system

Abstract

Provide a system. [Solution] means for collecting road condition data from a source; means for pre-processing the collected data; a means for assessing the reliability of the preprocessed data; a means for determining passable roads based on the reliability-evaluated data; means for calculating an optimal route based on the determined passable road information; means for providing the calculated optimal route information to the terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, natural disasters have become more frequent, and when disasters occur, road conditions often deteriorate, making recovery efforts extremely difficult. In particular, during disasters such as large-scale earthquakes and typhoons, road closures and congestion can hinder the smooth transport of relief and supplies. Under these circumstances, there is a need for fast and reliable information on passable roads. However, current systems rely on a wide variety of information sources, making it difficult to evaluate reliability and present optimal routes. Therefore, a system is needed that can evaluate the reliability of data collected from multiple information sources and provide optimal routes. [Means for solving the problem]

[0005] The present invention provides a system that collects road condition data from multiple sources, preprocesses the data, evaluates its reliability, and then presents passable roads and optimal routes. Specifically, the system includes means for collecting road condition data from sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, and means for providing the calculated optimal route information to a terminal. This system can quickly provide reliable road information even during disasters, facilitating recovery efforts and the evacuation of disaster victims.

[0006] "Sources of information" are public institutions and private sites that provide road condition data, as well as data suppliers such as telecommunications companies.

[0007] "Road condition data" refers to data relating to the availability of roads, such as road opening status, traffic congestion information, and road closure information.

[0008] "Gathering means" refers to the technology and interfaces for obtaining road condition data from the information source.

[0009] "Preprocessing" is the process of data cleansing, converting collected data into a common format and removing incomplete or incorrect data.

[0010] "Means for assessing reliability" refers to algorithms and scoring methods for assessing the accuracy and reliability of collected road condition data.

[0011] The "means for determining passable roads" is a process for determining which roads are currently passable based on highly reliable road condition data.

[0012] The "means for calculating the optimal route" is an algorithm for calculating the shortest or most efficient route between specified points based on passable road information.

[0013] "Means for providing to terminal" refers to the communications technology and interface for delivering the calculated optimal route information to the user's device.

[0014] "Terminal" means a device on which a User receives and displays route information, including a smartphone, tablet, navigation system, etc. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The system of this invention is an advanced information collection and analysis system for presenting passable roads in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates the reliability of the data, and then provides optimal route information.

[0037] Program processing explanation

[0038] 1. Data Collection

[0039] server

[0040] The server sends requests to API endpoints of public agencies to obtain the latest road condition data, scrapes private traffic information providers to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[0041] 2. Data Preprocessing

[0042] server

[0043] The server converts the collected data from various sources into a common format, for example, unifying the acquired data into JSON format, and also filters out incomplete, incorrect, and duplicate data to generate a clean dataset.

[0044] 3. Reliability evaluation

[0045] server

[0046] The server evaluates the reliability of the preprocessed data by scoring each information source based on its past history and frequency of information updates. For example, a source with a high level of accuracy in the past is given a high reliability score.

[0047] 4. Determining whether a road is passable

[0048] server

[0049] The server determines which roads are passable and which are not, based on reliable data, using machine learning models, taking into account, for example, past traffic conditions and current traffic congestion information.

[0050] 5. Optimal Route Calculation

[0051] server

[0052] The server then calculates the optimal route based on the results of the assessment. This route calculation takes into account the shortest route from the current location to the destination, evacuation routes, and logistics routes. It also incorporates real-time traffic congestion information.

[0053] 6. Information provision

[0054] server

[0055] The server generates the calculated optimal route information in a user-friendly format and provides it to the device, for example, by distributing the route information through an API.

[0056] 7. User Presentation

[0057] Terminal

[0058] The user's smartphone, navigation system, or other device receives the route information sent from the server and visually displays it, allowing the user to check passable routes on a map.

[0059] Specific examples

[0060] Example 1: Moving to a shelter

[0061] server

[0062] The server collects road condition data from various sources immediately after a disaster occurs and generates clean data.

[0063] Reliability assessment is performed based on clean data to determine whether roads are passable.

[0064] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated.

[0065] The calculation results are sent to the user's device via API.

[0066] Terminal

[0067] The device reflects the received route information in the map app and displays to the user the "passable route from the current location to the nearest evacuation shelter."

[0068] User

[0069] Users can follow the route displayed on their smartphone to safely reach an evacuation shelter.

[0070] Example 2: Transporting goods

[0071] server

[0072] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[0073] Logistics routes are determined based on highly reliable data.

[0074] Calculate the optimal route to your destination while taking traffic congestion information into account.

[0075] The calculated route information is provided to the logistics company's terminal via API.

[0076] Terminal

[0077] The logistics company's terminal displays the received route information on a navigation system and provides instructions to the driver.

[0078] User (logistics company)

[0079] Drivers can follow the route displayed on the terminal to transport goods quickly and safely to their destination.

[0080] In this way, the system of the present invention quickly provides highly reliable information on passable roads in the event of a disaster, and is of great help in smoothly carrying out restoration and evacuation activities.

[0081] The processing flow will be explained below.

[0082] Step 1: Data collection

[0083] server

[0084] The server sends an HTTP GET request to the public institution's API to obtain the latest road condition data, and performs authentication using the API key.

[0085] Scrape pages from private traffic information providers and extract real-time road condition data.

[0086] Traffic information data provided by telecommunications companies is obtained through a dedicated API.

[0087] Step 2: Data Preprocessing

[0088] server

[0089] The server converts the collected data into a common JSON format. For example, it converts XML data obtained from a public institution's API into JSON.

[0090] Filter incomplete and duplicate data from collected data to generate a clean dataset.

[0091] The converted data is stored in a temporary database.

[0092] Step 3: Reliability assessment

[0093] server

[0094] The server evaluates the reliability of the preprocessed data, scoring each information source based on its past history and frequency of updates.

[0095] The reliability score is calculated using a specific algorithm (e.g., a points system based on past accuracy and update frequency).

[0096] Unreliable data is filtered out and only reliable data is passed on to the next step.

[0097] Step 4: Determine whether roads are passable

[0098] server

[0099] The server runs machine learning models using reliable data to determine which roads are passable and which are not.

[0100] The machine learning model takes into account past traffic history and current traffic congestion data to predict whether a route can be passed.

[0101] The judgment results are stored in a database.

[0102] Step 5: Calculate the optimal route

[0103] server

[0104] The server runs an algorithm to calculate the optimal route based on the information about passable roads, such as Dijkstra's algorithm or A-search algorithm.

[0105] By incorporating real-time traffic congestion information, the optimal route is calculated to avoid unnecessary delays.

[0106] The optimal route information will be stored in a database and made accessible via API.

[0107] Step 6: Provide information

[0108] server

[0109] The server generates the calculated optimal route information in a user-friendly format and provides it to the device via an API.

[0110] The API processes route information requests and responds in JSON format.

[0111] The response includes roads that are passable, roads to avoid, and recommended routes.

[0112] Step 7: Display information

[0113] Terminal

[0114] The terminal analyzes the route information received from the server and displays it on the user interface.

[0115] The route is reflected in the map application, visually indicating navigable roads along the route and recommended routes.

[0116] If necessary, the voice navigation function will provide route guidance.

[0117] Step 8: User interaction

[0118] User

[0119] The user checks the passable routes displayed on the terminal and selects a route if necessary.

[0120] The user follows the displayed route to their destination, for example, to a safe evacuation shelter in an emergency.

[0121] Example 1

[0122] 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."

[0123] During disasters, it has been difficult to quickly and accurately grasp real-time road conditions and provide optimal passable routes. With conventional systems, data from different sources is fragmented and inconsistent, making it difficult to obtain reliable information. Furthermore, data preprocessing and reliability assessment are insufficient, leading to inaccurate determinations of passable roads. Furthermore, optimal route calculations do not adequately reflect real-time conditions, making it impossible to provide practical information to users.

[0124] 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.

[0125] In this invention, the server includes means for collecting road condition data from information sources, means for converting the collected data into a common format and cleaning it, means for evaluating the reliability of the preprocessed data, means for determining passable roads using a machine learning model based on the reliability-evaluated data, means for calculating an optimal route from the current location to the destination based on the determined passable road information, and means for providing the calculated optimal route information to the terminal. This allows for the rapid provision of reliable passable road information even during a disaster, enabling users to reach their destination safely and efficiently.

[0126] "Source" refers to the organization or institution that provides road condition data, or the API or website from which that data can be obtained.

[0127] "Road condition data" refers to real-time information related to roads, such as road passability, traffic congestion information, accident information, and road closures due to disasters.

[0128] "Collection Method" refers to the method or process used to obtain road condition data from a source, such as sending an API request or web scraping.

[0129] "Preprocessing" refers to the process of converting collected data into a common format and removing erroneous or incomplete data.

[0130] "Credibility assessment tools" refer to methods and processes for assessing the reliability of collected data, including, for example, scoring each source based on its past history and update frequency.

[0131] A "machine learning model" is an algorithm or system used by a computer to learn from large amounts of data and perform a specific task (in this case, determining which roads are passable).

[0132] "Means for determining passable roads" refers to a method or process for determining which roads are passable using reliability-assessed data.

[0133] "Optimal route calculation means" refers to a method or process for calculating the optimal route from the current location to the destination based on determined passable road information.

[0134] "Providing means" refers to the method or process for transmitting the calculated optimal route information to the terminal used by the user.

[0135] This invention is a system for providing passable road information quickly and accurately in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates its reliability, and then provides optimal route information.

[0136] Hardware and Software

[0137] server

[0138] The server collects road condition data from multiple sources. Specifically, it sends HTTP requests to API endpoints of public agencies to obtain the latest data. It also scrapes traffic information sites using the Python library BeautifulSoup to collect real-time data. Traffic information data from telecommunications companies is also obtained via FTP and saved in local storage.

[0139] The server loads the collected data into a Pandas DataFrame and converts it into a unified format. Next, it performs data cleaning, filtering out incomplete and duplicate data, and generating a clean dataset. This data cleaning process is performed using Python's Pandas and NumPy.

[0140] For reliability evaluation, the scikit-learn library is used to perform scoring based on past history and information update frequency. Based on the evaluation results, a machine learning model (using, for example, TENSORFLOW (registered trademark) or PyTorch) is used to determine which roads are passable.

[0141] To calculate the optimal route, a road network graph is constructed and the optimal route from the current location to the destination is calculated using the Dijkstra algorithm and the A algorithm. The calculation results are saved in JSON format and provided to the terminal via an API. The API is implemented using Flask and FastAPI.

[0142] Terminal

[0143] The terminals include smartphones and navigation systems. These terminals are equipped with software to receive route information sent from the server and display it on a map application. For example, the terminals display the route on a map using Google (registered trademark) Maps or Mapbox SDK. The terminals provide a user-friendly interface, allowing users to easily check the route information.

[0144] User

[0145] Users use this system to reach their destination safely and efficiently in the event of a disaster. They check real-time passable route information via their smartphone or navigation system and follow the instructions.

[0146] Specific examples

[0147] Example 1: Moving to a shelter

[0148] Immediately after a disaster occurs, the server collects road condition data from various sources, cleans the data, and then performs reliability evaluation to determine which roads are passable.

[0149] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated and sent to the user's device via an API.

[0150] The user follows the route displayed on their smartphone to reach the evacuation shelter. For example, if the user types "Tell me the best route to get to the evacuation shelter," the server will instantly calculate and provide the best route.

[0151] Example 2: Transporting goods

[0152] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies, and then determines logistics routes based on highly reliable data.

[0153] Taking traffic congestion information into account, the system calculates the optimal route to the destination and provides the results to the logistics company's terminal via an API.

[0154] Logistics companies transport goods quickly and safely by following the route displayed on the terminal. For example, when a driver types in "What is the best route to my destination?", the server quickly provides the optimal route.

[0155] In this way, the system of the present invention provides highly reliable information about passable roads in the event of a disaster, enabling users to reach their destination safely and efficiently.

[0156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0157] Step 1:

[0158] Data collection

[0159] server

[0160] The server collects road condition data from information sources. Specifically, it sends HTTP requests to public agency API endpoints to obtain the latest data. It also accesses private traffic information providers' websites using a scraping tool to extract text data. It also downloads traffic information data provided by telecommunications companies via FTP and stores it in local storage.

[0161] Input: Public API URL, private site URL, telecommunications company data file

[0162] Output: Raw data (JSON format, text data, binary data)

[0163] Specific behavior:

[0164] The server periodically sends API requests and stores the JSON data received as HTTP responses locally.

[0165] Use a tool such as BeautifulSoup to scrape the HTML page and extract the required text information.

[0166] Establish an FTP connection and download the traffic information data file.

[0167] Step 2:

[0168] Data Preprocessing

[0169] server

[0170] The server converts the collected data into a common format and cleans it. Using the Python Pandas library, the data obtained from each source is loaded into a DataFrame and unified into a common column structure. Next, the data is cleaned to remove incomplete and duplicate data.

[0171] Input: Raw data (JSON format, text data, binary data)

[0172] Output: Preprocessed common format data (DataFrame or JSON format)

[0173] Specific behavior:

[0174] Read the data using Pandas' read_json() or read_csv() functions.

[0175] Perform data cleaning using the dropna() and drop_duplicates() functions.

[0176] Save the clean data using the to_json() method.

[0177] Step 3:

[0178] Reliability evaluation

[0179] server

[0180] The server scores the preprocessed data to evaluate its reliability. It calculates a score for each information source based on its past history and update frequency, and prioritizes scores for highly reliable data. The server uses the scikit-learn library to evaluate reliability.

[0181] Input: Preprocessed common format data (DataFrame or JSON format)

[0182] Output: Data with confidence scores (DataFrame or JSON format)

[0183] Specific behavior:

[0184] The past data history and update frequency of each source is obtained from the database.

[0185] Calculate reliability scores using scikit-learn's KNeighborsClassifier or a custom scoring function.

[0186] Add and store a confidence score to the data.

[0187] Step 4:

[0188] Determining passable roads

[0189] server

[0190] The server uses the reliability-assessed data to determine whether roads are passable using a machine learning model. Specifically, it loads a model trained with TensorFlow or PyTorch and uses the data as input to determine whether a road is passable.

[0191] Input: Data with confidence scores (DataFrame or JSON format)

[0192] Output: Road data (DataFrame or JSON format) for which passability has been determined

[0193] Specific behavior:

[0194] Load a trained machine learning model.

[0195] Input data into the model and obtain labels indicating whether the road is passable or not.

[0196] The judgment result is added to the data and saved.

[0197] Step 5:

[0198] Optimal route calculation

[0199] server

[0200] The server then calculates the optimal route from the current location to the destination based on the results of the assessment, using the Dijkstra algorithm and the A algorithm, and taking real-time traffic congestion information into account.

[0201] Input: Road data (DataFrame or JSON format) for which passability is determined

[0202] Output: Optimal route information (JSON format)

[0203] Specific behavior:

[0204] A road network graph is constructed, and passability and traffic condition costs are set for each edge.

[0205] Finding the shortest path using the NetworkX library.

[0206] Save the optimal route information in JSON format.

[0207] Step 6:

[0208] Providing information

[0209] server

[0210] The server provides the calculated optimal route information through an API, and returns the latest route information in JSON format in response to a user request.

[0211] Input: User request

[0212] Output: Optimal route information (JSON format)

[0213] Specific behavior:

[0214] Build API endpoints using Flask and FastAPI.

[0215] Returns pre-calculated route information based on user requests.

[0216] Step 7:

[0217] What the user sees

[0218] Terminal

[0219] The device receives the route information sent from the server and displays it in the map app. It plots the route on a map using Google Maps or Mapbox SDK, providing a visual representation to the user.

[0220] Input: Optimal route information received from the server (JSON format)

[0221] Output: Route information plotted on a map

[0222] Specific behavior:

[0223] The terminal parses the received JSON data.

[0224] Plot your data on a map using the Google Maps or Mapbox SDK.

[0225] Users can check the route on the map and travel safely.

[0226] (Application example 1)

[0227] 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."

[0228] The present invention solves the problem of the difficulty of providing quick and accurate information on passable roads during disasters. Furthermore, there is a need for a system that enables autonomous vehicles to travel safely and efficiently based on that information.

[0229] 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.

[0230] In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for providing the calculated optimal route information to the autonomously driven vehicle, and means for controlling the vehicle based on the route information provided to the autonomously driven vehicle. This enables the autonomously driven vehicle to select and travel a safe and optimal route even during a disaster.

[0231] "Sources" refer to the origins of various publicly available data, including APIs of public institutions and private sites.

[0232] "Road condition data" is data that indicates whether roads are passable, traffic congestion information, traffic accident information, weather conditions, and the like.

[0233] "Preprocessing" refers to the process of standardizing collected raw data into a certain format and removing incomplete or incorrect data to generate a clean dataset.

[0234] "Credibility assessment" refers to the process of assessing the accuracy and reliability of data based on the source's past history and frequency of data updates.

[0235] "Passable roads" refer to roads that are determined to be passable even in the event of a disaster based on the results of data analysis.

[0236] The "optimal route" refers to the shortest and safest route from the current location to the destination, calculated by the program.

[0237] "Autonomous vehicle" refers to a vehicle that can be operated and driven by its own system.

[0238] "Route information" is data about the calculated optimal travel route, and is used in maps and navigation systems.

[0239] "Control means" refers to the function of controlling the movement of the vehicle based on the route information provided.

[0240] This invention is a system for autonomous vehicles to safely and quickly select and move along optimal routes during disasters. The system collects road condition data from information sources, preprocesses it, evaluates its reliability, determines which roads are passable, calculates the optimal route, and provides this information to autonomous vehicles to reflect in their control.

[0241] Hardware and software used

[0242] Hardware:

[0243] Embedded systems for autonomous vehicles (navigation systems, communication modules, etc.)

[0244] software:

[0245] Python

[0246] requests library (for API requests)

[0247] pandas library (for data preprocessing)

[0248] scikit-learn library (for machine learning modeling)

[0249] geopy library (for geographic information processing)

[0250] Details of data processing and calculation

[0251] The server collects road condition data from public APIs and private websites. It then standardizes the collected data into JSON format and removes incomplete or incorrect data to generate a clean dataset. Based on this dataset, the reliability of the source is evaluated using its past history and the frequency of data updates.

[0252] Using the evaluated data, a machine learning model (e.g., random forest) is used to determine whether a road is passable, taking into account historical traffic information and weather conditions. Next, the optimal route from the current location to the destination is calculated based on the passable road information.

[0253] The calculated optimal route information is provided to the autonomous vehicle, which then controls the vehicle based on that route information, enabling safe and rapid movement even in the event of a disaster.

[0254] Specific examples

[0255] Moving to a shelter:

[0256] Immediately after a disaster occurs, the server collects the latest road condition data from various sources, preprocesses it, and evaluates its reliability. It then determines which roads are passable and calculates the optimal route to the nearest evacuation shelter. This route information is provided to the autonomous vehicle, which then travels safely to the shelter based on the instructions.

[0257] Transport of goods:

[0258] The server collects real-time data and generates clean data, then performs reliability assessment and provides passable road information for logistics companies. After route calculation, it provides the optimal route information to autonomous vehicles, which then transport goods to their destinations quickly and safely.

[0259] Example prompts to input to the generative AI model

[0260] AI Assistant, please calculate the optimal route for safe and fast autonomous driving to an evacuation shelter based on the current damage situation caused by the earthquake, and update this information in the vehicle system. The current location is Tokyo Station, and the destination is an evacuation shelter within Tokyo.

[0261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0262] Step 1:

[0263] The server collects road condition data from sources. Specifically, it sends requests to API endpoints of public agencies to obtain the latest road condition data. It also scrapes private traffic information providers to collect real-time road information. It also obtains traffic information data provided by telecommunications companies. The input is the API request or scraping, and the output is the collected road condition data.

[0264] Step 2:

[0265] The server preprocesses the collected data. Specifically, it converts data from each source into a common JSON format and filters out incomplete, incorrect, and duplicate data to generate a clean dataset. The input is the raw collected data, and the output is the clean dataset.

[0266] Step 3:

[0267] The server evaluates the reliability of the preprocessed data. Specifically, it scores each information source based on its past history and the frequency of information updates. For example, it assigns a high reliability score to information sources that have been highly accurate in the past. The input is a clean dataset, and the output is reliability-evaluated data.

[0268] Step 4:

[0269] The server determines whether a road is passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (such as random forest) to determine whether the road is passable. This determination also takes into account past and current traffic information and weather conditions. The input is reliability-evaluated data, and the output is road information determined to be passable.

[0270] Step 5:

[0271] The server calculates the optimal route based on passable road information. Specifically, it calculates the shortest route from the current location to the destination, as well as evacuation routes and logistics routes. It also incorporates real-time traffic congestion information. The input is passable road information and the coordinates of the current location and destination, and the output is the optimal route information.

[0272] Step 6:

[0273] The server provides the calculated optimal route information to the autonomous vehicle. Specifically, it sends the route information to the autonomous vehicle's embedded system through an API. The input is the optimal route information, and the output is the route information received by the autonomous vehicle.

[0274] Step 7:

[0275] The embedded system of an autonomous vehicle reflects the provided route information and controls the vehicle. Specifically, the route is displayed on the navigation system, and the autonomous driving system operates according to that route. The input is the route information provided by the server, and the output is the vehicle's movement to reach the destination safely and quickly.

[0276] 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.

[0277] The system of this invention is an advanced information collection and analysis system that presents passable roads in the event of a disaster, recognizes the user's emotions, and adjusts navigation accordingly. This system collects road condition data from sources, preprocesses them, and evaluates their reliability before presenting passable roads and optimal routes. Furthermore, it is equipped with an emotion engine that realizes optimal navigation based on the user's emotions.

[0278] Program processing explanation

[0279] 1. Data Collection

[0280] server

[0281] The server obtains the latest road condition data from public agency APIs, scrapes private traffic information websites to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[0282] 2. Data Preprocessing

[0283] server

[0284] The server converts the collected data into a common JSON format and filters out incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[0285] 3. Reliability evaluation

[0286] server

[0287] The server evaluates the reliability of each information source based on the preprocessed data. It scores the information using a specific algorithm, taking into account past history and frequency of information updates. Unreliable data is filtered out, and only reliable data is allowed to proceed to the next step.

[0288] 4. Determining whether a road is passable

[0289] server

[0290] The server runs machine learning models using reliable data to determine which roads are passable and which are not, and the results are stored in a database.

[0291] 5. Optimal Route Calculation

[0292] server

[0293] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm, and incorporates real-time traffic information. The optimal route information is stored in a database and can be accessed via API.

[0294] 6. Emotion recognition

[0295] Terminal

[0296] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses the user's voice input and facial recognition to identify emotions. For example, if the user is anxious or nervous, that information is reflected in the navigation.

[0297] 7. Route Adjustment

[0298] server

[0299] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method, for example, proposing a route that avoids roads that are likely to cause stress to the user.

[0300] 8. Information provision

[0301] server

[0302] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[0303] 9. Information display

[0304] Terminal

[0305] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[0306] Specific examples

[0307] Example 1: Moving to a shelter

[0308] server

[0309] Immediately after a disaster occurs, the server collects road condition data from each source and generates clean data.

[0310] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[0311] In addition, it receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[0312] The calculation results are sent to the user's device via API.

[0313] Terminal

[0314] The device reflects the received route information in the map app and displays the user a passable route from their current location to the nearest evacuation shelter. Using information from the emotion engine, the device provides stable voice guidance.

[0315] User

[0316] Users can follow the route displayed on their smartphone and move safely to a shelter. With the support of the emotion engine, users can move with peace of mind.

[0317] Example 2: Transporting goods

[0318] server

[0319] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[0320] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[0321] It receives information from the emotion engine and provides routes that reduce driver stress.

[0322] The calculated route information is provided to the logistics company's terminal via API.

[0323] Terminal

[0324] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[0325] User (logistics company)

[0326] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[0327] In this way, the system of the present invention provides highly reliable traffic information during disasters, recognizes the user's emotions, and provides optimal navigation, thereby greatly assisting in smoothly carrying out recovery and evacuation activities.

[0328] The processing flow will be explained below.

[0329] Step 1: Data collection

[0330] server

[0331] The server sends an HTTP GET request to a public agency's API to retrieve the latest road condition data, for example, using the https: / / api.trafficinfo.gov endpoint.

[0332] Scrape private traffic information websites and extract road condition data using HTML analysis tools, such as libraries like BeautifulSoup.

[0333] Traffic information data provided by telecommunications companies is acquired through a dedicated API, and the acquired data is updated in real time.

[0334] Step 2: Data Preprocessing

[0335] server

[0336] The server converts the collected data into a common JSON format, for example using the xmltodict library to convert data in XML format into JSON.

[0337] Regular expressions are used to shape the collected data, filtering out incomplete and duplicate data and generating a clean dataset.

[0338] The transformed data is stored as a clean dataset in a temporary database.

[0339] Step 3: Reliability assessment

[0340] server

[0341] The server considers the past reliability history and update frequency of each source to assess the reliability of the pre-processed data, using an algorithm (e.g., weighted average) to assign a reliability score to each source.

[0342] Data with low confidence scores are filtered out and only data with high scores proceeds to the next step.

[0343] The evaluation results are stored in a database.

[0344] Step 4: Determine whether roads are passable

[0345] server

[0346] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, for example, using a random forest model.

[0347] Input data includes traffic history information and current congestion data.

[0348] The judgment results are stored in a database.

[0349] Step 5: Calculate the optimal route

[0350] server

[0351] The server executes an algorithm (for example, Dijkstra's algorithm or A-search algorithm) that calculates the optimal route between specified points based on passable road information.

[0352] By incorporating real-time traffic congestion information, the shortest route is calculated to avoid unnecessary delays.

[0353] The optimal route information will be stored in a database and made accessible via API.

[0354] Step 6: Emotion Recognition

[0355] Terminal

[0356] The device uses the user's voice input and camera to provide data to the emotion engine, for example, processing audio data from the user speaking into a microphone and facial expression data captured by a camera.

[0357] The emotion engine uses voice recognition software and facial recognition algorithms to identify the user's emotions (e.g., anxiety, relief, irritation).

[0358] Step 7: Route Adjustment

[0359] server

[0360] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. For example, for a user who is prone to anxiety, it suggests a route that eliminates roads that should be avoided.

[0361] The recalculated route information is stored in a database and provided to the device via an API.

[0362] Step 8: Provide information

[0363] server

[0364] The server generates an optimal route that reflects the emotion information in a user-friendly format and provides it to the device via an API, for example, by returning the route information in JSON format.

[0365] Step 9: Display Information

[0366] Terminal

[0367] The device analyzes the route information received from the server and displays it in a map application, with a user interface that visually indicates passable roads and the optimal route.

[0368] The device uses a voice navigation function to provide the user with appropriate route guidance, which is based on the user's emotions.

[0369] Step 10: User interaction

[0370] User

[0371] The user checks the passable routes displayed on the terminal and selects a route as necessary.

[0372] Users can follow the displayed route to their destination safely and comfortably. With the support of the emotion engine, they can travel with peace of mind.

[0373] Example 2

[0374] 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."

[0375] Conventional navigation systems are sometimes unable to accurately grasp real-time road conditions during disasters, limiting their ability to suggest optimal routes. Furthermore, they are unable to provide navigation that takes into account the user's emotional state, and do not take into consideration routes that are likely to cause stress to the user. It is necessary to solve these problems and realize fast and safe evacuation and transportation of supplies during disasters.

[0376] 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.

[0377] In this invention, the server includes means for collecting road condition data from an information source, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for recalculating the optimal route based on the recognized user emotion information, and means for providing the calculated optimal route information to the terminal. This makes it possible to propose an optimal route taking the user's emotional state into consideration, thereby enabling quick and safe evacuation and transportation of supplies in the event of a disaster.

[0378] "Information sources" are data sources that are the basis for collecting data, such as public agencies, private companies, and communication companies that provide road condition data.

[0379] "Road condition data" is information showing the latest road conditions, such as whether the road is passable, traffic congestion information, traffic accidents, and damage caused by disasters.

[0380] "Preprocessing" is the process of converting collected data into a common format and filtering out incomplete or duplicate data.

[0381] "Reliability assessment" is a method for assessing the accuracy and reliability of collected data and ensuring data quality. This assessment includes past history and frequency of information updates.

[0382] A "passable road" is one that is clear of obstacles and safe for vehicles and pedestrians to travel on. This determination is made using machine learning models.

[0383] The "optimal route" refers to the most efficient and safest route to the user's destination, calculated based on real-time road conditions and the user's emotional state.

[0384] "User emotion" refers to the psychological state, such as anxiety, tension, or stress, felt by the user, as identified by the user's voice input or facial recognition.

[0385] "Emotion recognition" is the process of identifying a user's emotions from their facial expressions and voice, and reflecting this in navigation.

[0386] "Recalculation" is a process of recalculating existing route calculation results based on the recognized user's emotions and proposing a route that is more suitable for the user.

[0387] A "terminal" is a device used by a user (such as a smartphone or tablet) that receives and displays optimal route information.

[0388] The system of the present invention is an advanced information collection and analysis system that collects road condition data from various information sources, recognizes the emotional state of the user, and provides optimal navigation. Specific embodiments are described below.

[0389] Data collection

[0390] server

[0391] The server obtains the latest road condition data through public agency APIs. It also accesses private traffic information providers and collects real-time road information using web scraping technology. This process uses Python libraries such as BeautifulSoup and Selenium. It also obtains traffic information data from telecommunications companies' data platforms. This data is then stored in a temporary database.

[0392] Data Preprocessing

[0393] server

[0394] The server converts the collected data into a common JSON format, then uses the Python pandas library to filter incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[0395] Reliability evaluation

[0396] server

[0397] The server evaluates the reliability of each information source based on the preprocessed data. The evaluation takes into account past data history and information update frequency, and uses algorithms such as the weighted average method. Unreliable data is filtered out, and only reliable data is advanced to the next step.

[0398] Determining passable roads

[0399] server

[0400] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, using libraries such as TensorFlow and PyTorch. The results are then stored in a database.

[0401] Optimal route calculation

[0402] server

[0403] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm. It also takes into account real-time traffic congestion information. The optimal route information is stored in a database and can be accessed via API.

[0404] emotion recognition

[0405] Terminal

[0406] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine identifies emotions through the user's voice input and facial recognition. For example, if the user is feeling anxious or nervous, that information is reflected in the navigation. Emotion recognition uses the Python open source library OpenCV and Emotion API.

[0407] Route Adjustment

[0408] server

[0409] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. It suggests routes that avoid roads that are likely to cause stress to the user, for example, prioritizing quiet roads and roads with good scenery.

[0410] Providing information

[0411] server

[0412] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[0413] Information display

[0414] Terminal

[0415] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[0416] Specific examples

[0417] Example 1: Moving to a shelter

[0418] server

[0419] Immediately after a disaster occurs, road condition data is collected from various sources and clean data is generated.

[0420] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[0421] It receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[0422] The calculation results are sent to the user's device via API.

[0423] Terminal

[0424] The device reflects the received route information in the map app and displays a passable route from the current location to the nearest evacuation shelter. It also uses information from the emotion engine to provide stable voice guidance.

[0425] User

[0426] Users can safely move to a shelter by following the route displayed on their smartphone. With the support of the emotion engine, users can move with peace of mind.

[0427] Example 2: Transporting goods

[0428] server

[0429] It collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[0430] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[0431] It receives information from the emotion engine and provides routes that reduce driver stress.

[0432] Route information calculated through the API is provided to the logistics company's terminal.

[0433] Terminal

[0434] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[0435] User (logistics company)

[0436] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[0437] These concrete examples show that the system of the present invention can provide highly reliable traffic information during disasters, recognize the user's emotions, and provide optimal navigation, thereby being of great help in smoothly carrying out recovery and evacuation activities.

[0438] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0439] Step 1: Data collection

[0440] server

[0441] The server collects road condition data. As input, it uses API endpoints from public agencies, URLs from private traffic information providers, and data platforms from telecommunications companies. Specifically, it obtains real-time data through web scraping using the Python library BeautifulSoup and Selenium. This collected raw data is stored in a temporary database. The output is the collected, unprocessed road condition data.

[0442] Step 2: Data Preprocessing

[0443] server

[0444] The server converts the collected raw data into a common JSON format. The input is the raw data collected in step 1. Specifically, it uses the Python pandas library to filter incomplete and duplicate data and generate a clean dataset. This preprocessing imputes missing data and corrects outliers. The output is a clean dataset, which is stored in a temporary database.

[0445] Step 3: Reliability assessment

[0446] server

[0447] The server evaluates the reliability of the preprocessed data. The input is the clean dataset generated in step 2. Specifically, it calculates the reliability score of each information source using algorithms such as the weighted average method based on past data history and information update frequency. Data with low reliability is filtered out. The output is the reliability-evaluated data.

[0448] Step 4: Determine whether roads are passable

[0449] server

[0450] The server determines which roads are passable based on the reliability-evaluated data. The input is the data evaluated in step 3. Specifically, it uses a machine learning model (e.g., TensorFlow or PyTorch) to analyze the data and determine which roads are passable and which are not. The results of this determination are stored in a database. The output is passable road information.

[0451] Step 5: Calculate the optimal route

[0452] server

[0453] The server calculates the optimal route based on passable road information. The input is the passable road information determined in step 4. Specifically, it calculates the optimal route using Dijkstra's algorithm and A-search algorithm together with real-time traffic congestion information. The calculation results are stored in a database and made accessible via API. The output is the optimal route information.

[0454] Step 6: Emotion Recognition

[0455] Terminal

[0456] The device uses an emotion engine to recognize the user's emotions. Inputs include the user's voice input and facial recognition data. Specific operations include analyzing the user's emotions using Python's OpenCV and Emotion API. For example, it can identify whether the user is feeling anxious or nervous based on their voice tone and facial expression. The output is the user's emotional information.

[0457] Step 7: Route Adjustment

[0458] server

[0459] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. The input is the optimal route information calculated in step 5 and the user's emotional information obtained in step 6. Specifically, the server takes the emotional data into consideration and recalculates a route that is less stressful. For example, it selects quiet roads or roads with beautiful scenery. The output is the adjusted optimal route information.

[0460] Step 8: Provide information

[0461] server

[0462] The server generates the adjusted optimal route information in a user-friendly format and provides it to the device via the API. The input is the optimal route information adjusted in step 7. Specifically, the server formats the information in an easy-to-understand format and sends it to the device via the API. The output is the optimal route information provided to the device.

[0463] Step 9: Display Information

[0464] Terminal

[0465] The terminal analyzes the optimal route information provided by the server and displays it on the user interface. The input is the optimal route information provided in step 8. Specifically, the route information is reflected in the map application and visually shown to the user. Also, real-time guidance is provided using the voice navigation function. The output is the route information displayed on the user interface and voice guidance.

[0466] (Application example 2)

[0467] 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."

[0468] Conventional navigation systems have difficulty providing fast and reliable travel information during disasters. Furthermore, they are unable to provide navigation that takes into account the user's emotional factors, making it difficult to reduce the stress and anxiety users feel while traveling. Therefore, there is a need for technology that provides safe routes that are passable even during disasters, and also provides comfortable navigation that takes into account the user's emotions.

[0469] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for acquiring user emotion information and adjusting the optimal route based on the emotion, and means for providing the calculated optimal route information to the terminal. This makes it possible to provide highly reliable traffic information and navigation that takes user emotion into consideration even during a disaster.

[0470] "Information source" refers to a data provider for collecting road condition data provided by public institutions, private sites, etc.

[0471] "Preprocessing" refers to the process of converting collected data into a common format and filtering out incomplete or duplicate data to produce a clean dataset.

[0472] "Reliability assessment" is the process of evaluating and scoring the reliability of collected data, taking into account past history and frequency of information updates.

[0473] A "passable road" is a road that is safe to use and not affected by weather or disasters.

[0474] The "optimal route" is calculated based on passable road information and is the most efficient and safe route to the destination.

[0475] "Emotion information" is data that indicates the user's emotional state, and is information that identifies the user's emotions using voice input or face recognition.

[0476] "Terminal" means a device used by a user to receive and display information, such as a smartphone or smart glasses.

[0477] "Means of collection" refers to the means of obtaining data from public institution APIs and private sites.

[0478] "Preprocessing means" refers to means for converting collected data into a common format and for filtering the data.

[0479] "Means for evaluation" refers to the means for evaluating and scoring the reliability of collected data.

[0480] The "means for determining" refers to a means for determining passable roads based on the reliability-evaluated data.

[0481] The "means for calculating" refers to a means for calculating an optimal route using passable road information.

[0482] The "means for acquiring" refers to a means for acquiring emotion information through a user's voice input or face recognition.

[0483] "Adjustment means" refers to the means for recalculating the optimal route based on the acquired emotional information.

[0484] The "means for providing" refers to the means for transmitting the calculated optimum route information to the terminal and displaying it.

[0485] This invention is an advanced information collection and analysis system that recognizes passable roads and user emotions during disasters and adjusts navigation based on the information. This makes it possible to provide highly reliable traffic information and navigation that takes user emotions into consideration. Specific embodiments for implementing this invention are described below.

[0486] First, the server uses the following hardware and software: Road condition data is collected from public APIs and private sites, and APIs and web scraping tools are used to collect the data. The collected data is preprocessed on the server and converted into a common JSON format. This preprocessing includes filtering incomplete and duplicate data. Next, to evaluate reliability, the server is equipped with a reliability scoring algorithm. This evaluates the reliability of the data based on past history and information update frequency, and filters out unreliable data.

[0487] Based on the reliability-assessed data, a machine learning model (such as Scikit-learn or TensorFlow) is used to determine which roads are passable. The results of this determination are stored in a database, and Dijkstra's algorithm or A-search algorithm is used to calculate the optimal route. The optimal route is calculated, incorporating real-time traffic congestion information, and the results are stored in a database.

[0488] Furthermore, the device is equipped with an emotion engine to acquire the user's emotional information. The emotion engine uses the camera and microphone of the smart glasses or smartphone to analyze the user's voice and facial expressions and recognize emotions in real time. For example, if the user is feeling anxious or nervous, this information is sent to the server, which then recalculates the optimal route. A route that reflects the emotional information is calculated, and the server provides this route information to the device via an API.

[0489] The device displays the received route information in a user-friendly format, including a map application that visually indicates passable roads and recommended routes along the route. Furthermore, the device uses voice navigation to provide appropriate guidance to the user, and the emotional engine supports the device to ensure a safe and secure journey.

[0490] As a concrete example, consider an evacuation scenario during a disaster. After a disaster occurs, the server collects information in real time from public institution APIs, quickly assesses reliability, and determines passable roads. It then calculates the optimal route to the nearest evacuation shelter, and if the user feels anxious, it provides a less stressful route. The device receives this information and provides voice guidance and a map display, guiding the user safely to the evacuation shelter. In this way, the invention supports quick and reliable evacuation while maintaining the user's sense of security, even during a disaster.

[0491] An example prompt is:

[0492] "Consider a scenario where a user needs to evacuate early in the morning. A large earthquake has occurred in the area and the user needs to move to a shelter immediately. Based on the user's emotions, suggest a safe and secure route. Provide appropriate navigation support methods, especially considering the user's anxiety."

[0493] By implementing the system in this way, it will be possible to provide fast and reliable traffic information during disasters and navigation that takes user emotions into consideration. It will also provide specialized functions for autonomous vehicles, realizing travel that ensures a sense of security for passengers.

[0494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0495] Step 1:

[0496] The server collects road condition data from public APIs and private websites. Specifically, it obtains real-time road information through APIs and also collects necessary information using web scraping tools. This allows for the centralized collection of up-to-date data from various sources. Response data from APIs and data obtained through scraping are used as input, and the collected raw data is generated as output.

[0497] Step 2:

[0498] The server preprocesses the collected raw data by converting it into a common JSON format and filtering out incomplete and duplicate data, resulting in a clean dataset for smoother subsequent processing. It uses the collected raw data as input and generates formatted clean data as output.

[0499] Step 3:

[0500] The server evaluates the reliability of the preprocessed data. Specifically, it scores the data based on its source, history, and update frequency, and filters out data with low reliability. This allows only highly reliable data to proceed to the next step. It uses formatted clean data as input and generates data with a reliability evaluation as output.

[0501] Step 4:

[0502] The server determines whether roads are passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (e.g., Scikit-learn or TensorFlow) to determine whether a road is passable. This enables highly reliable determination based on the latest road conditions. It uses the reliability-evaluated data as input and generates passable road information as output.

[0503] Step 5:

[0504] The server calculates the optimal route based on passable road information. Specifically, it uses Dijkstra's algorithm and A-search algorithm to determine the optimal route, taking real-time traffic congestion information into consideration. Passable road information is used as input, and the calculated optimal route information is generated as output.

[0505] Step 6:

[0506] The device acquires the user's emotional information. Specifically, it analyzes the user's voice and facial expressions using the camera and microphone of smart glasses or a smartphone to recognize emotions. It uses the user's voice data and image data as input and generates emotional information as output.

[0507] Step 7:

[0508] The server recalculates the optimal route based on the user's emotional information. Specifically, it analyzes the acquired emotional information and recalculates the optimal route to provide a route that is less stressful for the user. It uses the user's emotional information and existing optimal route information as input and generates adjusted optimal route information as output.

[0509] Step 8:

[0510] The device displays the calculated optimal route information in a user-friendly format. Specifically, the device reflects the route information in a map application and provides appropriate guidance to the user using a voice navigation function. The device uses the adjusted optimal route information as input and generates route information and voice guidance displayed on the user interface as output.

[0511] 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.

[0512] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0513] 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.

[0514] [Second embodiment]

[0515] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0516] 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.

[0517] 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).

[0518] 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.

[0519] 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.

[0520] 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).

[0521] 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.

[0522] 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.

[0523] 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.

[0524] 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.

[0525] 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.

[0526] 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."

[0527] The system of this invention is an advanced information collection and analysis system for presenting passable roads in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates the reliability of the data, and then provides optimal route information.

[0528] Program processing explanation

[0529] 1. Data Collection

[0530] server

[0531] The server sends requests to API endpoints of public agencies to obtain the latest road condition data, scrapes private traffic information providers to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[0532] 2. Data Preprocessing

[0533] server

[0534] The server converts the collected data from various sources into a common format, for example, unifying the acquired data into JSON format, and also filters out incomplete, incorrect, and duplicate data to generate a clean dataset.

[0535] 3. Reliability evaluation

[0536] server

[0537] The server evaluates the reliability of the preprocessed data by scoring each information source based on its past history and frequency of information updates. For example, a source with a high level of accuracy in the past is given a high reliability score.

[0538] 4. Determining whether a road is passable

[0539] server

[0540] The server determines which roads are passable and which are not, based on reliable data, using machine learning models, taking into account, for example, past traffic conditions and current traffic congestion information.

[0541] 5. Optimal Route Calculation

[0542] server

[0543] The server then calculates the optimal route based on the results of the assessment. This route calculation takes into account the shortest route from the current location to the destination, evacuation routes, and logistics routes. It also incorporates real-time traffic congestion information.

[0544] 6. Information provision

[0545] server

[0546] The server generates the calculated optimal route information in a user-friendly format and provides it to the device, for example, by distributing the route information through an API.

[0547] 7. User Presentation

[0548] Terminal

[0549] The user's smartphone, navigation system, or other device receives the route information sent from the server and visually displays it, allowing the user to check passable routes on a map.

[0550] Specific examples

[0551] Example 1: Moving to a shelter

[0552] server

[0553] The server collects road condition data from various sources immediately after a disaster occurs and generates clean data.

[0554] Reliability assessment is performed based on clean data to determine whether roads are passable.

[0555] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated.

[0556] The calculation results are sent to the user's device via API.

[0557] Terminal

[0558] The device reflects the received route information in the map app and displays to the user the "passable route from the current location to the nearest evacuation shelter."

[0559] User

[0560] Users can follow the route displayed on their smartphone to safely reach an evacuation shelter.

[0561] Example 2: Transporting goods

[0562] server

[0563] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[0564] Logistics routes are determined based on highly reliable data.

[0565] Calculate the optimal route to your destination while taking traffic congestion information into account.

[0566] The calculated route information is provided to the logistics company's terminal via API.

[0567] Terminal

[0568] The logistics company's terminal displays the received route information on a navigation system and provides instructions to the driver.

[0569] User (logistics company)

[0570] Drivers can follow the route displayed on the terminal to transport goods quickly and safely to their destination.

[0571] In this way, the system of the present invention quickly provides highly reliable information on passable roads in the event of a disaster, and is of great help in smoothly carrying out restoration and evacuation activities.

[0572] The processing flow will be explained below.

[0573] Step 1: Data collection

[0574] server

[0575] The server sends an HTTP GET request to the public institution's API to obtain the latest road condition data, and performs authentication using the API key.

[0576] Scrape pages from private traffic information providers and extract real-time road condition data.

[0577] Traffic information data provided by telecommunications companies is obtained through a dedicated API.

[0578] Step 2: Data Preprocessing

[0579] server

[0580] The server converts the collected data into a common JSON format. For example, it converts XML data obtained from a public institution's API into JSON.

[0581] Filter incomplete and duplicate data from collected data to generate a clean dataset.

[0582] The converted data is stored in a temporary database.

[0583] Step 3: Reliability assessment

[0584] server

[0585] The server evaluates the reliability of the preprocessed data, scoring each information source based on its past history and frequency of updates.

[0586] The reliability score is calculated using a specific algorithm (e.g., a points system based on past accuracy and update frequency).

[0587] Unreliable data is filtered out and only reliable data is passed on to the next step.

[0588] Step 4: Determine whether roads are passable

[0589] server

[0590] The server runs machine learning models using reliable data to determine which roads are passable and which are not.

[0591] The machine learning model takes into account past traffic history and current traffic congestion data to predict whether a route can be passed.

[0592] The judgment results are stored in a database.

[0593] Step 5: Calculate the optimal route

[0594] server

[0595] The server runs an algorithm to calculate the optimal route based on the information about passable roads, such as Dijkstra's algorithm or A-search algorithm.

[0596] By incorporating real-time traffic congestion information, the optimal route is calculated to avoid unnecessary delays.

[0597] The optimal route information will be stored in a database and made accessible via API.

[0598] Step 6: Provide information

[0599] server

[0600] The server generates the calculated optimal route information in a user-friendly format and provides it to the device via an API.

[0601] The API processes route information requests and responds in JSON format.

[0602] The response includes roads that are passable, roads to avoid, and recommended routes.

[0603] Step 7: Display information

[0604] Terminal

[0605] The terminal analyzes the route information received from the server and displays it on the user interface.

[0606] The route is reflected in the map application, visually indicating navigable roads along the route and recommended routes.

[0607] If necessary, the voice navigation function will provide route guidance.

[0608] Step 8: User interaction

[0609] User

[0610] The user checks the passable routes displayed on the terminal and selects a route if necessary.

[0611] The user follows the displayed route to their destination, for example, to a safe evacuation shelter in an emergency.

[0612] Example 1

[0613] 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."

[0614] During disasters, it has been difficult to quickly and accurately grasp real-time road conditions and provide optimal passable routes. With conventional systems, data from different sources is fragmented and inconsistent, making it difficult to obtain reliable information. Furthermore, data preprocessing and reliability assessment are insufficient, leading to inaccurate determinations of passable roads. Furthermore, optimal route calculations do not adequately reflect real-time conditions, making it impossible to provide practical information to users.

[0615] 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.

[0616] In this invention, the server includes means for collecting road condition data from information sources, means for converting the collected data into a common format and cleaning it, means for evaluating the reliability of the preprocessed data, means for determining passable roads using a machine learning model based on the reliability-evaluated data, means for calculating an optimal route from the current location to the destination based on the determined passable road information, and means for providing the calculated optimal route information to the terminal. This allows for the rapid provision of reliable passable road information even during a disaster, enabling users to reach their destination safely and efficiently.

[0617] "Source" refers to the organization or institution that provides road condition data, or the API or website from which that data can be obtained.

[0618] "Road condition data" refers to real-time information related to roads, such as road passability, traffic congestion information, accident information, and road closures due to disasters.

[0619] "Collection Method" refers to the method or process used to obtain road condition data from a source, such as sending an API request or web scraping.

[0620] "Preprocessing" refers to the process of converting collected data into a common format and removing erroneous or incomplete data.

[0621] "Credibility assessment tools" refer to methods and processes for assessing the reliability of collected data, including, for example, scoring each source based on its past history and update frequency.

[0622] A "machine learning model" is an algorithm or system used by a computer to learn from large amounts of data and perform a specific task (in this case, determining which roads are passable).

[0623] "Means for determining passable roads" refers to a method or process for determining which roads are passable using reliability-assessed data.

[0624] "Optimal route calculation means" refers to a method or process for calculating the optimal route from the current location to the destination based on determined passable road information.

[0625] "Providing means" refers to the method or process for transmitting the calculated optimal route information to the terminal used by the user.

[0626] This invention is a system for providing passable road information quickly and accurately in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates its reliability, and then provides optimal route information.

[0627] Hardware and Software

[0628] server

[0629] The server collects road condition data from multiple sources. Specifically, it sends HTTP requests to API endpoints of public agencies to obtain the latest data. It also scrapes traffic information sites using the Python library BeautifulSoup to collect real-time data. Traffic information data from telecommunications companies is also obtained via FTP and saved in local storage.

[0630] The server loads the collected data into a Pandas DataFrame and converts it into a unified format. Next, it performs data cleaning, filtering out incomplete and duplicate data, and generating a clean dataset. This data cleaning process is performed using Python's Pandas and NumPy.

[0631] For reliability evaluation, the scikit-learn library is used to perform scoring based on past history and information update frequency. Based on the evaluation results, a machine learning model (using, for example, TensorFlow or PyTorch) is used to determine whether the road is passable.

[0632] To calculate the optimal route, a road network graph is constructed and the optimal route from the current location to the destination is calculated using the Dijkstra algorithm and the A algorithm. The calculation results are saved in JSON format and provided to the terminal via an API. The API is implemented using Flask and FastAPI.

[0633] Terminal

[0634] The terminals include smartphones and navigation systems. These terminals are equipped with software to receive route information sent from the server and display it on a map application. For example, the terminals use Google Maps or Mapbox SDK to display the route on a map. The terminals provide a user-friendly interface, allowing users to easily check the route information.

[0635] User

[0636] Users use this system to reach their destination safely and efficiently in the event of a disaster. They check real-time passable route information via their smartphone or navigation system and follow the instructions.

[0637] Specific examples

[0638] Example 1: Moving to a shelter

[0639] Immediately after a disaster occurs, the server collects road condition data from various sources, cleans the data, and then performs reliability evaluation to determine which roads are passable.

[0640] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated and sent to the user's device via an API.

[0641] The user follows the route displayed on their smartphone to reach the evacuation shelter. For example, if the user types "Tell me the best route to get to the evacuation shelter," the server will instantly calculate and provide the best route.

[0642] Example 2: Transporting goods

[0643] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies, and then determines logistics routes based on highly reliable data.

[0644] Taking traffic congestion information into account, the system calculates the optimal route to the destination and provides the results to the logistics company's terminal via an API.

[0645] Logistics companies transport goods quickly and safely by following the route displayed on the terminal. For example, when a driver types in "What is the best route to my destination?", the server quickly provides the optimal route.

[0646] In this way, the system of the present invention provides highly reliable information about passable roads in the event of a disaster, enabling users to reach their destination safely and efficiently.

[0647] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0648] Step 1:

[0649] Data collection

[0650] server

[0651] The server collects road condition data from information sources. Specifically, it sends HTTP requests to public agency API endpoints to obtain the latest data. It also accesses private traffic information providers' websites using a scraping tool to extract text data. It also downloads traffic information data provided by telecommunications companies via FTP and stores it in local storage.

[0652] Input: Public API URL, private site URL, telecommunications company data file

[0653] Output: Raw data (JSON format, text data, binary data)

[0654] Specific behavior:

[0655] The server periodically sends API requests and stores the JSON data received as HTTP responses locally.

[0656] Use a tool such as BeautifulSoup to scrape the HTML page and extract the required text information.

[0657] Establish an FTP connection and download the traffic information data file.

[0658] Step 2:

[0659] Data Preprocessing

[0660] server

[0661] The server converts the collected data into a common format and cleans it. Using the Python Pandas library, the data obtained from each source is loaded into a DataFrame and unified into a common column structure. Next, the data is cleaned to remove incomplete and duplicate data.

[0662] Input: Raw data (JSON format, text data, binary data)

[0663] Output: Preprocessed common format data (DataFrame or JSON format)

[0664] Specific behavior:

[0665] Read the data using Pandas' read_json() or read_csv() functions.

[0666] Perform data cleaning using the dropna() and drop_duplicates() functions.

[0667] Save the clean data using the to_json() method.

[0668] Step 3:

[0669] Reliability evaluation

[0670] server

[0671] The server scores the preprocessed data to evaluate its reliability. It calculates a score for each information source based on its past history and update frequency, and prioritizes scores for highly reliable data. The server uses the scikit-learn library to evaluate reliability.

[0672] Input: Preprocessed common format data (DataFrame or JSON format)

[0673] Output: Data with confidence scores (DataFrame or JSON format)

[0674] Specific behavior:

[0675] The past data history and update frequency of each source is obtained from the database.

[0676] Calculate reliability scores using scikit-learn's KNeighborsClassifier or a custom scoring function.

[0677] Add and store a confidence score to the data.

[0678] Step 4:

[0679] Determining passable roads

[0680] server

[0681] The server uses the reliability-assessed data to determine whether roads are passable using a machine learning model. Specifically, it loads a model trained with TensorFlow or PyTorch and uses the data as input to determine whether a road is passable.

[0682] Input: Data with confidence scores (DataFrame or JSON format)

[0683] Output: Road data (DataFrame or JSON format) for which passability has been determined

[0684] Specific behavior:

[0685] Load a trained machine learning model.

[0686] Input data into the model and obtain labels indicating whether the road is passable or not.

[0687] The judgment result is added to the data and saved.

[0688] Step 5:

[0689] Optimal route calculation

[0690] server

[0691] The server then calculates the optimal route from the current location to the destination based on the results of the assessment, using the Dijkstra algorithm and the A algorithm, and taking real-time traffic congestion information into account.

[0692] Input: Road data (DataFrame or JSON format) for which passability is determined

[0693] Output: Optimal route information (JSON format)

[0694] Specific behavior:

[0695] A road network graph is constructed, and passability and traffic condition costs are set for each edge.

[0696] Finding the shortest path using the NetworkX library.

[0697] Save the optimal route information in JSON format.

[0698] Step 6:

[0699] Providing information

[0700] server

[0701] The server provides the calculated optimal route information through an API, and returns the latest route information in JSON format in response to a user request.

[0702] Input: User request

[0703] Output: Optimal route information (JSON format)

[0704] Specific behavior:

[0705] Build API endpoints using Flask and FastAPI.

[0706] Returns pre-calculated route information based on user requests.

[0707] Step 7:

[0708] What the user sees

[0709] Terminal

[0710] The device receives the route information sent from the server and displays it in the map app. It plots the route on a map using Google Maps or Mapbox SDK, providing a visual representation to the user.

[0711] Input: Optimal route information received from the server (JSON format)

[0712] Output: Route information plotted on a map

[0713] Specific behavior:

[0714] The terminal parses the received JSON data.

[0715] Plot your data on a map using the Google Maps or Mapbox SDK.

[0716] Users can check the route on the map and travel safely.

[0717] (Application example 1)

[0718] 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."

[0719] The present invention solves the problem of the difficulty of providing quick and accurate information on passable roads during disasters. Furthermore, there is a need for a system that enables autonomous vehicles to travel safely and efficiently based on that information.

[0720] 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.

[0721] In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for providing the calculated optimal route information to the autonomously driven vehicle, and means for controlling the vehicle based on the route information provided to the autonomously driven vehicle. This enables the autonomously driven vehicle to select and travel a safe and optimal route even during a disaster.

[0722] "Sources" refer to the origins of various publicly available data, including APIs of public institutions and private sites.

[0723] "Road condition data" is data that indicates whether roads are passable, traffic congestion information, traffic accident information, weather conditions, and the like.

[0724] "Preprocessing" refers to the process of standardizing collected raw data into a certain format and removing incomplete or incorrect data to generate a clean dataset.

[0725] "Credibility assessment" refers to the process of assessing the accuracy and reliability of data based on the source's past history and frequency of data updates.

[0726] "Passable roads" refer to roads that are determined to be passable even in the event of a disaster based on the results of data analysis.

[0727] The "optimal route" refers to the shortest and safest route from the current location to the destination, calculated by the program.

[0728] "Autonomous vehicle" refers to a vehicle that can be operated and driven by its own system.

[0729] "Route information" is data about the calculated optimal travel route, and is used in maps and navigation systems.

[0730] "Control means" refers to the function of controlling the movement of the vehicle based on the route information provided.

[0731] This invention is a system for autonomous vehicles to safely and quickly select and move along optimal routes during disasters. The system collects road condition data from information sources, preprocesses it, evaluates its reliability, determines which roads are passable, calculates the optimal route, and provides this information to autonomous vehicles to reflect in their control.

[0732] Hardware and software used

[0733] Hardware:

[0734] Embedded systems for autonomous vehicles (navigation systems, communication modules, etc.)

[0735] software:

[0736] Python

[0737] requests library (for API requests)

[0738] pandas library (for data preprocessing)

[0739] scikit-learn library (for machine learning modeling)

[0740] geopy library (for geographic information processing)

[0741] Details of data processing and calculation

[0742] The server collects road condition data from public APIs and private websites. It then standardizes the collected data into JSON format and removes incomplete or incorrect data to generate a clean dataset. Based on this dataset, the reliability of the source is evaluated using its past history and the frequency of data updates.

[0743] Using the evaluated data, a machine learning model (e.g., random forest) is used to determine whether a road is passable, taking into account historical traffic information and weather conditions. Next, the optimal route from the current location to the destination is calculated based on the passable road information.

[0744] The calculated optimal route information is provided to the autonomous vehicle, which then controls the vehicle based on that route information, enabling safe and rapid movement even in the event of a disaster.

[0745] Specific examples

[0746] Moving to a shelter:

[0747] Immediately after a disaster occurs, the server collects the latest road condition data from various sources, preprocesses it, and evaluates its reliability. It then determines which roads are passable and calculates the optimal route to the nearest evacuation shelter. This route information is provided to the autonomous vehicle, which then travels safely to the shelter based on the instructions.

[0748] Transport of goods:

[0749] The server collects real-time data and generates clean data, then performs reliability assessment and provides passable road information for logistics companies. After route calculation, it provides the optimal route information to autonomous vehicles, which then transport goods to their destinations quickly and safely.

[0750] Example prompts to input to the generative AI model

[0751] AI Assistant, please calculate the optimal route for safe and fast autonomous driving to an evacuation shelter based on the current damage situation caused by the earthquake, and update this information in the vehicle system. The current location is Tokyo Station, and the destination is an evacuation shelter within Tokyo.

[0752] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0753] Step 1:

[0754] The server collects road condition data from sources. Specifically, it sends requests to API endpoints of public agencies to obtain the latest road condition data. It also scrapes private traffic information providers to collect real-time road information. It also obtains traffic information data provided by telecommunications companies. The input is the API request or scraping, and the output is the collected road condition data.

[0755] Step 2:

[0756] The server preprocesses the collected data. Specifically, it converts data from each source into a common JSON format and filters out incomplete, incorrect, and duplicate data to generate a clean dataset. The input is the raw collected data, and the output is the clean dataset.

[0757] Step 3:

[0758] The server evaluates the reliability of the preprocessed data. Specifically, it scores each information source based on its past history and the frequency of information updates. For example, it assigns a high reliability score to information sources that have been highly accurate in the past. The input is a clean dataset, and the output is reliability-evaluated data.

[0759] Step 4:

[0760] The server determines whether a road is passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (such as random forest) to determine whether the road is passable. This determination also takes into account past and current traffic information and weather conditions. The input is reliability-evaluated data, and the output is road information determined to be passable.

[0761] Step 5:

[0762] The server calculates the optimal route based on passable road information. Specifically, it calculates the shortest route from the current location to the destination, as well as evacuation routes and logistics routes. It also incorporates real-time traffic congestion information. The input is passable road information and the coordinates of the current location and destination, and the output is the optimal route information.

[0763] Step 6:

[0764] The server provides the calculated optimal route information to the autonomous vehicle. Specifically, it sends the route information to the autonomous vehicle's embedded system through an API. The input is the optimal route information, and the output is the route information received by the autonomous vehicle.

[0765] Step 7:

[0766] The embedded system of an autonomous vehicle reflects the provided route information and controls the vehicle. Specifically, the route is displayed on the navigation system, and the autonomous driving system operates according to that route. The input is the route information provided by the server, and the output is the vehicle's movement to reach the destination safely and quickly.

[0767] 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.

[0768] The system of this invention is an advanced information collection and analysis system that presents passable roads in the event of a disaster, recognizes the user's emotions, and adjusts navigation accordingly. This system collects road condition data from sources, preprocesses them, and evaluates their reliability before presenting passable roads and optimal routes. Furthermore, it is equipped with an emotion engine that realizes optimal navigation based on the user's emotions.

[0769] Program processing explanation

[0770] 1. Data Collection

[0771] server

[0772] The server obtains the latest road condition data from public agency APIs, scrapes private traffic information websites to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[0773] 2. Data Preprocessing

[0774] server

[0775] The server converts the collected data into a common JSON format and filters out incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[0776] 3. Reliability evaluation

[0777] server

[0778] The server evaluates the reliability of each information source based on the preprocessed data. It scores the information using a specific algorithm, taking into account past history and frequency of information updates. Unreliable data is filtered out, and only reliable data is allowed to proceed to the next step.

[0779] 4. Determining whether a road is passable

[0780] server

[0781] The server runs machine learning models using reliable data to determine which roads are passable and which are not, and the results are stored in a database.

[0782] 5. Optimal Route Calculation

[0783] server

[0784] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm, and incorporates real-time traffic information. The optimal route information is stored in a database and can be accessed via API.

[0785] 6. Emotion recognition

[0786] Terminal

[0787] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses the user's voice input and facial recognition to identify emotions. For example, if the user is anxious or nervous, that information is reflected in the navigation.

[0788] 7. Route Adjustment

[0789] server

[0790] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method, for example, proposing a route that avoids roads that are likely to cause stress to the user.

[0791] 8. Information provision

[0792] server

[0793] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[0794] 9. Information display

[0795] Terminal

[0796] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[0797] Specific examples

[0798] Example 1: Moving to a shelter

[0799] server

[0800] Immediately after a disaster occurs, the server collects road condition data from each source and generates clean data.

[0801] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[0802] In addition, it receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[0803] The calculation results are sent to the user's device via API.

[0804] Terminal

[0805] The device reflects the received route information in the map app and displays the user a passable route from their current location to the nearest evacuation shelter. Using information from the emotion engine, the device provides stable voice guidance.

[0806] User

[0807] Users can follow the route displayed on their smartphone and move safely to a shelter. With the support of the emotion engine, users can move with peace of mind.

[0808] Example 2: Transporting goods

[0809] server

[0810] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[0811] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[0812] It receives information from the emotion engine and provides routes that reduce driver stress.

[0813] The calculated route information is provided to the logistics company's terminal via API.

[0814] Terminal

[0815] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[0816] User (logistics company)

[0817] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[0818] In this way, the system of the present invention provides highly reliable traffic information during disasters, recognizes the user's emotions, and provides optimal navigation, thereby greatly assisting in smoothly carrying out recovery and evacuation activities.

[0819] The processing flow will be explained below.

[0820] Step 1: Data collection

[0821] server

[0822] The server sends an HTTP GET request to a public agency's API to retrieve the latest road condition data, for example, using the https: / / api.trafficinfo.gov endpoint.

[0823] Scrape private traffic information websites and extract road condition data using HTML analysis tools, such as libraries like BeautifulSoup.

[0824] Traffic information data provided by telecommunications companies is acquired through a dedicated API, and the acquired data is updated in real time.

[0825] Step 2: Data Preprocessing

[0826] server

[0827] The server converts the collected data into a common JSON format, for example using the xmltodict library to convert data in XML format into JSON.

[0828] Regular expressions are used to shape the collected data, filtering out incomplete and duplicate data and generating a clean dataset.

[0829] The transformed data is stored as a clean dataset in a temporary database.

[0830] Step 3: Reliability assessment

[0831] server

[0832] The server considers the past reliability history and update frequency of each source to assess the reliability of the pre-processed data, using an algorithm (e.g., weighted average) to assign a reliability score to each source.

[0833] Data with low confidence scores are filtered out and only data with high scores proceeds to the next step.

[0834] The evaluation results are stored in a database.

[0835] Step 4: Determine whether roads are passable

[0836] server

[0837] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, for example, using a random forest model.

[0838] Input data includes traffic history information and current congestion data.

[0839] The judgment results are stored in a database.

[0840] Step 5: Calculate the optimal route

[0841] server

[0842] The server executes an algorithm (for example, Dijkstra's algorithm or A-search algorithm) that calculates the optimal route between specified points based on passable road information.

[0843] By incorporating real-time traffic congestion information, the shortest route is calculated to avoid unnecessary delays.

[0844] The optimal route information will be stored in a database and made accessible via API.

[0845] Step 6: Emotion Recognition

[0846] Terminal

[0847] The device uses the user's voice input and camera to provide data to the emotion engine, for example, processing audio data from the user speaking into a microphone and facial expression data captured by a camera.

[0848] The emotion engine uses voice recognition software and facial recognition algorithms to identify the user's emotions (e.g., anxiety, relief, irritation).

[0849] Step 7: Route Adjustment

[0850] server

[0851] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. For example, for a user who is prone to anxiety, it suggests a route that eliminates roads that should be avoided.

[0852] The recalculated route information is stored in a database and provided to the device via an API.

[0853] Step 8: Provide information

[0854] server

[0855] The server generates an optimal route that reflects the emotion information in a user-friendly format and provides it to the device via an API, for example, by returning the route information in JSON format.

[0856] Step 9: Display Information

[0857] Terminal

[0858] The device analyzes the route information received from the server and displays it in a map application, with a user interface that visually indicates passable roads and the optimal route.

[0859] The device uses a voice navigation function to provide the user with appropriate route guidance, which is based on the user's emotions.

[0860] Step 10: User interaction

[0861] User

[0862] The user checks the passable routes displayed on the terminal and selects a route as necessary.

[0863] Users can follow the displayed route to their destination safely and comfortably. With the support of the emotion engine, they can travel with peace of mind.

[0864] Example 2

[0865] 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."

[0866] Conventional navigation systems are sometimes unable to accurately grasp real-time road conditions during disasters, limiting their ability to suggest optimal routes. Furthermore, they are unable to provide navigation that takes into account the user's emotional state, and do not take into consideration routes that are likely to cause stress to the user. It is necessary to solve these problems and realize fast and safe evacuation and transportation of supplies during disasters.

[0867] 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.

[0868] In this invention, the server includes means for collecting road condition data from an information source, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for recalculating the optimal route based on the recognized user emotion information, and means for providing the calculated optimal route information to the terminal. This makes it possible to propose an optimal route taking the user's emotional state into consideration, thereby enabling quick and safe evacuation and transportation of supplies in the event of a disaster.

[0869] "Information sources" are data sources that are the basis for collecting data, such as public agencies, private companies, and communication companies that provide road condition data.

[0870] "Road condition data" is information showing the latest road conditions, such as whether the road is passable, traffic congestion information, traffic accidents, and damage caused by disasters.

[0871] "Preprocessing" is the process of converting collected data into a common format and filtering out incomplete or duplicate data.

[0872] "Reliability assessment" is a method for assessing the accuracy and reliability of collected data and ensuring data quality. This assessment includes past history and frequency of information updates.

[0873] A "passable road" is one that is clear of obstacles and safe for vehicles and pedestrians to travel on. This determination is made using machine learning models.

[0874] The "optimal route" refers to the most efficient and safest route to the user's destination, calculated based on real-time road conditions and the user's emotional state.

[0875] "User emotion" refers to the psychological state, such as anxiety, tension, or stress, felt by the user, as identified by the user's voice input or facial recognition.

[0876] "Emotion recognition" is the process of identifying a user's emotions from their facial expressions and voice, and reflecting this in navigation.

[0877] "Recalculation" is a process of recalculating existing route calculation results based on the recognized user's emotions and proposing a route that is more suitable for the user.

[0878] A "terminal" is a device used by a user (such as a smartphone or tablet) that receives and displays optimal route information.

[0879] The system of the present invention is an advanced information collection and analysis system that collects road condition data from various information sources, recognizes the emotional state of the user, and provides optimal navigation. Specific embodiments are described below.

[0880] Data collection

[0881] server

[0882] The server obtains the latest road condition data through public agency APIs. It also accesses private traffic information providers and collects real-time road information using web scraping technology. This process uses Python libraries such as BeautifulSoup and Selenium. It also obtains traffic information data from telecommunications companies' data platforms. This data is then stored in a temporary database.

[0883] Data Preprocessing

[0884] server

[0885] The server converts the collected data into a common JSON format, then uses the Python pandas library to filter incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[0886] Reliability evaluation

[0887] server

[0888] The server evaluates the reliability of each information source based on the preprocessed data. The evaluation takes into account past data history and information update frequency, and uses algorithms such as the weighted average method. Unreliable data is filtered out, and only reliable data is advanced to the next step.

[0889] Determining passable roads

[0890] server

[0891] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, using libraries such as TensorFlow and PyTorch. The results are then stored in a database.

[0892] Optimal route calculation

[0893] server

[0894] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm. It also takes into account real-time traffic congestion information. The optimal route information is stored in a database and can be accessed via API.

[0895] emotion recognition

[0896] Terminal

[0897] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine identifies emotions through the user's voice input and facial recognition. For example, if the user is feeling anxious or nervous, that information is reflected in the navigation. Emotion recognition uses the Python open source library OpenCV and Emotion API.

[0898] Route Adjustment

[0899] server

[0900] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. It suggests routes that avoid roads that are likely to cause stress to the user, for example, prioritizing quiet roads and roads with good scenery.

[0901] Providing information

[0902] server

[0903] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[0904] Information display

[0905] Terminal

[0906] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[0907] Specific examples

[0908] Example 1: Moving to a shelter

[0909] server

[0910] Immediately after a disaster occurs, road condition data is collected from various sources and clean data is generated.

[0911] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[0912] It receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[0913] The calculation results are sent to the user's device via API.

[0914] Terminal

[0915] The device reflects the received route information in the map app and displays a passable route from the current location to the nearest evacuation shelter. It also uses information from the emotion engine to provide stable voice guidance.

[0916] User

[0917] Users can safely move to a shelter by following the route displayed on their smartphone. With the support of the emotion engine, users can move with peace of mind.

[0918] Example 2: Transporting goods

[0919] server

[0920] It collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[0921] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[0922] It receives information from the emotion engine and provides routes that reduce driver stress.

[0923] Route information calculated through the API is provided to the logistics company's terminal.

[0924] Terminal

[0925] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[0926] User (logistics company)

[0927] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[0928] These concrete examples show that the system of the present invention can provide highly reliable traffic information during disasters, recognize the user's emotions, and provide optimal navigation, thereby being of great help in smoothly carrying out recovery and evacuation activities.

[0929] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0930] Step 1: Data collection

[0931] server

[0932] The server collects road condition data. As input, it uses API endpoints from public agencies, URLs from private traffic information providers, and data platforms from telecommunications companies. Specifically, it obtains real-time data through web scraping using the Python library BeautifulSoup and Selenium. This collected raw data is stored in a temporary database. The output is the collected, unprocessed road condition data.

[0933] Step 2: Data Preprocessing

[0934] server

[0935] The server converts the collected raw data into a common JSON format. The input is the raw data collected in step 1. Specifically, it uses the Python pandas library to filter incomplete and duplicate data and generate a clean dataset. This preprocessing imputes missing data and corrects outliers. The output is a clean dataset, which is stored in a temporary database.

[0936] Step 3: Reliability assessment

[0937] server

[0938] The server evaluates the reliability of the preprocessed data. The input is the clean dataset generated in step 2. Specifically, it calculates the reliability score of each information source using algorithms such as the weighted average method based on past data history and information update frequency. Data with low reliability is filtered out. The output is the reliability-evaluated data.

[0939] Step 4: Determine whether roads are passable

[0940] server

[0941] The server determines which roads are passable based on the reliability-evaluated data. The input is the data evaluated in step 3. Specifically, it uses a machine learning model (e.g., TensorFlow or PyTorch) to analyze the data and determine which roads are passable and which are not. The results of this determination are stored in a database. The output is passable road information.

[0942] Step 5: Calculate the optimal route

[0943] server

[0944] The server calculates the optimal route based on passable road information. The input is the passable road information determined in step 4. Specifically, it calculates the optimal route using Dijkstra's algorithm and A-search algorithm together with real-time traffic congestion information. The calculation results are stored in a database and made accessible via API. The output is the optimal route information.

[0945] Step 6: Emotion Recognition

[0946] Terminal

[0947] The device uses an emotion engine to recognize the user's emotions. Inputs include the user's voice input and facial recognition data. Specific operations include analyzing the user's emotions using Python's OpenCV and Emotion API. For example, it can identify whether the user is feeling anxious or nervous based on their voice tone and facial expression. The output is the user's emotional information.

[0948] Step 7: Route Adjustment

[0949] server

[0950] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. The input is the optimal route information calculated in step 5 and the user's emotional information obtained in step 6. Specifically, the server takes the emotional data into consideration and recalculates a route that is less stressful. For example, it selects quiet roads or roads with beautiful scenery. The output is the adjusted optimal route information.

[0951] Step 8: Provide information

[0952] server

[0953] The server generates the adjusted optimal route information in a user-friendly format and provides it to the device via the API. The input is the optimal route information adjusted in step 7. Specifically, the server formats the information in an easy-to-understand format and sends it to the device via the API. The output is the optimal route information provided to the device.

[0954] Step 9: Display Information

[0955] Terminal

[0956] The terminal analyzes the optimal route information provided by the server and displays it on the user interface. The input is the optimal route information provided in step 8. Specifically, the route information is reflected in the map application and visually shown to the user. Also, real-time guidance is provided using the voice navigation function. The output is the route information displayed on the user interface and voice guidance.

[0957] (Application example 2)

[0958] 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."

[0959] Conventional navigation systems have difficulty providing fast and reliable travel information during disasters. Furthermore, they are unable to provide navigation that takes into account the user's emotional factors, making it difficult to reduce the stress and anxiety users feel while traveling. Therefore, there is a need for technology that provides safe routes that are passable even during disasters, and also provides comfortable navigation that takes into account the user's emotions.

[0960] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for acquiring user emotion information and adjusting the optimal route based on the emotion, and means for providing the calculated optimal route information to the terminal. This makes it possible to provide highly reliable traffic information and navigation that takes user emotion into consideration even during a disaster.

[0961] "Information source" refers to a data provider for collecting road condition data provided by public institutions, private sites, etc.

[0962] "Preprocessing" refers to the process of converting collected data into a common format and filtering out incomplete or duplicate data to produce a clean dataset.

[0963] "Reliability assessment" is the process of evaluating and scoring the reliability of collected data, taking into account past history and frequency of information updates.

[0964] A "passable road" is a road that is safe to use and not affected by weather or disasters.

[0965] The "optimal route" is calculated based on passable road information and is the most efficient and safe route to the destination.

[0966] "Emotion information" is data that indicates the user's emotional state, and is information that identifies the user's emotions using voice input or face recognition.

[0967] "Terminal" means a device used by a user to receive and display information, such as a smartphone or smart glasses.

[0968] "Means of collection" refers to the means of obtaining data from public institution APIs and private sites.

[0969] "Preprocessing means" refers to means for converting collected data into a common format and for filtering the data.

[0970] "Means for evaluation" refers to the means for evaluating and scoring the reliability of collected data.

[0971] The "means for determining" refers to a means for determining passable roads based on the reliability-evaluated data.

[0972] The "means for calculating" refers to a means for calculating an optimal route using passable road information.

[0973] The "means for acquiring" refers to a means for acquiring emotion information through a user's voice input or face recognition.

[0974] "Adjustment means" refers to the means for recalculating the optimal route based on the acquired emotional information.

[0975] The "means for providing" refers to the means for transmitting the calculated optimum route information to the terminal and displaying it.

[0976] This invention is an advanced information collection and analysis system that recognizes passable roads and user emotions during disasters and adjusts navigation based on the information. This makes it possible to provide highly reliable traffic information and navigation that takes user emotions into consideration. Specific embodiments for implementing this invention are described below.

[0977] First, the server uses the following hardware and software: Road condition data is collected from public APIs and private sites, and APIs and web scraping tools are used to collect the data. The collected data is preprocessed on the server and converted into a common JSON format. This preprocessing includes filtering incomplete and duplicate data. Next, to evaluate reliability, the server is equipped with a reliability scoring algorithm. This evaluates the reliability of the data based on past history and information update frequency, and filters out unreliable data.

[0978] Based on the reliability-assessed data, a machine learning model (such as Scikit-learn or TensorFlow) is used to determine which roads are passable. The results of this determination are stored in a database, and Dijkstra's algorithm or A-search algorithm is used to calculate the optimal route. The optimal route is calculated, incorporating real-time traffic congestion information, and the results are stored in a database.

[0979] Furthermore, the device is equipped with an emotion engine to acquire the user's emotional information. The emotion engine uses the camera and microphone of the smart glasses or smartphone to analyze the user's voice and facial expressions and recognize emotions in real time. For example, if the user is feeling anxious or nervous, this information is sent to the server, which then recalculates the optimal route. A route that reflects the emotional information is calculated, and the server provides this route information to the device via an API.

[0980] The device displays the received route information in a user-friendly format, including a map application that visually indicates passable roads and recommended routes along the route. Furthermore, the device uses voice navigation to provide appropriate guidance to the user, and the emotional engine supports the device to ensure a safe and secure journey.

[0981] As a concrete example, consider an evacuation scenario during a disaster. After a disaster occurs, the server collects information in real time from public institution APIs, quickly assesses reliability, and determines passable roads. It then calculates the optimal route to the nearest evacuation shelter, and if the user feels anxious, it provides a less stressful route. The device receives this information and provides voice guidance and a map display, guiding the user safely to the evacuation shelter. In this way, the invention supports quick and reliable evacuation while maintaining the user's sense of security, even during a disaster.

[0982] An example prompt is:

[0983] "Consider a scenario where a user needs to evacuate early in the morning. A large earthquake has occurred in the area and the user needs to move to a shelter immediately. Based on the user's emotions, suggest a safe and secure route. Provide appropriate navigation support methods, especially considering the user's anxiety."

[0984] By implementing the system in this way, it will be possible to provide fast and reliable traffic information during disasters and navigation that takes user emotions into consideration. It will also provide specialized functions for autonomous vehicles, realizing travel that ensures a sense of security for passengers.

[0985] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0986] Step 1:

[0987] The server collects road condition data from public APIs and private websites. Specifically, it obtains real-time road information through APIs and also collects necessary information using web scraping tools. This allows for the centralized collection of up-to-date data from various sources. Response data from APIs and data obtained through scraping are used as input, and the collected raw data is generated as output.

[0988] Step 2:

[0989] The server preprocesses the collected raw data by converting it into a common JSON format and filtering out incomplete and duplicate data, resulting in a clean dataset for smoother subsequent processing. It uses the collected raw data as input and generates formatted clean data as output.

[0990] Step 3:

[0991] The server evaluates the reliability of the preprocessed data. Specifically, it scores the data based on its source, history, and update frequency, and filters out data with low reliability. This allows only highly reliable data to proceed to the next step. It uses formatted clean data as input and generates data with a reliability evaluation as output.

[0992] Step 4:

[0993] The server determines whether roads are passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (e.g., Scikit-learn or TensorFlow) to determine whether a road is passable. This enables highly reliable determination based on the latest road conditions. It uses the reliability-evaluated data as input and generates passable road information as output.

[0994] Step 5:

[0995] The server calculates the optimal route based on passable road information. Specifically, it uses Dijkstra's algorithm and A-search algorithm to determine the optimal route, taking real-time traffic congestion information into consideration. Passable road information is used as input, and the calculated optimal route information is generated as output.

[0996] Step 6:

[0997] The device acquires the user's emotional information. Specifically, it analyzes the user's voice and facial expressions using the camera and microphone of smart glasses or a smartphone to recognize emotions. It uses the user's voice data and image data as input and generates emotional information as output.

[0998] Step 7:

[0999] The server recalculates the optimal route based on the user's emotional information. Specifically, it analyzes the acquired emotional information and recalculates the optimal route to provide a route that is less stressful for the user. It uses the user's emotional information and existing optimal route information as input and generates adjusted optimal route information as output.

[1000] Step 8:

[1001] The device displays the calculated optimal route information in a user-friendly format. Specifically, the device reflects the route information in a map application and provides appropriate guidance to the user using a voice navigation function. The device uses the adjusted optimal route information as input and generates route information and voice guidance displayed on the user interface as output.

[1002] 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.

[1003] 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.

[1004] 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.

[1005] [Third embodiment]

[1006] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1007] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1008] 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).

[1009] 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.

[1010] 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.

[1011] 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).

[1012] 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.

[1013] 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.

[1014] 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.

[1015] 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.

[1016] 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.

[1017] 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."

[1018] The system of this invention is an advanced information collection and analysis system for presenting passable roads in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates the reliability of the data, and then provides optimal route information.

[1019] Program processing explanation

[1020] 1. Data Collection

[1021] server

[1022] The server sends requests to API endpoints of public agencies to obtain the latest road condition data, scrapes private traffic information providers to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[1023] 2. Data Preprocessing

[1024] server

[1025] The server converts the collected data from various sources into a common format, for example, unifying the acquired data into JSON format, and also filters out incomplete, incorrect, and duplicate data to generate a clean dataset.

[1026] 3. Reliability evaluation

[1027] server

[1028] The server evaluates the reliability of the preprocessed data by scoring each information source based on its past history and frequency of information updates. For example, a source with a high level of accuracy in the past is given a high reliability score.

[1029] 4. Determining whether a road is passable

[1030] server

[1031] The server determines which roads are passable and which are not, based on reliable data, using machine learning models, taking into account, for example, past traffic conditions and current traffic congestion information.

[1032] 5. Optimal Route Calculation

[1033] server

[1034] The server then calculates the optimal route based on the results of the assessment. This route calculation takes into account the shortest route from the current location to the destination, evacuation routes, and logistics routes. It also incorporates real-time traffic congestion information.

[1035] 6. Information provision

[1036] server

[1037] The server generates the calculated optimal route information in a user-friendly format and provides it to the device, for example, by distributing the route information through an API.

[1038] 7. User Presentation

[1039] Terminal

[1040] The user's smartphone, navigation system, or other device receives the route information sent from the server and visually displays it, allowing the user to check passable routes on a map.

[1041] Specific examples

[1042] Example 1: Moving to a shelter

[1043] server

[1044] The server collects road condition data from various sources immediately after a disaster occurs and generates clean data.

[1045] Reliability assessment is performed based on clean data to determine whether roads are passable.

[1046] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated.

[1047] The calculation results are sent to the user's device via API.

[1048] Terminal

[1049] The device reflects the received route information in the map app and displays to the user the "passable route from the current location to the nearest evacuation shelter."

[1050] User

[1051] Users can follow the route displayed on their smartphone to safely reach an evacuation shelter.

[1052] Example 2: Transporting goods

[1053] server

[1054] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[1055] Logistics routes are determined based on highly reliable data.

[1056] Calculate the optimal route to your destination while taking traffic congestion information into account.

[1057] The calculated route information is provided to the logistics company's terminal via API.

[1058] Terminal

[1059] The logistics company's terminal displays the received route information on a navigation system and provides instructions to the driver.

[1060] User (logistics company)

[1061] Drivers can follow the route displayed on the terminal to transport goods quickly and safely to their destination.

[1062] In this way, the system of the present invention quickly provides highly reliable information on passable roads in the event of a disaster, and is of great help in smoothly carrying out restoration and evacuation activities.

[1063] The processing flow will be explained below.

[1064] Step 1: Data collection

[1065] server

[1066] The server sends an HTTP GET request to the public institution's API to obtain the latest road condition data, and performs authentication using the API key.

[1067] Scrape pages from private traffic information providers and extract real-time road condition data.

[1068] Traffic information data provided by telecommunications companies is obtained through a dedicated API.

[1069] Step 2: Data Preprocessing

[1070] server

[1071] The server converts the collected data into a common JSON format. For example, it converts XML data obtained from a public institution's API into JSON.

[1072] Filter incomplete and duplicate data from collected data to generate a clean dataset.

[1073] The converted data is stored in a temporary database.

[1074] Step 3: Reliability assessment

[1075] server

[1076] The server evaluates the reliability of the preprocessed data, scoring each information source based on its past history and frequency of updates.

[1077] The reliability score is calculated using a specific algorithm (e.g., a points system based on past accuracy and update frequency).

[1078] Unreliable data is filtered out and only reliable data is passed on to the next step.

[1079] Step 4: Determine whether roads are passable

[1080] server

[1081] The server runs machine learning models using reliable data to determine which roads are passable and which are not.

[1082] The machine learning model takes into account past traffic history and current traffic congestion data to predict whether a route can be passed.

[1083] The judgment results are stored in a database.

[1084] Step 5: Calculate the optimal route

[1085] server

[1086] The server runs an algorithm to calculate the optimal route based on the information about passable roads, such as Dijkstra's algorithm or A-search algorithm.

[1087] By incorporating real-time traffic congestion information, the optimal route is calculated to avoid unnecessary delays.

[1088] The optimal route information will be stored in a database and made accessible via API.

[1089] Step 6: Provide information

[1090] server

[1091] The server generates the calculated optimal route information in a user-friendly format and provides it to the device via an API.

[1092] The API processes route information requests and responds in JSON format.

[1093] The response includes roads that are passable, roads to avoid, and recommended routes.

[1094] Step 7: Display information

[1095] Terminal

[1096] The terminal analyzes the route information received from the server and displays it on the user interface.

[1097] The route is reflected in the map application, visually indicating navigable roads along the route and recommended routes.

[1098] If necessary, the voice navigation function will provide route guidance.

[1099] Step 8: User interaction

[1100] User

[1101] The user checks the passable routes displayed on the terminal and selects a route if necessary.

[1102] The user follows the displayed route to their destination, for example, to a safe evacuation shelter in an emergency.

[1103] Example 1

[1104] 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."

[1105] During disasters, it has been difficult to quickly and accurately grasp real-time road conditions and provide optimal passable routes. With conventional systems, data from different sources is fragmented and inconsistent, making it difficult to obtain reliable information. Furthermore, data preprocessing and reliability assessment are insufficient, leading to inaccurate determinations of passable roads. Furthermore, optimal route calculations do not adequately reflect real-time conditions, making it impossible to provide practical information to users.

[1106] 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.

[1107] In this invention, the server includes means for collecting road condition data from information sources, means for converting the collected data into a common format and cleaning it, means for evaluating the reliability of the preprocessed data, means for determining passable roads using a machine learning model based on the reliability-evaluated data, means for calculating an optimal route from the current location to the destination based on the determined passable road information, and means for providing the calculated optimal route information to the terminal. This allows for the rapid provision of reliable passable road information even during a disaster, enabling users to reach their destination safely and efficiently.

[1108] "Source" refers to the organization or institution that provides road condition data, or the API or website from which that data can be obtained.

[1109] "Road condition data" refers to real-time information related to roads, such as road passability, traffic congestion information, accident information, and road closures due to disasters.

[1110] "Collection Method" refers to the method or process used to obtain road condition data from a source, such as sending an API request or web scraping.

[1111] "Preprocessing" refers to the process of converting collected data into a common format and removing erroneous or incomplete data.

[1112] "Credibility assessment tools" refer to methods and processes for assessing the reliability of collected data, including, for example, scoring each source based on its past history and update frequency.

[1113] A "machine learning model" is an algorithm or system used by a computer to learn from large amounts of data and perform a specific task (in this case, determining which roads are passable).

[1114] "Means for determining passable roads" refers to a method or process for determining which roads are passable using reliability-assessed data.

[1115] "Optimal route calculation means" refers to a method or process for calculating the optimal route from the current location to the destination based on determined passable road information.

[1116] "Providing means" refers to the method or process for transmitting the calculated optimal route information to the terminal used by the user.

[1117] This invention is a system for providing passable road information quickly and accurately in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates its reliability, and then provides optimal route information.

[1118] Hardware and Software

[1119] server

[1120] The server collects road condition data from multiple sources. Specifically, it sends HTTP requests to API endpoints of public agencies to obtain the latest data. It also scrapes traffic information sites using the Python library BeautifulSoup to collect real-time data. Traffic information data from telecommunications companies is also obtained via FTP and saved in local storage.

[1121] The server loads the collected data into a Pandas DataFrame and converts it into a unified format. Next, it performs data cleaning, filtering out incomplete and duplicate data, and generating a clean dataset. This data cleaning process is performed using Python's Pandas and NumPy.

[1122] For reliability evaluation, the scikit-learn library is used to perform scoring based on past history and information update frequency. Based on the evaluation results, a machine learning model (using, for example, TensorFlow or PyTorch) is used to determine whether the road is passable.

[1123] To calculate the optimal route, a road network graph is constructed and the optimal route from the current location to the destination is calculated using the Dijkstra algorithm and the A algorithm. The calculation results are saved in JSON format and provided to the terminal via an API. The API is implemented using Flask and FastAPI.

[1124] Terminal

[1125] The terminals include smartphones and navigation systems. These terminals are equipped with software to receive route information sent from the server and display it on a map application. For example, the terminals use Google Maps or Mapbox SDK to display the route on a map. The terminals provide a user-friendly interface, allowing users to easily check the route information.

[1126] User

[1127] Users use this system to reach their destination safely and efficiently in the event of a disaster. They check real-time passable route information via their smartphone or navigation system and follow the instructions.

[1128] Specific examples

[1129] Example 1: Moving to a shelter

[1130] Immediately after a disaster occurs, the server collects road condition data from various sources, cleans the data, and then performs reliability evaluation to determine which roads are passable.

[1131] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated and sent to the user's device via an API.

[1132] The user follows the route displayed on their smartphone to reach the evacuation shelter. For example, if the user types "Tell me the best route to get to the evacuation shelter," the server will instantly calculate and provide the best route.

[1133] Example 2: Transporting goods

[1134] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies, and then determines logistics routes based on highly reliable data.

[1135] Taking traffic congestion information into account, the system calculates the optimal route to the destination and provides the results to the logistics company's terminal via an API.

[1136] Logistics companies transport goods quickly and safely by following the route displayed on the terminal. For example, when a driver types in "What is the best route to my destination?", the server quickly provides the optimal route.

[1137] In this way, the system of the present invention provides highly reliable information about passable roads in the event of a disaster, enabling users to reach their destination safely and efficiently.

[1138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1139] Step 1:

[1140] Data collection

[1141] server

[1142] The server collects road condition data from information sources. Specifically, it sends HTTP requests to public agency API endpoints to obtain the latest data. It also accesses private traffic information providers' websites using a scraping tool to extract text data. It also downloads traffic information data provided by telecommunications companies via FTP and stores it in local storage.

[1143] Input: Public API URL, private site URL, telecommunications company data file

[1144] Output: Raw data (JSON format, text data, binary data)

[1145] Specific behavior:

[1146] The server periodically sends API requests and stores the JSON data received as HTTP responses locally.

[1147] Use a tool such as BeautifulSoup to scrape the HTML page and extract the required text information.

[1148] Establish an FTP connection and download the traffic information data file.

[1149] Step 2:

[1150] Data Preprocessing

[1151] server

[1152] The server converts the collected data into a common format and cleans it. Using the Python Pandas library, the data obtained from each source is loaded into a DataFrame and unified into a common column structure. Next, the data is cleaned to remove incomplete and duplicate data.

[1153] Input: Raw data (JSON format, text data, binary data)

[1154] Output: Preprocessed common format data (DataFrame or JSON format)

[1155] Specific behavior:

[1156] Read the data using Pandas' read_json() or read_csv() functions.

[1157] Perform data cleaning using the dropna() and drop_duplicates() functions.

[1158] Save the clean data using the to_json() method.

[1159] Step 3:

[1160] Reliability evaluation

[1161] server

[1162] The server scores the preprocessed data to evaluate its reliability. It calculates a score for each information source based on its past history and update frequency, and prioritizes scores for highly reliable data. The server uses the scikit-learn library to evaluate reliability.

[1163] Input: Preprocessed common format data (DataFrame or JSON format)

[1164] Output: Data with confidence scores (DataFrame or JSON format)

[1165] Specific behavior:

[1166] The past data history and update frequency of each source is obtained from the database.

[1167] Calculate reliability scores using scikit-learn's KNeighborsClassifier or a custom scoring function.

[1168] Add and store a confidence score to the data.

[1169] Step 4:

[1170] Determining passable roads

[1171] server

[1172] The server uses the reliability-assessed data to determine whether roads are passable using a machine learning model. Specifically, it loads a model trained with TensorFlow or PyTorch and uses the data as input to determine whether a road is passable.

[1173] Input: Data with confidence scores (DataFrame or JSON format)

[1174] Output: Road data (DataFrame or JSON format) for which passability has been determined

[1175] Specific behavior:

[1176] Load a trained machine learning model.

[1177] Input data into the model and obtain labels indicating whether the road is passable or not.

[1178] The judgment result is added to the data and saved.

[1179] Step 5:

[1180] Optimal route calculation

[1181] server

[1182] The server then calculates the optimal route from the current location to the destination based on the results of the assessment, using the Dijkstra algorithm and the A algorithm, and taking real-time traffic congestion information into account.

[1183] Input: Road data (DataFrame or JSON format) for which passability is determined

[1184] Output: Optimal route information (JSON format)

[1185] Specific behavior:

[1186] A road network graph is constructed, and passability and traffic condition costs are set for each edge.

[1187] Finding the shortest path using the NetworkX library.

[1188] Save the optimal route information in JSON format.

[1189] Step 6:

[1190] Providing information

[1191] server

[1192] The server provides the calculated optimal route information through an API, and returns the latest route information in JSON format in response to a user request.

[1193] Input: User request

[1194] Output: Optimal route information (JSON format)

[1195] Specific behavior:

[1196] Build API endpoints using Flask and FastAPI.

[1197] Returns pre-calculated route information based on user requests.

[1198] Step 7:

[1199] What the user sees

[1200] Terminal

[1201] The device receives the route information sent from the server and displays it in the map app. It plots the route on a map using Google Maps or Mapbox SDK, providing a visual representation to the user.

[1202] Input: Optimal route information received from the server (JSON format)

[1203] Output: Route information plotted on a map

[1204] Specific behavior:

[1205] The terminal parses the received JSON data.

[1206] Plot your data on a map using the Google Maps or Mapbox SDK.

[1207] Users can check the route on the map and travel safely.

[1208] (Application example 1)

[1209] 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."

[1210] The present invention solves the problem of the difficulty of providing quick and accurate information on passable roads during disasters. Furthermore, there is a need for a system that enables autonomous vehicles to travel safely and efficiently based on that information.

[1211] 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.

[1212] In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for providing the calculated optimal route information to the autonomously driven vehicle, and means for controlling the vehicle based on the route information provided to the autonomously driven vehicle. This enables the autonomously driven vehicle to select and travel a safe and optimal route even during a disaster.

[1213] "Sources" refer to the origins of various publicly available data, including APIs of public institutions and private sites.

[1214] "Road condition data" is data that indicates whether roads are passable, traffic congestion information, traffic accident information, weather conditions, and the like.

[1215] "Preprocessing" refers to the process of standardizing collected raw data into a certain format and removing incomplete or incorrect data to generate a clean dataset.

[1216] "Credibility assessment" refers to the process of assessing the accuracy and reliability of data based on the source's past history and frequency of data updates.

[1217] "Passable roads" refer to roads that are determined to be passable even in the event of a disaster based on the results of data analysis.

[1218] The "optimal route" refers to the shortest and safest route from the current location to the destination, calculated by the program.

[1219] "Autonomous vehicle" refers to a vehicle that can be operated and driven by its own system.

[1220] "Route information" is data about the calculated optimal travel route, and is used in maps and navigation systems.

[1221] "Control means" refers to the function of controlling the movement of the vehicle based on the route information provided.

[1222] This invention is a system for autonomous vehicles to safely and quickly select and move along optimal routes during disasters. The system collects road condition data from information sources, preprocesses it, evaluates its reliability, determines which roads are passable, calculates the optimal route, and provides this information to autonomous vehicles to reflect in their control.

[1223] Hardware and software used

[1224] Hardware:

[1225] Embedded systems for autonomous vehicles (navigation systems, communication modules, etc.)

[1226] software:

[1227] Python

[1228] requests library (for API requests)

[1229] pandas library (for data preprocessing)

[1230] scikit-learn library (for machine learning modeling)

[1231] geopy library (for geographic information processing)

[1232] Details of data processing and calculation

[1233] The server collects road condition data from public APIs and private websites. It then standardizes the collected data into JSON format and removes incomplete or incorrect data to generate a clean dataset. Based on this dataset, the reliability of the source is evaluated using its past history and the frequency of data updates.

[1234] Using the evaluated data, a machine learning model (e.g., random forest) is used to determine whether a road is passable, taking into account historical traffic information and weather conditions. Next, the optimal route from the current location to the destination is calculated based on the passable road information.

[1235] The calculated optimal route information is provided to the autonomous vehicle, which then controls the vehicle based on that route information, enabling safe and rapid movement even in the event of a disaster.

[1236] Specific examples

[1237] Moving to a shelter:

[1238] Immediately after a disaster occurs, the server collects the latest road condition data from various sources, preprocesses it, and evaluates its reliability. It then determines which roads are passable and calculates the optimal route to the nearest evacuation shelter. This route information is provided to the autonomous vehicle, which then travels safely to the shelter based on the instructions.

[1239] Transport of goods:

[1240] The server collects real-time data and generates clean data, then performs reliability assessment and provides passable road information for logistics companies. After route calculation, it provides the optimal route information to autonomous vehicles, which then transport goods to their destinations quickly and safely.

[1241] Example prompts to input to the generative AI model

[1242] AI Assistant, please calculate the optimal route for safe and fast autonomous driving to an evacuation shelter based on the current damage situation caused by the earthquake, and update this information in the vehicle system. The current location is Tokyo Station, and the destination is an evacuation shelter within Tokyo.

[1243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1244] Step 1:

[1245] The server collects road condition data from sources. Specifically, it sends requests to API endpoints of public agencies to obtain the latest road condition data. It also scrapes private traffic information providers to collect real-time road information. It also obtains traffic information data provided by telecommunications companies. The input is the API request or scraping, and the output is the collected road condition data.

[1246] Step 2:

[1247] The server preprocesses the collected data. Specifically, it converts data from each source into a common JSON format and filters out incomplete, incorrect, and duplicate data to generate a clean dataset. The input is the raw collected data, and the output is the clean dataset.

[1248] Step 3:

[1249] The server evaluates the reliability of the preprocessed data. Specifically, it scores each information source based on its past history and the frequency of information updates. For example, it assigns a high reliability score to information sources that have been highly accurate in the past. The input is a clean dataset, and the output is reliability-evaluated data.

[1250] Step 4:

[1251] The server determines whether a road is passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (such as random forest) to determine whether the road is passable. This determination also takes into account past and current traffic information and weather conditions. The input is reliability-evaluated data, and the output is road information determined to be passable.

[1252] Step 5:

[1253] The server calculates the optimal route based on passable road information. Specifically, it calculates the shortest route from the current location to the destination, as well as evacuation routes and logistics routes. It also incorporates real-time traffic congestion information. The input is passable road information and the coordinates of the current location and destination, and the output is the optimal route information.

[1254] Step 6:

[1255] The server provides the calculated optimal route information to the autonomous vehicle. Specifically, it sends the route information to the autonomous vehicle's embedded system through an API. The input is the optimal route information, and the output is the route information received by the autonomous vehicle.

[1256] Step 7:

[1257] The embedded system of an autonomous vehicle reflects the provided route information and controls the vehicle. Specifically, the route is displayed on the navigation system, and the autonomous driving system operates according to that route. The input is the route information provided by the server, and the output is the vehicle's movement to reach the destination safely and quickly.

[1258] 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.

[1259] The system of this invention is an advanced information collection and analysis system that presents passable roads in the event of a disaster, recognizes the user's emotions, and adjusts navigation accordingly. This system collects road condition data from sources, preprocesses them, and evaluates their reliability before presenting passable roads and optimal routes. Furthermore, it is equipped with an emotion engine that realizes optimal navigation based on the user's emotions.

[1260] Program processing explanation

[1261] 1. Data Collection

[1262] server

[1263] The server obtains the latest road condition data from public agency APIs, scrapes private traffic information websites to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[1264] 2. Data Preprocessing

[1265] server

[1266] The server converts the collected data into a common JSON format and filters out incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[1267] 3. Reliability evaluation

[1268] server

[1269] The server evaluates the reliability of each information source based on the preprocessed data. It scores the information using a specific algorithm, taking into account past history and frequency of information updates. Unreliable data is filtered out, and only reliable data is allowed to proceed to the next step.

[1270] 4. Determining whether a road is passable

[1271] server

[1272] The server runs machine learning models using reliable data to determine which roads are passable and which are not, and the results are stored in a database.

[1273] 5. Optimal Route Calculation

[1274] server

[1275] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm, and incorporates real-time traffic information. The optimal route information is stored in a database and can be accessed via API.

[1276] 6. Emotion recognition

[1277] Terminal

[1278] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses the user's voice input and facial recognition to identify emotions. For example, if the user is anxious or nervous, that information is reflected in the navigation.

[1279] 7. Route Adjustment

[1280] server

[1281] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method, for example, proposing a route that avoids roads that are likely to cause stress to the user.

[1282] 8. Information provision

[1283] server

[1284] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[1285] 9. Information display

[1286] Terminal

[1287] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[1288] Specific examples

[1289] Example 1: Moving to a shelter

[1290] server

[1291] Immediately after a disaster occurs, the server collects road condition data from each source and generates clean data.

[1292] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[1293] In addition, it receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[1294] The calculation results are sent to the user's device via API.

[1295] Terminal

[1296] The device reflects the received route information in the map app and displays the user a passable route from their current location to the nearest evacuation shelter. Using information from the emotion engine, the device provides stable voice guidance.

[1297] User

[1298] Users can follow the route displayed on their smartphone and move safely to a shelter. With the support of the emotion engine, users can move with peace of mind.

[1299] Example 2: Transporting goods

[1300] server

[1301] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[1302] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[1303] It receives information from the emotion engine and provides routes that reduce driver stress.

[1304] The calculated route information is provided to the logistics company's terminal via API.

[1305] Terminal

[1306] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[1307] User (logistics company)

[1308] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[1309] In this way, the system of the present invention provides highly reliable traffic information during disasters, recognizes the user's emotions, and provides optimal navigation, thereby greatly assisting in smoothly carrying out recovery and evacuation activities.

[1310] The processing flow will be explained below.

[1311] Step 1: Data collection

[1312] server

[1313] The server sends an HTTP GET request to a public agency's API to retrieve the latest road condition data, for example, using the https: / / api.trafficinfo.gov endpoint.

[1314] Scrape private traffic information websites and extract road condition data using HTML analysis tools, such as libraries like BeautifulSoup.

[1315] Traffic information data provided by telecommunications companies is acquired through a dedicated API, and the acquired data is updated in real time.

[1316] Step 2: Data Preprocessing

[1317] server

[1318] The server converts the collected data into a common JSON format, for example using the xmltodict library to convert data in XML format into JSON.

[1319] Regular expressions are used to shape the collected data, filtering out incomplete and duplicate data and generating a clean dataset.

[1320] The transformed data is stored as a clean dataset in a temporary database.

[1321] Step 3: Reliability assessment

[1322] server

[1323] The server considers the past reliability history and update frequency of each source to assess the reliability of the pre-processed data, using an algorithm (e.g., weighted average) to assign a reliability score to each source.

[1324] Data with low confidence scores are filtered out and only data with high scores proceeds to the next step.

[1325] The evaluation results are stored in a database.

[1326] Step 4: Determine whether roads are passable

[1327] server

[1328] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, for example, using a random forest model.

[1329] Input data includes traffic history information and current congestion data.

[1330] The judgment results are stored in a database.

[1331] Step 5: Calculate the optimal route

[1332] server

[1333] The server executes an algorithm (for example, Dijkstra's algorithm or A-search algorithm) that calculates the optimal route between specified points based on passable road information.

[1334] By incorporating real-time traffic congestion information, the shortest route is calculated to avoid unnecessary delays.

[1335] The optimal route information will be stored in a database and made accessible via API.

[1336] Step 6: Emotion Recognition

[1337] Terminal

[1338] The device uses the user's voice input and camera to provide data to the emotion engine, for example, processing audio data from the user speaking into a microphone and facial expression data captured by a camera.

[1339] The emotion engine uses voice recognition software and facial recognition algorithms to identify the user's emotions (e.g., anxiety, relief, irritation).

[1340] Step 7: Route Adjustment

[1341] server

[1342] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. For example, for a user who is prone to anxiety, it suggests a route that eliminates roads that should be avoided.

[1343] The recalculated route information is stored in a database and provided to the device via an API.

[1344] Step 8: Provide information

[1345] server

[1346] The server generates an optimal route that reflects the emotion information in a user-friendly format and provides it to the device via an API, for example, by returning the route information in JSON format.

[1347] Step 9: Display Information

[1348] Terminal

[1349] The device analyzes the route information received from the server and displays it in a map application, with a user interface that visually indicates passable roads and the optimal route.

[1350] The device uses a voice navigation function to provide the user with appropriate route guidance, which is based on the user's emotions.

[1351] Step 10: User interaction

[1352] User

[1353] The user checks the passable routes displayed on the terminal and selects a route as necessary.

[1354] Users can follow the displayed route to their destination safely and comfortably. With the support of the emotion engine, they can travel with peace of mind.

[1355] Example 2

[1356] 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."

[1357] Conventional navigation systems are sometimes unable to accurately grasp real-time road conditions during disasters, limiting their ability to suggest optimal routes. Furthermore, they are unable to provide navigation that takes into account the user's emotional state, and do not take into consideration routes that are likely to cause stress to the user. It is necessary to solve these problems and realize fast and safe evacuation and transportation of supplies during disasters.

[1358] 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.

[1359] In this invention, the server includes means for collecting road condition data from an information source, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for recalculating the optimal route based on the recognized user emotion information, and means for providing the calculated optimal route information to the terminal. This makes it possible to propose an optimal route taking the user's emotional state into consideration, thereby enabling quick and safe evacuation and transportation of supplies in the event of a disaster.

[1360] "Information sources" are data sources that are the basis for collecting data, such as public agencies, private companies, and communication companies that provide road condition data.

[1361] "Road condition data" is information showing the latest road conditions, such as whether the road is passable, traffic congestion information, traffic accidents, and damage caused by disasters.

[1362] "Preprocessing" is the process of converting collected data into a common format and filtering out incomplete or duplicate data.

[1363] "Reliability assessment" is a method for assessing the accuracy and reliability of collected data and ensuring data quality. This assessment includes past history and frequency of information updates.

[1364] A "passable road" is one that is clear of obstacles and safe for vehicles and pedestrians to travel on. This determination is made using machine learning models.

[1365] The "optimal route" refers to the most efficient and safest route to the user's destination, calculated based on real-time road conditions and the user's emotional state.

[1366] "User emotion" refers to the psychological state, such as anxiety, tension, or stress, felt by the user, as identified by the user's voice input or facial recognition.

[1367] "Emotion recognition" is the process of identifying a user's emotions from their facial expressions and voice, and reflecting this in navigation.

[1368] "Recalculation" is a process of recalculating existing route calculation results based on the recognized user's emotions and proposing a route that is more suitable for the user.

[1369] A "terminal" is a device used by a user (such as a smartphone or tablet) that receives and displays optimal route information.

[1370] The system of the present invention is an advanced information collection and analysis system that collects road condition data from various information sources, recognizes the emotional state of the user, and provides optimal navigation. Specific embodiments are described below.

[1371] Data collection

[1372] server

[1373] The server obtains the latest road condition data through public agency APIs. It also accesses private traffic information providers and collects real-time road information using web scraping technology. This process uses Python libraries such as BeautifulSoup and Selenium. It also obtains traffic information data from telecommunications companies' data platforms. This data is then stored in a temporary database.

[1374] Data Preprocessing

[1375] server

[1376] The server converts the collected data into a common JSON format, then uses the Python pandas library to filter incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[1377] Reliability evaluation

[1378] server

[1379] The server evaluates the reliability of each information source based on the preprocessed data. The evaluation takes into account past data history and information update frequency, and uses algorithms such as the weighted average method. Unreliable data is filtered out, and only reliable data is advanced to the next step.

[1380] Determining passable roads

[1381] server

[1382] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, using libraries such as TensorFlow and PyTorch. The results are then stored in a database.

[1383] Optimal route calculation

[1384] server

[1385] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm. It also takes into account real-time traffic congestion information. The optimal route information is stored in a database and can be accessed via API.

[1386] emotion recognition

[1387] Terminal

[1388] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine identifies emotions through the user's voice input and facial recognition. For example, if the user is feeling anxious or nervous, that information is reflected in the navigation. Emotion recognition uses the Python open source library OpenCV and Emotion API.

[1389] Route Adjustment

[1390] server

[1391] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. It suggests routes that avoid roads that are likely to cause stress to the user, for example, prioritizing quiet roads and roads with good scenery.

[1392] Providing information

[1393] server

[1394] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[1395] Information display

[1396] Terminal

[1397] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[1398] Specific examples

[1399] Example 1: Moving to a shelter

[1400] server

[1401] Immediately after a disaster occurs, road condition data is collected from various sources and clean data is generated.

[1402] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[1403] It receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[1404] The calculation results are sent to the user's device via API.

[1405] Terminal

[1406] The device reflects the received route information in the map app and displays a passable route from the current location to the nearest evacuation shelter. It also uses information from the emotion engine to provide stable voice guidance.

[1407] User

[1408] Users can safely move to a shelter by following the route displayed on their smartphone. With the support of the emotion engine, users can move with peace of mind.

[1409] Example 2: Transporting goods

[1410] server

[1411] It collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[1412] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[1413] It receives information from the emotion engine and provides routes that reduce driver stress.

[1414] Route information calculated through the API is provided to the logistics company's terminal.

[1415] Terminal

[1416] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[1417] User (logistics company)

[1418] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[1419] These concrete examples show that the system of the present invention can provide highly reliable traffic information during disasters, recognize the user's emotions, and provide optimal navigation, thereby being of great help in smoothly carrying out recovery and evacuation activities.

[1420] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1421] Step 1: Data collection

[1422] server

[1423] The server collects road condition data. As input, it uses API endpoints from public agencies, URLs from private traffic information providers, and data platforms from telecommunications companies. Specifically, it obtains real-time data through web scraping using the Python library BeautifulSoup and Selenium. This collected raw data is stored in a temporary database. The output is the collected, unprocessed road condition data.

[1424] Step 2: Data Preprocessing

[1425] server

[1426] The server converts the collected raw data into a common JSON format. The input is the raw data collected in step 1. Specifically, it uses the Python pandas library to filter incomplete and duplicate data and generate a clean dataset. This preprocessing imputes missing data and corrects outliers. The output is a clean dataset, which is stored in a temporary database.

[1427] Step 3: Reliability assessment

[1428] server

[1429] The server evaluates the reliability of the preprocessed data. The input is the clean dataset generated in step 2. Specifically, it calculates the reliability score of each information source using algorithms such as the weighted average method based on past data history and information update frequency. Data with low reliability is filtered out. The output is the reliability-evaluated data.

[1430] Step 4: Determine whether roads are passable

[1431] server

[1432] The server determines which roads are passable based on the reliability-evaluated data. The input is the data evaluated in step 3. Specifically, it uses a machine learning model (e.g., TensorFlow or PyTorch) to analyze the data and determine which roads are passable and which are not. The results of this determination are stored in a database. The output is passable road information.

[1433] Step 5: Calculate the optimal route

[1434] server

[1435] The server calculates the optimal route based on passable road information. The input is the passable road information determined in step 4. Specifically, it calculates the optimal route using Dijkstra's algorithm and A-search algorithm together with real-time traffic congestion information. The calculation results are stored in a database and made accessible via API. The output is the optimal route information.

[1436] Step 6: Emotion Recognition

[1437] Terminal

[1438] The device uses an emotion engine to recognize the user's emotions. Inputs include the user's voice input and facial recognition data. Specific operations include analyzing the user's emotions using Python's OpenCV and Emotion API. For example, it can identify whether the user is feeling anxious or nervous based on their voice tone and facial expression. The output is the user's emotional information.

[1439] Step 7: Route Adjustment

[1440] server

[1441] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. The input is the optimal route information calculated in step 5 and the user's emotional information obtained in step 6. Specifically, the server takes the emotional data into consideration and recalculates a route that is less stressful. For example, it selects quiet roads or roads with beautiful scenery. The output is the adjusted optimal route information.

[1442] Step 8: Provide information

[1443] server

[1444] The server generates the adjusted optimal route information in a user-friendly format and provides it to the device via the API. The input is the optimal route information adjusted in step 7. Specifically, the server formats the information in an easy-to-understand format and sends it to the device via the API. The output is the optimal route information provided to the device.

[1445] Step 9: Display Information

[1446] Terminal

[1447] The terminal analyzes the optimal route information provided by the server and displays it on the user interface. The input is the optimal route information provided in step 8. Specifically, the route information is reflected in the map application and visually shown to the user. Also, real-time guidance is provided using the voice navigation function. The output is the route information displayed on the user interface and voice guidance.

[1448] (Application example 2)

[1449] 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."

[1450] Conventional navigation systems have difficulty providing fast and reliable travel information during disasters. Furthermore, they are unable to provide navigation that takes into account the user's emotional factors, making it difficult to reduce the stress and anxiety users feel while traveling. Therefore, there is a need for technology that provides safe routes that are passable even during disasters, and also provides comfortable navigation that takes into account the user's emotions.

[1451] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for acquiring user emotion information and adjusting the optimal route based on the emotion, and means for providing the calculated optimal route information to the terminal. This makes it possible to provide highly reliable traffic information and navigation that takes user emotion into consideration even during a disaster.

[1452] "Information source" refers to a data provider for collecting road condition data provided by public institutions, private sites, etc.

[1453] "Preprocessing" refers to the process of converting collected data into a common format and filtering out incomplete or duplicate data to produce a clean dataset.

[1454] "Reliability assessment" is the process of evaluating and scoring the reliability of collected data, taking into account past history and frequency of information updates.

[1455] A "passable road" is a road that is safe to use and not affected by weather or disasters.

[1456] The "optimal route" is calculated based on passable road information and is the most efficient and safe route to the destination.

[1457] "Emotion information" is data that indicates the user's emotional state, and is information that identifies the user's emotions using voice input or face recognition.

[1458] "Terminal" means a device used by a user to receive and display information, such as a smartphone or smart glasses.

[1459] "Means of collection" refers to the means of obtaining data from public institution APIs and private sites.

[1460] "Preprocessing means" refers to means for converting collected data into a common format and for filtering the data.

[1461] "Means for evaluation" refers to the means for evaluating and scoring the reliability of collected data.

[1462] The "means for determining" refers to a means for determining passable roads based on the reliability-evaluated data.

[1463] The "means for calculating" refers to a means for calculating an optimal route using passable road information.

[1464] The "means for acquiring" refers to a means for acquiring emotion information through a user's voice input or face recognition.

[1465] "Adjustment means" refers to the means for recalculating the optimal route based on the acquired emotional information.

[1466] The "means for providing" refers to the means for transmitting the calculated optimum route information to the terminal and displaying it.

[1467] This invention is an advanced information collection and analysis system that recognizes passable roads and user emotions during disasters and adjusts navigation based on the information. This makes it possible to provide highly reliable traffic information and navigation that takes user emotions into consideration. Specific embodiments for implementing this invention are described below.

[1468] First, the server uses the following hardware and software: Road condition data is collected from public APIs and private sites, and APIs and web scraping tools are used to collect the data. The collected data is preprocessed on the server and converted into a common JSON format. This preprocessing includes filtering incomplete and duplicate data. Next, to evaluate reliability, the server is equipped with a reliability scoring algorithm. This evaluates the reliability of the data based on past history and information update frequency, and filters out unreliable data.

[1469] Based on the reliability-assessed data, a machine learning model (such as Scikit-learn or TensorFlow) is used to determine which roads are passable. The results of this determination are stored in a database, and Dijkstra's algorithm or A-search algorithm is used to calculate the optimal route. The optimal route is calculated, incorporating real-time traffic congestion information, and the results are stored in a database.

[1470] Furthermore, the device is equipped with an emotion engine to acquire the user's emotional information. The emotion engine uses the camera and microphone of the smart glasses or smartphone to analyze the user's voice and facial expressions and recognize emotions in real time. For example, if the user is feeling anxious or nervous, this information is sent to the server, which then recalculates the optimal route. A route that reflects the emotional information is calculated, and the server provides this route information to the device via an API.

[1471] The device displays the received route information in a user-friendly format, including a map application that visually indicates passable roads and recommended routes along the route. Furthermore, the device uses voice navigation to provide appropriate guidance to the user, and the emotional engine supports the device to ensure a safe and secure journey.

[1472] As a concrete example, consider an evacuation scenario during a disaster. After a disaster occurs, the server collects information in real time from public institution APIs, quickly assesses reliability, and determines passable roads. It then calculates the optimal route to the nearest evacuation shelter, and if the user feels anxious, it provides a less stressful route. The device receives this information and provides voice guidance and a map display, guiding the user safely to the evacuation shelter. In this way, the invention supports quick and reliable evacuation while maintaining the user's sense of security, even during a disaster.

[1473] An example prompt is:

[1474] "Consider a scenario where a user needs to evacuate early in the morning. A large earthquake has occurred in the area and the user needs to move to a shelter immediately. Based on the user's emotions, suggest a safe and secure route. Provide appropriate navigation support methods, especially considering the user's anxiety."

[1475] By implementing the system in this way, it will be possible to provide fast and reliable traffic information during disasters and navigation that takes user emotions into consideration. It will also provide specialized functions for autonomous vehicles, realizing travel that ensures a sense of security for passengers.

[1476] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1477] Step 1:

[1478] The server collects road condition data from public APIs and private websites. Specifically, it obtains real-time road information through APIs and also collects necessary information using web scraping tools. This allows for the centralized collection of up-to-date data from various sources. Response data from APIs and data obtained through scraping are used as input, and the collected raw data is generated as output.

[1479] Step 2:

[1480] The server preprocesses the collected raw data by converting it into a common JSON format and filtering out incomplete and duplicate data, resulting in a clean dataset for smoother subsequent processing. It uses the collected raw data as input and generates formatted clean data as output.

[1481] Step 3:

[1482] The server evaluates the reliability of the preprocessed data. Specifically, it scores the data based on its source, history, and update frequency, and filters out data with low reliability. This allows only highly reliable data to proceed to the next step. It uses formatted clean data as input and generates data with a reliability evaluation as output.

[1483] Step 4:

[1484] The server determines whether roads are passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (e.g., Scikit-learn or TensorFlow) to determine whether a road is passable. This enables highly reliable determination based on the latest road conditions. It uses the reliability-evaluated data as input and generates passable road information as output.

[1485] Step 5:

[1486] The server calculates the optimal route based on passable road information. Specifically, it uses Dijkstra's algorithm and A-search algorithm to determine the optimal route, taking real-time traffic congestion information into consideration. Passable road information is used as input, and the calculated optimal route information is generated as output.

[1487] Step 6:

[1488] The device acquires the user's emotional information. Specifically, it analyzes the user's voice and facial expressions using the camera and microphone of smart glasses or a smartphone to recognize emotions. It uses the user's voice data and image data as input and generates emotional information as output.

[1489] Step 7:

[1490] The server recalculates the optimal route based on the user's emotional information. Specifically, it analyzes the acquired emotional information and recalculates the optimal route to provide a route that is less stressful for the user. It uses the user's emotional information and existing optimal route information as input and generates adjusted optimal route information as output.

[1491] Step 8:

[1492] The device displays the calculated optimal route information in a user-friendly format. Specifically, the device reflects the route information in a map application and provides appropriate guidance to the user using a voice navigation function. The device uses the adjusted optimal route information as input and generates route information and voice guidance displayed on the user interface as output.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] [Fourth embodiment]

[1497] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1498] 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.

[1499] 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).

[1500] 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.

[1501] 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.

[1502] 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).

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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."

[1510] The system of this invention is an advanced information collection and analysis system for presenting passable roads in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates the reliability of the data, and then provides optimal route information.

[1511] Program processing explanation

[1512] 1. Data Collection

[1513] server

[1514] The server sends requests to API endpoints of public agencies to obtain the latest road condition data, scrapes private traffic information providers to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[1515] 2. Data Preprocessing

[1516] server

[1517] The server converts the collected data from various sources into a common format, for example, unifying the acquired data into JSON format, and also filters out incomplete, incorrect, and duplicate data to generate a clean dataset.

[1518] 3. Reliability evaluation

[1519] server

[1520] The server evaluates the reliability of the preprocessed data by scoring each information source based on its past history and frequency of information updates. For example, a source with a high level of accuracy in the past is given a high reliability score.

[1521] 4. Determining whether a road is passable

[1522] server

[1523] The server determines which roads are passable and which are not, based on reliable data, using machine learning models, taking into account, for example, past traffic conditions and current traffic congestion information.

[1524] 5. Optimal Route Calculation

[1525] server

[1526] The server then calculates the optimal route based on the results of the assessment. This route calculation takes into account the shortest route from the current location to the destination, evacuation routes, and logistics routes. It also incorporates real-time traffic congestion information.

[1527] 6. Information provision

[1528] server

[1529] The server generates the calculated optimal route information in a user-friendly format and provides it to the device, for example, by distributing the route information through an API.

[1530] 7. User Presentation

[1531] Terminal

[1532] The user's smartphone, navigation system, or other device receives the route information sent from the server and visually displays it, allowing the user to check passable routes on a map.

[1533] Specific examples

[1534] Example 1: Moving to a shelter

[1535] server

[1536] The server collects road condition data from various sources immediately after a disaster occurs and generates clean data.

[1537] Reliability assessment is performed based on clean data to determine whether roads are passable.

[1538] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated.

[1539] The calculation results are sent to the user's device via API.

[1540] Terminal

[1541] The device reflects the received route information in the map app and displays to the user the "passable route from the current location to the nearest evacuation shelter."

[1542] User

[1543] Users can follow the route displayed on their smartphone to safely reach an evacuation shelter.

[1544] Example 2: Transporting goods

[1545] server

[1546] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[1547] Logistics routes are determined based on highly reliable data.

[1548] Calculate the optimal route to your destination while taking traffic congestion information into account.

[1549] The calculated route information is provided to the logistics company's terminal via API.

[1550] Terminal

[1551] The logistics company's terminal displays the received route information on a navigation system and provides instructions to the driver.

[1552] User (logistics company)

[1553] Drivers can follow the route displayed on the terminal to transport goods quickly and safely to their destination.

[1554] In this way, the system of the present invention quickly provides highly reliable information on passable roads in the event of a disaster, and is of great help in smoothly carrying out restoration and evacuation activities.

[1555] The processing flow will be explained below.

[1556] Step 1: Data collection

[1557] server

[1558] The server sends an HTTP GET request to the public institution's API to obtain the latest road condition data, and performs authentication using the API key.

[1559] Scrape pages from private traffic information providers and extract real-time road condition data.

[1560] Traffic information data provided by telecommunications companies is obtained through a dedicated API.

[1561] Step 2: Data Preprocessing

[1562] server

[1563] The server converts the collected data into a common JSON format. For example, it converts XML data obtained from a public institution's API into JSON.

[1564] Filter incomplete and duplicate data from collected data to generate a clean dataset.

[1565] The converted data is stored in a temporary database.

[1566] Step 3: Reliability assessment

[1567] server

[1568] The server evaluates the reliability of the preprocessed data, scoring each information source based on its past history and frequency of updates.

[1569] The reliability score is calculated using a specific algorithm (e.g., a points system based on past accuracy and update frequency).

[1570] Unreliable data is filtered out and only reliable data is passed on to the next step.

[1571] Step 4: Determine whether roads are passable

[1572] server

[1573] The server runs machine learning models using reliable data to determine which roads are passable and which are not.

[1574] The machine learning model takes into account past traffic history and current traffic congestion data to predict whether a route can be passed.

[1575] The judgment results are stored in a database.

[1576] Step 5: Calculate the optimal route

[1577] server

[1578] The server runs an algorithm to calculate the optimal route based on the information about passable roads, such as Dijkstra's algorithm or A-search algorithm.

[1579] By incorporating real-time traffic congestion information, the optimal route is calculated to avoid unnecessary delays.

[1580] The optimal route information will be stored in a database and made accessible via API.

[1581] Step 6: Provide information

[1582] server

[1583] The server generates the calculated optimal route information in a user-friendly format and provides it to the device via an API.

[1584] The API processes route information requests and responds in JSON format.

[1585] The response includes roads that are passable, roads to avoid, and recommended routes.

[1586] Step 7: Display information

[1587] Terminal

[1588] The terminal analyzes the route information received from the server and displays it on the user interface.

[1589] The route is reflected in the map application, visually indicating navigable roads along the route and recommended routes.

[1590] If necessary, the voice navigation function will provide route guidance.

[1591] Step 8: User interaction

[1592] User

[1593] The user checks the passable routes displayed on the terminal and selects a route if necessary.

[1594] The user follows the displayed route to their destination, for example, to a safe evacuation shelter in an emergency.

[1595] Example 1

[1596] 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."

[1597] During disasters, it has been difficult to quickly and accurately grasp real-time road conditions and provide optimal passable routes. With conventional systems, data from different sources is fragmented and inconsistent, making it difficult to obtain reliable information. Furthermore, data preprocessing and reliability assessment are insufficient, leading to inaccurate determinations of passable roads. Furthermore, optimal route calculations do not adequately reflect real-time conditions, making it impossible to provide practical information to users.

[1598] 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.

[1599] In this invention, the server includes means for collecting road condition data from information sources, means for converting the collected data into a common format and cleaning it, means for evaluating the reliability of the preprocessed data, means for determining passable roads using a machine learning model based on the reliability-evaluated data, means for calculating an optimal route from the current location to the destination based on the determined passable road information, and means for providing the calculated optimal route information to the terminal. This allows for the rapid provision of reliable passable road information even during a disaster, enabling users to reach their destination safely and efficiently.

[1600] "Source" refers to the organization or institution that provides road condition data, or the API or website from which that data can be obtained.

[1601] "Road condition data" refers to real-time information related to roads, such as road passability, traffic congestion information, accident information, and road closures due to disasters.

[1602] "Collection Method" refers to the method or process used to obtain road condition data from a source, such as sending an API request or web scraping.

[1603] "Preprocessing" refers to the process of converting collected data into a common format and removing erroneous or incomplete data.

[1604] "Credibility assessment tools" refer to methods and processes for assessing the reliability of collected data, including, for example, scoring each source based on its past history and update frequency.

[1605] A "machine learning model" is an algorithm or system used by a computer to learn from large amounts of data and perform a specific task (in this case, determining which roads are passable).

[1606] "Means for determining passable roads" refers to a method or process for determining which roads are passable using reliability-assessed data.

[1607] "Optimal route calculation means" refers to a method or process for calculating the optimal route from the current location to the destination based on determined passable road information.

[1608] "Providing means" refers to the method or process for transmitting the calculated optimal route information to the terminal used by the user.

[1609] This invention is a system for providing passable road information quickly and accurately in the event of a disaster. This system collects road condition data from multiple sources, preprocesses it, evaluates its reliability, and then provides optimal route information.

[1610] Hardware and Software

[1611] server

[1612] The server collects road condition data from multiple sources. Specifically, it sends HTTP requests to API endpoints of public agencies to obtain the latest data. It also scrapes traffic information sites using the Python library BeautifulSoup to collect real-time data. Traffic information data from telecommunications companies is also obtained via FTP and saved in local storage.

[1613] The server loads the collected data into a Pandas DataFrame and converts it into a unified format. Next, it performs data cleaning, filtering out incomplete and duplicate data, and generating a clean dataset. This data cleaning process is performed using Python's Pandas and NumPy.

[1614] For reliability evaluation, the scikit-learn library is used to perform scoring based on past history and information update frequency. Based on the evaluation results, a machine learning model (using, for example, TensorFlow or PyTorch) is used to determine whether the road is passable.

[1615] To calculate the optimal route, a road network graph is constructed and the optimal route from the current location to the destination is calculated using the Dijkstra algorithm and the A algorithm. The calculation results are saved in JSON format and provided to the terminal via an API. The API is implemented using Flask and FastAPI.

[1616] Terminal

[1617] The terminals include smartphones and navigation systems. These terminals are equipped with software to receive route information sent from the server and display it on a map application. For example, the terminals use Google Maps or Mapbox SDK to display the route on a map. The terminals provide a user-friendly interface, allowing users to easily check the route information.

[1618] User

[1619] Users use this system to reach their destination safely and efficiently in the event of a disaster. They check real-time passable route information via their smartphone or navigation system and follow the instructions.

[1620] Specific examples

[1621] Example 1: Moving to a shelter

[1622] Immediately after a disaster occurs, the server collects road condition data from various sources, cleans the data, and then performs reliability evaluation to determine which roads are passable.

[1623] Based on the results of the assessment, the optimal route to the nearest evacuation shelter is calculated and sent to the user's device via an API.

[1624] The user follows the route displayed on their smartphone to reach the evacuation shelter. For example, if the user types "Tell me the best route to get to the evacuation shelter," the server will instantly calculate and provide the best route.

[1625] Example 2: Transporting goods

[1626] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies, and then determines logistics routes based on highly reliable data.

[1627] Taking traffic congestion information into account, the system calculates the optimal route to the destination and provides the results to the logistics company's terminal via an API.

[1628] Logistics companies transport goods quickly and safely by following the route displayed on the terminal. For example, when a driver types in "What is the best route to my destination?", the server quickly provides the optimal route.

[1629] In this way, the system of the present invention provides highly reliable information about passable roads in the event of a disaster, enabling users to reach their destination safely and efficiently.

[1630] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1631] Step 1:

[1632] Data collection

[1633] server

[1634] The server collects road condition data from information sources. Specifically, it sends HTTP requests to public agency API endpoints to obtain the latest data. It also accesses private traffic information providers' websites using a scraping tool to extract text data. It also downloads traffic information data provided by telecommunications companies via FTP and stores it in local storage.

[1635] Input: Public API URL, private site URL, telecommunications company data file

[1636] Output: Raw data (JSON format, text data, binary data)

[1637] Specific behavior:

[1638] The server periodically sends API requests and stores the JSON data received as HTTP responses locally.

[1639] Use a tool such as BeautifulSoup to scrape the HTML page and extract the required text information.

[1640] Establish an FTP connection and download the traffic information data file.

[1641] Step 2:

[1642] Data Preprocessing

[1643] server

[1644] The server converts the collected data into a common format and cleans it. Using the Python Pandas library, the data obtained from each source is loaded into a DataFrame and unified into a common column structure. Next, the data is cleaned to remove incomplete and duplicate data.

[1645] Input: Raw data (JSON format, text data, binary data)

[1646] Output: Preprocessed common format data (DataFrame or JSON format)

[1647] Specific behavior:

[1648] Read the data using Pandas' read_json() or read_csv() functions.

[1649] Perform data cleaning using the dropna() and drop_duplicates() functions.

[1650] Save the clean data using the to_json() method.

[1651] Step 3:

[1652] Reliability evaluation

[1653] server

[1654] The server scores the preprocessed data to evaluate its reliability. It calculates a score for each information source based on its past history and update frequency, and prioritizes scores for highly reliable data. The server uses the scikit-learn library to evaluate reliability.

[1655] Input: Preprocessed common format data (DataFrame or JSON format)

[1656] Output: Data with confidence scores (DataFrame or JSON format)

[1657] Specific behavior:

[1658] The past data history and update frequency of each source is obtained from the database.

[1659] Calculate reliability scores using scikit-learn's KNeighborsClassifier or a custom scoring function.

[1660] Add and store a confidence score to the data.

[1661] Step 4:

[1662] Determining passable roads

[1663] server

[1664] The server uses the reliability-assessed data to determine whether roads are passable using a machine learning model. Specifically, it loads a model trained with TensorFlow or PyTorch and uses the data as input to determine whether a road is passable.

[1665] Input: Data with confidence scores (DataFrame or JSON format)

[1666] Output: Road data (DataFrame or JSON format) for which passability has been determined

[1667] Specific behavior:

[1668] Load a trained machine learning model.

[1669] Input data into the model and obtain labels indicating whether the road is passable or not.

[1670] The judgment result is added to the data and saved.

[1671] Step 5:

[1672] Optimal route calculation

[1673] server

[1674] The server then calculates the optimal route from the current location to the destination based on the results of the assessment, using the Dijkstra algorithm and the A algorithm, and taking real-time traffic congestion information into account.

[1675] Input: Road data (DataFrame or JSON format) for which passability is determined

[1676] Output: Optimal route information (JSON format)

[1677] Specific behavior:

[1678] A road network graph is constructed, and passability and traffic condition costs are set for each edge.

[1679] Finding the shortest path using the NetworkX library.

[1680] Save the optimal route information in JSON format.

[1681] Step 6:

[1682] Providing information

[1683] server

[1684] The server provides the calculated optimal route information through an API, and returns the latest route information in JSON format in response to a user request.

[1685] Input: User request

[1686] Output: Optimal route information (JSON format)

[1687] Specific behavior:

[1688] Build API endpoints using Flask and FastAPI.

[1689] Returns pre-calculated route information based on user requests.

[1690] Step 7:

[1691] What the user sees

[1692] Terminal

[1693] The device receives the route information sent from the server and displays it in the map app. It plots the route on a map using Google Maps or Mapbox SDK, providing a visual representation to the user.

[1694] Input: Optimal route information received from the server (JSON format)

[1695] Output: Route information plotted on a map

[1696] Specific behavior:

[1697] The terminal parses the received JSON data.

[1698] Plot your data on a map using the Google Maps or Mapbox SDK.

[1699] Users can check the route on the map and travel safely.

[1700] (Application example 1)

[1701] 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."

[1702] The present invention solves the problem of the difficulty of providing quick and accurate information on passable roads during disasters. Furthermore, there is a need for a system that enables autonomous vehicles to travel safely and efficiently based on that information.

[1703] 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.

[1704] In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for providing the calculated optimal route information to the autonomously driven vehicle, and means for controlling the vehicle based on the route information provided to the autonomously driven vehicle. This enables the autonomously driven vehicle to select and travel a safe and optimal route even during a disaster.

[1705] "Sources" refer to the origins of various publicly available data, including APIs of public institutions and private sites.

[1706] "Road condition data" is data that indicates whether roads are passable, traffic congestion information, traffic accident information, weather conditions, and the like.

[1707] "Preprocessing" refers to the process of standardizing collected raw data into a certain format and removing incomplete or incorrect data to generate a clean dataset.

[1708] "Credibility assessment" refers to the process of assessing the accuracy and reliability of data based on the source's past history and frequency of data updates.

[1709] "Passable roads" refer to roads that are determined to be passable even in the event of a disaster based on the results of data analysis.

[1710] The "optimal route" refers to the shortest and safest route from the current location to the destination, calculated by the program.

[1711] "Autonomous vehicle" refers to a vehicle that can be operated and driven by its own system.

[1712] "Route information" is data about the calculated optimal travel route, and is used in maps and navigation systems.

[1713] "Control means" refers to the function of controlling the movement of the vehicle based on the route information provided.

[1714] This invention is a system for autonomous vehicles to safely and quickly select and move along optimal routes during disasters. The system collects road condition data from information sources, preprocesses it, evaluates its reliability, determines which roads are passable, calculates the optimal route, and provides this information to autonomous vehicles to reflect in their control.

[1715] Hardware and software used

[1716] Hardware:

[1717] Embedded systems for autonomous vehicles (navigation systems, communication modules, etc.)

[1718] software:

[1719] Python

[1720] requests library (for API requests)

[1721] pandas library (for data preprocessing)

[1722] scikit-learn library (for machine learning modeling)

[1723] geopy library (for geographic information processing)

[1724] Details of data processing and calculation

[1725] The server collects road condition data from public APIs and private websites. It then standardizes the collected data into JSON format and removes incomplete or incorrect data to generate a clean dataset. Based on this dataset, the reliability of the source is evaluated using its past history and the frequency of data updates.

[1726] Using the evaluated data, a machine learning model (e.g., random forest) is used to determine whether a road is passable, taking into account historical traffic information and weather conditions. Next, the optimal route from the current location to the destination is calculated based on the passable road information.

[1727] The calculated optimal route information is provided to the autonomous vehicle, which then controls the vehicle based on that route information, enabling safe and rapid movement even in the event of a disaster.

[1728] Specific examples

[1729] Moving to a shelter:

[1730] Immediately after a disaster occurs, the server collects the latest road condition data from various sources, preprocesses it, and evaluates its reliability. It then determines which roads are passable and calculates the optimal route to the nearest evacuation shelter. This route information is provided to the autonomous vehicle, which then travels safely to the shelter based on the instructions.

[1731] Transport of goods:

[1732] The server collects real-time data and generates clean data, then performs reliability assessment and provides passable road information for logistics companies. After route calculation, it provides the optimal route information to autonomous vehicles, which then transport goods to their destinations quickly and safely.

[1733] Example prompts to input to the generative AI model

[1734] AI Assistant, please calculate the optimal route for safe and fast autonomous driving to an evacuation shelter based on the current damage situation caused by the earthquake, and update this information in the vehicle system. The current location is Tokyo Station, and the destination is an evacuation shelter within Tokyo.

[1735] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1736] Step 1:

[1737] The server collects road condition data from sources. Specifically, it sends requests to API endpoints of public agencies to obtain the latest road condition data. It also scrapes private traffic information providers to collect real-time road information. It also obtains traffic information data provided by telecommunications companies. The input is the API request or scraping, and the output is the collected road condition data.

[1738] Step 2:

[1739] The server preprocesses the collected data. Specifically, it converts data from each source into a common JSON format and filters out incomplete, incorrect, and duplicate data to generate a clean dataset. The input is the raw collected data, and the output is the clean dataset.

[1740] Step 3:

[1741] The server evaluates the reliability of the preprocessed data. Specifically, it scores each information source based on its past history and the frequency of information updates. For example, it assigns a high reliability score to information sources that have been highly accurate in the past. The input is a clean dataset, and the output is reliability-evaluated data.

[1742] Step 4:

[1743] The server determines whether a road is passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (such as random forest) to determine whether the road is passable. This determination also takes into account past and current traffic information and weather conditions. The input is reliability-evaluated data, and the output is road information determined to be passable.

[1744] Step 5:

[1745] The server calculates the optimal route based on passable road information. Specifically, it calculates the shortest route from the current location to the destination, as well as evacuation routes and logistics routes. It also incorporates real-time traffic congestion information. The input is passable road information and the coordinates of the current location and destination, and the output is the optimal route information.

[1746] Step 6:

[1747] The server provides the calculated optimal route information to the autonomous vehicle. Specifically, it sends the route information to the autonomous vehicle's embedded system through an API. The input is the optimal route information, and the output is the route information received by the autonomous vehicle.

[1748] Step 7:

[1749] The embedded system of an autonomous vehicle reflects the provided route information and controls the vehicle. Specifically, the route is displayed on the navigation system, and the autonomous driving system operates according to that route. The input is the route information provided by the server, and the output is the vehicle's movement to reach the destination safely and quickly.

[1750] 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.

[1751] The system of this invention is an advanced information collection and analysis system that presents passable roads in the event of a disaster, recognizes the user's emotions, and adjusts navigation accordingly. This system collects road condition data from sources, preprocesses them, and evaluates their reliability before presenting passable roads and optimal routes. Furthermore, it is equipped with an emotion engine that realizes optimal navigation based on the user's emotions.

[1752] Program processing explanation

[1753] 1. Data Collection

[1754] server

[1755] The server obtains the latest road condition data from public agency APIs, scrapes private traffic information websites to collect real-time road information, and also obtains traffic information data provided by telecommunications companies.

[1756] 2. Data Preprocessing

[1757] server

[1758] The server converts the collected data into a common JSON format and filters out incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[1759] 3. Reliability evaluation

[1760] server

[1761] The server evaluates the reliability of each information source based on the preprocessed data. It scores the information using a specific algorithm, taking into account past history and frequency of information updates. Unreliable data is filtered out, and only reliable data is allowed to proceed to the next step.

[1762] 4. Determining whether a road is passable

[1763] server

[1764] The server runs machine learning models using reliable data to determine which roads are passable and which are not, and the results are stored in a database.

[1765] 5. Optimal Route Calculation

[1766] server

[1767] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm, and incorporates real-time traffic information. The optimal route information is stored in a database and can be accessed via API.

[1768] 6. Emotion recognition

[1769] Terminal

[1770] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine uses the user's voice input and facial recognition to identify emotions. For example, if the user is anxious or nervous, that information is reflected in the navigation.

[1771] 7. Route Adjustment

[1772] server

[1773] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method, for example, proposing a route that avoids roads that are likely to cause stress to the user.

[1774] 8. Information provision

[1775] server

[1776] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[1777] 9. Information display

[1778] Terminal

[1779] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[1780] Specific examples

[1781] Example 1: Moving to a shelter

[1782] server

[1783] Immediately after a disaster occurs, the server collects road condition data from each source and generates clean data.

[1784] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[1785] In addition, it receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[1786] The calculation results are sent to the user's device via API.

[1787] Terminal

[1788] The device reflects the received route information in the map app and displays the user a passable route from their current location to the nearest evacuation shelter. Using information from the emotion engine, the device provides stable voice guidance.

[1789] User

[1790] Users can follow the route displayed on their smartphone and move safely to a shelter. With the support of the emotion engine, users can move with peace of mind.

[1791] Example 2: Transporting goods

[1792] server

[1793] The server collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[1794] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[1795] It receives information from the emotion engine and provides routes that reduce driver stress.

[1796] The calculated route information is provided to the logistics company's terminal via API.

[1797] Terminal

[1798] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[1799] User (logistics company)

[1800] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[1801] In this way, the system of the present invention provides highly reliable traffic information during disasters, recognizes the user's emotions, and provides optimal navigation, thereby greatly assisting in smoothly carrying out recovery and evacuation activities.

[1802] The processing flow will be explained below.

[1803] Step 1: Data collection

[1804] server

[1805] The server sends an HTTP GET request to a public agency's API to retrieve the latest road condition data, for example, using the https: / / api.trafficinfo.gov endpoint.

[1806] Scrape private traffic information websites and extract road condition data using HTML analysis tools, such as libraries like BeautifulSoup.

[1807] Traffic information data provided by telecommunications companies is acquired through a dedicated API, and the acquired data is updated in real time.

[1808] Step 2: Data Preprocessing

[1809] server

[1810] The server converts the collected data into a common JSON format, for example using the xmltodict library to convert data in XML format into JSON.

[1811] Regular expressions are used to shape the collected data, filtering out incomplete and duplicate data and generating a clean dataset.

[1812] The transformed data is stored as a clean dataset in a temporary database.

[1813] Step 3: Reliability assessment

[1814] server

[1815] The server considers the past reliability history and update frequency of each source to assess the reliability of the pre-processed data, using an algorithm (e.g., weighted average) to assign a reliability score to each source.

[1816] Data with low confidence scores are filtered out and only data with high scores proceeds to the next step.

[1817] The evaluation results are stored in a database.

[1818] Step 4: Determine whether roads are passable

[1819] server

[1820] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, for example, using a random forest model.

[1821] Input data includes traffic history information and current congestion data.

[1822] The judgment results are stored in a database.

[1823] Step 5: Calculate the optimal route

[1824] server

[1825] The server executes an algorithm (for example, Dijkstra's algorithm or A-search algorithm) that calculates the optimal route between specified points based on passable road information.

[1826] By incorporating real-time traffic congestion information, the shortest route is calculated to avoid unnecessary delays.

[1827] The optimal route information will be stored in a database and made accessible via API.

[1828] Step 6: Emotion Recognition

[1829] Terminal

[1830] The device uses the user's voice input and camera to provide data to the emotion engine, for example, processing audio data from the user speaking into a microphone and facial expression data captured by a camera.

[1831] The emotion engine uses voice recognition software and facial recognition algorithms to identify the user's emotions (e.g., anxiety, relief, irritation).

[1832] Step 7: Route Adjustment

[1833] server

[1834] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. For example, for a user who is prone to anxiety, it suggests a route that eliminates roads that should be avoided.

[1835] The recalculated route information is stored in a database and provided to the device via an API.

[1836] Step 8: Provide information

[1837] server

[1838] The server generates an optimal route that reflects the emotion information in a user-friendly format and provides it to the device via an API, for example, by returning the route information in JSON format.

[1839] Step 9: Display Information

[1840] Terminal

[1841] The device analyzes the route information received from the server and displays it in a map application, with a user interface that visually indicates passable roads and the optimal route.

[1842] The device uses a voice navigation function to provide the user with appropriate route guidance, which is based on the user's emotions.

[1843] Step 10: User interaction

[1844] User

[1845] The user checks the passable routes displayed on the terminal and selects a route as necessary.

[1846] Users can follow the displayed route to their destination safely and comfortably. With the support of the emotion engine, they can travel with peace of mind.

[1847] Example 2

[1848] 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."

[1849] Conventional navigation systems are sometimes unable to accurately grasp real-time road conditions during disasters, limiting their ability to suggest optimal routes. Furthermore, they are unable to provide navigation that takes into account the user's emotional state, and do not take into consideration routes that are likely to cause stress to the user. It is necessary to solve these problems and realize fast and safe evacuation and transportation of supplies during disasters.

[1850] 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.

[1851] In this invention, the server includes means for collecting road condition data from an information source, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for recalculating the optimal route based on the recognized user emotion information, and means for providing the calculated optimal route information to the terminal. This makes it possible to propose an optimal route taking the user's emotional state into consideration, thereby enabling quick and safe evacuation and transportation of supplies in the event of a disaster.

[1852] "Information sources" are data sources that are the basis for collecting data, such as public agencies, private companies, and communication companies that provide road condition data.

[1853] "Road condition data" is information showing the latest road conditions, such as whether the road is passable, traffic congestion information, traffic accidents, and damage caused by disasters.

[1854] "Preprocessing" is the process of converting collected data into a common format and filtering out incomplete or duplicate data.

[1855] "Reliability assessment" is a method for assessing the accuracy and reliability of collected data and ensuring data quality. This assessment includes past history and frequency of information updates.

[1856] A "passable road" is one that is clear of obstacles and safe for vehicles and pedestrians to travel on. This determination is made using machine learning models.

[1857] The "optimal route" refers to the most efficient and safest route to the user's destination, calculated based on real-time road conditions and the user's emotional state.

[1858] "User emotion" refers to the psychological state, such as anxiety, tension, or stress, felt by the user, as identified by the user's voice input or facial recognition.

[1859] "Emotion recognition" is the process of identifying a user's emotions from their facial expressions and voice, and reflecting this in navigation.

[1860] "Recalculation" is a process of recalculating existing route calculation results based on the recognized user's emotions and proposing a route that is more suitable for the user.

[1861] A "terminal" is a device used by a user (such as a smartphone or tablet) that receives and displays optimal route information.

[1862] The system of the present invention is an advanced information collection and analysis system that collects road condition data from various information sources, recognizes the emotional state of the user, and provides optimal navigation. Specific embodiments are described below.

[1863] Data collection

[1864] server

[1865] The server obtains the latest road condition data through public agency APIs. It also accesses private traffic information providers and collects real-time road information using web scraping technology. This process uses Python libraries such as BeautifulSoup and Selenium. It also obtains traffic information data from telecommunications companies' data platforms. This data is then stored in a temporary database.

[1866] Data Preprocessing

[1867] server

[1868] The server converts the collected data into a common JSON format, then uses the Python pandas library to filter incomplete and duplicate data to generate a clean dataset, which is then stored in a temporary database.

[1869] Reliability evaluation

[1870] server

[1871] The server evaluates the reliability of each information source based on the preprocessed data. The evaluation takes into account past data history and information update frequency, and uses algorithms such as the weighted average method. Unreliable data is filtered out, and only reliable data is advanced to the next step.

[1872] Determining passable roads

[1873] server

[1874] The server uses reliable data to run machine learning models to determine which roads are passable and which are not, using libraries such as TensorFlow and PyTorch. The results are then stored in a database.

[1875] Optimal route calculation

[1876] server

[1877] The server calculates the optimal route based on passable road information. The route calculation uses Dijkstra's algorithm and A-search algorithm. It also takes into account real-time traffic congestion information. The optimal route information is stored in a database and can be accessed via API.

[1878] emotion recognition

[1879] Terminal

[1880] The device is equipped with an emotion engine that recognizes the user's emotions. The emotion engine identifies emotions through the user's voice input and facial recognition. For example, if the user is feeling anxious or nervous, that information is reflected in the navigation. Emotion recognition uses the Python open source library OpenCV and Emotion API.

[1881] Route Adjustment

[1882] server

[1883] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. It suggests routes that avoid roads that are likely to cause stress to the user, for example, prioritizing quiet roads and roads with good scenery.

[1884] Providing information

[1885] server

[1886] The server generates an optimal route that reflects the information from the emotion engine in a user-friendly format and provides it to the device via an API.

[1887] Information display

[1888] Terminal

[1889] The device analyzes the optimal route information provided by the server and displays it on the user interface. It also reflects this information in the map application, visually indicating passable roads along the route and recommended routes. It also uses the voice navigation function to provide appropriate guidance to the user.

[1890] Specific examples

[1891] Example 1: Moving to a shelter

[1892] server

[1893] Immediately after a disaster occurs, road condition data is collected from various sources and clean data is generated.

[1894] The reliability of the data is evaluated, roads that are passable are determined, and the optimal route to the nearest evacuation shelter is calculated.

[1895] It receives information from the emotion engine and suggests routes that avoid factors that cause the user anxiety or tension.

[1896] The calculation results are sent to the user's device via API.

[1897] Terminal

[1898] The device reflects the received route information in the map app and displays a passable route from the current location to the nearest evacuation shelter. It also uses information from the emotion engine to provide stable voice guidance.

[1899] User

[1900] Users can safely move to a shelter by following the route displayed on their smartphone. With the support of the emotion engine, users can move with peace of mind.

[1901] Example 2: Transporting goods

[1902] server

[1903] It collects real-time data from various sources, analyzes and updates traffic information for logistics companies.

[1904] Logistics routes are determined based on highly reliable data, and the optimal route is calculated taking into account traffic congestion information.

[1905] It receives information from the emotion engine and provides routes that reduce driver stress.

[1906] Route information calculated through the API is provided to the logistics company's terminal.

[1907] Terminal

[1908] The logistics company's terminal displays the received route information on the navigation system and gives instructions to the driver. With the support of the emotion engine, the driver can be guided with relaxing music and voice guidance.

[1909] User (logistics company)

[1910] The driver follows the route displayed on the terminal to transport goods quickly and safely to their destination, and with the support of the emotion engine, stress while driving can be reduced.

[1911] These concrete examples show that the system of the present invention can provide highly reliable traffic information during disasters, recognize the user's emotions, and provide optimal navigation, thereby being of great help in smoothly carrying out recovery and evacuation activities.

[1912] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1913] Step 1: Data collection

[1914] server

[1915] The server collects road condition data. As input, it uses API endpoints from public agencies, URLs from private traffic information providers, and data platforms from telecommunications companies. Specifically, it obtains real-time data through web scraping using the Python library BeautifulSoup and Selenium. This collected raw data is stored in a temporary database. The output is the collected, unprocessed road condition data.

[1916] Step 2: Data Preprocessing

[1917] server

[1918] The server converts the collected raw data into a common JSON format. The input is the raw data collected in step 1. Specifically, it uses the Python pandas library to filter incomplete and duplicate data and generate a clean dataset. This preprocessing imputes missing data and corrects outliers. The output is a clean dataset, which is stored in a temporary database.

[1919] Step 3: Reliability assessment

[1920] server

[1921] The server evaluates the reliability of the preprocessed data. The input is the clean dataset generated in step 2. Specifically, it calculates the reliability score of each information source using algorithms such as the weighted average method based on past data history and information update frequency. Data with low reliability is filtered out. The output is the reliability-evaluated data.

[1922] Step 4: Determine whether roads are passable

[1923] server

[1924] The server determines which roads are passable based on the reliability-evaluated data. The input is the data evaluated in step 3. Specifically, it uses a machine learning model (e.g., TensorFlow or PyTorch) to analyze the data and determine which roads are passable and which are not. The results of this determination are stored in a database. The output is passable road information.

[1925] Step 5: Calculate the optimal route

[1926] server

[1927] The server calculates the optimal route based on passable road information. The input is the passable road information determined in step 4. Specifically, it calculates the optimal route using Dijkstra's algorithm and A-search algorithm together with real-time traffic congestion information. The calculation results are stored in a database and made accessible via API. The output is the optimal route information.

[1928] Step 6: Emotion Recognition

[1929] Terminal

[1930] The device uses an emotion engine to recognize the user's emotions. Inputs include the user's voice input and facial recognition data. Specific operations include analyzing the user's emotions using Python's OpenCV and Emotion API. For example, it can identify whether the user is feeling anxious or nervous based on their voice tone and facial expression. The output is the user's emotional information.

[1931] Step 7: Route Adjustment

[1932] server

[1933] The server receives the user's emotional information provided by the emotion engine and recalculates the optimal route and navigation method. The input is the optimal route information calculated in step 5 and the user's emotional information obtained in step 6. Specifically, the server takes the emotional data into consideration and recalculates a route that is less stressful. For example, it selects quiet roads or roads with beautiful scenery. The output is the adjusted optimal route information.

[1934] Step 8: Provide information

[1935] server

[1936] The server generates the adjusted optimal route information in a user-friendly format and provides it to the device via the API. The input is the optimal route information adjusted in step 7. Specifically, the server formats the information in an easy-to-understand format and sends it to the device via the API. The output is the optimal route information provided to the device.

[1937] Step 9: Display Information

[1938] Terminal

[1939] The terminal analyzes the optimal route information provided by the server and displays it on the user interface. The input is the optimal route information provided in step 8. Specifically, the route information is reflected in the map application and visually shown to the user. Also, real-time guidance is provided using the voice navigation function. The output is the route information displayed on the user interface and voice guidance.

[1940] (Application example 2)

[1941] 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."

[1942] Conventional navigation systems have difficulty providing fast and reliable travel information during disasters. Furthermore, they are unable to provide navigation that takes into account the user's emotional factors, making it difficult to reduce the stress and anxiety users feel while traveling. Therefore, there is a need for technology that provides safe routes that are passable even during disasters, and also provides comfortable navigation that takes into account the user's emotions.

[1943] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting road condition data from information sources, means for preprocessing the collected data, means for evaluating the reliability of the preprocessed data, means for determining passable roads based on the reliability-evaluated data, means for calculating an optimal route based on the determined passable road information, means for acquiring user emotion information and adjusting the optimal route based on the emotion, and means for providing the calculated optimal route information to the terminal. This makes it possible to provide highly reliable traffic information and navigation that takes user emotion into consideration even during a disaster.

[1944] "Information source" refers to a data provider for collecting road condition data provided by public institutions, private sites, etc.

[1945] "Preprocessing" refers to the process of converting collected data into a common format and filtering out incomplete or duplicate data to produce a clean dataset.

[1946] "Reliability assessment" is the process of evaluating and scoring the reliability of collected data, taking into account past history and frequency of information updates.

[1947] A "passable road" is a road that is safe to use and not affected by weather or disasters.

[1948] The "optimal route" is calculated based on passable road information and is the most efficient and safe route to the destination.

[1949] "Emotion information" is data that indicates the user's emotional state, and is information that identifies the user's emotions using voice input or face recognition.

[1950] "Terminal" means a device used by a user to receive and display information, such as a smartphone or smart glasses.

[1951] "Means of collection" refers to the means of obtaining data from public institution APIs and private sites.

[1952] "Preprocessing means" refers to means for converting collected data into a common format and for filtering the data.

[1953] "Means for evaluation" refers to the means for evaluating and scoring the reliability of collected data.

[1954] The "means for determining" refers to a means for determining passable roads based on the reliability-evaluated data.

[1955] The "means for calculating" refers to a means for calculating an optimal route using passable road information.

[1956] The "means for acquiring" refers to a means for acquiring emotion information through a user's voice input or face recognition.

[1957] "Adjustment means" refers to the means for recalculating the optimal route based on the acquired emotional information.

[1958] The "means for providing" refers to the means for transmitting the calculated optimum route information to the terminal and displaying it.

[1959] This invention is an advanced information collection and analysis system that recognizes passable roads and user emotions during disasters and adjusts navigation based on the information. This makes it possible to provide highly reliable traffic information and navigation that takes user emotions into consideration. Specific embodiments for implementing this invention are described below.

[1960] First, the server uses the following hardware and software: Road condition data is collected from public APIs and private sites, and APIs and web scraping tools are used to collect the data. The collected data is preprocessed on the server and converted into a common JSON format. This preprocessing includes filtering incomplete and duplicate data. Next, to evaluate reliability, the server is equipped with a reliability scoring algorithm. This evaluates the reliability of the data based on past history and information update frequency, and filters out unreliable data.

[1961] Based on the reliability-assessed data, a machine learning model (such as Scikit-learn or TensorFlow) is used to determine which roads are passable. The results of this determination are stored in a database, and Dijkstra's algorithm or A-search algorithm is used to calculate the optimal route. The optimal route is calculated, incorporating real-time traffic congestion information, and the results are stored in a database.

[1962] Furthermore, the device is equipped with an emotion engine to acquire the user's emotional information. The emotion engine uses the camera and microphone of the smart glasses or smartphone to analyze the user's voice and facial expressions and recognize emotions in real time. For example, if the user is feeling anxious or nervous, this information is sent to the server, which then recalculates the optimal route. A route that reflects the emotional information is calculated, and the server provides this route information to the device via an API.

[1963] The device displays the received route information in a user-friendly format, including a map application that visually indicates passable roads and recommended routes along the route. Furthermore, the device uses voice navigation to provide appropriate guidance to the user, and the emotional engine supports the device to ensure a safe and secure journey.

[1964] As a concrete example, consider an evacuation scenario during a disaster. After a disaster occurs, the server collects information in real time from public institution APIs, quickly assesses reliability, and determines passable roads. It then calculates the optimal route to the nearest evacuation shelter, and if the user feels anxious, it provides a less stressful route. The device receives this information and provides voice guidance and a map display, guiding the user safely to the evacuation shelter. In this way, the invention supports quick and reliable evacuation while maintaining the user's sense of security, even during a disaster.

[1965] An example prompt is:

[1966] "Consider a scenario where a user needs to evacuate early in the morning. A large earthquake has occurred in the area and the user needs to move to a shelter immediately. Based on the user's emotions, suggest a safe and secure route. Provide appropriate navigation support methods, especially considering the user's anxiety."

[1967] By implementing the system in this way, it will be possible to provide fast and reliable traffic information during disasters and navigation that takes user emotions into consideration. It will also provide specialized functions for autonomous vehicles, realizing travel that ensures a sense of security for passengers.

[1968] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1969] Step 1:

[1970] The server collects road condition data from public APIs and private websites. Specifically, it obtains real-time road information through APIs and also collects necessary information using web scraping tools. This allows for the centralized collection of up-to-date data from various sources. Response data from APIs and data obtained through scraping are used as input, and the collected raw data is generated as output.

[1971] Step 2:

[1972] The server preprocesses the collected raw data by converting it into a common JSON format and filtering out incomplete and duplicate data, resulting in a clean dataset for smoother subsequent processing. It uses the collected raw data as input and generates formatted clean data as output.

[1973] Step 3:

[1974] The server evaluates the reliability of the preprocessed data. Specifically, it scores the data based on its source, history, and update frequency, and filters out data with low reliability. This allows only highly reliable data to proceed to the next step. It uses formatted clean data as input and generates data with a reliability evaluation as output.

[1975] Step 4:

[1976] The server determines whether roads are passable based on the reliability-evaluated data. Specifically, it uses a machine learning model (e.g., Scikit-learn or TensorFlow) to determine whether a road is passable. This enables highly reliable determination based on the latest road conditions. It uses the reliability-evaluated data as input and generates passable road information as output.

[1977] Step 5:

[1978] The server calculates the optimal route based on passable road information. Specifically, it uses Dijkstra's algorithm and A-search algorithm to determine the optimal route, taking real-time traffic congestion information into consideration. Passable road information is used as input, and the calculated optimal route information is generated as output.

[1979] Step 6:

[1980] The device acquires the user's emotional information. Specifically, it analyzes the user's voice and facial expressions using the camera and microphone of smart glasses or a smartphone to recognize emotions. It uses the user's voice data and image data as input and generates emotional information as output.

[1981] Step 7:

[1982] The server recalculates the optimal route based on the user's emotional information. Specifically, it analyzes the acquired emotional information and recalculates the optimal route to provide a route that is less stressful for the user. It uses the user's emotional information and existing optimal route information as input and generates adjusted optimal route information as output.

[1983] Step 8:

[1984] The device displays the calculated optimal route information in a user-friendly format. Specifically, the device reflects the route information in a map application and provides appropriate guidance to the user using a voice navigation function. The device uses the adjusted optimal route information as input and generates route information and voice guidance displayed on the user interface as output.

[1985] 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.

[1986] 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.

[1987] 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.

[1988] 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.

[1989] 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.

[1990] 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.

[1991] 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).

[1992] 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.

[1993] 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."

[1994] 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.

[1995] 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).

[1996] 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.

[1997] In the above embodiment, an example in which the specific pr...

Claims

1. means for collecting road condition data from a source; means for pre-processing the collected data; a means for assessing the reliability of the preprocessed data; a means for determining passable roads based on the reliability-evaluated data; means for calculating an optimal route based on the determined passable road information; means for providing the calculated optimal route information to the terminal; A system including:

2. 2. The system of claim 1, wherein the means for collecting road condition data includes APIs from public agencies and scraping from private sites.

3. The system according to claim 1 , wherein the means for determining passable roads based on the reliability-evaluated data uses a machine learning model.

Images