if necessary based on the user's emotional state obtained from the emotion engine. The input is the analyzed emotional state information, and the output is the reevaluated route information. The server recalculates a less stressful route according to the emotion engine's results.

[0398] In this way, data is collected, processed, and analyzed at each processing step of the server, terminal, and user, and optimal route information is constantly provided. In particular, reevaluating the route according to the driver's emotional state enables quick and safe rescue operations.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] [Second embodiment]

[0403] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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."

[0415] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[0416] System Overview

[0417] This system provides an optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[0418] Data collection

[0419] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[0420] Data Preprocessing

[0421] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[0422] Data Analysis and Prediction

[0423] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[0424] Route Optimization

[0425] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[0426] Route information distribution

[0427] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0428] Real-time updates

[0429] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is then redistributed to the device, and the emergency vehicle adjusts its actions based on the latest optimal route.

[0430] Specific examples

[0431] Example 1: Dispatch of emergency vehicles during floods

[0432] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0433] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0434] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0435] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0436] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[0437] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[0438] Example 2: Transporting relief supplies after an earthquake

[0439] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[0440] 2. The server removes outliers and normalizes the data.

[0441] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[0442] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[0443] 5. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[0444] In this way, emergency vehicles can act quickly and rescue operations can be carried out smoothly in the event of a disaster.

[0445] The processing flow will be explained below.

[0446] Step 1: Data collection

[0447] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it obtains current location and speed information from multiple mobile devices. It also integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[0448] Step 2: Data Preprocessing

[0449] The server preprocesses the collected data. First, it detects and removes outliers from the collected data. Next, it standardizes the formats of GPS data and traffic data and performs normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[0450] Step 3: Data analysis

[0451] The server then analyzes the preprocessed data using a generative AI model. For example, the underlying deep learning model learns general traffic patterns based on past data, and then uses newly collected data to predict impassable areas and congestion risks in specific areas.

[0452] Step 4: Identify impassable areas

[0453] The server analyzes the data and determines that a particular road is impassable due to a flood or earthquake. For example, a road at a particular latitude and longitude is predicted to be impassable based on the latest weather and traffic data.

[0454] Step 5: Predict congestion risk

[0455] Based on the results of the data analysis, the server determines that there is a high possibility of traffic congestion in a particular area. For example, congestion is predicted based on a temporary increase in traffic flow around an evacuation shelter.

[0456] Step 6: Route optimization

[0457] The server calculates the optimal route that avoids identified impassable areas and predicted congestion risks. For example, Algorithm A calculates a route for emergency vehicles to use the expressway, generating a route that will allow them to reach their destination safely and quickly.

[0458] Step 7: Route Distribution

[0459] The server distributes optimal route information to the terminals of local governments and rescue teams in real time. For example, the optimal route is displayed on the screen of a terminal at a local government emergency response center, and the person in charge conveys it to the driver of the emergency vehicle providing assistance.

[0460] Step 8: Real-time updates

[0461] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. When new road impassability or congestion occurs, the route is recalculated based on the new collected data and updated optimal route information is distributed. For example, if a new congestion occurs along the way, a new route reflecting that information is recalculated in real time and distributed to the rescue team's terminal.

[0462] In this way, the system always provides the best route based on the latest conditions, enabling emergency vehicles to provide assistance efficiently and quickly.

[0463] Example 1

[0464] 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."

[0465] In the event of a disaster, it is important for emergency vehicles to obtain real-time information on traffic conditions and passable routes and select an appropriate route in order to reach their destination quickly. However, conventional systems do not perform this process efficiently enough, and emergency vehicles may get caught in traffic jams or impassable areas. In addition, a system that can quickly respond to new changes in the situation is required.

[0466] 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.

[0467] In this invention, the server includes a data collection means for collecting location information and movement histories acquired in real time from multiple mobile objects in the event of a disaster, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to terminals, a real-time route update means for recalculating a route using recollected data based on the optimal route information distributed by the route information distribution means, and a means for distributing the recalculated route to each terminal in real time when new data is collected. This enables emergency vehicles to quickly obtain an optimal route and reach their destination quickly even in the event of a disaster.

[0468] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or tsunami occurs, or a man-made disaster such as a fire or accident occurs.

[0469] "Mobile objects" refers to all moving objects, such as cars, motorbikes, and pedestrians, that can provide location information in real time.

[0470] "Real-time" refers to a timeframe in which data collection, processing, and delivery occur almost instantly, with little or no specific delay.

[0471] "Location Information" refers to latitude, longitude and altitude data obtained through location information systems such as GPS.

[0472] "Movement history" refers to data that records the routes and stopping points taken by a moving object over a certain period of time.

[0473] "Data collection means" refers to a device or system for acquiring location information and movement history from a mobile object in real time.

[0474] "Data preprocessing means" refers to a device or program that performs processing to remove outliers from collected data and normalize the data.

[0475] An "outlier" is an inaccurate or unnatural value in the collected data that falls outside the normal range.

[0476] "Data normalization" refers to the process of converting data collected in different formats or units into a consistent format.

[0477] "Generative AI model" refers to an artificial intelligence model that learns patterns from data and is used to make predictions or classifications. Examples include deep learning models.

[0478] "Data analysis means" refers to a device or program that uses preprocessed data to perform processing for a specific purpose, such as predicting impassable areas or congestion risks.

[0479] An "impassable area" refers to a location where vehicles and pedestrians are temporarily or permanently unable to pass due to a disaster, traffic accident, or other cause.

[0480] "Congestion risk" refers to the prediction of situations and locations that may cause traffic flow to slow down.

[0481] "Route optimization means" refers to a device or program for calculating the optimal route based on given conditions and analysis results.

[0482] "Route information distribution means" refers to a device or system for transmitting calculated optimal route information to a terminal in real time.

[0483] "Terminal" refers to mobile terminals and fixed computer systems used by emergency vehicles and local governments.

[0484] "Real-time route update means" refers to a device or program that updates a route in real time by recalculating it based on new data collected.

[0485] The system of the present invention is designed to support efficient rescue operations by emergency vehicles in the event of a disaster. This system uses data collected from mobile objects in real time to calculate and provide optimal routes. Specific embodiments of the system are described below.

[0486] Data collection

[0487] The server collects real-time GPS data from mobile devices, traffic sensor data, and weather data using high-performance data collection equipment and dedicated software. The collected data is used to track the location and movement history of emergency vehicles and general vehicles.

[0488] Data Preprocessing

[0489] The server preprocesses the collected data with high accuracy. Specifically, it removes outliers and normalizes the data. The software used is a program that implements data cleaning tools and normalization algorithms. For example, if GPS data contains abnormal values, it removes them and converts the data into data that is consistent with other formats.

[0490] Data Analysis and Prediction

[0491] The server uses the preprocessed data to train and analyze generative AI models (e.g., deep learning models). This allows for highly accurate prediction of impassable areas and congestion risks. The AI ​​models used are built using architectures such as TensorFlow and PyTorch. For example, they can identify roads and bridges that have become impassable due to floods or earthquakes, and also predict the risk of future traffic congestion.

[0492] Route Optimization

[0493] The server uses the results of the data analysis to calculate the optimal route. In this process, the A algorithm and Dijkstra algorithm are applied. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible. For example, a specific route is calculated to bypass certain impassable areas.

[0494] Route information distribution

[0495] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time using technologies such as HTTP and WebSocket communication, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0496] Real-time updates

[0497] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server automatically detects this, collects new data, and recalculates the route. The updated route information is quickly delivered to the device, allowing the emergency vehicle to adjust its activities based on the latest information.

[0498] Specific examples

[0499] Dispatch of emergency vehicles during floods

[0500] 1. The server collects GPS data, traffic data, and weather data from mobile devices and traffic sensors in real time.

[0501] 2. The server preprocesses the acquired data, removes outliers, and normalizes the data.

[0502] 3. The server uses the generative AI model to identify the locations of bridges that have become impassable due to flooding.

[0503] 4. The server uses the A algorithm to calculate a fast and safe route.

[0504] 5. The server distributes the optimal route to local government and emergency vehicle terminals in real time.

[0505] 6. Emergency vehicles will use this information to quickly reach the affected area.

[0506] Transporting relief supplies in the event of an earthquake

[0507] 1. The server collects traffic and weather data and analyzes impassable areas and congestion risks due to earthquakes.

[0508] 2. The server removes outliers and normalizes the data.

[0509] 3. The server uses the generated AI model to predict future congestion risks.

[0510] 4. The server calculates the optimal route for delivering relief supplies using the Dijkstra algorithm.

[0511] 5. The server distributes the calculated route information to the Self-Defense Forces' terminals in real time.

[0512] 6. The Self-Defense Forces will use this information to effectively transport relief supplies.

[0513] Prompt Sentence Examples

[0514] "Show the best route for emergency vehicles to quickly reach a particular area in the event of flooding."

[0515] "What is the best route to transport relief supplies effectively in the event of an earthquake?"

[0516] In this way, it is possible to realize rapid action by emergency vehicles and smooth rescue operations in the event of a disaster.

[0517] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0518] Step 1: Data collection

[0519] The server acquires GPS data from mobile devices, traffic sensor data, weather data, and other data in real time. The server connects to each data source and periodically acquires data. The input is raw data acquired from each data source, and the output is a set of collected real-time data. Specifically, the server updates GPS data every 5 seconds and collects data from traffic sensors every 10 seconds.

[0520] Step 2: Data Preprocessing

[0521] The server preprocesses the collected data. Specifically, it fills in missing data, removes outliers, and normalizes the data. The input is the raw data collected in step 1, and the output is the preprocessed clean data. For example, if the GPS data contains abnormal location information, it deletes that data, fills in the missing parts, and standardizes the data format.

[0522] Step 3: Data analysis and prediction

[0523] The server uses the preprocessed data to train a generative AI model and perform analysis. During this process, deep learning models are used to predict impassable areas and congestion risks. The input is preprocessed clean data, and the output is analysis and prediction results. Specifically, it identifies impassable areas due to floods or earthquakes and analyzes past data sets against real-time data to predict future congestion risks.

[0524] Step 4: Route optimization

[0525] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is the analysis results and prediction results, and the output is the optimal route information. For example, it performs specific operations such as avoiding multiple impassable areas and traffic jams and calculating the quickest and safest route.

[0526] Step 5: Route information distribution

[0527] The server distributes the calculated optimal route information to the terminal in real time. This is done using HTTP or WebSocket communication. The input is the optimal route information, and the output is the route information distributed in real time. For example, the server has a list of mobile terminals and fixed computer systems to which it should distribute, and performs the specific operation of sending the latest route information to each terminal in real time.

[0528] Step 6: Real-time updates

[0529] The server collects new data and recalculates the route. When new information about impassable areas or traffic congestion is acquired, it automatically recalculates and redistributes the updated route information. The input is newly collected real-time data, and the output is the latest recalculated route information. Specifically, after new data is collected, it immediately recalculates, generates a new route, and instantly distributes it to each device.

[0530] (Application example 1)

[0531] 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."

[0532] When a disaster occurs, it is important for emergency vehicles to reach their destination quickly and efficiently. However, in reality, emergency vehicle movement is often hindered by ever-changing road conditions and newly emerging obstacles. Furthermore, conventional navigation systems lack the ability to adapt in real time, which can delay the optimization of emergency routes. This can delay rescue efforts and exacerbate disaster damage.

[0533] 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.

[0534] In this invention, the server includes a data collection means for collecting location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to a terminal, a real-time route update means for recalculating a route using re-collected data based on the optimal route information distributed by the route information distribution means, and a means for notifying a smartphone of the route information recalculated by the real-time route update means, thereby enabling rapid and efficient movement of emergency vehicles.

[0535] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or typhoon occurs.

[0536] "Multiple moving objects" refers to various means of transportation such as emergency vehicles, regular vehicles, and drones.

[0537] "Real-time" refers to data acquired continuously in ongoing time.

[0538] "Location information" refers to information about your current location, such as GPS data obtained from a mobile device or vehicle.

[0539] "Movement history" refers to a record of movement based on past location information.

[0540] "Data collection means" refers to the devices and systems used to collect the necessary data.

[0541] "Data preprocessing means" refers to means for preprocessing collected data, such as removing outliers and normalizing data.

[0542] An "outlier" is data that falls outside the normal range.

[0543] "Normalization" refers to the process of standardizing data formats so that they can be handled according to common standards.

[0544] "Data analysis means" refers to a device or system for analyzing collected and pre-processed data.

[0545] A "generative AI model" refers to a machine learning model that uses artificial intelligence to perform data analysis, etc.

[0546] "Impassable areas" refer to areas that are impassable due to disasters or other reasons.

[0547] "Congestion risk" refers to the possibility of traffic flow slowing down.

[0548] "Route optimizer" refers to a device or system for calculating the most efficient route.

[0549] The "route information distribution means" refers to a device or system for distributing calculated route information to a terminal.

[0550] "Real-time route update means" refers to a device or system for recalculating and updating route information based on the latest data.

[0551] "Terminal" refers to a device for receiving and displaying information.

[0552] A "smartphone" refers to a mobile phone with advanced computing power and internet connectivity.

[0553] A "prompt sentence" refers to an instruction sentence input to a generative AI model to obtain an appropriate output result.

[0554] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[0555] System Overview

[0556] This system provides the optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[0557] Data collection

[0558] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[0559] Data Preprocessing

[0560] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[0561] Data Analysis and Prediction

[0562] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[0563] Route Optimization

[0564] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[0565] Route information distribution

[0566] The server then delivers the calculated optimal route information to smartphones and other devices in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0567] Real-time updates

[0568] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is again sent to the smartphone, and the emergency vehicle adjusts its actions based on the latest optimal route.

[0569] Specific examples

[0570] Dispatch of emergency vehicles during floods

[0571] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0572] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0573] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0574] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0575] 5. The server distributes optimal route information to smartphones and other devices.

[0576] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[0577] Example prompts for generative AI models

[0578] "Identify areas that have become impassable due to flooding and generate safe routes."

[0579] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0580] Step 1:

[0581] The server collects data in real time from mobile devices, traffic sensors, and weather data collection devices. The input data includes the location information of each mobile object and its movement history. This data consists of GPS data, traffic condition data, weather data, etc. The server initially collects this data and prepares it for subsequent processing.

[0582] Step 2:

[0583] The server preprocesses the collected data. Specifically, if there are any outliers in the data, they are removed. The data format is also standardized and normalized. For example, if there are any outliers in the GPS data (such as extremely distant location information), they are removed. The preprocessed data is then passed to the subsequent analysis step.

[0584] Step 3:

[0585] The server analyzes the preprocessed data. A generative AI model (e.g., a deep learning model) is used to predict impassable areas and congestion risks. The input data includes location information, movement history, and traffic condition data preprocessed in the previous step. This data is analyzed using a generative AI model to predict impassable areas and future congestion risks. The output includes location information of impassable areas and congestion risks.

[0586] Step 4:

[0587] The server calculates the optimal route based on the results of the data analysis. It uses route search algorithms such as the A algorithm and Dijkstra algorithm to calculate a route that avoids impassable areas and congestion risks. The input data includes information on impassable areas and congestion risks predicted in the previous step. The server calculates the optimal route based on this data and provides it as output.

[0588] Step 5:

[0589] The server delivers the calculated optimal route information to smartphones and other devices in real time. The input data includes the optimal route information. The server sends this information to the device in real time and notifies the emergency vehicle driver.

[0590] Step 6:

[0591] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server collects data again and updates the route. The input data includes newly collected location information and traffic condition data. The server recalculates the route based on this data and notifies the smartphone of the updated optimal route information. The emergency vehicle driver continues traveling according to the new route notified again.

[0592] These steps will enable the rapid and efficient movement of emergency vehicles in the event of a disaster.

[0593] 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.

[0594] A specific embodiment of a system that supports efficient rescue operations by emergency vehicles in the event of a disaster by combining an emotion engine will be described below.

[0595] System Overview

[0596] This system includes a data collection means, data preprocessing means, data analysis means, route optimization means, route information distribution means, real-time route update means, and an emotion engine that recognizes the user's emotions. This not only enables emergency vehicles to reach their destinations quickly, but also reduces the stress of users (such as emergency vehicle drivers).

[0597] Data collection

[0598] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it acquires current location and speed information from multiple mobile devices, and integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[0599] Data Preprocessing

[0600] The server preprocesses the collected data, detecting and removing outliers from the collected data, standardizing the formats of GPS data and traffic data, and performing normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[0601] Data Analysis and Prediction

[0602] The server then analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks. For example, it can identify roads and bridges that have become impassable due to floods or earthquakes and predict the risk of future traffic congestion.

[0603] Route Optimization

[0604] The server calculates the optimal route based on the results of data analysis. It uses the A algorithm and Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly.

[0605] Route information distribution

[0606] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0607] Real-time updates

[0608] The server continuously collects real-time data and monitors changes in road closures and congestion risks. If new road closures or congestion occur, the server recalculates the route based on the new data collected and distributes updated optimal route information.

[0609] Recognizing user emotions with an emotion engine

[0610] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions. For example, if an emergency vehicle driver is nervous, the emotion engine will quantify the level of nervousness based on the driver's facial expression and voice data.

[0611] Reassessing your route based on emotions

[0612] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, it recalculates an easier and less stressful route.

[0613] Specific examples

[0614] Example 1: Dispatch of emergency vehicles during floods

[0615] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0616] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0617] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0618] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0619] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[0620] 6. The emotion engine analyzes the voice and facial expressions of emergency vehicle drivers and reevaluates routes to reduce stress if the driver is feeling stressed.

[0621] 7. Emergency vehicles will follow this information to quickly reach the affected area.

[0622] Example 2: Transporting relief supplies after an earthquake

[0623] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[0624] 2. The server removes outliers and normalizes the data.

[0625] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[0626] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[0627] 5. An emotion engine assesses the driver's level of tension and stress and adjusts routes as needed.

[0628] 6. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[0629] In this way, the system not only supports the rapid action of emergency vehicles in the event of a disaster, but also takes into account the emotions and stress of emergency vehicle drivers, enabling more effective rescue operations.

[0630] The processing flow will be explained below.

[0631] Step 1: Data collection

[0632] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. For example, it obtains GPS data from each mobile device, vehicle flow and speed data from traffic sensors, and the latest weather information from weather data collectors.

[0633] Step 2: Data Preprocessing

[0634] The server preprocesses the collected data. First, it detects and removes outliers, then standardizes the data format and performs normalization. For example, it converts GPS data into a common coordinate system and standardizes time information to improve data accuracy.

[0635] Step 3: Data analysis

[0636] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts impassable areas and congestion risks. For example, it identifies roads that have become impassable due to floods or earthquakes, and time periods and areas where congestion is likely to occur.

[0637] Step 4: Identify impassable areas

[0638] The server analyzes the data and identifies impassable areas, for example, roads and bridges damaged by floods.

[0639] Step 5: Predict congestion risk

[0640] The server uses the results of data analysis to predict future congestion risks. For example, it predicts a sudden increase in traffic flow around evacuation shelters and determines that there is a high possibility of congestion occurring as a result.

[0641] Step 6: Route optimization

[0642] The server calculates the optimal route that avoids identified impassable areas and congestion risks, for example using the A algorithm or Dijkstra algorithm to determine the fastest and safest route for emergency vehicles to reach their destination.

[0643] Step 7: Route Distribution

[0644] The server distributes the generated optimal route information to the terminals of local governments and rescue teams, for example by sending the route information in real time to the navigation systems of emergency vehicles.

[0645] Step 8: Collect emotion data

[0646] The terminal collects the user's voice data, facial expression data, or biometric data. For example, real-time biometric information is collected from a wearable device worn by an emergency vehicle driver.

[0647] Step 9: Sentiment Analysis

[0648] The emotion engine analyzes the collected data and recognizes the user's emotions (level of tension and stress). For example, it quantifies how tense the user is based on the tone of their voice data and changes in their facial expressions.

[0649] Step 10: Reassess your route based on your emotions

[0650] The server takes into account the user's emotional data recognized by the emotion engine and reevaluates the route. For example, if the driver is extremely nervous, it will recalculate a straighter and easier route.

[0651] Step 11: Distributing recalculated route information

[0652] The server then redistributes the recalculated optimal route information to the emergency vehicle's terminal, allowing the driver to head to their destination with less stress based on the latest information.

[0653] In this way, the system can grasp the user's emotional state in real time and provide the optimal route accordingly, helping emergency vehicles reach their destination efficiently and safely.

[0654] Example 2

[0655] 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."

[0656] Conventional disaster response systems, even if capable of collecting information and quickly preprocessing data in real time, do not take into account the influence of driver emotions and stress when operating emergency vehicles. As a result, even if an emergency vehicle selects the optimal route, if the driver is overly nervous or stressed, it may be difficult to operate quickly and safely. Furthermore, even if the route is updated in real time, it may not always be optimal for the driver. A solution to these issues is needed.

[0657] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0658] In this invention, the server includes a data collection means for collecting location information and movement history acquired in real time from multiple mobile objects, a data preprocessing means for preprocessing the collected data, removing outliers, and normalizing the data, a data analysis means for analyzing the preprocessed data and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the predicted impassable areas and congestion risks, a route information distribution means for distributing the calculated optimal route information to the terminal, a real-time route update means for recalculating the route using recollected data based on the distributed optimal route information, an emotion engine means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotion, and an emotion-based route reevaluation means for reevaluating and recalculating the route based on the recognized user emotion data. This enables emergency vehicles to not only select the optimal route but also operate while taking into account the driver's emotion and stress level.

[0659] The "data collection means" is a means for collecting location information and movement history in real time from multiple mobile objects when a disaster occurs.

[0660] The "data preprocessing means" is a means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data.

[0661] A "generative AI model" is an artificial intelligence model that analyzes preprocessed data and predicts impassable areas and congestion risks.

[0662] The "data analysis means" is a means for analyzing data preprocessed by the data preprocessing means using a generative AI model to predict impassable areas and congestion risks.

[0663] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[0664] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[0665] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[0666] The "emotion engine means" is a means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotions.

[0667] The "route re-evaluation means based on emotion" is a means for re-evaluating and re-calculating the route based on the emotion data of the user recognized by the emotion engine means.

[0668] This invention relates to a system that supports efficient rescue operations by emergency vehicles when a disaster occurs, and specifically, the system includes data collection, data preprocessing, data analysis, route optimization, route information distribution, real-time route update, and user emotion recognition and route reevaluation based on that emotion. Each element of this system is described in detail below.

[0669] Data collection

[0670] When a disaster occurs, the server collects real-time location information and movement history from multiple mobile devices (e.g., emergency vehicles, personal devices). Specifically, it integrates GPS data from mobile devices, vehicle flow data from traffic sensors, and weather observation data from weather data collection devices. The hardware used for this data collection includes GPS modules, traffic sensors, and weather observation devices.

[0671] Data Preprocessing

[0672] The server preprocesses the data acquired by the data collection means. This preprocessing involves detecting and removing outliers and normalizing data provided in different formats. For example, abnormal values ​​for altitude and position in GPS data are removed. Furthermore, different time formats are unified to standardize the data.

[0673] Data analysis

[0674] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts potential road impassability and congestion risks. Specifically, a deep learning model is trained using past and current traffic data as input to predict future road impassability and congestion. For example, it can identify areas where roads and bridges will be impassable due to floods or earthquakes.

[0675] Route Optimization

[0676] The server calculates the optimal route based on the prediction results from the data analysis method. It uses the A algorithm or Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly. For example, it proposes the shortest route that avoids impassable areas.

[0677] Route information distribution

[0678] The server then distributes the calculated optimal route information in real time to the devices of local governments and rescue teams, allowing emergency vehicle drivers to instantly obtain the latest route information and take swift and safe action.

[0679] Real-time updates

[0680] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. If new road impassability or congestion occurs, the server immediately updates the data, recalculates the optimal route, and distributes the latest route information.

[0681] Recognizing user emotions with an emotion engine

[0682] The server or a dedicated emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotion. For example, if an emergency vehicle driver is nervous, the emotion engine can analyze the voice tone and facial expression to quantify the level of nervousness.

[0683] Emotion-based route reassessment

[0684] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, the server recalculates the route to select safer and wider roads, thereby reducing the driver's burden.

[0685] Specific examples

[0686] One example is the dispatch of emergency vehicles during floods. The server collects data from mobile devices and traffic sensors, including data on bridges that are impassable due to flooding. After preprocessing the data and removing outliers, a generative AI model is used to identify impassable areas. Route optimization is performed to generate a route that uses highways and distributes it to the local government's terminal and the emergency vehicle's terminal. In addition, an emotion engine evaluates the driver's level of stress and reevaluates the route if necessary.

[0687] An example prompt for using a generative AI model is:

[0688] "Predict expected road impassability and congestion risk within the next hour based on current traffic and weather data."

[0689] As a result, the system can support the swift and safe operation of emergency vehicles in the event of a disaster, reducing stress and tension for drivers.

[0690] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0691] Program processing flow

[0692] Step 1: Data collection

[0693] The server collects GPS data from mobile devices, data from traffic sensors, and weather data in real time.

[0694] (Input) Location information from mobile devices, flow rate and velocity data from traffic sensors, and observation data from the Meteorological Agency.

[0695] (Output) A consolidated real-time dataset.

[0696] Specifically, the server periodically retrieves information from each data source and stores the data in different formats in a single database.

[0697] Step 2: Data Preprocessing

[0698] The server pre-processes the collected data.

[0699] (Input) Integrated real-time dataset.

[0700] (Output) The normalized dataset with outliers removed.

[0701] Detect and remove outliers in collected data, and standardize the formats of GPS and traffic data, for example by standardizing the coordinate system for location information and standardizing time information.

[0702] Step 3: Data analysis and prediction

[0703] The server analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[0704] (Input) The preprocessed dataset.

[0705] (Output) Predicted impassable areas and congestion risk data.

[0706] Specifically, the server performs analysis based on deep learning models to predict future risks based on past and current traffic conditions.

[0707] Step 4: Route optimization

[0708] The server calculates the optimal route based on the results of data analysis.

[0709] (Input) Predicted impassable areas and congestion risk data.

[0710] (Output) Optimal route information.

[0711] The A algorithm and Dijkstra algorithm are used to calculate the shortest and safest route. Specifically, it searches for a route with the objectives of minimizing time and avoiding risk.

[0712] Step 5: Route information distribution

[0713] The server distributes the calculated optimal route information to the terminals of local governments and rescue teams in real time.

[0714] (Input) Optimal route information.

[0715] (Output) Notification of delivery completion to each device.

[0716] Specifically, the server transmits route information to each terminal via the communication module and records the transmission log.

[0717] Step 6: Real-time updates

[0718] The server continuously collects real-time data and monitors changes in impassable areas and congestion risks.

[0719] (Input) Newly collected real-time data.

[0720] (Output) Updated optimal route information.

[0721] If a new road closure or congestion occurs, the server immediately recalculates the route and delivers the latest route information again.

[0722] Step 7: Recognizing user emotions with the emotion engine

[0723] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions.

[0724] (Input) Voice data, facial expression data, biometric data.

[0725] (Output) User emotion data.

[0726] Specifically, the server or emotion engine uses voice activity detection (VAD) and facial expression recognition algorithms to assess and quantify the user's emotional state.

[0727] Step 8: Emotion-Based Route Reassessment

[0728] The server receives the user's emotion data recognized by the emotion engine and reevaluates the route if necessary.

[0729] (Input) User emotion data.

[0730] (Output) The reevaluated optimal route information.

[0731] For example, if the driver is overly nervous, the server will recalculate the route to select safer, wider roads, and the reevaluated route information will be sent to the device again.

[0732] The above is the specific flow of program processing for this system.

[0733] (Application example 2)

[0734] 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."

[0735] In order for emergency vehicles to carry out rescue operations quickly and safely in the event of a disaster, it is essential to obtain accurate traffic and weather information in real time and provide optimal routes. However, current systems do not reevaluate routes taking into account the driver's emotions and stress, which creates the risk that emergency vehicle drivers will become overly nervous and make incorrect decisions. Therefore, a system is needed that can recognize the driver's emotional state in real time and reevaluate routes based on that information.

[0736] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a data collection means that collects location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs; a data preprocessing means that preprocesses the data collected by the data collection means, removes outliers, and normalizes the data; a data analysis means that analyzes the data preprocessed by the data preprocessing means and predicts impassable areas and congestion risks using a generative AI model; a route optimization means that calculates an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means; a route information distribution means that distributes optimal route information calculated by the route optimization means to a terminal; a real-time route update means that recalculates a route using re-collected data based on the optimal route information distributed by the route information distribution means; and an emotion engine means that collects user emotion data using the real-time route update means and re-evaluates the route based on the data. This enables fast and safe rescue operations that take into account the emotions and stress of emergency vehicle drivers.

[0737] The "data collection means" is a means for acquiring location information and movement history from multiple mobile objects in real time when a disaster occurs.

[0738] The "data preprocessing means" is a means for removing outliers in the data collected by the data collection means and for normalizing the data.

[0739] "Data analysis means" refers to a means of predicting impassable areas and congestion risks using an AI model generated from preprocessed data.

[0740] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[0741] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[0742] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[0743] The "emotion engine means" is a means for collecting user emotion data and re-evaluating the route based on that data.

[0744] A "generative AI model" is an algorithm that uses machine learning technology to learn patterns from large amounts of data and predict impassable areas and congestion risks.

[0745] The "A algorithm" is a type of graph search algorithm used to calculate the shortest route.

[0746] The "Dijkstra algorithm" is an algorithm for finding the shortest path on a graph with non-negative weights.

[0747] "Device" means a computer or mobile device used by an emergency vehicle driver or local government.

[0748] An "impassable area" is an area where vehicles cannot pass due to a disaster or other reason.

[0749] "Congestion risk" indicates the possibility of traffic congestion occurring on a particular road or area.

[0750] The present invention is a system for supporting efficient rescue operations by emergency vehicles when a disaster occurs, and specific embodiments thereof will be described below.

[0751] System Overview

[0752] The system includes a data collection means, a data pre-processing means, a data analysis means, a route optimization means, a route information distribution means, a real-time route update means, and an emotion engine means.

[0753] The server collects GPS data from mobile devices, traffic sensor data, and weather data in real time. A data preprocessing means detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. Furthermore, a data analysis means analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[0754] The route optimization means calculates the optimal route using the A algorithm or the Dijkstra algorithm based on the analysis results obtained from the data analysis means. The route information distribution means distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The real-time route update means recalculates the route based on new data and distributes the updated optimal route information. In addition, the emotion engine means collects emotion data from the user (emergency vehicle driver) and reevaluates the route based on that data.

[0755] Hardware and Software

[0756] The system requires hardware such as GPS sensors, traffic sensors, weather data collection devices, and computers installed in autonomous vehicles. The software includes Python, machine learning libraries (e.g., Scikit-learn), Dijkstra's algorithm, A algorithm, generative AI models, and emotion engines. Specific examples of Python libraries include Numpy, Pandas, Scikit-learn, and PyTorch.

[0757] Specific examples

[0758] The server collects GPS data, traffic sensor data, and weather data in real time as emergency vehicles head toward flood-prone areas. The collected data is subjected to a data pre-processing means, which removes outliers and normalizes them. Then, a data analysis means using a generative AI model predicts impassable areas and congestion risks. Next, a route optimization means calculates the optimal route based on the analysis results, and the route information distribution means distributes it to the emergency vehicle's terminal. The driver's emotional state is analyzed in real time by an emotion engine means, and the route is reevaluated as necessary.

[0759] Prompt Sentence Examples

[0760] Suggest the optimal route based on traffic and weather data from the designated emergency vehicle's current location to its destination. Calculate routes to avoid impassable areas or potential congestion. Also, choose a route that minimizes stress for drivers who are under stress.

[0761] This concrete example demonstrates how the system can achieve fast and safe rescue operations while taking into account the emotions and stress of emergency vehicle drivers.

[0762] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0763] Step 1: Data collection

[0764] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. The inputs are location information, speed information, traffic sensor data, and weather data. The server receives these data and outputs them as an integrated dataset.

[0765] Step 2: Data Preprocessing

[0766] The server detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. The input is the data collected in step 1, and the output is a preprocessed dataset. The server uses libraries such as Numpy and Pandas for this processing.

[0767] Step 3: Data analysis

[0768] The server uses the preprocessed data to predict road impassability and congestion risk using a generative AI model. The input is the preprocessed dataset, and the output is predicted road impassability and congestion risk information. At this stage, the server performs data analysis using machine learning libraries (e.g., Scikit-learn and PyTorch).

[0769] Step 4: Route optimization

[0770] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is information on predicted impassable areas and congestion risks, and the output is optimal route information. The server runs programs that implement these algorithms.

[0771] Step 5: Route information distribution

[0772] The server distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The input is the optimal route information, and the output is the route information distributed to the terminal. The server distributes the information using a communication protocol.

[0773] Step 6: Real-time route updates

[0774] The server recalculates routes based on newly collected data in real time and distributes updated optimal route information. The input is newly collected data, and the output is recalculated route information. The server performs this process periodically to adapt to the latest traffic conditions.

[0775] Step 7: Collect emotional data

[0776] The server collects emotional data from the user (emergency vehicle driver) through voice and facial expressions. The input is the user's voice data and facial expression data, and the output is analyzed emotional state information. The emotion engine performs this analysis.

[0777] Step 8: Route reevaluation

[0778] The server reevaluates the route if necessary based on the user's emotional state obtained from the emotion engine. The input is the analyzed emotional state information, and the output is the reevaluated route information. The server recalculates a less stressful route according to the emotion engine's results.

[0779] In this way, data is collected, processed, and analyzed at each processing step of the server, terminal, and user, and optimal route information is constantly provided. In particular, reevaluating the route according to the driver's emotional state enables quick and safe rescue operations.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] [Third embodiment]

[0784] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0785] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0786] 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).

[0787] 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.

[0788] 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.

[0789] 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).

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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."

[0796] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[0797] System Overview

[0798] This system provides an optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[0799] Data collection

[0800] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[0801] Data Preprocessing

[0802] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[0803] Data Analysis and Prediction

[0804] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[0805] Route Optimization

[0806] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[0807] Route information distribution

[0808] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0809] Real-time updates

[0810] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is then redistributed to the device, and the emergency vehicle adjusts its actions based on the latest optimal route.

[0811] Specific examples

[0812] Example 1: Dispatch of emergency vehicles during floods

[0813] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0814] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0815] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0816] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0817] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[0818] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[0819] Example 2: Transporting relief supplies after an earthquake

[0820] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[0821] 2. The server removes outliers and normalizes the data.

[0822] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[0823] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[0824] 5. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[0825] In this way, emergency vehicles can act quickly and rescue operations can be carried out smoothly in the event of a disaster.

[0826] The processing flow will be explained below.

[0827] Step 1: Data collection

[0828] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it obtains current location and speed information from multiple mobile devices. It also integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[0829] Step 2: Data Preprocessing

[0830] The server preprocesses the collected data. First, it detects and removes outliers from the collected data. Next, it standardizes the formats of GPS data and traffic data and performs normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[0831] Step 3: Data analysis

[0832] The server then analyzes the preprocessed data using a generative AI model. For example, the underlying deep learning model learns general traffic patterns based on past data, and then uses newly collected data to predict impassable areas and congestion risks in specific areas.

[0833] Step 4: Identify impassable areas

[0834] The server analyzes the data and determines that a particular road is impassable due to a flood or earthquake. For example, a road at a particular latitude and longitude is predicted to be impassable based on the latest weather and traffic data.

[0835] Step 5: Predict congestion risk

[0836] Based on the results of the data analysis, the server determines that there is a high possibility of traffic congestion in a particular area. For example, congestion is predicted based on a temporary increase in traffic flow around an evacuation shelter.

[0837] Step 6: Route optimization

[0838] The server calculates the optimal route that avoids identified impassable areas and predicted congestion risks. For example, Algorithm A calculates a route for emergency vehicles to use the expressway, generating a route that will allow them to reach their destination safely and quickly.

[0839] Step 7: Route Distribution

[0840] The server distributes optimal route information to the terminals of local governments and rescue teams in real time. For example, the optimal route is displayed on the screen of a terminal at a local government emergency response center, and the person in charge conveys it to the driver of the emergency vehicle providing assistance.

[0841] Step 8: Real-time updates

[0842] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. When new road impassability or congestion occurs, the route is recalculated based on the new collected data and updated optimal route information is distributed. For example, if a new congestion occurs along the way, a new route reflecting that information is recalculated in real time and distributed to the rescue team's terminal.

[0843] In this way, the system always provides the best route based on the latest conditions, enabling emergency vehicles to provide assistance efficiently and quickly.

[0844] Example 1

[0845] 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."

[0846] In the event of a disaster, it is important for emergency vehicles to obtain real-time information on traffic conditions and passable routes and select an appropriate route in order to reach their destination quickly. However, conventional systems do not perform this process efficiently enough, and emergency vehicles may get caught in traffic jams or impassable areas. In addition, a system that can quickly respond to new changes in the situation is required.

[0847] 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.

[0848] In this invention, the server includes a data collection means for collecting location information and movement histories acquired in real time from multiple mobile objects in the event of a disaster, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to terminals, a real-time route update means for recalculating a route using recollected data based on the optimal route information distributed by the route information distribution means, and a means for distributing the recalculated route to each terminal in real time when new data is collected. This enables emergency vehicles to quickly obtain an optimal route and reach their destination quickly even in the event of a disaster.

[0849] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or tsunami occurs, or a man-made disaster such as a fire or accident occurs.

[0850] "Mobile objects" refers to all moving objects, such as cars, motorbikes, and pedestrians, that can provide location information in real time.

[0851] "Real-time" refers to a timeframe in which data collection, processing, and delivery occur almost instantly, with little or no specific delay.

[0852] "Location Information" refers to latitude, longitude and altitude data obtained through location information systems such as GPS.

[0853] "Movement history" refers to data that records the routes and stopping points taken by a moving object over a certain period of time.

[0854] "Data collection means" refers to a device or system for acquiring location information and movement history from a mobile object in real time.

[0855] "Data preprocessing means" refers to a device or program that performs processing to remove outliers from collected data and normalize the data.

[0856] An "outlier" is an inaccurate or unnatural value in the collected data that falls outside the normal range.

[0857] "Data normalization" refers to the process of converting data collected in different formats or units into a consistent format.

[0858] "Generative AI model" refers to an artificial intelligence model that learns patterns from data and is used to make predictions or classifications. Examples include deep learning models.

[0859] "Data analysis means" refers to a device or program that uses preprocessed data to perform processing for a specific purpose, such as predicting impassable areas or congestion risks.

[0860] An "impassable area" refers to a location where vehicles and pedestrians are temporarily or permanently unable to pass due to a disaster, traffic accident, or other cause.

[0861] "Congestion risk" refers to the prediction of situations and locations that may cause traffic flow to slow down.

[0862] "Route optimization means" refers to a device or program for calculating the optimal route based on given conditions and analysis results.

[0863] "Route information distribution means" refers to a device or system for transmitting calculated optimal route information to a terminal in real time.

[0864] "Terminal" refers to mobile terminals and fixed computer systems used by emergency vehicles and local governments.

[0865] "Real-time route update means" refers to a device or program that updates a route in real time by recalculating it based on new data collected.

[0866] The system of the present invention is designed to support efficient rescue operations by emergency vehicles in the event of a disaster. This system uses data collected from mobile objects in real time to calculate and provide optimal routes. Specific embodiments of the system are described below.

[0867] Data collection

[0868] The server collects real-time GPS data from mobile devices, traffic sensor data, and weather data using high-performance data collection equipment and dedicated software. The collected data is used to track the location and movement history of emergency vehicles and general vehicles.

[0869] Data Preprocessing

[0870] The server preprocesses the collected data with high accuracy. Specifically, it removes outliers and normalizes the data. The software used is a program that implements data cleaning tools and normalization algorithms. For example, if GPS data contains abnormal values, it removes them and converts the data into data that is consistent with other formats.

[0871] Data Analysis and Prediction

[0872] The server uses the preprocessed data to train and analyze generative AI models (e.g., deep learning models). This allows for highly accurate prediction of impassable areas and congestion risks. The AI ​​models used are built using architectures such as TensorFlow and PyTorch. For example, they can identify roads and bridges that have become impassable due to floods or earthquakes, and also predict the risk of future traffic congestion.

[0873] Route Optimization

[0874] The server uses the results of the data analysis to calculate the optimal route. In this process, the A algorithm and Dijkstra algorithm are applied. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible. For example, a specific route is calculated to bypass certain impassable areas.

[0875] Route information distribution

[0876] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time using technologies such as HTTP and WebSocket communication, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0877] Real-time updates

[0878] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server automatically detects this, collects new data, and recalculates the route. The updated route information is quickly delivered to the device, allowing the emergency vehicle to adjust its activities based on the latest information.

[0879] Specific examples

[0880] Dispatch of emergency vehicles during floods

[0881] 1. The server collects GPS data, traffic data, and weather data from mobile devices and traffic sensors in real time.

[0882] 2. The server preprocesses the acquired data, removes outliers, and normalizes the data.

[0883] 3. The server uses the generative AI model to identify the locations of bridges that have become impassable due to flooding.

[0884] 4. The server uses the A algorithm to calculate a fast and safe route.

[0885] 5. The server distributes the optimal route to local government and emergency vehicle terminals in real time.

[0886] 6. Emergency vehicles will use this information to quickly reach the affected area.

[0887] Transporting relief supplies in the event of an earthquake

[0888] 1. The server collects traffic and weather data and analyzes impassable areas and congestion risks due to earthquakes.

[0889] 2. The server removes outliers and normalizes the data.

[0890] 3. The server uses the generated AI model to predict future congestion risks.

[0891] 4. The server calculates the optimal route for delivering relief supplies using the Dijkstra algorithm.

[0892] 5. The server distributes the calculated route information to the Self-Defense Forces' terminals in real time.

[0893] 6. The Self-Defense Forces will use this information to effectively transport relief supplies.

[0894] Prompt Sentence Examples

[0895] "Show the best route for emergency vehicles to quickly reach a particular area in the event of flooding."

[0896] "What is the best route to transport relief supplies effectively in the event of an earthquake?"

[0897] In this way, it is possible to realize rapid action by emergency vehicles and smooth rescue operations in the event of a disaster.

[0898] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0899] Step 1: Data collection

[0900] The server acquires GPS data from mobile devices, traffic sensor data, weather data, and other data in real time. The server connects to each data source and periodically acquires data. The input is raw data acquired from each data source, and the output is a set of collected real-time data. Specifically, the server updates GPS data every 5 seconds and collects data from traffic sensors every 10 seconds.

[0901] Step 2: Data Preprocessing

[0902] The server preprocesses the collected data. Specifically, it fills in missing data, removes outliers, and normalizes the data. The input is the raw data collected in step 1, and the output is the preprocessed clean data. For example, if the GPS data contains abnormal location information, it deletes that data, fills in the missing parts, and standardizes the data format.

[0903] Step 3: Data analysis and prediction

[0904] The server uses the preprocessed data to train a generative AI model and perform analysis. During this process, deep learning models are used to predict impassable areas and congestion risks. The input is preprocessed clean data, and the output is analysis and prediction results. Specifically, it identifies impassable areas due to floods or earthquakes and analyzes past data sets against real-time data to predict future congestion risks.

[0905] Step 4: Route optimization

[0906] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is the analysis results and prediction results, and the output is the optimal route information. For example, it performs specific operations such as avoiding multiple impassable areas and traffic jams and calculating the quickest and safest route.

[0907] Step 5: Route information distribution

[0908] The server distributes the calculated optimal route information to the terminal in real time. This is done using HTTP or WebSocket communication. The input is the optimal route information, and the output is the route information distributed in real time. For example, the server has a list of mobile terminals and fixed computer systems to which it should distribute, and performs the specific operation of sending the latest route information to each terminal in real time.

[0909] Step 6: Real-time updates

[0910] The server collects new data and recalculates the route. When new information about impassable areas or traffic congestion is acquired, it automatically recalculates and redistributes the updated route information. The input is newly collected real-time data, and the output is the latest recalculated route information. Specifically, after new data is collected, it immediately recalculates, generates a new route, and instantly distributes it to each device.

[0911] (Application example 1)

[0912] 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."

[0913] When a disaster occurs, it is important for emergency vehicles to reach their destination quickly and efficiently. However, in reality, emergency vehicle movement is often hindered by ever-changing road conditions and newly emerging obstacles. Furthermore, conventional navigation systems lack the ability to adapt in real time, which can delay the optimization of emergency routes. This can delay rescue efforts and exacerbate disaster damage.

[0914] 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.

[0915] In this invention, the server includes a data collection means for collecting location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to a terminal, a real-time route update means for recalculating a route using re-collected data based on the optimal route information distributed by the route information distribution means, and a means for notifying a smartphone of the route information recalculated by the real-time route update means, thereby enabling rapid and efficient movement of emergency vehicles.

[0916] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or typhoon occurs.

[0917] "Multiple moving objects" refers to various means of transportation such as emergency vehicles, regular vehicles, and drones.

[0918] "Real-time" refers to data acquired continuously in ongoing time.

[0919] "Location information" refers to information about your current location, such as GPS data obtained from a mobile device or vehicle.

[0920] "Movement history" refers to a record of movement based on past location information.

[0921] "Data collection means" refers to the devices and systems used to collect the necessary data.

[0922] "Data preprocessing means" refers to means for preprocessing collected data, such as removing outliers and normalizing data.

[0923] An "outlier" is data that falls outside the normal range.

[0924] "Normalization" refers to the process of standardizing data formats so that they can be handled according to common standards.

[0925] "Data analysis means" refers to a device or system for analyzing collected and pre-processed data.

[0926] A "generative AI model" refers to a machine learning model that uses artificial intelligence to perform data analysis, etc.

[0927] "Impassable areas" refer to areas that are impassable due to disasters or other reasons.

[0928] "Congestion risk" refers to the possibility of traffic flow slowing down.

[0929] "Route optimizer" refers to a device or system for calculating the most efficient route.

[0930] The "route information distribution means" refers to a device or system for distributing calculated route information to a terminal.

[0931] "Real-time route update means" refers to a device or system for recalculating and updating route information based on the latest data.

[0932] "Terminal" refers to a device for receiving and displaying information.

[0933] A "smartphone" refers to a mobile phone with advanced computing power and internet connectivity.

[0934] A "prompt sentence" refers to an instruction sentence input to a generative AI model to obtain an appropriate output result.

[0935] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[0936] System Overview

[0937] This system provides the optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[0938] Data collection

[0939] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[0940] Data Preprocessing

[0941] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[0942] Data Analysis and Prediction

[0943] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[0944] Route Optimization

[0945] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[0946] Route information distribution

[0947] The server then delivers the calculated optimal route information to smartphones and other devices in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0948] Real-time updates

[0949] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is again sent to the smartphone, and the emergency vehicle adjusts its actions based on the latest optimal route.

[0950] Specific examples

[0951] Dispatch of emergency vehicles during floods

[0952] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0953] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0954] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0955] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[0956] 5. The server distributes optimal route information to smartphones and other devices.

[0957] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[0958] Example prompts for generative AI models

[0959] "Identify areas that have become impassable due to flooding and generate safe routes."

[0960] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0961] Step 1:

[0962] The server collects data in real time from mobile devices, traffic sensors, and weather data collection devices. The input data includes the location information of each mobile object and its movement history. This data consists of GPS data, traffic condition data, weather data, etc. The server initially collects this data and prepares it for subsequent processing.

[0963] Step 2:

[0964] The server preprocesses the collected data. Specifically, if there are any outliers in the data, they are removed. The data format is also standardized and normalized. For example, if there are any outliers in the GPS data (such as extremely distant location information), they are removed. The preprocessed data is then passed to the subsequent analysis step.

[0965] Step 3:

[0966] The server analyzes the preprocessed data. A generative AI model (e.g., a deep learning model) is used to predict impassable areas and congestion risks. The input data includes location information, movement history, and traffic condition data preprocessed in the previous step. This data is analyzed using a generative AI model to predict impassable areas and future congestion risks. The output includes location information of impassable areas and congestion risks.

[0967] Step 4:

[0968] The server calculates the optimal route based on the results of the data analysis. It uses route search algorithms such as the A algorithm and Dijkstra algorithm to calculate a route that avoids impassable areas and congestion risks. The input data includes information on impassable areas and congestion risks predicted in the previous step. The server calculates the optimal route based on this data and provides it as output.

[0969] Step 5:

[0970] The server delivers the calculated optimal route information to smartphones and other devices in real time. The input data includes the optimal route information. The server sends this information to the device in real time and notifies the emergency vehicle driver.

[0971] Step 6:

[0972] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server collects data again and updates the route. The input data includes newly collected location information and traffic condition data. The server recalculates the route based on this data and notifies the smartphone of the updated optimal route information. The emergency vehicle driver continues traveling according to the new route notified again.

[0973] These steps will enable the rapid and efficient movement of emergency vehicles in the event of a disaster.

[0974] 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.

[0975] A specific embodiment of a system that supports efficient rescue operations by emergency vehicles in the event of a disaster by combining an emotion engine will be described below.

[0976] System Overview

[0977] This system includes a data collection means, data preprocessing means, data analysis means, route optimization means, route information distribution means, real-time route update means, and an emotion engine that recognizes the user's emotions. This not only enables emergency vehicles to reach their destinations quickly, but also reduces the stress of users (such as emergency vehicle drivers).

[0978] Data collection

[0979] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it acquires current location and speed information from multiple mobile devices, and integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[0980] Data Preprocessing

[0981] The server preprocesses the collected data, detecting and removing outliers from the collected data, standardizing the formats of GPS data and traffic data, and performing normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[0982] Data Analysis and Prediction

[0983] The server then analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks. For example, it can identify roads and bridges that have become impassable due to floods or earthquakes and predict the risk of future traffic congestion.

[0984] Route Optimization

[0985] The server calculates the optimal route based on the results of data analysis. It uses the A algorithm and Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly.

[0986] Route information distribution

[0987] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[0988] Real-time updates

[0989] The server continuously collects real-time data and monitors changes in road closures and congestion risks. If new road closures or congestion occur, the server recalculates the route based on the new data collected and distributes updated optimal route information.

[0990] Recognizing user emotions with an emotion engine

[0991] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions. For example, if an emergency vehicle driver is nervous, the emotion engine will quantify the level of nervousness based on the driver's facial expression and voice data.

[0992] Reassessing your route based on emotions

[0993] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, it recalculates an easier and less stressful route.

[0994] Specific examples

[0995] Example 1: Dispatch of emergency vehicles during floods

[0996] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[0997] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[0998] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[0999] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[1000] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[1001] 6. The emotion engine analyzes the voice and facial expressions of emergency vehicle drivers and reevaluates routes to reduce stress if the driver is feeling stressed.

[1002] 7. Emergency vehicles will follow this information to quickly reach the affected area.

[1003] Example 2: Transporting relief supplies after an earthquake

[1004] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[1005] 2. The server removes outliers and normalizes the data.

[1006] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[1007] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[1008] 5. An emotion engine assesses the driver's level of tension and stress and adjusts routes as needed.

[1009] 6. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[1010] In this way, the system not only supports the rapid action of emergency vehicles in the event of a disaster, but also takes into account the emotions and stress of emergency vehicle drivers, enabling more effective rescue operations.

[1011] The processing flow will be explained below.

[1012] Step 1: Data collection

[1013] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. For example, it obtains GPS data from each mobile device, vehicle flow and speed data from traffic sensors, and the latest weather information from weather data collectors.

[1014] Step 2: Data Preprocessing

[1015] The server preprocesses the collected data. First, it detects and removes outliers, then standardizes the data format and performs normalization. For example, it converts GPS data into a common coordinate system and standardizes time information to improve data accuracy.

[1016] Step 3: Data analysis

[1017] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts impassable areas and congestion risks. For example, it identifies roads that have become impassable due to floods or earthquakes, and time periods and areas where congestion is likely to occur.

[1018] Step 4: Identify impassable areas

[1019] The server analyzes the data and identifies impassable areas, for example, roads and bridges damaged by floods.

[1020] Step 5: Predict congestion risk

[1021] The server uses the results of data analysis to predict future congestion risks. For example, it predicts a sudden increase in traffic flow around evacuation shelters and determines that there is a high possibility of congestion occurring as a result.

[1022] Step 6: Route optimization

[1023] The server calculates the optimal route that avoids identified impassable areas and congestion risks, for example using the A algorithm or Dijkstra algorithm to determine the fastest and safest route for emergency vehicles to reach their destination.

[1024] Step 7: Route Distribution

[1025] The server distributes the generated optimal route information to the terminals of local governments and rescue teams, for example by sending the route information in real time to the navigation systems of emergency vehicles.

[1026] Step 8: Collect emotion data

[1027] The terminal collects the user's voice data, facial expression data, or biometric data. For example, real-time biometric information is collected from a wearable device worn by an emergency vehicle driver.

[1028] Step 9: Sentiment Analysis

[1029] The emotion engine analyzes the collected data and recognizes the user's emotions (level of tension and stress). For example, it quantifies how tense the user is based on the tone of their voice data and changes in their facial expressions.

[1030] Step 10: Reassess your route based on your emotions

[1031] The server takes into account the user's emotional data recognized by the emotion engine and reevaluates the route. For example, if the driver is extremely nervous, it will recalculate a straighter and easier route.

[1032] Step 11: Distributing recalculated route information

[1033] The server then redistributes the recalculated optimal route information to the emergency vehicle's terminal, allowing the driver to head to their destination with less stress based on the latest information.

[1034] In this way, the system can grasp the user's emotional state in real time and provide the optimal route accordingly, helping emergency vehicles reach their destination efficiently and safely.

[1035] Example 2

[1036] 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."

[1037] Conventional disaster response systems, even if capable of collecting information and quickly preprocessing data in real time, do not take into account the influence of driver emotions and stress when operating emergency vehicles. As a result, even if an emergency vehicle selects the optimal route, if the driver is overly nervous or stressed, it may be difficult to operate quickly and safely. Furthermore, even if the route is updated in real time, it may not always be optimal for the driver. A solution to these issues is needed.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1039] In this invention, the server includes a data collection means for collecting location information and movement history acquired in real time from multiple mobile objects, a data preprocessing means for preprocessing the collected data, removing outliers, and normalizing the data, a data analysis means for analyzing the preprocessed data and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the predicted impassable areas and congestion risks, a route information distribution means for distributing the calculated optimal route information to the terminal, a real-time route update means for recalculating the route using recollected data based on the distributed optimal route information, an emotion engine means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotion, and an emotion-based route reevaluation means for reevaluating and recalculating the route based on the recognized user emotion data. This enables emergency vehicles to not only select the optimal route but also operate while taking into account the driver's emotion and stress level.

[1040] The "data collection means" is a means for collecting location information and movement history in real time from multiple mobile objects when a disaster occurs.

[1041] The "data preprocessing means" is a means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data.

[1042] A "generative AI model" is an artificial intelligence model that analyzes preprocessed data and predicts impassable areas and congestion risks.

[1043] The "data analysis means" is a means for analyzing data preprocessed by the data preprocessing means using a generative AI model to predict impassable areas and congestion risks.

[1044] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[1045] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[1046] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[1047] The "emotion engine means" is a means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotions.

[1048] The "route re-evaluation means based on emotion" is a means for re-evaluating and re-calculating the route based on the emotion data of the user recognized by the emotion engine means.

[1049] This invention relates to a system that supports efficient rescue operations by emergency vehicles when a disaster occurs, and specifically, the system includes data collection, data preprocessing, data analysis, route optimization, route information distribution, real-time route update, and user emotion recognition and route reevaluation based on that emotion. Each element of this system is described in detail below.

[1050] Data collection

[1051] When a disaster occurs, the server collects real-time location information and movement history from multiple mobile devices (e.g., emergency vehicles, personal devices). Specifically, it integrates GPS data from mobile devices, vehicle flow data from traffic sensors, and weather observation data from weather data collection devices. The hardware used for this data collection includes GPS modules, traffic sensors, and weather observation devices.

[1052] Data Preprocessing

[1053] The server preprocesses the data acquired by the data collection means. This preprocessing involves detecting and removing outliers and normalizing data provided in different formats. For example, abnormal values ​​for altitude and position in GPS data are removed. Furthermore, different time formats are unified to standardize the data.

[1054] Data analysis

[1055] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts potential road impassability and congestion risks. Specifically, a deep learning model is trained using past and current traffic data as input to predict future road impassability and congestion. For example, it can identify areas where roads and bridges will be impassable due to floods or earthquakes.

[1056] Route Optimization

[1057] The server calculates the optimal route based on the prediction results from the data analysis method. It uses the A algorithm or Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly. For example, it proposes the shortest route that avoids impassable areas.

[1058] Route information distribution

[1059] The server then distributes the calculated optimal route information in real time to the devices of local governments and rescue teams, allowing emergency vehicle drivers to instantly obtain the latest route information and take swift and safe action.

[1060] Real-time updates

[1061] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. If new road impassability or congestion occurs, the server immediately updates the data, recalculates the optimal route, and distributes the latest route information.

[1062] Recognizing user emotions with an emotion engine

[1063] The server or a dedicated emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotion. For example, if an emergency vehicle driver is nervous, the emotion engine can analyze the voice tone and facial expression to quantify the level of nervousness.

[1064] Emotion-based route reassessment

[1065] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, the server recalculates the route to select safer and wider roads, thereby reducing the driver's burden.

[1066] Specific examples

[1067] One example is the dispatch of emergency vehicles during floods. The server collects data from mobile devices and traffic sensors, including data on bridges that are impassable due to flooding. After preprocessing the data and removing outliers, a generative AI model is used to identify impassable areas. Route optimization is performed to generate a route that uses highways and distributes it to the local government's terminal and the emergency vehicle's terminal. In addition, an emotion engine evaluates the driver's level of stress and reevaluates the route if necessary.

[1068] An example prompt for using a generative AI model is:

[1069] "Predict expected road impassability and congestion risk within the next hour based on current traffic and weather data."

[1070] As a result, the system can support the swift and safe operation of emergency vehicles in the event of a disaster, reducing stress and tension for drivers.

[1071] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1072] Program processing flow

[1073] Step 1: Data collection

[1074] The server collects GPS data from mobile devices, data from traffic sensors, and weather data in real time.

[1075] (Input) Location information from mobile devices, flow rate and velocity data from traffic sensors, and observation data from the Meteorological Agency.

[1076] (Output) A consolidated real-time dataset.

[1077] Specifically, the server periodically retrieves information from each data source and stores the data in different formats in a single database.

[1078] Step 2: Data Preprocessing

[1079] The server pre-processes the collected data.

[1080] (Input) Integrated real-time dataset.

[1081] (Output) The normalized dataset with outliers removed.

[1082] Detect and remove outliers in collected data, and standardize the formats of GPS and traffic data, for example by standardizing the coordinate system for location information and standardizing time information.

[1083] Step 3: Data analysis and prediction

[1084] The server analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[1085] (Input) The preprocessed dataset.

[1086] (Output) Predicted impassable areas and congestion risk data.

[1087] Specifically, the server performs analysis based on deep learning models to predict future risks based on past and current traffic conditions.

[1088] Step 4: Route optimization

[1089] The server calculates the optimal route based on the results of data analysis.

[1090] (Input) Predicted impassable areas and congestion risk data.

[1091] (Output) Optimal route information.

[1092] The A algorithm and Dijkstra algorithm are used to calculate the shortest and safest route. Specifically, it searches for a route with the objectives of minimizing time and avoiding risk.

[1093] Step 5: Route information distribution

[1094] The server distributes the calculated optimal route information to the terminals of local governments and rescue teams in real time.

[1095] (Input) Optimal route information.

[1096] (Output) Notification of delivery completion to each device.

[1097] Specifically, the server transmits route information to each terminal via the communication module and records the transmission log.

[1098] Step 6: Real-time updates

[1099] The server continuously collects real-time data and monitors changes in impassable areas and congestion risks.

[1100] (Input) Newly collected real-time data.

[1101] (Output) Updated optimal route information.

[1102] If a new road closure or congestion occurs, the server immediately recalculates the route and delivers the latest route information again.

[1103] Step 7: Recognizing user emotions with the emotion engine

[1104] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions.

[1105] (Input) Voice data, facial expression data, biometric data.

[1106] (Output) User emotion data.

[1107] Specifically, the server or emotion engine uses voice activity detection (VAD) and facial expression recognition algorithms to assess and quantify the user's emotional state.

[1108] Step 8: Emotion-Based Route Reassessment

[1109] The server receives the user's emotion data recognized by the emotion engine and reevaluates the route if necessary.

[1110] (Input) User emotion data.

[1111] (Output) The reevaluated optimal route information.

[1112] For example, if the driver is overly nervous, the server will recalculate the route to select safer, wider roads, and the reevaluated route information will be sent to the device again.

[1113] The above is the specific flow of program processing for this system.

[1114] (Application example 2)

[1115] 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."

[1116] In order for emergency vehicles to carry out rescue operations quickly and safely in the event of a disaster, it is essential to obtain accurate traffic and weather information in real time and provide optimal routes. However, current systems do not reevaluate routes taking into account the driver's emotions and stress, which creates the risk that emergency vehicle drivers will become overly nervous and make incorrect decisions. Therefore, a system is needed that can recognize the driver's emotional state in real time and reevaluate routes based on that information.

[1117] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a data collection means that collects location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs; a data preprocessing means that preprocesses the data collected by the data collection means, removes outliers, and normalizes the data; a data analysis means that analyzes the data preprocessed by the data preprocessing means and predicts impassable areas and congestion risks using a generative AI model; a route optimization means that calculates an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means; a route information distribution means that distributes optimal route information calculated by the route optimization means to a terminal; a real-time route update means that recalculates a route using re-collected data based on the optimal route information distributed by the route information distribution means; and an emotion engine means that collects user emotion data using the real-time route update means and re-evaluates the route based on the data. This enables fast and safe rescue operations that take into account the emotions and stress of emergency vehicle drivers.

[1118] The "data collection means" is a means for acquiring location information and movement history from multiple mobile objects in real time when a disaster occurs.

[1119] The "data preprocessing means" is a means for removing outliers in the data collected by the data collection means and for normalizing the data.

[1120] "Data analysis means" refers to a means of predicting impassable areas and congestion risks using an AI model generated from preprocessed data.

[1121] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[1122] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[1123] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[1124] The "emotion engine means" is a means for collecting user emotion data and re-evaluating the route based on that data.

[1125] A "generative AI model" is an algorithm that uses machine learning technology to learn patterns from large amounts of data and predict impassable areas and congestion risks.

[1126] The "A algorithm" is a type of graph search algorithm used to calculate the shortest route.

[1127] The "Dijkstra algorithm" is an algorithm for finding the shortest path on a graph with non-negative weights.

[1128] "Device" means a computer or mobile device used by an emergency vehicle driver or local government.

[1129] An "impassable area" is an area where vehicles cannot pass due to a disaster or other reason.

[1130] "Congestion risk" indicates the possibility of traffic congestion occurring on a particular road or area.

[1131] The present invention is a system for supporting efficient rescue operations by emergency vehicles when a disaster occurs, and specific embodiments thereof will be described below.

[1132] System Overview

[1133] The system includes a data collection means, a data pre-processing means, a data analysis means, a route optimization means, a route information distribution means, a real-time route update means, and an emotion engine means.

[1134] The server collects GPS data from mobile devices, traffic sensor data, and weather data in real time. A data preprocessing means detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. Furthermore, a data analysis means analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[1135] The route optimization means calculates the optimal route using the A algorithm or the Dijkstra algorithm based on the analysis results obtained from the data analysis means. The route information distribution means distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The real-time route update means recalculates the route based on new data and distributes the updated optimal route information. In addition, the emotion engine means collects emotion data from the user (emergency vehicle driver) and reevaluates the route based on that data.

[1136] Hardware and Software

[1137] The system requires hardware such as GPS sensors, traffic sensors, weather data collection devices, and computers installed in autonomous vehicles. The software includes Python, machine learning libraries (e.g., Scikit-learn), Dijkstra's algorithm, A algorithm, generative AI models, and emotion engines. Specific examples of Python libraries include Numpy, Pandas, Scikit-learn, and PyTorch.

[1138] Specific examples

[1139] The server collects GPS data, traffic sensor data, and weather data in real time as emergency vehicles head toward flood-prone areas. The collected data is subjected to a data pre-processing means, which removes outliers and normalizes them. Then, a data analysis means using a generative AI model predicts impassable areas and congestion risks. Next, a route optimization means calculates the optimal route based on the analysis results, and the route information distribution means distributes it to the emergency vehicle's terminal. The driver's emotional state is analyzed in real time by an emotion engine means, and the route is reevaluated as necessary.

[1140] Prompt Sentence Examples

[1141] Suggest the optimal route based on traffic and weather data from the designated emergency vehicle's current location to its destination. Calculate routes to avoid impassable areas or potential congestion. Also, choose a route that minimizes stress for drivers who are under stress.

[1142] This concrete example demonstrates how the system can achieve fast and safe rescue operations while taking into account the emotions and stress of emergency vehicle drivers.

[1143] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1144] Step 1: Data collection

[1145] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. The inputs are location information, speed information, traffic sensor data, and weather data. The server receives these data and outputs them as an integrated dataset.

[1146] Step 2: Data Preprocessing

[1147] The server detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. The input is the data collected in step 1, and the output is a preprocessed dataset. The server uses libraries such as Numpy and Pandas for this processing.

[1148] Step 3: Data analysis

[1149] The server uses the preprocessed data to predict road impassability and congestion risk using a generative AI model. The input is the preprocessed dataset, and the output is predicted road impassability and congestion risk information. At this stage, the server performs data analysis using machine learning libraries (e.g., Scikit-learn and PyTorch).

[1150] Step 4: Route optimization

[1151] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is information on predicted impassable areas and congestion risks, and the output is optimal route information. The server runs programs that implement these algorithms.

[1152] Step 5: Route information distribution

[1153] The server distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The input is the optimal route information, and the output is the route information distributed to the terminal. The server distributes the information using a communication protocol.

[1154] Step 6: Real-time route updates

[1155] The server recalculates routes based on newly collected data in real time and distributes updated optimal route information. The input is newly collected data, and the output is recalculated route information. The server performs this process periodically to adapt to the latest traffic conditions.

[1156] Step 7: Collect emotional data

[1157] The server collects emotional data from the user (emergency vehicle driver) through voice and facial expressions. The input is the user's voice data and facial expression data, and the output is analyzed emotional state information. The emotion engine performs this analysis.

[1158] Step 8: Route reevaluation

[1159] The server reevaluates the route if necessary based on the user's emotional state obtained from the emotion engine. The input is the analyzed emotional state information, and the output is the reevaluated route information. The server recalculates a less stressful route according to the emotion engine's results.

[1160] In this way, data is collected, processed, and analyzed at each processing step of the server, terminal, and user, and optimal route information is constantly provided. In particular, reevaluating the route according to the driver's emotional state enables quick and safe rescue operations.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] [Fourth embodiment]

[1165] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1166] 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.

[1167] 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).

[1168] 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.

[1169] 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.

[1170] 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).

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] 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."

[1178] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[1179] System Overview

[1180] This system provides an optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[1181] Data collection

[1182] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[1183] Data Preprocessing

[1184] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[1185] Data Analysis and Prediction

[1186] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[1187] Route Optimization

[1188] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[1189] Route information distribution

[1190] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[1191] Real-time updates

[1192] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is then redistributed to the device, and the emergency vehicle adjusts its actions based on the latest optimal route.

[1193] Specific examples

[1194] Example 1: Dispatch of emergency vehicles during floods

[1195] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[1196] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[1197] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[1198] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[1199] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[1200] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[1201] Example 2: Transporting relief supplies after an earthquake

[1202] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[1203] 2. The server removes outliers and normalizes the data.

[1204] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[1205] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[1206] 5. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[1207] In this way, emergency vehicles can act quickly and rescue operations can be carried out smoothly in the event of a disaster.

[1208] The processing flow will be explained below.

[1209] Step 1: Data collection

[1210] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it obtains current location and speed information from multiple mobile devices. It also integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[1211] Step 2: Data Preprocessing

[1212] The server preprocesses the collected data. First, it detects and removes outliers from the collected data. Next, it standardizes the formats of GPS data and traffic data and performs normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[1213] Step 3: Data analysis

[1214] The server then analyzes the preprocessed data using a generative AI model. For example, the underlying deep learning model learns general traffic patterns based on past data, and then uses newly collected data to predict impassable areas and congestion risks in specific areas.

[1215] Step 4: Identify impassable areas

[1216] The server analyzes the data and determines that a particular road is impassable due to a flood or earthquake. For example, a road at a particular latitude and longitude is predicted to be impassable based on the latest weather and traffic data.

[1217] Step 5: Predict congestion risk

[1218] Based on the results of the data analysis, the server determines that there is a high possibility of traffic congestion in a particular area. For example, congestion is predicted based on a temporary increase in traffic flow around an evacuation shelter.

[1219] Step 6: Route optimization

[1220] The server calculates the optimal route that avoids identified impassable areas and predicted congestion risks. For example, Algorithm A calculates a route for emergency vehicles to use the expressway, generating a route that will allow them to reach their destination safely and quickly.

[1221] Step 7: Route Distribution

[1222] The server distributes optimal route information to the terminals of local governments and rescue teams in real time. For example, the optimal route is displayed on the screen of a terminal at a local government emergency response center, and the person in charge conveys it to the driver of the emergency vehicle providing assistance.

[1223] Step 8: Real-time updates

[1224] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. When new road impassability or congestion occurs, the route is recalculated based on the new collected data and updated optimal route information is distributed. For example, if a new congestion occurs along the way, a new route reflecting that information is recalculated in real time and distributed to the rescue team's terminal.

[1225] In this way, the system always provides the best route based on the latest conditions, enabling emergency vehicles to provide assistance efficiently and quickly.

[1226] Example 1

[1227] 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."

[1228] In the event of a disaster, it is important for emergency vehicles to obtain real-time information on traffic conditions and passable routes and select an appropriate route in order to reach their destination quickly. However, conventional systems do not perform this process efficiently enough, and emergency vehicles may get caught in traffic jams or impassable areas. In addition, a system that can quickly respond to new changes in the situation is required.

[1229] 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.

[1230] In this invention, the server includes a data collection means for collecting location information and movement histories acquired in real time from multiple mobile objects in the event of a disaster, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to terminals, a real-time route update means for recalculating a route using recollected data based on the optimal route information distributed by the route information distribution means, and a means for distributing the recalculated route to each terminal in real time when new data is collected. This enables emergency vehicles to quickly obtain an optimal route and reach their destination quickly even in the event of a disaster.

[1231] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or tsunami occurs, or a man-made disaster such as a fire or accident occurs.

[1232] "Mobile objects" refers to all moving objects, such as cars, motorbikes, and pedestrians, that can provide location information in real time.

[1233] "Real-time" refers to a timeframe in which data collection, processing, and delivery occur almost instantly, with little or no specific delay.

[1234] "Location Information" refers to latitude, longitude and altitude data obtained through location information systems such as GPS.

[1235] "Movement history" refers to data that records the routes and stopping points taken by a moving object over a certain period of time.

[1236] "Data collection means" refers to a device or system for acquiring location information and movement history from a mobile object in real time.

[1237] "Data preprocessing means" refers to a device or program that performs processing to remove outliers from collected data and normalize the data.

[1238] An "outlier" is an inaccurate or unnatural value in the collected data that falls outside the normal range.

[1239] "Data normalization" refers to the process of converting data collected in different formats or units into a consistent format.

[1240] "Generative AI model" refers to an artificial intelligence model that learns patterns from data and is used to make predictions or classifications. Examples include deep learning models.

[1241] "Data analysis means" refers to a device or program that uses preprocessed data to perform processing for a specific purpose, such as predicting impassable areas or congestion risks.

[1242] An "impassable area" refers to a location where vehicles and pedestrians are temporarily or permanently unable to pass due to a disaster, traffic accident, or other cause.

[1243] "Congestion risk" refers to the prediction of situations and locations that may cause traffic flow to slow down.

[1244] "Route optimization means" refers to a device or program for calculating the optimal route based on given conditions and analysis results.

[1245] "Route information distribution means" refers to a device or system for transmitting calculated optimal route information to a terminal in real time.

[1246] "Terminal" refers to mobile terminals and fixed computer systems used by emergency vehicles and local governments.

[1247] "Real-time route update means" refers to a device or program that updates a route in real time by recalculating it based on new data collected.

[1248] The system of the present invention is designed to support efficient rescue operations by emergency vehicles in the event of a disaster. This system uses data collected from mobile objects in real time to calculate and provide optimal routes. Specific embodiments of the system are described below.

[1249] Data collection

[1250] The server collects real-time GPS data from mobile devices, traffic sensor data, and weather data using high-performance data collection equipment and dedicated software. The collected data is used to track the location and movement history of emergency vehicles and general vehicles.

[1251] Data Preprocessing

[1252] The server preprocesses the collected data with high accuracy. Specifically, it removes outliers and normalizes the data. The software used is a program that implements data cleaning tools and normalization algorithms. For example, if GPS data contains abnormal values, it removes them and converts the data into data that is consistent with other formats.

[1253] Data Analysis and Prediction

[1254] The server uses the preprocessed data to train and analyze generative AI models (e.g., deep learning models). This allows for highly accurate prediction of impassable areas and congestion risks. The AI ​​models used are built using architectures such as TensorFlow and PyTorch. For example, they can identify roads and bridges that have become impassable due to floods or earthquakes, and also predict the risk of future traffic congestion.

[1255] Route Optimization

[1256] The server uses the results of the data analysis to calculate the optimal route. In this process, the A algorithm and Dijkstra algorithm are applied. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible. For example, a specific route is calculated to bypass certain impassable areas.

[1257] Route information distribution

[1258] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time using technologies such as HTTP and WebSocket communication, allowing emergency vehicle drivers to act quickly based on the latest route information.

[1259] Real-time updates

[1260] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server automatically detects this, collects new data, and recalculates the route. The updated route information is quickly delivered to the device, allowing the emergency vehicle to adjust its activities based on the latest information.

[1261] Specific examples

[1262] Dispatch of emergency vehicles during floods

[1263] 1. The server collects GPS data, traffic data, and weather data from mobile devices and traffic sensors in real time.

[1264] 2. The server preprocesses the acquired data, removes outliers, and normalizes the data.

[1265] 3. The server uses the generative AI model to identify the locations of bridges that have become impassable due to flooding.

[1266] 4. The server uses the A algorithm to calculate a fast and safe route.

[1267] 5. The server distributes the optimal route to local government and emergency vehicle terminals in real time.

[1268] 6. Emergency vehicles will use this information to quickly reach the affected area.

[1269] Transporting relief supplies in the event of an earthquake

[1270] 1. The server collects traffic and weather data and analyzes impassable areas and congestion risks due to earthquakes.

[1271] 2. The server removes outliers and normalizes the data.

[1272] 3. The server uses the generated AI model to predict future congestion risks.

[1273] 4. The server calculates the optimal route for delivering relief supplies using the Dijkstra algorithm.

[1274] 5. The server distributes the calculated route information to the Self-Defense Forces' terminals in real time.

[1275] 6. The Self-Defense Forces will use this information to effectively transport relief supplies.

[1276] Prompt Sentence Examples

[1277] "Show the best route for emergency vehicles to quickly reach a particular area in the event of flooding."

[1278] "What is the best route to transport relief supplies effectively in the event of an earthquake?"

[1279] In this way, it is possible to realize rapid action by emergency vehicles and smooth rescue operations in the event of a disaster.

[1280] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1281] Step 1: Data collection

[1282] The server acquires GPS data from mobile devices, traffic sensor data, weather data, and other data in real time. The server connects to each data source and periodically acquires data. The input is raw data acquired from each data source, and the output is a set of collected real-time data. Specifically, the server updates GPS data every 5 seconds and collects data from traffic sensors every 10 seconds.

[1283] Step 2: Data Preprocessing

[1284] The server preprocesses the collected data. Specifically, it fills in missing data, removes outliers, and normalizes the data. The input is the raw data collected in step 1, and the output is the preprocessed clean data. For example, if the GPS data contains abnormal location information, it deletes that data, fills in the missing parts, and standardizes the data format.

[1285] Step 3: Data analysis and prediction

[1286] The server uses the preprocessed data to train a generative AI model and perform analysis. During this process, deep learning models are used to predict impassable areas and congestion risks. The input is preprocessed clean data, and the output is analysis and prediction results. Specifically, it identifies impassable areas due to floods or earthquakes and analyzes past data sets against real-time data to predict future congestion risks.

[1287] Step 4: Route optimization

[1288] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is the analysis results and prediction results, and the output is the optimal route information. For example, it performs specific operations such as avoiding multiple impassable areas and traffic jams and calculating the quickest and safest route.

[1289] Step 5: Route information distribution

[1290] The server distributes the calculated optimal route information to the terminal in real time. This is done using HTTP or WebSocket communication. The input is the optimal route information, and the output is the route information distributed in real time. For example, the server has a list of mobile terminals and fixed computer systems to which it should distribute, and performs the specific operation of sending the latest route information to each terminal in real time.

[1291] Step 6: Real-time updates

[1292] The server collects new data and recalculates the route. When new information about impassable areas or traffic congestion is acquired, it automatically recalculates and redistributes the updated route information. The input is newly collected real-time data, and the output is the latest recalculated route information. Specifically, after new data is collected, it immediately recalculates, generates a new route, and instantly distributes it to each device.

[1293] (Application example 1)

[1294] 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."

[1295] When a disaster occurs, it is important for emergency vehicles to reach their destination quickly and efficiently. However, in reality, emergency vehicle movement is often hindered by ever-changing road conditions and newly emerging obstacles. Furthermore, conventional navigation systems lack the ability to adapt in real time, which can delay the optimization of emergency routes. This can delay rescue efforts and exacerbate disaster damage.

[1296] 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.

[1297] In this invention, the server includes a data collection means for collecting location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs, a data preprocessing means for preprocessing the data collected by the data collection means to remove outliers and normalize the data, a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means, a route information distribution means for distributing optimal route information calculated by the route optimization means to a terminal, a real-time route update means for recalculating a route using re-collected data based on the optimal route information distributed by the route information distribution means, and a means for notifying a smartphone of the route information recalculated by the real-time route update means, thereby enabling rapid and efficient movement of emergency vehicles.

[1298] "When a disaster occurs" refers to a situation when a natural disaster such as an earthquake, flood, or typhoon occurs.

[1299] "Multiple moving objects" refers to various means of transportation such as emergency vehicles, regular vehicles, and drones.

[1300] "Real-time" refers to data acquired continuously in ongoing time.

[1301] "Location information" refers to information about your current location, such as GPS data obtained from a mobile device or vehicle.

[1302] "Movement history" refers to a record of movement based on past location information.

[1303] "Data collection means" refers to the devices and systems used to collect the necessary data.

[1304] "Data preprocessing means" refers to means for preprocessing collected data, such as removing outliers and normalizing data.

[1305] An "outlier" is data that falls outside the normal range.

[1306] "Normalization" refers to the process of standardizing data formats so that they can be handled according to common standards.

[1307] "Data analysis means" refers to a device or system for analyzing collected and pre-processed data.

[1308] A "generative AI model" refers to a machine learning model that uses artificial intelligence to perform data analysis, etc.

[1309] "Impassable areas" refer to areas that are impassable due to disasters or other reasons.

[1310] "Congestion risk" refers to the possibility of traffic flow slowing down.

[1311] "Route optimizer" refers to a device or system for calculating the most efficient route.

[1312] The "route information distribution means" refers to a device or system for distributing calculated route information to a terminal.

[1313] "Real-time route update means" refers to a device or system for recalculating and updating route information based on the latest data.

[1314] "Terminal" refers to a device for receiving and displaying information.

[1315] A "smartphone" refers to a mobile phone with advanced computing power and internet connectivity.

[1316] A "prompt sentence" refers to an instruction sentence input to a generative AI model to obtain an appropriate output result.

[1317] A specific embodiment of the system for supporting efficient rescue operations by emergency vehicles in the event of a disaster according to the present invention will be described below.

[1318] System Overview

[1319] This system provides the optimal route for emergency vehicles to quickly reach their destination based on data collected from moving objects in real time. The system includes a data collection means, a data preprocessing means, a data analysis means, a route optimization means, a route information distribution means, and a real-time route update means.

[1320] Data collection

[1321] The server collects GPS data from mobile devices, traffic sensor data, weather data, and other data in real time, allowing the location and movement history of emergency vehicles and general vehicles to be tracked.

[1322] Data Preprocessing

[1323] The server preprocesses the collected data, removes outliers, and normalizes the data. For example, if there is an anomaly in the acquired GPS data, that data is excluded and unified with other data formats.

[1324] Data Analysis and Prediction

[1325] The server analyzes the preprocessed data using a generative AI model (e.g., a deep learning model) to predict impassable areas and congestion risks. For example, it identifies roads and bridges that have become impassable due to floods or earthquakes and predicts the risk of future traffic congestion.

[1326] Route Optimization

[1327] The server calculates the optimal route based on the results of the data analysis. This can be done using the A algorithm or Dijkstra algorithm. This generates a route that will allow emergency vehicles to reach their destination as quickly as possible.

[1328] Route information distribution

[1329] The server then delivers the calculated optimal route information to smartphones and other devices in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[1330] Real-time updates

[1331] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server detects this, collects new data, and recalculates the route. The updated route information is again sent to the smartphone, and the emergency vehicle adjusts its actions based on the latest optimal route.

[1332] Specific examples

[1333] Dispatch of emergency vehicles during floods

[1334] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[1335] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[1336] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[1337] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[1338] 5. The server distributes optimal route information to smartphones and other devices.

[1339] 6. Emergency vehicles will follow this route information to quickly reach the disaster area.

[1340] Example prompts for generative AI models

[1341] "Identify areas that have become impassable due to flooding and generate safe routes."

[1342] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1343] Step 1:

[1344] The server collects data in real time from mobile devices, traffic sensors, and weather data collection devices. The input data includes the location information of each mobile object and its movement history. This data consists of GPS data, traffic condition data, weather data, etc. The server initially collects this data and prepares it for subsequent processing.

[1345] Step 2:

[1346] The server preprocesses the collected data. Specifically, if there are any outliers in the data, they are removed. The data format is also standardized and normalized. For example, if there are any outliers in the GPS data (such as extremely distant location information), they are removed. The preprocessed data is then passed to the subsequent analysis step.

[1347] Step 3:

[1348] The server analyzes the preprocessed data. A generative AI model (e.g., a deep learning model) is used to predict impassable areas and congestion risks. The input data includes location information, movement history, and traffic condition data preprocessed in the previous step. This data is analyzed using a generative AI model to predict impassable areas and future congestion risks. The output includes location information of impassable areas and congestion risks.

[1349] Step 4:

[1350] The server calculates the optimal route based on the results of the data analysis. It uses route search algorithms such as the A algorithm and Dijkstra algorithm to calculate a route that avoids impassable areas and congestion risks. The input data includes information on impassable areas and congestion risks predicted in the previous step. The server calculates the optimal route based on this data and provides it as output.

[1351] Step 5:

[1352] The server delivers the calculated optimal route information to smartphones and other devices in real time. The input data includes the optimal route information. The server sends this information to the device in real time and notifies the emergency vehicle driver.

[1353] Step 6:

[1354] If an emergency vehicle encounters a new impassable area or traffic jam while traveling, the server collects data again and updates the route. The input data includes newly collected location information and traffic condition data. The server recalculates the route based on this data and notifies the smartphone of the updated optimal route information. The emergency vehicle driver continues traveling according to the new route notified again.

[1355] These steps will enable the rapid and efficient movement of emergency vehicles in the event of a disaster.

[1356] 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.

[1357] A specific embodiment of a system that supports efficient rescue operations by emergency vehicles in the event of a disaster by combining an emotion engine will be described below.

[1358] System Overview

[1359] This system includes a data collection means, data preprocessing means, data analysis means, route optimization means, route information distribution means, real-time route update means, and an emotion engine that recognizes the user's emotions. This not only enables emergency vehicles to reach their destinations quickly, but also reduces the stress of users (such as emergency vehicle drivers).

[1360] Data collection

[1361] The server collects GPS data, traffic sensor data, and weather data from mobile devices in real time. For example, it acquires current location and speed information from multiple mobile devices, and integrates vehicle flow rate data and flow speed data from traffic sensors and weather observation data from meteorological stations.

[1362] Data Preprocessing

[1363] The server preprocesses the collected data, detecting and removing outliers from the collected data, standardizing the formats of GPS data and traffic data, and performing normalization processing. For example, it converts location data obtained from different devices into a common coordinate system and standardizes time information.

[1364] Data Analysis and Prediction

[1365] The server then analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks. For example, it can identify roads and bridges that have become impassable due to floods or earthquakes and predict the risk of future traffic congestion.

[1366] Route Optimization

[1367] The server calculates the optimal route based on the results of data analysis. It uses the A algorithm and Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly.

[1368] Route information distribution

[1369] The server then distributes the calculated optimal route information to the devices of local governments and rescue teams in real time, allowing emergency vehicle drivers to act quickly based on the latest route information.

[1370] Real-time updates

[1371] The server continuously collects real-time data and monitors changes in road closures and congestion risks. If new road closures or congestion occur, the server recalculates the route based on the new data collected and distributes updated optimal route information.

[1372] Recognizing user emotions with an emotion engine

[1373] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions. For example, if an emergency vehicle driver is nervous, the emotion engine will quantify the level of nervousness based on the driver's facial expression and voice data.

[1374] Reassessing your route based on emotions

[1375] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, it recalculates an easier and less stressful route.

[1376] Specific examples

[1377] Example 1: Dispatch of emergency vehicles during floods

[1378] 1. A server collects data from mobile devices and traffic sensors, including data on major bridges being impassable due to flooding.

[1379] 2. The server preprocesses the data, removes outliers, and normalizes the data.

[1380] 3. The server analyzes the data using a generative AI model to identify the locations of impassable bridges.

[1381] 4. The server calculates the optimal route that avoids impassable areas and generates a route that uses the expressway.

[1382] 5. The server distributes optimal route information to local government terminals and emergency vehicle terminals.

[1383] 6. The emotion engine analyzes the voice and facial expressions of emergency vehicle drivers and reevaluates routes to reduce stress if the driver is feeling stressed.

[1384] 7. Emergency vehicles will follow this information to quickly reach the affected area.

[1385] Example 2: Transporting relief supplies after an earthquake

[1386] 1. The server analyzes real-time traffic and weather data, including data on the likelihood of roads becoming impassable around evacuation zones.

[1387] 2. The server removes outliers and normalizes the data.

[1388] 3. The server uses the generated AI model to predict congestion risk and calculate the optimal route.

[1389] 4. The server distributes the calculated route information and displays it on the Self-Defense Forces' terminals.

[1390] 5. An emotion engine assesses the driver's level of tension and stress and adjusts routes as needed.

[1391] 6. The Self-Defense Forces will use this route information to transport relief supplies quickly and efficiently.

[1392] In this way, the system not only supports the rapid action of emergency vehicles in the event of a disaster, but also takes into account the emotions and stress of emergency vehicle drivers, enabling more effective rescue operations.

[1393] The processing flow will be explained below.

[1394] Step 1: Data collection

[1395] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. For example, it obtains GPS data from each mobile device, vehicle flow and speed data from traffic sensors, and the latest weather information from weather data collectors.

[1396] Step 2: Data Preprocessing

[1397] The server preprocesses the collected data. First, it detects and removes outliers, then standardizes the data format and performs normalization. For example, it converts GPS data into a common coordinate system and standardizes time information to improve data accuracy.

[1398] Step 3: Data analysis

[1399] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts impassable areas and congestion risks. For example, it identifies roads that have become impassable due to floods or earthquakes, and time periods and areas where congestion is likely to occur.

[1400] Step 4: Identify impassable areas

[1401] The server analyzes the data and identifies impassable areas, for example, roads and bridges damaged by floods.

[1402] Step 5: Predict congestion risk

[1403] The server uses the results of data analysis to predict future congestion risks. For example, it predicts a sudden increase in traffic flow around evacuation shelters and determines that there is a high possibility of congestion occurring as a result.

[1404] Step 6: Route optimization

[1405] The server calculates the optimal route that avoids identified impassable areas and congestion risks, for example using the A algorithm or Dijkstra algorithm to determine the fastest and safest route for emergency vehicles to reach their destination.

[1406] Step 7: Route Distribution

[1407] The server distributes the generated optimal route information to the terminals of local governments and rescue teams, for example by sending the route information in real time to the navigation systems of emergency vehicles.

[1408] Step 8: Collect emotion data

[1409] The terminal collects the user's voice data, facial expression data, or biometric data. For example, real-time biometric information is collected from a wearable device worn by an emergency vehicle driver.

[1410] Step 9: Sentiment Analysis

[1411] The emotion engine analyzes the collected data and recognizes the user's emotions (level of tension and stress). For example, it quantifies how tense the user is based on the tone of their voice data and changes in their facial expressions.

[1412] Step 10: Reassess your route based on your emotions

[1413] The server takes into account the user's emotional data recognized by the emotion engine and reevaluates the route. For example, if the driver is extremely nervous, it will recalculate a straighter and easier route.

[1414] Step 11: Distributing recalculated route information

[1415] The server then redistributes the recalculated optimal route information to the emergency vehicle's terminal, allowing the driver to head to their destination with less stress based on the latest information.

[1416] In this way, the system can grasp the user's emotional state in real time and provide the optimal route accordingly, helping emergency vehicles reach their destination efficiently and safely.

[1417] Example 2

[1418] 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."

[1419] Conventional disaster response systems, even if capable of collecting information and quickly preprocessing data in real time, do not take into account the influence of driver emotions and stress when operating emergency vehicles. As a result, even if an emergency vehicle selects the optimal route, if the driver is overly nervous or stressed, it may be difficult to operate quickly and safely. Furthermore, even if the route is updated in real time, it may not always be optimal for the driver. A solution to these issues is needed.

[1420] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1421] In this invention, the server includes a data collection means for collecting location information and movement history acquired in real time from multiple mobile objects, a data preprocessing means for preprocessing the collected data, removing outliers, and normalizing the data, a data analysis means for analyzing the preprocessed data and predicting impassable areas and congestion risks using a generative AI model, a route optimization means for calculating an optimal route that avoids the predicted impassable areas and congestion risks, a route information distribution means for distributing the calculated optimal route information to the terminal, a real-time route update means for recalculating the route using recollected data based on the distributed optimal route information, an emotion engine means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotion, and an emotion-based route reevaluation means for reevaluating and recalculating the route based on the recognized user emotion data. This enables emergency vehicles to not only select the optimal route but also operate while taking into account the driver's emotion and stress level.

[1422] The "data collection means" is a means for collecting location information and movement history in real time from multiple mobile objects when a disaster occurs.

[1423] The "data preprocessing means" is a means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data.

[1424] A "generative AI model" is an artificial intelligence model that analyzes preprocessed data and predicts impassable areas and congestion risks.

[1425] The "data analysis means" is a means for analyzing data preprocessed by the data preprocessing means using a generative AI model to predict impassable areas and congestion risks.

[1426] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[1427] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[1428] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[1429] The "emotion engine means" is a means for analyzing the user's voice data, facial expression data, or biometric data and recognizing the user's emotions.

[1430] The "route re-evaluation means based on emotion" is a means for re-evaluating and re-calculating the route based on the emotion data of the user recognized by the emotion engine means.

[1431] This invention relates to a system that supports efficient rescue operations by emergency vehicles when a disaster occurs, and specifically, the system includes data collection, data preprocessing, data analysis, route optimization, route information distribution, real-time route update, and user emotion recognition and route reevaluation based on that emotion. Each element of this system is described in detail below.

[1432] Data collection

[1433] When a disaster occurs, the server collects real-time location information and movement history from multiple mobile devices (e.g., emergency vehicles, personal devices). Specifically, it integrates GPS data from mobile devices, vehicle flow data from traffic sensors, and weather observation data from weather data collection devices. The hardware used for this data collection includes GPS modules, traffic sensors, and weather observation devices.

[1434] Data Preprocessing

[1435] The server preprocesses the data acquired by the data collection means. This preprocessing involves detecting and removing outliers and normalizing data provided in different formats. For example, abnormal values ​​for altitude and position in GPS data are removed. Furthermore, different time formats are unified to standardize the data.

[1436] Data analysis

[1437] The server then analyzes the preprocessed data using a generative AI model. This analysis predicts potential road impassability and congestion risks. Specifically, a deep learning model is trained using past and current traffic data as input to predict future road impassability and congestion. For example, it can identify areas where roads and bridges will be impassable due to floods or earthquakes.

[1438] Route Optimization

[1439] The server calculates the optimal route based on the prediction results from the data analysis method. It uses the A algorithm or Dijkstra algorithm to generate a route that will allow emergency vehicles to reach their destination safely and quickly. For example, it proposes the shortest route that avoids impassable areas.

[1440] Route information distribution

[1441] The server then distributes the calculated optimal route information in real time to the devices of local governments and rescue teams, allowing emergency vehicle drivers to instantly obtain the latest route information and take swift and safe action.

[1442] Real-time updates

[1443] The server continuously collects real-time data and monitors changes in road impassability and congestion risk. If new road impassability or congestion occurs, the server immediately updates the data, recalculates the optimal route, and distributes the latest route information.

[1444] Recognizing user emotions with an emotion engine

[1445] The server or a dedicated emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotion. For example, if an emergency vehicle driver is nervous, the emotion engine can analyze the voice tone and facial expression to quantify the level of nervousness.

[1446] Emotion-based route reassessment

[1447] The server receives the user's emotional data recognized by the emotion engine and reevaluates the route to reduce tension and stress. For example, if the driver is overly nervous, the server recalculates the route to select safer and wider roads, thereby reducing the driver's burden.

[1448] Specific examples

[1449] One example is the dispatch of emergency vehicles during floods. The server collects data from mobile devices and traffic sensors, including data on bridges that are impassable due to flooding. After preprocessing the data and removing outliers, a generative AI model is used to identify impassable areas. Route optimization is performed to generate a route that uses highways and distributes it to the local government's terminal and the emergency vehicle's terminal. In addition, an emotion engine evaluates the driver's level of stress and reevaluates the route if necessary.

[1450] An example prompt for using a generative AI model is:

[1451] "Predict expected road impassability and congestion risk within the next hour based on current traffic and weather data."

[1452] As a result, the system can support the swift and safe operation of emergency vehicles in the event of a disaster, reducing stress and tension for drivers.

[1453] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1454] Program processing flow

[1455] Step 1: Data collection

[1456] The server collects GPS data from mobile devices, data from traffic sensors, and weather data in real time.

[1457] (Input) Location information from mobile devices, flow rate and velocity data from traffic sensors, and observation data from the Meteorological Agency.

[1458] (Output) A consolidated real-time dataset.

[1459] Specifically, the server periodically retrieves information from each data source and stores the data in different formats in a single database.

[1460] Step 2: Data Preprocessing

[1461] The server pre-processes the collected data.

[1462] (Input) Integrated real-time dataset.

[1463] (Output) The normalized dataset with outliers removed.

[1464] Detect and remove outliers in collected data, and standardize the formats of GPS and traffic data, for example by standardizing the coordinate system for location information and standardizing time information.

[1465] Step 3: Data analysis and prediction

[1466] The server analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[1467] (Input) The preprocessed dataset.

[1468] (Output) Predicted impassable areas and congestion risk data.

[1469] Specifically, the server performs analysis based on deep learning models to predict future risks based on past and current traffic conditions.

[1470] Step 4: Route optimization

[1471] The server calculates the optimal route based on the results of data analysis.

[1472] (Input) Predicted impassable areas and congestion risk data.

[1473] (Output) Optimal route information.

[1474] The A algorithm and Dijkstra algorithm are used to calculate the shortest and safest route. Specifically, it searches for a route with the objectives of minimizing time and avoiding risk.

[1475] Step 5: Route information distribution

[1476] The server distributes the calculated optimal route information to the terminals of local governments and rescue teams in real time.

[1477] (Input) Optimal route information.

[1478] (Output) Notification of delivery completion to each device.

[1479] Specifically, the server transmits route information to each terminal via the communication module and records the transmission log.

[1480] Step 6: Real-time updates

[1481] The server continuously collects real-time data and monitors changes in impassable areas and congestion risks.

[1482] (Input) Newly collected real-time data.

[1483] (Output) Updated optimal route information.

[1484] If a new road closure or congestion occurs, the server immediately recalculates the route and delivers the latest route information again.

[1485] Step 7: Recognizing user emotions with the emotion engine

[1486] The emotion engine analyzes the user's voice data, facial expression data, or biometric data to recognize the user's emotions.

[1487] (Input) Voice data, facial expression data, biometric data.

[1488] (Output) User emotion data.

[1489] Specifically, the server or emotion engine uses voice activity detection (VAD) and facial expression recognition algorithms to assess and quantify the user's emotional state.

[1490] Step 8: Emotion-Based Route Reassessment

[1491] The server receives the user's emotion data recognized by the emotion engine and reevaluates the route if necessary.

[1492] (Input) User emotion data.

[1493] (Output) The reevaluated optimal route information.

[1494] For example, if the driver is overly nervous, the server will recalculate the route to select safer, wider roads, and the reevaluated route information will be sent to the device again.

[1495] The above is the specific flow of program processing for this system.

[1496] (Application example 2)

[1497] 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."

[1498] In order for emergency vehicles to carry out rescue operations quickly and safely in the event of a disaster, it is essential to obtain accurate traffic and weather information in real time and provide optimal routes. However, current systems do not reevaluate routes taking into account the driver's emotions and stress, which creates the risk that emergency vehicle drivers will become overly nervous and make incorrect decisions. Therefore, a system is needed that can recognize the driver's emotional state in real time and reevaluate routes based on that information.

[1499] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a data collection means that collects location information and movement histories obtained in real time from multiple mobile objects when a disaster occurs; a data preprocessing means that preprocesses the data collected by the data collection means, removes outliers, and normalizes the data; a data analysis means that analyzes the data preprocessed by the data preprocessing means and predicts impassable areas and congestion risks using a generative AI model; a route optimization means that calculates an optimal route that avoids the impassable areas and congestion risks predicted by the data analysis means; a route information distribution means that distributes optimal route information calculated by the route optimization means to a terminal; a real-time route update means that recalculates a route using re-collected data based on the optimal route information distributed by the route information distribution means; and an emotion engine means that collects user emotion data using the real-time route update means and re-evaluates the route based on the data. This enables fast and safe rescue operations that take into account the emotions and stress of emergency vehicle drivers.

[1500] The "data collection means" is a means for acquiring location information and movement history from multiple mobile objects in real time when a disaster occurs.

[1501] The "data preprocessing means" is a means for removing outliers in the data collected by the data collection means and for normalizing the data.

[1502] "Data analysis means" refers to a means of predicting impassable areas and congestion risks using an AI model generated from preprocessed data.

[1503] The "route optimization means" is a means for calculating an optimal route that avoids impassable areas and congestion risks predicted by the data analysis means.

[1504] The "route information distribution means" is a means for distributing the optimum route information calculated by the route optimization means to the terminal.

[1505] The "real-time route update means" is a means for recalculating a route using data collected again based on the optimum route information distributed by the route information distribution means.

[1506] The "emotion engine means" is a means for collecting user emotion data and re-evaluating the route based on that data.

[1507] A "generative AI model" is an algorithm that uses machine learning technology to learn patterns from large amounts of data and predict impassable areas and congestion risks.

[1508] The "A algorithm" is a type of graph search algorithm used to calculate the shortest route.

[1509] The "Dijkstra algorithm" is an algorithm for finding the shortest path on a graph with non-negative weights.

[1510] "Device" means a computer or mobile device used by an emergency vehicle driver or local government.

[1511] An "impassable area" is an area where vehicles cannot pass due to a disaster or other reason.

[1512] "Congestion risk" indicates the possibility of traffic congestion occurring on a particular road or area.

[1513] The present invention is a system for supporting efficient rescue operations by emergency vehicles when a disaster occurs, and specific embodiments thereof will be described below.

[1514] System Overview

[1515] The system includes a data collection means, a data pre-processing means, a data analysis means, a route optimization means, a route information distribution means, a real-time route update means, and an emotion engine means.

[1516] The server collects GPS data from mobile devices, traffic sensor data, and weather data in real time. A data preprocessing means detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. Furthermore, a data analysis means analyzes the preprocessed data using a generative AI model to predict impassable areas and congestion risks.

[1517] The route optimization means calculates the optimal route using the A algorithm or the Dijkstra algorithm based on the analysis results obtained from the data analysis means. The route information distribution means distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The real-time route update means recalculates the route based on new data and distributes the updated optimal route information. In addition, the emotion engine means collects emotion data from the user (emergency vehicle driver) and reevaluates the route based on that data.

[1518] Hardware and Software

[1519] The system requires hardware such as GPS sensors, traffic sensors, weather data collection devices, and computers installed in autonomous vehicles. The software includes Python, machine learning libraries (e.g., Scikit-learn), Dijkstra's algorithm, A algorithm, generative AI models, and emotion engines. Specific examples of Python libraries include Numpy, Pandas, Scikit-learn, and PyTorch.

[1520] Specific examples

[1521] The server collects GPS data, traffic sensor data, and weather data in real time as emergency vehicles head toward flood-prone areas. The collected data is subjected to a data pre-processing means, which removes outliers and normalizes them. Then, a data analysis means using a generative AI model predicts impassable areas and congestion risks. Next, a route optimization means calculates the optimal route based on the analysis results, and the route information distribution means distributes it to the emergency vehicle's terminal. The driver's emotional state is analyzed in real time by an emotion engine means, and the route is reevaluated as necessary.

[1522] Prompt Sentence Examples

[1523] Suggest the optimal route based on traffic and weather data from the designated emergency vehicle's current location to its destination. Calculate routes to avoid impassable areas or potential congestion. Also, choose a route that minimizes stress for drivers who are under stress.

[1524] This concrete example demonstrates how the system can achieve fast and safe rescue operations while taking into account the emotions and stress of emergency vehicle drivers.

[1525] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1526] Step 1: Data collection

[1527] The server collects data in real time from mobile devices, traffic sensors, and weather data collectors. The inputs are location information, speed information, traffic sensor data, and weather data. The server receives these data and outputs them as an integrated dataset.

[1528] Step 2: Data Preprocessing

[1529] The server detects and removes outliers from the collected data, standardizes the data format, and performs normalization processing. The input is the data collected in step 1, and the output is a preprocessed dataset. The server uses libraries such as Numpy and Pandas for this processing.

[1530] Step 3: Data analysis

[1531] The server uses the preprocessed data to predict road impassability and congestion risk using a generative AI model. The input is the preprocessed dataset, and the output is predicted road impassability and congestion risk information. At this stage, the server performs data analysis using machine learning libraries (e.g., Scikit-learn and PyTorch).

[1532] Step 4: Route optimization

[1533] The server calculates the optimal route based on the results of data analysis using the A algorithm or Dijkstra algorithm. The input is information on predicted impassable areas and congestion risks, and the output is optimal route information. The server runs programs that implement these algorithms.

[1534] Step 5: Route information distribution

[1535] The server distributes the calculated optimal route information to the emergency vehicle's terminal in real time. The input is the optimal route information, and the output is the route information distributed to the terminal. The server distributes the information using a communication protocol.

[1536] Step 6: Real-time route updates

[1537] The server recalculates routes based on newly collected data in real time and distributes updated optimal route information. The input is newly collected data, and the output is recalculated route information. The server performs this process periodically to adapt to the latest traffic conditions.

[1538] Step 7: Collect emotional data

[1539] The server collects emotional data from the user (emergency vehicle driver) through voice and facial expressions. The input is the user's voice data and facial expression data, and the output is analyzed emotional state information. The emotion engine performs this analysis.

[1540] Step 8: Route reevaluation

[1541] The server reevaluates the route if necessary based on the user's emotional state obtained from the emotion engine. The input is the analyzed emotional state information, and the output is the reevaluated route information. The server recalculates a less stressful route according to the emotion engine's results.

[1542] In this way, data is collected, processed, and analyzed at each processing step of the server, terminal, and user, and optimal route information is constantly provided. In particular, reevaluating the route according to the driver's emotional state enables quick and safe rescue operations.

[1543] 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.

[1544] 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.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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).

[1550] 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.

[1551] 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."

[1552] 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.

[1553] 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).

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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.

[1562] 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.

[1563] 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.

[1564] The following is further disclosed regarding the above embodiment.

[1565] (Claim 1)

[1566] a data collection means for collecting location information and movement history obtained in real time from a plurality of mobile objects when a disaster occurs;

[1567] a data preprocessing means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data;

[1568] a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable locations and congestion risks using a generation AI model;

[1569] a route optimization means for calculating an optimal route that avoids impassable locations and congestion risks predicted by the data analysis means;

[1570] a route information distribution means for distributing the optimum route information calculated by the route optimization means to a terminal;

[1571] a real-time route update means for recalculating a route using data recollected based on the optimum route information distributed by the route information distribution means;

[1572] A system including:

[1573] (Claim 2)

[1574] 2. The system of claim 1, wherein the route optimization means calculates the route using the A algorithm or the Dijkstra algorithm.

[1575] (Claim 3)

[1576] 2. The system of claim 1, wherein the data collection means collects data from mobile devices, traffic sensors, and meteorological data collection devices.

[1577] "Example 1"

[1578] (Claim 1)

[1579] a data collection means for collecting location information and movement history obtained in real time from a plurality of mobile objects when a disaster occurs;

[1580] a data preprocessing means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data;

[1581] a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable locations and congestion risks using a generation AI model;

[1582] a route optimization means for calculating an optimal route that avoids impassable locations and congestion risks predicted by the data analysis means;

[1583] a route information distribution means for distributing the optimum route information calculated by the route optimization means to a terminal;

[1584] a real-time route update means for recalculating a route using data recollected based on the optimum route information distributed by the route information distribution means;

[1585] A means for distributing recalculated routes to each device in real time as new data is collected; and

[1586] A system including:

[1587] (Claim 2)

[1588] 2. The system of claim 1, wherein the route optimization means calculates the route using the A algorithm or the Dijkstra algorithm.

[1589] (Claim 3)

[1590] 2. The system of claim 1, wherein the data collection means collects data from mobile devices, traffic sensors, and meteorological data collection devices.

[1591] "Application Example 1"

[1592] (Claim 1)

[1593] a data collection means for collecting location information and movement history obtained in real time from a plurality of mobile objects when a disaster occurs;

[1594] a data preprocessing means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data;

[1595] a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable locations and congestion risks using a generation AI model;

[1596] a route optimization means for calculating an optimal route that avoids impassable locations and congestion risks predicted by the data analysis means;

[1597] a route information distribution means for distributing the optimum route information calculated by the route optimization means to a terminal;

[1598] a real-time route update means for recalculating a route using data recollected based on the optimum route information distributed by the route information distribution means;

[1599] a means for notifying a smartphone of route information recalculated by the real-time route update means;

[1600] A system including:

[1601] (Claim 2)

[1602] 2. The system of claim 1, wherein the route optimization means calculates the route using the A algorithm or the Dijkstra algorithm.

[1603] (Claim 3)

[1604] 2. The system of claim 1, wherein the data collection means collects data from mobile devices, traffic sensors, and meteorological data collection devices.

[1605] (Claim 4)

[1606] The system described in claim 1 is characterized in that it predicts impassable areas and congestion risks by inputting prompt sentences into the generative AI model.

[1607] "Example 2: Combining Emotion Engines"

[1608] (Claim 1)

[1609] a data collection means for collecting location information and movement history obtained in real time from a plurality of mobile objects when a disaster occurs;

[1610] a data preprocessing means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data;

[1611] a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable locations and congestion risks using a generation AI model;

[1612] a route optimization means for calculating an optimal route that avoids impassable locations and congestion risks predicted by the data analysis means;

[1613] a route information distribution means for distributing the optimum route information calculated by the route optimization means to a terminal;

[1614] a real-time route update means for recalculating a route using data recollected based on the optimum route information distributed by the route information distribution means;

[1615] emotion engine means for analyzing voice data, facial expression data, or biometric data of a user and recognizing the emotion of the user;

[1616] emotion-based route re-evaluation means for re-evaluating and re-calculating a route based on the emotion data of the user recognized by the emotion engine means;

[1617] A system including:

[1618] (Claim 2)

[1619] 2. The system of claim 1, wherein the route optimization means calculates the route using the A algorithm or the Dijkstra algorithm.

[1620] (Claim 3)

[1621] 2. The system according to claim 1, wherein the data collection means collects data from a mobile terminal, a traffic information sensor, and a weather data collection device.

[1622] "Application example 2 when combining emotion engines"

[1623] (Claim 1)

[1624] a data collection means for collecting location information and movement history obtained in real time from a plurality of mobile objects when a disaster occurs;

[1625] a data preprocessing means for preprocessing the data collected by the data collection means, removing outliers, and nor...

Claims

1. a data collection means for collecting location information and movement history obtained in real time from a plurality of mobile objects when a disaster occurs; a data preprocessing means for preprocessing the data collected by the data collection means, removing outliers, and normalizing the data; a data analysis means for analyzing the data preprocessed by the data preprocessing means and predicting impassable locations and congestion risks using a generation AI model; a route optimization means for calculating an optimal route that avoids impassable locations and congestion risks predicted by the data analysis means; a route information distribution means for distributing the optimum route information calculated by the route optimization means to a terminal; a real-time route update means for recalculating a route using data recollected based on the optimum route information distributed by the route information distribution means; A system including:

2. 2. The system of claim 1, wherein the route optimization means calculates the route using the A algorithm or the Dijkstra algorithm.

3. 2. The system of claim 1, wherein the data collection means collects data from mobile devices, traffic sensors, and meteorological data collection devices.

Images