system

Abstract

We provide the system. [Solution] In an information processing device that provides evacuation routes during a disaster, A means of collecting geographical information and disaster history from an external database, A means for analyzing geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster, Means for calculating evacuation routes that avoid the identified area, A means for distributing the evacuation route information to the user terminal in advance, A means for storing the evacuation route information on the user terminal and providing the evacuation route in the event of a disaster, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a natural disaster occurs, it is very important to grasp in advance a route for safe and rapid evacuation. However, since conventional evacuation route guidance systems assume real - time communication, the communication environment often becomes unstable during disasters, and there is a possibility that appropriate information may not be provided. As a result, there is a problem that users cannot find a safe evacuation route and are exposed to danger.

Means for Solving the Problems

[0005] This invention relates to an information processing device that provides evacuation routes during disasters, and includes means for collecting geographical information and disaster history from an external database. It also includes means for analyzing the collected geographical information and disaster history using a machine learning algorithm to identify areas where damage is expected during a disaster, and for calculating evacuation routes that avoid these identified areas. Furthermore, by pre-distributing evacuation route information to user terminals and allowing them to retain this information, the device can provide evacuation routes even when offline during a disaster. This ensures that information necessary for safe evacuation is provided without interruption.

[0006] An "information processing device" is an electronic device used to collect, analyze, and process data and generate specific information.

[0007] "Geographical information" refers to location data, topography, and infrastructure information related to a specific geographical area.

[0008] "Disaster history" refers to records of past disasters, including their type, location, scope of impact, and extent of damage.

[0009] A "machine learning algorithm" is a computational method that uses large amounts of data to build specific patterns or predictive models, and then uses that data to make decisions or predictions.

[0010] An "evacuation route" refers to a path or route established to safely reach a destination during a disaster.

[0011] A "user terminal" refers to an electronic device such as a mobile phone, tablet, or personal computer that the end user uses to receive and display information. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface that includes a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention relates to an information processing system that enables safe and rapid evacuation during disasters. This system primarily consists of a server, terminals, and users who utilize them.

[0034] Server Operation: The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, and the extent of impact from past disasters. Next, the server uses this data to run machine learning algorithms to analyze building strength and topographical characteristics, and identify areas where damage is predicted during a disaster. Based on this analysis, it calculates optimized evacuation routes and generates customized route information for each user. The generated evacuation route information is delivered in advance to the user's smartphone or other device.

[0035] Device Operation: The device stores evacuation route information received from the server in local storage, allowing access to this information even when offline during a disaster. When the user launches the app, the device uses GPS to determine the user's current location and provides appropriate directions based on the previously stored evacuation route information. This includes displaying maps, providing voice guidance, and text instructions.

[0036] How users can use the system: When a disaster occurs, users can launch the app on their device to immediately check pre-distributed evacuation routes. For example, if a major earthquake occurs while a user is at home, the app will present the optimal evacuation route calculated in advance and guide the user to the nearest safe evacuation center. This procedure allows users to evacuate safely even in situations with unstable communication environments. This system reduces anxiety during evacuation and enables users to evacuate safely based on appropriate decisions.

[0037] As described above, the present invention improves the safety and speed of evacuation during disasters, and is a system that provides substantial safety to users.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server automatically collects geographical information and disaster history from external databases. This process involves retrieving road conditions, weather conditions, and historical disaster data via various APIs and data feeds.

[0041] Step 2:

[0042] The server uses the collected data to run machine learning algorithms. This identifies areas where damage is expected due to the strength of buildings and terrain, as well as river flooding and earthquakes. This analysis then displays high-risk zones on a map.

[0043] Step 3:

[0044] Based on the analysis results, the server calculates an optimized evacuation route that avoids the danger zone. This calculation takes into account available roads, the location of shelters, and means of transportation to identify the safest route.

[0045] Step 4:

[0046] The server compresses evacuation route information and distributes it to the user's device in advance. This information is encrypted and prepared for offline use on the device.

[0047] Step 5:

[0048] The terminal saves the evacuation route information received from the server to its local storage. At this time, data verification, such as checksums, is performed to confirm that the information has been saved correctly.

[0049] Step 6:

[0050] When a disaster occurs, the user launches an evacuation route app on their device. The app refers to pre-saved evacuation route information and displays the optimal evacuation route in real time.

[0051] Step 7:

[0052] The device uses GPS to determine the user's current location and provides directions along an evacuation route. This includes map display, voice guidance, and text instructions as needed.

[0053] Step 8:

[0054] Users move safely and quickly to evacuation shelters by following the displayed evacuation route. The device updates location information in real time during movement and adjusts route guidance as needed.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In emergency situations such as disasters, it is necessary to provide accurate and individually tailored evacuation information in advance to enable many people to evacuate quickly and safely. However, conventional route guidance systems have difficulty providing evacuation routes that take into account real-time geographical conditions and the impact of events. Furthermore, while it would be effective to save evacuation route information on devices in advance when communication environments are limited during a disaster, many systems do not have such functionality.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting area information and event history from general information sources, means for analyzing the area information and event history using a data analysis algorithm to identify areas where damage is expected during an event, and means for calculating routes that avoid the identified areas. This makes it possible to provide users with individually optimized route information even in the event of a disaster or emergency, thereby supporting rapid and safe evacuation.

[0060] "Information sources" refer to general databases and information services that provide domain information and event histories.

[0061] "Regional information" refers to data that includes location information, topography, infrastructure conditions, and other information related to a specific geographical area.

[0062] "Event history" refers to recorded data regarding the circumstances and scope of past disasters and emergencies.

[0063] A "data analysis algorithm" refers to computational methods and models used to analyze collected data and derive effective judgments and predictions.

[0064] "Identified areas" refer to locations where damage is expected to occur when an event takes place, as revealed using data analysis algorithms.

[0065] A "route" refers to the path a user takes to travel safely and quickly from one point to another.

[0066] "User device" refers to a communication terminal or device carried by a user, which is used for receiving, storing, and displaying information.

[0067] "Route information" refers to detailed instructions and guidance regarding the optimal travel route that has been analyzed and calculated.

[0068] This invention supports efficient evacuation during disasters and emergencies using an information processing system consisting of a server, terminals, and users. Specifically, the server collects area information and event history from general information sources and executes a data analysis algorithm based on this information to predict risks in a specific area.

[0069] The server collects necessary data using open-source geographic information and public event databases. It also analyzes the collected data using TENSORFLOW® or similar data analysis software to identify areas predicted to be high-risk during an event. Through this analysis, the server calculates the optimal route avoiding risk areas and distributes the generated route information to the user's device. The generated route information is handled as text prompts, not in JSON format. An example of such a prompt might be, "Calculate the safest evacuation route during a disaster and generate a route from the user's current location to the nearest evacuation shelter."

[0070] The device saves received route information to local storage, making it accessible offline even in unstable network conditions. When the user launches the app, the device uses its built-in GPS function to determine the user's current location and provides voice and visual route guidance based on the saved route information. This guidance includes map display, voice guidance, and text directions.

[0071] By operating the terminal, users can quickly confirm evacuation routes during a disaster and move safely to their destination. Therefore, this system provides an effective means of supporting users to act quickly and safely during a disaster.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects regional information and event history from common sources. Inputs include URLs and API keys for geographic information databases and event history databases. The server queries these sources to retrieve geographical data and historical event history for a given region. Outputs are raw data retrieved from the databases, specifically including map data, road conditions, and historical disaster history.

[0075] Step 2:

[0076] The server analyzes the collected data using data analysis algorithms. The input is the raw data obtained in Step 1. The server uses analysis tools such as TensorFlow to evaluate the strength of structures within the region, topographic characteristics, and the impact of past disasters. For data processing, it utilizes neural networks to identify risk areas. The output is evaluation data indicating risk areas. Specifically, it represents high-risk areas in a heatmap format.

[0077] Step 3:

[0078] The server calculates the optimal route based on the analysis results. The input is the risk assessment data obtained in step 2. The server uses Dijkstra's algorithm or the A algorithm to calculate a route that avoids high-risk areas. The data calculation involves finding the shortest route based on the distance and time between each point. The output is evacuation route information. Specifically, it includes detailed routes for the user to reach their destination.

[0079] Step 4:

[0080] The server sends the generated route information to the user's device. The input is the evacuation route information generated in step 3. The server converts this information into a JSON prompt message and sends it to the terminal via push notification or the cloud. The output is the route information stored on the terminal. Specifically, it is saved as a file on the terminal so that the user can access it even when offline.

[0081] Step 5:

[0082] The device provides instructions to the user based on stored route information. Input is route information received from the server and stored on the device. When the user launches the app, the device uses GPS to determine the current location and refers to the stored data to provide optimal route guidance. It uses a map display library to visually show the route and provides voice guidance and text instructions. Output is evacuation instructions provided to the user, specifically including on-screen map displays and voice guidance.

[0083] Step 6:

[0084] The user follows the evacuation instructions provided by the device. The input is the evacuation instructions shown in step 5. The user confirms the suggested route and begins moving safely. By following the route as instructed, the user can safely evacuate to their destination. The output is that the user has reached the evacuation shelter. Specifically, this refers to the situation where the user has safely completed the evacuation.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] Evacuation during disasters is highly urgent and requires rapid and safe movement. However, conventional evacuation route guidance systems lack features that enhance user confidence, such as real-time progress updates and voice instructions. Therefore, there is a need for the development of a system that provides flexible evacuation routes tailored to disaster situations and ensures user safety.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for collecting geographical information and disaster history from an external database, means for analyzing the geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster, and means for providing voice instructions and real-time display of progress. This enables users to evacuate safely and quickly during a disaster, and to select an evacuation route with a sense of security through appropriate guidance and voice instructions.

[0090] An "evacuation route" is a route selected to ensure that one can reach their destination safely and quickly in the event of a disaster.

[0091] An "information processing device" is a device used to collect and analyze data and generate or provide necessary information.

[0092] An "external database" is an external storage device or data management system that stores data such as geographical information and disaster history.

[0093] "Geographical information" refers to information related to geographic space, such as the layout of roads, topography, and the location of buildings.

[0094] "Disaster history" refers to records and data related to disasters that have occurred in the past, including the frequency and scope of disaster occurrences.

[0095] A "machine learning algorithm" is a mathematical model that learns patterns and rules from data to perform analysis and prediction.

[0096] "Voice instructions" refer to instructions or guidance provided to users using voice.

[0097] "Real-time display" refers to a display method that provides users with the current situation and information immediately.

[0098] "Durability analysis" is an analysis used to evaluate the strength and lifespan of buildings and structures.

[0099] "Information updating" means keeping data up-to-date by adding new information or correcting existing information.

[0100] In an embodiment of this invention, the information processing system consists of a server, a terminal, and a user. The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, and the extent of impact of past disasters. The server uses the collected data to execute machine learning algorithms and predict disaster damage in a specific geographical area. Based on the results, it calculates the optimal evacuation route to avoid the identified damage prediction area and generates customized route information for each user. This generated evacuation route information is delivered to the user's terminal in advance.

[0101] The device stores evacuation route information received from the server in local storage, allowing access to this information even when offline. When the user launches the app, the device uses GPS to determine its current location and, based on the pre-stored evacuation route information, provides appropriate guidance to the user using a combination of voice instructions and real-time progress displays. This enables the user to evacuate safely and quickly.

[0102] For example, in the event of a major earthquake, users can use their smartphones to check evacuation route information they have obtained in advance and proceed along the optimal route from their home to the nearest evacuation center. This system reduces anxiety during disasters and enables safe evacuation even in situations where communication environments are unstable.

[0103] An example of a prompt for a generative AI model is: "Describe the design of an AI system that, when a user faces an increased risk of flooding, allows them to pre-determine a safe evacuation route and then evacuate according to voice guidance." This prompt is used to explain to the generative AI model how this system would be used in an emergency.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects geographical information and disaster history from an external database. Its inputs are geographical information and disaster history data, which are retrieved via the network. As output, the retrieved data is stored in an internal data structure. Specifically, it uses APIs to retrieve the latest geographical data and historical disaster data from external data providers.

[0107] Step 2:

[0108] The server analyzes the collected data using machine learning algorithms to identify the areas where damage is expected. The input consists of geographical information and disaster history obtained in step 1, which are then input into the model to perform predictive calculations. The output is data showing geographical areas at risk of disaster. Specifically, it predicts the expected collapse of buildings and changes in terrain during a disaster and visualizes the risk areas on a map based on these predictions.

[0109] Step 3:

[0110] The server calculates the optimal evacuation route that avoids risk areas and creates this route information. The input is map information of the risk areas identified in step 2. A route optimization algorithm is used to calculate a safe route. The output is customized evacuation route information provided to the user. Specifically, it calculates a route that avoids risks while reaching a shelter in the shortest possible time.

[0111] Step 4:

[0112] The server pre-distributes the generated evacuation route information to the user's terminal. The input is the evacuation route data generated in step 3, which is sent to the terminal via a communication protocol. The output is the terminal's storage holding the evacuation route information. Specifically, the server sends the data to the terminal via the communication line and saves it locally.

[0113] Step 5:

[0114] When the user launches the app, the device starts navigation based on saved evacuation route information. The input is the user's current location, which is obtained using GPS. Using this information, the device provides real-time voice instructions and displays progress while comparing it with the saved route. The output is navigation information to help the user safely navigate the evacuation route. Specifically, it starts voice guidance along with a map display and provides visual and auditory feedback to the user according to their progress.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] This invention provides a system combining an information processing device, an emotion engine, and a user terminal to support evacuation during disasters. This system is implemented as follows.

[0117] Server Operation: The server first collects geographical information and historical disaster data from an external database. Based on this data, it uses machine learning algorithms to analyze the area where damage is expected during a disaster and calculates the optimal evacuation route to avoid that area. The server also performs structural analysis of buildings and generates data to predict the risk of damage. Furthermore, it generates optimized evacuation route information for each user and distributes it to their terminals.

[0118] Emotional Engine Operation: The emotional engine recognizes the user's emotional state by analyzing the user's voice and operation data. For example, it measures anxiety and stress levels in real time through voice analysis. Based on these results, the emotional engine dynamically adjusts the evacuation route guidance method to suit the user's state.

[0119] Terminal Operation: The terminal stores evacuation route information delivered from the server and modifies the way it guides the user based on feedback provided by the emotion engine. Specifically, if the user is experiencing high levels of anxiety, the terminal provides more detailed guidance and words of encouragement via voice. Also, if the user's stress level is high, it recalculates the evacuation route to recommend rest points and suggests them to the user.

[0120] User Usage: When a disaster occurs, users launch the app on their device to check evacuation routes. For example, if a user is in an area where river flooding is a concern, the app will refer to pre-stored data and suggest a safe detour route. At the same time, the device continuously monitors the user's emotions and provides flexible guidance as needed.

[0121] As a result, users can receive evacuation information customized to their emotional state, enabling them to evacuate with peace of mind. This system provides a comprehensive solution to reduce stress during disasters and support safe evacuation.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server accesses multiple external databases to collect the latest geographical information and disaster history data. This collection includes local weather data, infrastructure conditions, and records of past disasters.

[0125] Step 2:

[0126] The server runs machine learning algorithms based on the collected data to analyze areas where danger is expected during a disaster. This analysis displays specific areas where damage is predicted on a map.

[0127] Step 3:

[0128] The server works with the analysis results to calculate the optimal evacuation route. This route calculation takes into account the location of evacuation sites, the available road network, and bridge conditions. The calculated evacuation route is customized to suit the user's place of residence and mode of transportation.

[0129] Step 4:

[0130] The emotion engine analyzes the user's voice input and device sensor information to evaluate the user's emotional state. The emotion engine identifies the user's level of anxiety and stress in real time based on the tone of voice and word choice.

[0131] Step 5:

[0132] The server pre-distributes calculated evacuation route information to the user's terminal. This distribution includes not only the evacuation route but also settings for guidance methods tailored to the user's emotional state, as analyzed by the emotion engine.

[0133] Step 6:

[0134] The device stores received evacuation information locally and prepares guidance methods tailored to the user's emotional state. Based on evacuation route information, it adjusts screen displays and voice guidance to provide flexible directions to the user.

[0135] Step 7:

[0136] The user launches an app on their device to check the current evacuation route. If the device determines that the user is experiencing high stress, it provides encouraging messages and detailed guides via voice.

[0137] Step 8:

[0138] The device continuously updates location information even after the user begins evacuating, providing real-time guidance for safe routes. It also monitors the user's emotional state and updates or recalculates route guidance as needed to support safe evacuation.

[0139] (Example 2)

[0140] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0141] Evacuation during disasters is often prone to confusion, and there is a problem in that people may not be able to take appropriate evacuation actions, especially when their emotional state is unstable. Furthermore, conventional evacuation route guidance systems cannot provide flexible route guidance that takes emotions into account, making safe and secure evacuation difficult.

[0142] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0143] In this invention, the server includes means for collecting spatial information and past disaster history from external information sources, means for analyzing the spatial information and past disaster history using a machine learning algorithm to identify areas expected to be affected during a disaster, and means for acquiring the user's emotional state and adapting the route guidance unit based on that emotional state. As a result, users can obtain evacuation information optimized to their own emotional state.

[0144] "External information sources" is a general term for databases and repositories that systems use to acquire disaster-related information, including geographical information and disaster history.

[0145] "Spatial information" refers to information about geographical location, regional structure, topography, etc.

[0146] "Past disaster history" refers to record data regarding the type, scale, and scope of impact of disasters that have occurred in the past.

[0147] A "machine learning algorithm" is a collection of programs used to analyze large amounts of data and perform pattern recognition and prediction.

[0148] "User terminal" refers to electronic devices such as mobile phones, tablets, and PCs that users directly operate to obtain information.

[0149] "Emotional state" refers to the user's mental state, mood, stress levels, and anxiety levels.

[0150] The "route guidance section" refers to the functions and components within a system that present evacuation routes to users and provide navigation.

[0151] This system is designed to support evacuation during disasters by combining an information processing device, an emotion analysis mechanism, and user terminals.

[0152] The server first collects spatial information and historical disaster data from external sources. Based on this data, the server uses machine learning algorithms to analyze areas expected to be affected during a disaster. By using the Python Scikit-learn library for machine learning, the server can quickly and accurately analyze large amounts of data and identify the extent of the impact. The server also uses a map API to calculate the optimal evacuation route based on the user's location and delivers it to the user's terminal.

[0153] The emotion analysis mechanism monitors the user's voice data and operation history to analyze their emotional state in real time. This analysis uses a natural language processing framework (e.g., Transformers) as the emotion analysis model. This allows for the measurement of the user's anxiety and stress levels, and the adjustment of evacuation route guidance methods as needed.

[0154] The terminal stores evacuation route information distributed from the server and provides it to users through structured visual and audio interfaces in the event of a disaster. The terminal can also adapt its guidance based on feedback from an emotion analysis mechanism. For example, if the user is highly anxious, the terminal will reinforce the guidance with reassuring language.

[0155] When signs of a disaster appear, users can use their devices to check evacuation routes. An example of a prompt related to suggesting evacuation routes is, "Please tell me the best evacuation route in an area where river flooding is expected." By inputting this prompt into a generating AI model, more appropriate evacuation information can be obtained quickly.

[0156] Based on the above, the system can provide a concrete form of support for safe and secure evacuation that takes into account the emotional state of the users.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The server collects spatial information and historical disaster data from external sources. Inputs include geographic location information and access to historical disaster databases. This allows the server to utilize a Geographic Information System (GIS) to store this information in a database.

[0160] Step 2:

[0161] The server analyzes collected spatial information and past disaster history using machine learning algorithms. The input is the geographic information and disaster data collected in the previous step. The server uses this information to extract risk areas using Scikit-learn. The output generates identification of areas expected to be affected and candidate evacuation routes.

[0162] Step 3:

[0163] The server receives the user's current location information as input and calculates the optimal evacuation route. This utilizes location data confirmed in real time via a map API. The server generates route information to provide the user with the calculation results and delivers it as output to the user's terminal.

[0164] Step 4:

[0165] The emotion engine monitors voice data and operation logs obtained when the user operates the device in real time. Inputs include voice samples and screen operation history. The emotion engine analyzes these and determines the emotional state through a natural language processing framework. The output is the result of the emotional state analysis.

[0166] Step 5:

[0167] The terminal provides the user with evacuation route information received from the server. Input to the terminal consists of structured data and audio from the server. The terminal uses this information to provide guidance through visual and audio interfaces. Output is evacuation route information that the user can visually confirm and is also navigated by voice.

[0168] Step 6:

[0169] The user checks the evacuation route information provided on the device and actually begins evacuating according to that route. Inputs include route information from the device and emotion-based guidance provided by the device. Based on this information, the user can safely evacuate from the disaster area. The output is simply the user reaching a safe location.

[0170] (Application Example 2)

[0171] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0172] Providing appropriate evacuation routes during disasters is crucial, but flexible responses that take into account the emotional state of users are required. Furthermore, the current lack of systems for evacuation support using autonomous vehicles makes it difficult to evacuate with peace of mind. Additionally, technology for analyzing user emotions from voice data and dynamically adjusting evacuation guidance based on the results is insufficient. Therefore, a system is needed that provides appropriate evacuation guidance tailored to emotions, ensuring safe and secure evacuation.

[0173] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0174] In this invention, the server includes means for collecting geographical information and disaster history from an external database; means for analyzing the geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster; means for calculating evacuation routes that avoid the identified area; means for pre-distributing the evacuation route information to a user terminal; means for storing the evacuation route information on the user terminal and providing the evacuation route when a disaster occurs; means for evaluating voice data for analyzing the user's emotional state; and means for dynamically adjusting evacuation route guidance based on the user's emotional state. This enables flexible evacuation guidance that responds to the user's emotions, allowing for safe and secure evacuation.

[0175] An "external database" is an external source of information that stores geographical information and disaster history information.

[0176] "Geographic information" refers to data about the physical characteristics of a particular area, such as its topography, transportation, and building layout.

[0177] "Disaster history" refers to record data regarding the types, scope, and impact of disasters that have occurred in the past.

[0178] A "machine learning algorithm" is a computational method that automatically learns patterns and rules from large amounts of data to perform decision-making and classification.

[0179] "Areas where damage is expected" refers to geographical areas identified as having a high probability of property damage and personal injury during a disaster.

[0180] An "evacuation route" is a path that indicates the route and steps to take to move to a safe place in the event of a disaster.

[0181] A "user terminal" refers to a digital device such as a smartphone or tablet owned by a user.

[0182] "Emotional state" refers to the psychological situation and emotional level inferred from the user's voice and other actions.

[0183] "Voice data" refers to information recorded in digital format using the user's voice.

[0184] To realize this invention, the server efficiently collects and analyzes information necessary during a disaster. Specifically, the server obtains geographical information and past disaster history through an external database, and uses machine learning algorithms based on this information to identify the area where damage is expected. This can be achieved using machine learning libraries such as TensorFlow. Furthermore, based on the analysis results, the server calculates the optimal evacuation route and delivers that information to user terminals.

[0185] The terminal receives evacuation route information distributed from the server and displays it appropriately to the user. Furthermore, the terminal is equipped with an emotion engine that acquires the user's voice data and evaluates their emotional state in real time. Natural language processing tools are used for voice analysis, and the method of evacuation guidance is dynamically adjusted based on the emotional state obtained. If the user shows anxiety, detailed guides and encouraging messages are provided to reassure them.

[0186] Users can use their devices to check evacuation routes during a disaster. For example, if a user is in an area at risk of flooding, the app will provide a safe alternative route based on previously saved data. If the user is feeling anxious, the device will display a message such as, "Don't worry, this is a safe route, please stay calm."

[0187] The system utilizes a generative AI model to generate guidance text that is tailored to the user's emotions. Examples of prompt text include the following:

[0188] "Disaster relief evacuation support app for autonomous vehicles: We will build a system that evaluates the user's emotions based on voice data, provides the optimal evacuation route, and offers reassuring navigation. How will this be implemented?"

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server collects geographical information and disaster history from an external database. In this step, the server retrieves the necessary data via an API, collecting geographical information such as regional topography and road information, and disaster history data such as past disaster locations. The input is the API endpoint, and the output is a dataset containing this information.

[0192] Step 2:

[0193] The server uses a machine learning algorithm to identify the area where damage is expected in the event of a disaster. The server takes the dataset collected in step 1 as input and uses a specific algorithm (e.g., random forest) to predict the risk area. The output specifies the geographical area where damage is expected.

[0194] Step 3:

[0195] The server calculates evacuation routes to avoid identified risk areas. Here, geolocation data is used as input, and a suitable mapping tool (e.g., Google® Maps API) is used to generate safe evacuation routes. The output is route information for the evacuation routes.

[0196] Step 4:

[0197] The server distributes the calculated evacuation route information to the user terminal. The server uses the route information generated in the previous step as input and sends data to the user terminal. The output is route information accessible on the user terminal.

[0198] Step 5:

[0199] The terminal stores evacuation route information received from the server and displays it to the user. In this step, the terminal processes the received route information and visualizes it as a map on the interface. The input is evacuation route data, and the output is the display on the user interface.

[0200] Step 6:

[0201] The device acquires the user's voice data and analyzes their emotional state using an emotion engine. Here, the device uses a microphone to collect the user's voice as input and utilizes NLP (Natural Language Processing) to evaluate their emotional state. The output is the result of the user's emotional state analysis.

[0202] Step 7:

[0203] The device dynamically adjusts evacuation instructions based on the user's emotional state. It uses the results of the emotional analysis as input to generate appropriate navigation instructions and provide them to the user. Specifically, if the user is showing anxiety, it plays an encouraging message via voice. The output is the adjusted guidance instructions.

[0204] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0205] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0206] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0210] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0211] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0212] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0214] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0215] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0216] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0217] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0218] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0219] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0220] This invention relates to an information processing system that enables safe and rapid evacuation during disasters. This system primarily consists of a server, terminals, and users who utilize them.

[0221] Server Operation: The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, and the extent of impact from past disasters. Next, the server uses this data to run machine learning algorithms to analyze building strength and topographical characteristics, and identify areas where damage is predicted during a disaster. Based on this analysis, it calculates optimized evacuation routes and generates customized route information for each user. The generated evacuation route information is delivered in advance to the user's smartphone or other device.

[0222] Device Operation: The device stores evacuation route information received from the server in local storage, allowing access to this information even when offline during a disaster. When the user launches the app, the device uses GPS to determine the user's current location and provides appropriate directions based on the previously stored evacuation route information. This includes displaying maps, providing voice guidance, and text instructions.

[0223] How users can use the system: When a disaster occurs, users can launch the app on their device to immediately check pre-distributed evacuation routes. For example, if a major earthquake occurs while a user is at home, the app will present the optimal evacuation route calculated in advance and guide the user to the nearest safe evacuation center. This procedure allows users to evacuate safely even in situations with unstable communication environments. This system reduces anxiety during evacuation and enables users to evacuate safely based on appropriate decisions.

[0224] As described above, the present invention improves the safety and speed of evacuation during disasters, and is a system that provides substantial safety to users.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server automatically collects geographical information and disaster history from external databases. This process involves retrieving road conditions, weather conditions, and historical disaster data via various APIs and data feeds.

[0228] Step 2:

[0229] The server uses the collected data to run machine learning algorithms. This identifies areas where damage is expected due to the strength of buildings and terrain, as well as river flooding and earthquakes. This analysis then displays high-risk zones on a map.

[0230] Step 3:

[0231] Based on the analysis results, the server calculates an optimized evacuation route that avoids the danger zone. This calculation takes into account available roads, the location of shelters, and means of transportation to identify the safest route.

[0232] Step 4:

[0233] The server compresses evacuation route information and distributes it to the user's device in advance. This information is encrypted and prepared for offline use on the device.

[0234] Step 5:

[0235] The terminal saves the evacuation route information received from the server to its local storage. At this time, data verification, such as checksums, is performed to confirm that the information has been saved correctly.

[0236] Step 6:

[0237] When a disaster occurs, the user launches an evacuation route app on their device. The app refers to pre-saved evacuation route information and displays the optimal evacuation route in real time.

[0238] Step 7:

[0239] The device uses GPS to determine the user's current location and provides directions along an evacuation route. This includes map display, voice guidance, and text instructions as needed.

[0240] Step 8:

[0241] Users move safely and quickly to evacuation shelters by following the displayed evacuation route. The device updates location information in real time during movement and adjusts route guidance as needed.

[0242] (Example 1)

[0243] Next, we will describe Example 1. 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."

[0244] In emergency situations such as disasters, it is necessary to provide accurate and individually tailored evacuation information in advance to enable many people to evacuate quickly and safely. However, conventional route guidance systems have difficulty providing evacuation routes that take into account real-time geographical conditions and the impact of events. Furthermore, while it would be effective to save evacuation route information on devices in advance when communication environments are limited during a disaster, many systems do not have such functionality.

[0245] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0246] In this invention, the server includes means for collecting area information and event history from general information sources, means for analyzing the area information and event history using a data analysis algorithm to identify areas where damage is expected during an event, and means for calculating routes that avoid the identified areas. This makes it possible to provide users with individually optimized route information even in the event of a disaster or emergency, thereby supporting rapid and safe evacuation.

[0247] "Information sources" refer to general databases and information services that provide domain information and event histories.

[0248] "Regional information" refers to data that includes location information, topography, infrastructure conditions, and other information related to a specific geographical area.

[0249] "Event history" refers to recorded data regarding the circumstances and scope of past disasters and emergencies.

[0250] A "data analysis algorithm" refers to computational methods and models used to analyze collected data and derive effective judgments and predictions.

[0251] "Identified areas" refer to locations where damage is expected to occur when an event takes place, as revealed using data analysis algorithms.

[0252] A "route" refers to the path a user takes to travel safely and quickly from one point to another.

[0253] "User device" refers to a communication terminal or device carried by a user, which is used for receiving, storing, and displaying information.

[0254] "Route information" refers to detailed instructions and guidance regarding the optimal travel route that has been analyzed and calculated.

[0255] This invention supports efficient evacuation during disasters and emergencies using an information processing system consisting of a server, terminals, and users. Specifically, the server collects area information and event history from general information sources and executes a data analysis algorithm based on this information to predict risks in a specific area.

[0256] The server uses open-source geographic information and public event databases to collect necessary data. It also uses TensorFlow or similar data analysis software to analyze the collected data and identify areas predicted to be high-risk during an event. Through this analysis, the server calculates the optimal route avoiding risk areas and delivers the generated route information to the user's device. The generated route information is handled as text prompts, not in JSON format. An example of such a prompt might be, "Calculate the safest evacuation route during a disaster and generate a route from the user's current location to the nearest evacuation shelter."

[0257] The device saves received route information to local storage, making it accessible offline even in unstable network conditions. When the user launches the app, the device uses its built-in GPS function to determine the user's current location and provides voice and visual route guidance based on the saved route information. This guidance includes map display, voice guidance, and text directions.

[0258] By operating the terminal, users can quickly confirm evacuation routes during a disaster and move safely to their destination. Therefore, this system provides an effective means of supporting users to act quickly and safely during a disaster.

[0259] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0260] Step 1:

[0261] The server collects regional information and event history from common sources. Inputs include URLs and API keys for geographic information databases and event history databases. The server queries these sources to retrieve geographical data and historical event history for a given region. Outputs are raw data retrieved from the databases, specifically including map data, road conditions, and historical disaster history.

[0262] Step 2:

[0263] The server analyzes the collected data using data analysis algorithms. The input is the raw data obtained in Step 1. The server uses analysis tools such as TensorFlow to evaluate the strength of structures within the region, topographic characteristics, and the impact of past disasters. For data processing, it utilizes neural networks to identify risk areas. The output is evaluation data indicating risk areas. Specifically, it represents high-risk areas in a heatmap format.

[0264] Step 3:

[0265] The server calculates the optimal route based on the analysis results. The input is the risk assessment data obtained in step 2. The server uses Dijkstra's algorithm or the A algorithm to calculate a route that avoids high-risk areas. The data calculation involves finding the shortest route based on the distance and time between each point. The output is evacuation route information. Specifically, it includes detailed routes for the user to reach their destination.

[0266] Step 4:

[0267] The server sends the generated route information to the user's device. The input is the evacuation route information generated in step 3. The server converts this information into a JSON prompt message and sends it to the terminal via push notification or the cloud. The output is the route information stored on the terminal. Specifically, it is saved as a file on the terminal so that the user can access it even when offline.

[0268] Step 5:

[0269] The device provides instructions to the user based on stored route information. Input is route information received from the server and stored on the device. When the user launches the app, the device uses GPS to determine the current location and refers to the stored data to provide optimal route guidance. It uses a map display library to visually show the route and provides voice guidance and text instructions. Output is evacuation instructions provided to the user, specifically including on-screen map displays and voice guidance.

[0270] Step 6:

[0271] The user follows the evacuation instructions provided by the device. The input is the evacuation instructions shown in step 5. The user confirms the suggested route and begins moving safely. By following the route as instructed, the user can safely evacuate to their destination. The output is that the user has reached the evacuation shelter. Specifically, this refers to the situation where the user has safely completed the evacuation.

[0272] (Application Example 1)

[0273] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] Evacuation during disasters is highly urgent and requires rapid and safe movement. However, conventional evacuation route guidance systems lack features that enhance user confidence, such as real-time progress updates and voice instructions. Therefore, there is a need for the development of a system that provides flexible evacuation routes tailored to disaster situations and ensures user safety.

[0275] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0276] In this invention, the server includes means for collecting geographical information and disaster history from an external database, means for analyzing the geographical information and the disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster, and means for providing both voice instructions and real-time display of progress. As a result, users can safely and quickly evacuate during a disaster, and can choose an evacuation route with confidence based on appropriate route guidance and voice instructions.

[0277] An "evacuation route" is a route selected to safely and quickly reach a destination during a disaster.

[0278] An "information processing device" is a device for collecting, analyzing data, and generating or providing necessary information.

[0279] An "external database" is an external storage device or data management system storing data such as geographical information and disaster history.

[0280] "Geographical information" is information related to the geographical space, such as the layout of roads, terrain, and the location of buildings.

[0281] "Disaster history" is records and data related to disasters that have occurred in the past, including the frequency and scope of disaster occurrences.

[0282] A "machine learning algorithm" is a mathematical model for learning patterns and rules from data and performing analysis and prediction.

[0283] "Voice instructions" refer to instructions and guidance provided to users using voice.

[0284] "Real-time display" is a display method for immediately providing users with current situations and information.

[0285] "Durability analysis" is an analysis for evaluating the strength and lifespan of buildings and structures.

[0286] "Information update" means keeping data in the latest state by adding new information or modifying existing information.

[0287] As a form of implementing this invention, an information processing system consists of a server, terminals, and users. The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, the affected areas of past disasters, etc. The server executes a machine learning algorithm using the collected data to predict disaster damage in a specific geographical area. Based on the results, it calculates an optimal evacuation route to avoid the identified predicted damage area and generates customized route information for each user. This generated evacuation route information is pre-delivered to the users' terminals.

[0288] The terminal saves the evacuation route information received from the server in local storage so that the information can be referenced even in an offline state. When the user launches the app, the terminal uses GPS to confirm the current location and provides appropriate route guidance to the user while using both voice instructions and real-time display of the progress status based on the pre-saved evacuation route information. This enables the user to evacuate safely and quickly.

[0289] For example, when a large-scale earthquake occurs, the user can check the evacuation route information obtained in advance using a smartphone and proceed along the optimal route from home to the nearest evacuation shelter. This system reduces the anxiety during disasters and enables safe evacuation even in situations where the communication environment is unstable.

[0290] An example of a prompt sentence for the generation AI model is "Please explain the design of an AI system that allows a user to pre-check a safe evacuation route and proceed with evacuation following voice guidance during an increased flood risk." This prompt sentence is used to explain to the generation AI model how this system is utilized in an emergency.

[0291] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0292] Step 1:

[0293] The server collects geographical information and disaster history from an external database. Its inputs are geographical information and disaster history data, which are retrieved via the network. As output, the retrieved data is stored in an internal data structure. Specifically, it uses APIs to retrieve the latest geographical data and historical disaster data from external data providers.

[0294] Step 2:

[0295] The server analyzes the collected data using machine learning algorithms to identify the areas where damage is expected. The input consists of geographical information and disaster history obtained in step 1, which are then input into the model to perform predictive calculations. The output is data showing geographical areas at risk of disaster. Specifically, it predicts the expected collapse of buildings and changes in terrain during a disaster and visualizes the risk areas on a map based on these predictions.

[0296] Step 3:

[0297] The server calculates the optimal evacuation route that avoids risk areas and creates this route information. The input is map information of the risk areas identified in step 2. A route optimization algorithm is used to calculate a safe route. The output is customized evacuation route information provided to the user. Specifically, it calculates a route that avoids risks while reaching a shelter in the shortest possible time.

[0298] Step 4:

[0299] The server pre-distributes the generated evacuation route information to the user's terminal. The input is the evacuation route data generated in step 3, which is sent to the terminal via a communication protocol. The output is the terminal's storage holding the evacuation route information. Specifically, the server sends the data to the terminal via the communication line and saves it locally.

[0300] Step 5:

[0301] When the user launches the app, the device starts navigation based on saved evacuation route information. The input is the user's current location, which is obtained using GPS. Using this information, the device provides real-time voice instructions and displays progress while comparing it with the saved route. The output is navigation information to help the user safely navigate the evacuation route. Specifically, it starts voice guidance along with a map display and provides visual and auditory feedback to the user according to their progress.

[0302] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0303] This invention provides a system combining an information processing device, an emotion engine, and a user terminal to support evacuation during disasters. This system is implemented as follows.

[0304] Server Operation: The server first collects geographical information and historical disaster data from an external database. Based on this data, it uses machine learning algorithms to analyze the area where damage is expected during a disaster and calculates the optimal evacuation route to avoid that area. The server also performs structural analysis of buildings and generates data to predict the risk of damage. Furthermore, it generates optimized evacuation route information for each user and distributes it to their terminals.

[0305] Operation of the Emotion Engine: The emotion engine recognizes the user's emotional state by analyzing the user's voice and operation data. For example, it measures the levels of anxiety and stress in real time through voice analysis. Based on this result, the emotion engine dynamically adjusts the method of guiding the evacuation route suitable for the user's state.

[0306] Operation of the Terminal: The terminal stores the evacuation route information distributed from the server and changes the guidance method for the user based on the feedback provided by the emotion engine. Specifically, when the user feels strong anxiety, the terminal provides more detailed guidance and encouraging words in voice. Also, when the user's stress level is high, the terminal recalculates the evacuation route to recommend a rest point and proposes it to the user.

[0307] How the User Uses It: The user launches the app on the terminal during a disaster and checks the evacuation route. For example, when the user is in an area where flooding of a river is a concern, the app presents a safe detour route while referring to the pre-stored data. At the same time, the terminal continuously monitors the user's emotions and provides flexible guidance as needed.

[0308] As described above, the user can receive customized evacuation information according to their emotional state and can evacuate with peace of mind. This system provides a comprehensive solution for reducing stress during disasters and supporting safe evacuation.

[0309] The following explains the processing flow.

[0310] Step 1:

[0311] The server accesses multiple external databases to collect the latest geographical information and disaster history data. This collection includes local weather data, infrastructure status, and past disaster records.

[0312] Step 2:

[0313] The server runs machine learning algorithms based on the collected data to analyze areas where danger is expected during a disaster. This analysis displays specific areas where damage is predicted on a map.

[0314] Step 3:

[0315] The server works with the analysis results to calculate the optimal evacuation route. This route calculation takes into account the location of evacuation sites, the available road network, and bridge conditions. The calculated evacuation route is customized to suit the user's place of residence and mode of transportation.

[0316] Step 4:

[0317] The emotion engine analyzes the user's voice input and device sensor information to evaluate the user's emotional state. The emotion engine identifies the user's level of anxiety and stress in real time based on the tone of voice and word choice.

[0318] Step 5:

[0319] The server pre-distributes calculated evacuation route information to the user's terminal. This distribution includes not only the evacuation route but also settings for guidance methods tailored to the user's emotional state, as analyzed by the emotion engine.

[0320] Step 6:

[0321] The device stores received evacuation information locally and prepares guidance methods tailored to the user's emotional state. Based on evacuation route information, it adjusts screen displays and voice guidance to provide flexible directions to the user.

[0322] Step 7:

[0323] The user launches an app on their device to check the current evacuation route. If the device determines that the user is experiencing high stress, it provides encouraging messages and detailed guides via voice.

[0324] Step 8:

[0325] The device continuously updates location information even after the user begins evacuating, providing real-time guidance for safe routes. It also monitors the user's emotional state and updates or recalculates route guidance as needed to support safe evacuation.

[0326] (Example 2)

[0327] Next, we will describe Example 2. 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".

[0328] Evacuation during disasters is often prone to confusion, and there is a problem in that people may not be able to take appropriate evacuation actions, especially when their emotional state is unstable. Furthermore, conventional evacuation route guidance systems cannot provide flexible route guidance that takes emotions into account, making safe and secure evacuation difficult.

[0329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0330] In this invention, the server includes means for collecting spatial information and past disaster history from external information sources, means for analyzing the spatial information and past disaster history using a machine learning algorithm to identify areas expected to be affected during a disaster, and means for acquiring the user's emotional state and adapting the route guidance unit based on that emotional state. As a result, users can obtain evacuation information optimized to their own emotional state.

[0331] "External information sources" is a general term for databases and repositories that systems use to acquire disaster-related information, including geographical information and disaster history.

[0332] "Spatial information" refers to information about geographical location, regional structure, topography, etc.

[0333] "Past disaster history" refers to record data regarding the type, scale, and scope of impact of disasters that have occurred in the past.

[0334] A "machine learning algorithm" is a collection of programs used to analyze large amounts of data and perform pattern recognition and prediction.

[0335] "User terminal" refers to electronic devices such as mobile phones, tablets, and PCs that users directly operate to obtain information.

[0336] "Emotional state" refers to the user's mental state, mood, stress levels, and anxiety levels.

[0337] The "route guidance section" refers to the functions and components within a system that present evacuation routes to users and provide navigation.

[0338] This system is designed to support evacuation during disasters by combining an information processing device, an emotion analysis mechanism, and user terminals.

[0339] The server first collects spatial information and historical disaster data from external sources. Based on this data, the server uses machine learning algorithms to analyze areas expected to be affected during a disaster. By using the Python Scikit-learn library for machine learning, the server can quickly and accurately analyze large amounts of data and identify the extent of the impact. The server also uses a map API to calculate the optimal evacuation route based on the user's location and delivers it to the user's terminal.

[0340] The emotion analysis mechanism monitors the user's voice data and operation history to analyze their emotional state in real time. This analysis uses a natural language processing framework (e.g., Transformers) as the emotion analysis model. This allows for the measurement of the user's anxiety and stress levels, and the adjustment of evacuation route guidance methods as needed.

[0341] The terminal stores evacuation route information distributed from the server and provides it to users through structured visual and audio interfaces in the event of a disaster. The terminal can also adapt its guidance based on feedback from an emotion analysis mechanism. For example, if the user is highly anxious, the terminal will reinforce the guidance with reassuring language.

[0342] When signs of a disaster appear, users can use their devices to check evacuation routes. An example of a prompt related to suggesting evacuation routes is, "Please tell me the best evacuation route in an area where river flooding is expected." By inputting this prompt into a generating AI model, more appropriate evacuation information can be obtained quickly.

[0343] Based on the above, the system can provide a concrete form of support for safe and secure evacuation that takes into account the emotional state of the users.

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] The server collects spatial information and historical disaster data from external sources. Inputs include geographic location information and access to historical disaster databases. This allows the server to utilize a Geographic Information System (GIS) to store this information in a database.

[0347] Step 2:

[0348] The server analyzes collected spatial information and past disaster history using machine learning algorithms. The input is the geographic information and disaster data collected in the previous step. The server uses this information to extract risk areas using Scikit-learn. The output generates identification of areas expected to be affected and candidate evacuation routes.

[0349] Step 3:

[0350] The server receives the user's current location information as input and calculates the optimal evacuation route. This utilizes location data confirmed in real time via a map API. The server generates route information to provide the user with the calculation results and delivers it as output to the user's terminal.

[0351] Step 4:

[0352] The emotion engine monitors voice data and operation logs obtained when the user operates the device in real time. Inputs include voice samples and screen operation history. The emotion engine analyzes these and determines the emotional state through a natural language processing framework. The output is the result of the emotional state analysis.

[0353] Step 5:

[0354] The terminal provides the user with evacuation route information received from the server. Input to the terminal consists of structured data and audio from the server. The terminal uses this information to provide guidance through visual and audio interfaces. Output is evacuation route information that the user can visually confirm and is also navigated by voice.

[0355] Step 6:

[0356] The user checks the evacuation route information provided on the device and actually begins evacuating according to that route. Inputs include route information from the device and emotion-based guidance provided by the device. Based on this information, the user can safely evacuate from the disaster area. The output is simply the user reaching a safe location.

[0357] (Application Example 2)

[0358] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0359] Providing appropriate evacuation routes during disasters is crucial, but flexible responses that take into account the emotional state of users are required. Furthermore, the current lack of systems for evacuation support using autonomous vehicles makes it difficult to evacuate with peace of mind. Additionally, technology for analyzing user emotions from voice data and dynamically adjusting evacuation guidance based on the results is insufficient. Therefore, a system is needed that provides appropriate evacuation guidance tailored to emotions, ensuring safe and secure evacuation.

[0360] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0361] In this invention, the server includes means for collecting geographical information and disaster history from an external database; means for analyzing the geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster; means for calculating evacuation routes that avoid the identified area; means for pre-distributing the evacuation route information to a user terminal; means for storing the evacuation route information on the user terminal and providing the evacuation route when a disaster occurs; means for evaluating voice data for analyzing the user's emotional state; and means for dynamically adjusting evacuation route guidance based on the user's emotional state. This enables flexible evacuation guidance that responds to the user's emotions, allowing for safe and secure evacuation.

[0362] An "external database" is an external source of information that stores geographical information and disaster history information.

[0363] "Geographic information" refers to data about the physical characteristics of a particular area, such as its topography, transportation, and building layout.

[0364] "Disaster history" refers to record data regarding the types, scope, and impact of disasters that have occurred in the past.

[0365] A "machine learning algorithm" is a computational method that automatically learns patterns and rules from large amounts of data to perform decision-making and classification.

[0366] "Areas where damage is expected" refers to geographical areas identified as having a high probability of property damage and personal injury during a disaster.

[0367] An "evacuation route" is a path that indicates the route and steps to take to move to a safe place in the event of a disaster.

[0368] A "user terminal" refers to a digital device such as a smartphone or tablet owned by a user.

[0369] "Emotional state" refers to the psychological situation and emotional level inferred from the user's voice and other actions.

[0370] "Voice data" refers to information recorded in digital format using the user's voice.

[0371] To realize this invention, the server efficiently collects and analyzes information necessary during a disaster. Specifically, the server obtains geographical information and past disaster history through an external database, and uses machine learning algorithms based on this information to identify the area where damage is expected. This can be achieved using machine learning libraries such as TensorFlow. Furthermore, based on the analysis results, the server calculates the optimal evacuation route and delivers that information to user terminals.

[0372] The terminal receives evacuation route information distributed from the server and displays it appropriately to the user. Furthermore, the terminal is equipped with an emotion engine that acquires the user's voice data and evaluates their emotional state in real time. Natural language processing tools are used for voice analysis, and the method of evacuation guidance is dynamically adjusted based on the emotional state obtained. If the user shows anxiety, detailed guides and encouraging messages are provided to reassure them.

[0373] Users can use their devices to check evacuation routes during a disaster. For example, if a user is in an area at risk of flooding, the app will provide a safe alternative route based on previously saved data. If the user is feeling anxious, the device will display a message such as, "Don't worry, this is a safe route, please stay calm."

[0374] The system utilizes a generative AI model to generate guidance text that is tailored to the user's emotions. Examples of prompt text include the following:

[0375] "Disaster relief evacuation support app for autonomous vehicles: We will build a system that evaluates the user's emotions based on voice data, provides the optimal evacuation route, and offers reassuring navigation. How will this be implemented?"

[0376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0377] Step 1:

[0378] The server collects geographical information and disaster history from an external database. In this step, the server retrieves the necessary data via an API, collecting geographical information such as regional topography and road information, and disaster history data such as past disaster locations. The input is the API endpoint, and the output is a dataset containing this information.

[0379] Step 2:

[0380] The server uses a machine learning algorithm to identify the area where damage is expected in the event of a disaster. The server takes the dataset collected in step 1 as input and uses a specific algorithm (e.g., random forest) to predict the risk area. The output specifies the geographical area where damage is expected.

[0381] Step 3:

[0382] The system calculates evacuation routes to avoid identified risk areas for the server. Here, geolocation data is used as input, and a suitable mapping tool (e.g., Google Maps API) is used to generate safe evacuation routes. The output is route information for the evacuation routes.

[0383] Step 4:

[0384] The server distributes the calculated evacuation route information to the user terminal. The server uses the route information generated in the previous step as input and sends data to the user terminal. The output is route information accessible on the user terminal.

[0385] Step 5:

[0386] The terminal stores evacuation route information received from the server and displays it to the user. In this step, the terminal processes the received route information and visualizes it as a map on the interface. The input is evacuation route data, and the output is the display on the user interface.

[0387] Step 6:

[0388] The device acquires the user's voice data and analyzes their emotional state using an emotion engine. Here, the device uses a microphone to collect the user's voice as input and utilizes NLP (Natural Language Processing) to evaluate their emotional state. The output is the result of the user's emotional state analysis.

[0389] Step 7:

[0390] The device dynamically adjusts evacuation instructions based on the user's emotional state. It uses the results of the emotional analysis as input to generate appropriate navigation instructions and provide them to the user. Specifically, if the user is showing anxiety, it plays an encouraging message via voice. The output is the adjusted guidance instructions.

[0391] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0392] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0393] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0394] [Third Embodiment]

[0395] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0396] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0397] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0398] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0399] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0400] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0401] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0402] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0403] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0404] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0405] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0406] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0407] This invention relates to an information processing system that enables safe and rapid evacuation during disasters. This system primarily consists of a server, terminals, and users who utilize them.

[0408] Server Operation: The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, and the extent of impact from past disasters. Next, the server uses this data to run machine learning algorithms to analyze building strength and topographical characteristics, and identify areas where damage is predicted during a disaster. Based on this analysis, it calculates optimized evacuation routes and generates customized route information for each user. The generated evacuation route information is delivered in advance to the user's smartphone or other device.

[0409] Device Operation: The device stores evacuation route information received from the server in local storage, allowing access to this information even when offline during a disaster. When the user launches the app, the device uses GPS to determine the user's current location and provides appropriate directions based on the previously stored evacuation route information. This includes displaying maps, providing voice guidance, and text instructions.

[0410] How users can use the system: When a disaster occurs, users can launch the app on their device to immediately check pre-distributed evacuation routes. For example, if a major earthquake occurs while a user is at home, the app will present the optimal evacuation route calculated in advance and guide the user to the nearest safe evacuation center. This procedure allows users to evacuate safely even in situations with unstable communication environments. This system reduces anxiety during evacuation and enables users to evacuate safely based on appropriate decisions.

[0411] As described above, the present invention improves the safety and speed of evacuation during disasters, and is a system that provides substantial safety to users.

[0412] The following describes the processing flow.

[0413] Step 1:

[0414] The server automatically collects geographical information and disaster history from external databases. This process involves retrieving road conditions, weather conditions, and historical disaster data via various APIs and data feeds.

[0415] Step 2:

[0416] The server uses the collected data to run machine learning algorithms. This identifies areas where damage is expected due to the strength of buildings and terrain, as well as river flooding and earthquakes. This analysis then displays high-risk zones on a map.

[0417] Step 3:

[0418] Based on the analysis results, the server calculates an optimized evacuation route that avoids the danger zone. This calculation takes into account available roads, the location of shelters, and means of transportation to identify the safest route.

[0419] Step 4:

[0420] The server compresses evacuation route information and distributes it to the user's device in advance. This information is encrypted and prepared for offline use on the device.

[0421] Step 5:

[0422] The terminal saves the evacuation route information received from the server to its local storage. At this time, data verification, such as checksums, is performed to confirm that the information has been saved correctly.

[0423] Step 6:

[0424] When a disaster occurs, the user launches an evacuation route app on their device. The app refers to pre-saved evacuation route information and displays the optimal evacuation route in real time.

[0425] Step 7:

[0426] The device uses GPS to determine the user's current location and provides directions along an evacuation route. This includes map display, voice guidance, and text instructions as needed.

[0427] Step 8:

[0428] Users move safely and quickly to evacuation shelters by following the displayed evacuation route. The device updates location information in real time during movement and adjusts route guidance as needed.

[0429] (Example 1)

[0430] Next, we will describe Example 1. 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."

[0431] In emergency situations such as disasters, it is necessary to provide accurate and individually tailored evacuation information in advance to enable many people to evacuate quickly and safely. However, conventional route guidance systems have difficulty providing evacuation routes that take into account real-time geographical conditions and the impact of events. Furthermore, while it would be effective to save evacuation route information on devices in advance when communication environments are limited during a disaster, many systems do not have such functionality.

[0432] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0433] In this invention, the server includes means for collecting area information and event history from general information sources, means for analyzing the area information and event history using a data analysis algorithm to identify areas where damage is expected during an event, and means for calculating routes that avoid the identified areas. This makes it possible to provide users with individually optimized route information even in the event of a disaster or emergency, thereby supporting rapid and safe evacuation.

[0434] "Information sources" refer to general databases and information services that provide domain information and event histories.

[0435] "Regional information" refers to data that includes location information, topography, infrastructure conditions, and other information related to a specific geographical area.

[0436] "Event history" refers to recorded data regarding the circumstances and scope of past disasters and emergencies.

[0437] A "data analysis algorithm" refers to computational methods and models used to analyze collected data and derive effective judgments and predictions.

[0438] "Identified areas" refer to locations where damage is expected to occur when an event takes place, as revealed using data analysis algorithms.

[0439] A "route" refers to the path a user takes to travel safely and quickly from one point to another.

[0440] "User device" refers to a communication terminal or device carried by a user, which is used for receiving, storing, and displaying information.

[0441] "Route information" refers to detailed instructions and guidance regarding the optimal travel route that has been analyzed and calculated.

[0442] This invention supports efficient evacuation during disasters and emergencies using an information processing system consisting of a server, terminals, and users. Specifically, the server collects area information and event history from general information sources and executes a data analysis algorithm based on this information to predict risks in a specific area.

[0443] The server uses open-source geographic information and public event databases to collect necessary data. It also uses TensorFlow or similar data analysis software to analyze the collected data and identify areas predicted to be high-risk during an event. Through this analysis, the server calculates the optimal route avoiding risk areas and delivers the generated route information to the user's device. The generated route information is handled as text prompts, not in JSON format. An example of such a prompt might be, "Calculate the safest evacuation route during a disaster and generate a route from the user's current location to the nearest evacuation shelter."

[0444] The device saves received route information to local storage, making it accessible offline even in unstable network conditions. When the user launches the app, the device uses its built-in GPS function to determine the user's current location and provides voice and visual route guidance based on the saved route information. This guidance includes map display, voice guidance, and text directions.

[0445] By operating the terminal, users can quickly confirm evacuation routes during a disaster and move safely to their destination. Therefore, this system provides an effective means of supporting users to act quickly and safely during a disaster.

[0446] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0447] Step 1:

[0448] The server collects regional information and event history from common sources. Inputs include URLs and API keys for geographic information databases and event history databases. The server queries these sources to retrieve geographical data and historical event history for a given region. Outputs are raw data retrieved from the databases, specifically including map data, road conditions, and historical disaster history.

[0449] Step 2:

[0450] The server analyzes the collected data using data analysis algorithms. The input is the raw data obtained in Step 1. The server uses analysis tools such as TensorFlow to evaluate the strength of structures within the region, topographic characteristics, and the impact of past disasters. For data processing, it utilizes neural networks to identify risk areas. The output is evaluation data indicating risk areas. Specifically, it represents high-risk areas in a heatmap format.

[0451] Step 3:

[0452] The server calculates the optimal route based on the analysis results. The input is the risk assessment data obtained in step 2. The server uses Dijkstra's algorithm or the A algorithm to calculate a route that avoids high-risk areas. The data calculation involves finding the shortest route based on the distance and time between each point. The output is evacuation route information. Specifically, it includes detailed routes for the user to reach their destination.

[0453] Step 4:

[0454] The server sends the generated route information to the user's device. The input is the evacuation route information generated in step 3. The server converts this information into a JSON prompt message and sends it to the terminal via push notification or the cloud. The output is the route information stored on the terminal. Specifically, it is saved as a file on the terminal so that the user can access it even when offline.

[0455] Step 5:

[0456] The device provides instructions to the user based on stored route information. Input is route information received from the server and stored on the device. When the user launches the app, the device uses GPS to determine the current location and refers to the stored data to provide optimal route guidance. It uses a map display library to visually show the route and provides voice guidance and text instructions. Output is evacuation instructions provided to the user, specifically including on-screen map displays and voice guidance.

[0457] Step 6:

[0458] The user follows the evacuation instructions provided by the device. The input is the evacuation instructions shown in step 5. The user confirms the suggested route and begins moving safely. By following the route as instructed, the user can safely evacuate to their destination. The output is that the user has reached the evacuation shelter. Specifically, this refers to the situation where the user has safely completed the evacuation.

[0459] (Application Example 1)

[0460] Next, we will explain Application Example 1. In the following explanation, 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."

[0461] Evacuation during disasters is highly urgent and requires rapid and safe movement. However, conventional evacuation route guidance systems lack features that enhance user confidence, such as real-time progress updates and voice instructions. Therefore, there is a need for the development of a system that provides flexible evacuation routes tailored to disaster situations and ensures user safety.

[0462] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0463] In this invention, the server includes means for collecting geographical information and disaster history from an external database, means for analyzing the geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster, and means for providing voice instructions and real-time display of progress. This enables users to evacuate safely and quickly during a disaster, and to select an evacuation route with a sense of security through appropriate guidance and voice instructions.

[0464] An "evacuation route" is a route selected to ensure that one can reach their destination safely and quickly in the event of a disaster.

[0465] An "information processing device" is a device used to collect and analyze data and generate or provide necessary information.

[0466] An "external database" is an external storage device or data management system that stores data such as geographical information and disaster history.

[0467] "Geographical information" refers to information related to geographic space, such as the layout of roads, topography, and the location of buildings.

[0468] "Disaster history" refers to records and data related to disasters that have occurred in the past, including the frequency and scope of disaster occurrences.

[0469] A "machine learning algorithm" is a mathematical model that learns patterns and rules from data to perform analysis and prediction.

[0470] "Voice instructions" refer to instructions or guidance provided to users using voice.

[0471] "Real-time display" refers to a display method that provides users with the current situation and information immediately.

[0472] "Durability analysis" is an analysis used to evaluate the strength and lifespan of buildings and structures.

[0473] "Information updating" means keeping data up-to-date by adding new information or correcting existing information.

[0474] In an embodiment of this invention, the information processing system consists of a server, a terminal, and a user. The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, and the extent of impact of past disasters. The server uses the collected data to execute machine learning algorithms and predict disaster damage in a specific geographical area. Based on the results, it calculates the optimal evacuation route to avoid the identified damage prediction area and generates customized route information for each user. This generated evacuation route information is delivered to the user's terminal in advance.

[0475] The device stores evacuation route information received from the server in local storage, allowing access to this information even when offline. When the user launches the app, the device uses GPS to determine its current location and, based on the pre-stored evacuation route information, provides appropriate guidance to the user using a combination of voice instructions and real-time progress displays. This enables the user to evacuate safely and quickly.

[0476] For example, in the event of a major earthquake, users can use their smartphones to check evacuation route information they have obtained in advance and proceed along the optimal route from their home to the nearest evacuation center. This system reduces anxiety during disasters and enables safe evacuation even in situations where communication environments are unstable.

[0477] An example of a prompt for a generative AI model is: "Describe the design of an AI system that, when a user faces an increased risk of flooding, allows them to pre-determine a safe evacuation route and then evacuate according to voice guidance." This prompt is used to explain to the generative AI model how this system would be used in an emergency.

[0478] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0479] Step 1:

[0480] The server collects geographical information and disaster history from an external database. Its inputs are geographical information and disaster history data, which are retrieved via the network. As output, the retrieved data is stored in an internal data structure. Specifically, it uses APIs to retrieve the latest geographical data and historical disaster data from external data providers.

[0481] Step 2:

[0482] The server analyzes the collected data using machine learning algorithms to identify the areas where damage is expected. The input consists of geographical information and disaster history obtained in step 1, which are then input into the model to perform predictive calculations. The output is data showing geographical areas at risk of disaster. Specifically, it predicts the expected collapse of buildings and changes in terrain during a disaster and visualizes the risk areas on a map based on these predictions.

[0483] Step 3:

[0484] The server calculates the optimal evacuation route that avoids risk areas and creates this route information. The input is map information of the risk areas identified in step 2. A route optimization algorithm is used to calculate a safe route. The output is customized evacuation route information provided to the user. Specifically, it calculates a route that avoids risks while reaching a shelter in the shortest possible time.

[0485] Step 4:

[0486] The server pre-distributes the generated evacuation route information to the user's terminal. The input is the evacuation route data generated in step 3, which is sent to the terminal via a communication protocol. The output is the terminal's storage holding the evacuation route information. Specifically, the server sends the data to the terminal via the communication line and saves it locally.

[0487] Step 5:

[0488] When the user launches the app, the device starts navigation based on saved evacuation route information. The input is the user's current location, which is obtained using GPS. Using this information, the device provides real-time voice instructions and displays progress while comparing it with the saved route. The output is navigation information to help the user safely navigate the evacuation route. Specifically, it starts voice guidance along with a map display and provides visual and auditory feedback to the user according to their progress.

[0489] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0490] This invention provides a system combining an information processing device, an emotion engine, and a user terminal to support evacuation during disasters. This system is implemented as follows.

[0491] Server Operation: The server first collects geographical information and historical disaster data from an external database. Based on this data, it uses machine learning algorithms to analyze the area where damage is expected during a disaster and calculates the optimal evacuation route to avoid that area. The server also performs structural analysis of buildings and generates data to predict the risk of damage. Furthermore, it generates optimized evacuation route information for each user and distributes it to their terminals.

[0492] Emotional Engine Operation: The emotional engine recognizes the user's emotional state by analyzing the user's voice and operation data. For example, it measures anxiety and stress levels in real time through voice analysis. Based on these results, the emotional engine dynamically adjusts the evacuation route guidance method to suit the user's state.

[0493] Terminal Operation: The terminal stores evacuation route information delivered from the server and modifies the way it guides the user based on feedback provided by the emotion engine. Specifically, if the user is experiencing high levels of anxiety, the terminal provides more detailed guidance and words of encouragement via voice. Also, if the user's stress level is high, it recalculates the evacuation route to recommend rest points and suggests them to the user.

[0494] User Usage: When a disaster occurs, users launch the app on their device to check evacuation routes. For example, if a user is in an area where river flooding is a concern, the app will refer to pre-stored data and suggest a safe detour route. At the same time, the device continuously monitors the user's emotions and provides flexible guidance as needed.

[0495] As a result, users can receive evacuation information customized to their emotional state, enabling them to evacuate with peace of mind. This system provides a comprehensive solution to reduce stress during disasters and support safe evacuation.

[0496] The following describes the processing flow.

[0497] Step 1:

[0498] The server accesses multiple external databases to collect the latest geographical information and disaster history data. This collection includes local weather data, infrastructure conditions, and records of past disasters.

[0499] Step 2:

[0500] The server runs machine learning algorithms based on the collected data to analyze areas where danger is expected during a disaster. This analysis displays specific areas where damage is predicted on a map.

[0501] Step 3:

[0502] The server works with the analysis results to calculate the optimal evacuation route. This route calculation takes into account the location of evacuation sites, the available road network, and bridge conditions. The calculated evacuation route is customized to suit the user's place of residence and mode of transportation.

[0503] Step 4:

[0504] The emotion engine analyzes the user's voice input and device sensor information to evaluate the user's emotional state. The emotion engine identifies the user's level of anxiety and stress in real time based on the tone of voice and word choice.

[0505] Step 5:

[0506] The server pre-distributes calculated evacuation route information to the user's terminal. This distribution includes not only the evacuation route but also settings for guidance methods tailored to the user's emotional state, as analyzed by the emotion engine.

[0507] Step 6:

[0508] The device stores received evacuation information locally and prepares guidance methods tailored to the user's emotional state. Based on evacuation route information, it adjusts screen displays and voice guidance to provide flexible directions to the user.

[0509] Step 7:

[0510] The user launches an app on their device to check the current evacuation route. If the device determines that the user is experiencing high stress, it provides encouraging messages and detailed guides via voice.

[0511] Step 8:

[0512] The device continuously updates location information even after the user begins evacuating, providing real-time guidance for safe routes. It also monitors the user's emotional state and updates or recalculates route guidance as needed to support safe evacuation.

[0513] (Example 2)

[0514] Next, we will describe Example 2. 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."

[0515] Evacuation during disasters is often prone to confusion, and there is a problem in that people may not be able to take appropriate evacuation actions, especially when their emotional state is unstable. Furthermore, conventional evacuation route guidance systems cannot provide flexible route guidance that takes emotions into account, making safe and secure evacuation difficult.

[0516] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0517] In this invention, the server includes means for collecting spatial information and past disaster history from external information sources, means for analyzing the spatial information and past disaster history using a machine learning algorithm to identify areas expected to be affected during a disaster, and means for acquiring the user's emotional state and adapting the route guidance unit based on that emotional state. As a result, users can obtain evacuation information optimized to their own emotional state.

[0518] "External information sources" is a general term for databases and repositories that systems use to acquire disaster-related information, including geographical information and disaster history.

[0519] "Spatial information" refers to information about geographical location, regional structure, topography, etc.

[0520] "Past disaster history" refers to record data regarding the type, scale, and scope of impact of disasters that have occurred in the past.

[0521] A "machine learning algorithm" is a collection of programs used to analyze large amounts of data and perform pattern recognition and prediction.

[0522] "User terminal" refers to electronic devices such as mobile phones, tablets, and PCs that users directly operate to obtain information.

[0523] "Emotional state" refers to the user's mental state, mood, stress levels, and anxiety levels.

[0524] The "route guidance section" refers to the functions and components within a system that present evacuation routes to users and provide navigation.

[0525] This system is designed to support evacuation during disasters by combining an information processing device, an emotion analysis mechanism, and user terminals.

[0526] The server first collects spatial information and historical disaster data from external sources. Based on this data, the server uses machine learning algorithms to analyze areas expected to be affected during a disaster. By using the Python Scikit-learn library for machine learning, the server can quickly and accurately analyze large amounts of data and identify the extent of the impact. The server also uses a map API to calculate the optimal evacuation route based on the user's location and delivers it to the user's terminal.

[0527] The emotion analysis mechanism monitors the user's voice data and operation history to analyze their emotional state in real time. This analysis uses a natural language processing framework (e.g., Transformers) as the emotion analysis model. This allows for the measurement of the user's anxiety and stress levels, and the adjustment of evacuation route guidance methods as needed.

[0528] The terminal stores evacuation route information distributed from the server and provides it to users through structured visual and audio interfaces in the event of a disaster. The terminal can also adapt its guidance based on feedback from an emotion analysis mechanism. For example, if the user is highly anxious, the terminal will reinforce the guidance with reassuring language.

[0529] When signs of a disaster appear, users can use their devices to check evacuation routes. An example of a prompt related to suggesting evacuation routes is, "Please tell me the best evacuation route in an area where river flooding is expected." By inputting this prompt into a generating AI model, more appropriate evacuation information can be obtained quickly.

[0530] Based on the above, the system can provide a concrete form of support for safe and secure evacuation that takes into account the emotional state of the users.

[0531] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0532] Step 1:

[0533] The server collects spatial information and historical disaster data from external sources. Inputs include geographic location information and access to historical disaster databases. This allows the server to utilize a Geographic Information System (GIS) to store this information in a database.

[0534] Step 2:

[0535] The server analyzes collected spatial information and past disaster history using machine learning algorithms. The input is the geographic information and disaster data collected in the previous step. The server uses this information to extract risk areas using Scikit-learn. The output generates identification of areas expected to be affected and candidate evacuation routes.

[0536] Step 3:

[0537] The server receives the user's current location information as input and calculates the optimal evacuation route. This utilizes location data confirmed in real time via a map API. The server generates route information to provide the user with the calculation results and delivers it as output to the user's terminal.

[0538] Step 4:

[0539] The emotion engine monitors voice data and operation logs obtained when the user operates the device in real time. Inputs include voice samples and screen operation history. The emotion engine analyzes these and determines the emotional state through a natural language processing framework. The output is the result of the emotional state analysis.

[0540] Step 5:

[0541] The terminal provides the user with evacuation route information received from the server. Input to the terminal consists of structured data and audio from the server. The terminal uses this information to provide guidance through visual and audio interfaces. Output is evacuation route information that the user can visually confirm and is also navigated by voice.

[0542] Step 6:

[0543] The user checks the evacuation route information provided on the device and actually begins evacuating according to that route. Inputs include route information from the device and emotion-based guidance provided by the device. Based on this information, the user can safely evacuate from the disaster area. The output is simply the user reaching a safe location.

[0544] (Application Example 2)

[0545] Next, we will explain application example 2. In the following explanation, 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."

[0546] Providing appropriate evacuation routes during disasters is crucial, but flexible responses that take into account the emotional state of users are required. Furthermore, the current lack of systems for evacuation support using autonomous vehicles makes it difficult to evacuate with peace of mind. Additionally, technology for analyzing user emotions from voice data and dynamically adjusting evacuation guidance based on the results is insufficient. Therefore, a system is needed that provides appropriate evacuation guidance tailored to emotions, ensuring safe and secure evacuation.

[0547] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0548] In this invention, the server includes means for collecting geographical information and disaster history from an external database; means for analyzing the geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster; means for calculating evacuation routes that avoid the identified area; means for pre-distributing the evacuation route information to a user terminal; means for storing the evacuation route information on the user terminal and providing the evacuation route when a disaster occurs; means for evaluating voice data for analyzing the user's emotional state; and means for dynamically adjusting evacuation route guidance based on the user's emotional state. This enables flexible evacuation guidance that responds to the user's emotions, allowing for safe and secure evacuation.

[0549] An "external database" is an external source of information that stores geographical information and disaster history information.

[0550] "Geographic information" refers to data about the physical characteristics of a particular area, such as its topography, transportation, and building layout.

[0551] "Disaster history" refers to record data regarding the types, scope, and impact of disasters that have occurred in the past.

[0552] A "machine learning algorithm" is a computational method that automatically learns patterns and rules from large amounts of data to perform decision-making and classification.

[0553] "Areas where damage is expected" refers to geographical areas identified as having a high probability of property damage and personal injury during a disaster.

[0554] An "evacuation route" is a path that indicates the route and steps to take to move to a safe place in the event of a disaster.

[0555] A "user terminal" refers to a digital device such as a smartphone or tablet owned by a user.

[0556] "Emotional state" refers to the psychological situation and emotional level inferred from the user's voice and other actions.

[0557] "Voice data" refers to information recorded in digital format using the user's voice.

[0558] To realize this invention, the server efficiently collects and analyzes information necessary during a disaster. Specifically, the server obtains geographical information and past disaster history through an external database, and uses machine learning algorithms based on this information to identify the area where damage is expected. This can be achieved using machine learning libraries such as TensorFlow. Furthermore, based on the analysis results, the server calculates the optimal evacuation route and delivers that information to user terminals.

[0559] The terminal receives evacuation route information distributed from the server and displays it appropriately to the user. Furthermore, the terminal is equipped with an emotion engine that acquires the user's voice data and evaluates their emotional state in real time. Natural language processing tools are used for voice analysis, and the method of evacuation guidance is dynamically adjusted based on the emotional state obtained. If the user shows anxiety, detailed guides and encouraging messages are provided to reassure them.

[0560] Users can use their devices to check evacuation routes during a disaster. For example, if a user is in an area at risk of flooding, the app will provide a safe alternative route based on previously saved data. If the user is feeling anxious, the device will display a message such as, "Don't worry, this is a safe route, please stay calm."

[0561] The system utilizes a generative AI model to generate guidance text that is tailored to the user's emotions. Examples of prompt text include the following:

[0562] "Disaster relief evacuation support app for autonomous vehicles: We will build a system that evaluates the user's emotions based on voice data, provides the optimal evacuation route, and offers reassuring navigation. How will this be implemented?"

[0563] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0564] Step 1:

[0565] The server collects geographical information and disaster history from an external database. In this step, the server retrieves the necessary data via an API, collecting geographical information such as regional topography and road information, and disaster history data such as past disaster locations. The input is the API endpoint, and the output is a dataset containing this information.

[0566] Step 2:

[0567] The server uses a machine learning algorithm to identify the area where damage is expected in the event of a disaster. The server takes the dataset collected in step 1 as input and uses a specific algorithm (e.g., random forest) to predict the risk area. The output specifies the geographical area where damage is expected.

[0568] Step 3:

[0569] The system calculates evacuation routes to avoid identified risk areas for the server. Here, geolocation data is used as input, and a suitable mapping tool (e.g., Google Maps API) is used to generate safe evacuation routes. The output is route information for the evacuation routes.

[0570] Step 4:

[0571] The server distributes the calculated evacuation route information to the user terminal. The server uses the route information generated in the previous step as input and sends data to the user terminal. The output is route information accessible on the user terminal.

[0572] Step 5:

[0573] The terminal stores evacuation route information received from the server and displays it to the user. In this step, the terminal processes the received route information and visualizes it as a map on the interface. The input is evacuation route data, and the output is the display on the user interface.

[0574] Step 6:

[0575] The device acquires the user's voice data and analyzes their emotional state using an emotion engine. Here, the device uses a microphone to collect the user's voice as input and utilizes NLP (Natural Language Processing) to evaluate their emotional state. The output is the result of the user's emotional state analysis.

[0576] Step 7:

[0577] The device dynamically adjusts evacuation instructions based on the user's emotional state. It uses the results of the emotional analysis as input to generate appropriate navigation instructions and provide them to the user. Specifically, if the user is showing anxiety, it plays an encouraging message via voice. The output is the adjusted guidance instructions.

[0578] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0579] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0580] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0581] [Fourth Embodiment]

[0582] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0583] As shown in Figure 7, the 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.

[0584] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0585] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0586] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0587] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0588] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0589] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0590] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0591] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0592] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0593] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0594] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0595] This invention relates to an information processing system that enables safe and rapid evacuation during disasters. This system primarily consists of a server, terminals, and users who utilize them.

[0596] Server Operation: The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, and the extent of impact from past disasters. Next, the server uses this data to run machine learning algorithms to analyze building strength and topographical characteristics, and identify areas where damage is predicted during a disaster. Based on this analysis, it calculates optimized evacuation routes and generates customized route information for each user. The generated evacuation route information is delivered in advance to the user's smartphone or other device.

[0597] Device Operation: The device stores evacuation route information received from the server in local storage, allowing access to this information even when offline during a disaster. When the user launches the app, the device uses GPS to determine the user's current location and provides appropriate directions based on the previously stored evacuation route information. This includes displaying maps, providing voice guidance, and text instructions.

[0598] How users can use the system: When a disaster occurs, users can launch the app on their device to immediately check pre-distributed evacuation routes. For example, if a major earthquake occurs while a user is at home, the app will present the optimal evacuation route calculated in advance and guide the user to the nearest safe evacuation center. This procedure allows users to evacuate safely even in situations with unstable communication environments. This system reduces anxiety during evacuation and enables users to evacuate safely based on appropriate decisions.

[0599] As described above, the present invention improves the safety and speed of evacuation during disasters, and is a system that provides substantial safety to users.

[0600] The following describes the processing flow.

[0601] Step 1:

[0602] The server automatically collects geographical information and disaster history from external databases. This process involves retrieving road conditions, weather conditions, and historical disaster data via various APIs and data feeds.

[0603] Step 2:

[0604] The server uses the collected data to run machine learning algorithms. This identifies areas where damage is expected due to the strength of buildings and terrain, as well as river flooding and earthquakes. This analysis then displays high-risk zones on a map.

[0605] Step 3:

[0606] Based on the analysis results, the server calculates an optimized evacuation route that avoids the danger zone. This calculation takes into account available roads, the location of shelters, and means of transportation to identify the safest route.

[0607] Step 4:

[0608] The server compresses evacuation route information and distributes it to the user's device in advance. This information is encrypted and prepared for offline use on the device.

[0609] Step 5:

[0610] The terminal saves the evacuation route information received from the server to its local storage. At this time, data verification, such as checksums, is performed to confirm that the information has been saved correctly.

[0611] Step 6:

[0612] When a disaster occurs, the user launches an evacuation route app on their device. The app refers to pre-saved evacuation route information and displays the optimal evacuation route in real time.

[0613] Step 7:

[0614] The device uses GPS to determine the user's current location and provides directions along an evacuation route. This includes map display, voice guidance, and text instructions as needed.

[0615] Step 8:

[0616] Users move safely and quickly to evacuation shelters by following the displayed evacuation route. The device updates location information in real time during movement and adjusts route guidance as needed.

[0617] (Example 1)

[0618] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0619] In emergency situations such as disasters, it is necessary to provide accurate and individually tailored evacuation information in advance to enable many people to evacuate quickly and safely. However, conventional route guidance systems have difficulty providing evacuation routes that take into account real-time geographical conditions and the impact of events. Furthermore, while it would be effective to save evacuation route information on devices in advance when communication environments are limited during a disaster, many systems do not have such functionality.

[0620] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0621] In this invention, the server includes means for collecting area information and event history from general information sources, means for analyzing the area information and event history using a data analysis algorithm to identify areas where damage is expected during an event, and means for calculating routes that avoid the identified areas. This makes it possible to provide users with individually optimized route information even in the event of a disaster or emergency, thereby supporting rapid and safe evacuation.

[0622] "Information sources" refer to general databases and information services that provide domain information and event histories.

[0623] "Regional information" refers to data that includes location information, topography, infrastructure conditions, and other information related to a specific geographical area.

[0624] "Event history" refers to recorded data regarding the circumstances and scope of past disasters and emergencies.

[0625] A "data analysis algorithm" refers to computational methods and models used to analyze collected data and derive effective judgments and predictions.

[0626] "Identified areas" refer to locations where damage is expected to occur when an event takes place, as revealed using data analysis algorithms.

[0627] A "route" refers to the path a user takes to travel safely and quickly from one point to another.

[0628] "User device" refers to a communication terminal or device carried by a user, which is used for receiving, storing, and displaying information.

[0629] "Route information" refers to detailed instructions and guidance regarding the optimal travel route that has been analyzed and calculated.

[0630] This invention supports efficient evacuation during disasters and emergencies using an information processing system consisting of a server, terminals, and users. Specifically, the server collects area information and event history from general information sources and executes a data analysis algorithm based on this information to predict risks in a specific area.

[0631] The server uses open-source geographic information and public event databases to collect necessary data. It also uses TensorFlow or similar data analysis software to analyze the collected data and identify areas predicted to be high-risk during an event. Through this analysis, the server calculates the optimal route avoiding risk areas and delivers the generated route information to the user's device. The generated route information is handled as text prompts, not in JSON format. An example of such a prompt might be, "Calculate the safest evacuation route during a disaster and generate a route from the user's current location to the nearest evacuation shelter."

[0632] The device saves received route information to local storage, making it accessible offline even in unstable network conditions. When the user launches the app, the device uses its built-in GPS function to determine the user's current location and provides voice and visual route guidance based on the saved route information. This guidance includes map display, voice guidance, and text directions.

[0633] By operating the terminal, users can quickly confirm evacuation routes during a disaster and move safely to their destination. Therefore, this system provides an effective means of supporting users to act quickly and safely during a disaster.

[0634] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0635] Step 1:

[0636] The server collects regional information and event history from common sources. Inputs include URLs and API keys for geographic information databases and event history databases. The server queries these sources to retrieve geographical data and historical event history for a given region. Outputs are raw data retrieved from the databases, specifically including map data, road conditions, and historical disaster history.

[0637] Step 2:

[0638] The server analyzes the collected data using data analysis algorithms. The input is the raw data obtained in Step 1. The server uses analysis tools such as TensorFlow to evaluate the strength of structures within the region, topographic characteristics, and the impact of past disasters. For data processing, it utilizes neural networks to identify risk areas. The output is evaluation data indicating risk areas. Specifically, it represents high-risk areas in a heatmap format.

[0639] Step 3:

[0640] The server calculates the optimal route based on the analysis results. The input is the risk assessment data obtained in step 2. The server uses Dijkstra's algorithm or the A algorithm to calculate a route that avoids high-risk areas. The data calculation involves finding the shortest route based on the distance and time between each point. The output is evacuation route information. Specifically, it includes detailed routes for the user to reach their destination.

[0641] Step 4:

[0642] The server sends the generated route information to the user's device. The input is the evacuation route information generated in step 3. The server converts this information into a JSON prompt message and sends it to the terminal via push notification or the cloud. The output is the route information stored on the terminal. Specifically, it is saved as a file on the terminal so that the user can access it even when offline.

[0643] Step 5:

[0644] The device provides instructions to the user based on stored route information. Input is route information received from the server and stored on the device. When the user launches the app, the device uses GPS to determine the current location and refers to the stored data to provide optimal route guidance. It uses a map display library to visually show the route and provides voice guidance and text instructions. Output is evacuation instructions provided to the user, specifically including on-screen map displays and voice guidance.

[0645] Step 6:

[0646] The user follows the evacuation instructions provided by the device. The input is the evacuation instructions shown in step 5. The user confirms the suggested route and begins moving safely. By following the route as instructed, the user can safely evacuate to their destination. The output is that the user has reached the evacuation shelter. Specifically, this refers to the situation where the user has safely completed the evacuation.

[0647] (Application Example 1)

[0648] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0649] Evacuation during disasters is highly urgent and requires rapid and safe movement. However, conventional evacuation route guidance systems lack features that enhance user confidence, such as real-time progress updates and voice instructions. Therefore, there is a need for the development of a system that provides flexible evacuation routes tailored to disaster situations and ensures user safety.

[0650] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0651] In this invention, the server includes means for collecting geographical information and disaster history from an external database, means for analyzing the geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster, and means for providing voice instructions and real-time display of progress. This enables users to evacuate safely and quickly during a disaster, and to select an evacuation route with a sense of security through appropriate guidance and voice instructions.

[0652] An "evacuation route" is a route selected to ensure that one can reach their destination safely and quickly in the event of a disaster.

[0653] An "information processing device" is a device used to collect and analyze data and generate or provide necessary information.

[0654] An "external database" is an external storage device or data management system that stores data such as geographical information and disaster history.

[0655] "Geographical information" refers to information related to geographic space, such as the layout of roads, topography, and the location of buildings.

[0656] "Disaster history" refers to records and data related to disasters that have occurred in the past, including the frequency and scope of disaster occurrences.

[0657] A "machine learning algorithm" is a mathematical model that learns patterns and rules from data to perform analysis and prediction.

[0658] "Voice instructions" refer to instructions or guidance provided to users using voice.

[0659] "Real-time display" refers to a display method that provides users with the current situation and information immediately.

[0660] "Durability analysis" is an analysis used to evaluate the strength and lifespan of buildings and structures.

[0661] "Information updating" means keeping data up-to-date by adding new information or correcting existing information.

[0662] In an embodiment of this invention, the information processing system consists of a server, a terminal, and a user. The server connects to multiple external databases and periodically collects geographical information and disaster history. This includes road conditions, infrastructure information, and the extent of impact of past disasters. The server uses the collected data to execute machine learning algorithms and predict disaster damage in a specific geographical area. Based on the results, it calculates the optimal evacuation route to avoid the identified damage prediction area and generates customized route information for each user. This generated evacuation route information is delivered to the user's terminal in advance.

[0663] The device stores evacuation route information received from the server in local storage, allowing access to this information even when offline. When the user launches the app, the device uses GPS to determine its current location and, based on the pre-stored evacuation route information, provides appropriate guidance to the user using a combination of voice instructions and real-time progress displays. This enables the user to evacuate safely and quickly.

[0664] For example, in the event of a major earthquake, users can use their smartphones to check evacuation route information they have obtained in advance and proceed along the optimal route from their home to the nearest evacuation center. This system reduces anxiety during disasters and enables safe evacuation even in situations where communication environments are unstable.

[0665] An example of a prompt for a generative AI model is: "Describe the design of an AI system that, when a user faces an increased risk of flooding, allows them to pre-determine a safe evacuation route and then evacuate according to voice guidance." This prompt is used to explain to the generative AI model how this system would be used in an emergency.

[0666] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0667] Step 1:

[0668] The server collects geographical information and disaster history from an external database. Its inputs are geographical information and disaster history data, which are retrieved via the network. As output, the retrieved data is stored in an internal data structure. Specifically, it uses APIs to retrieve the latest geographical data and historical disaster data from external data providers.

[0669] Step 2:

[0670] The server analyzes the collected data using machine learning algorithms to identify the areas where damage is expected. The input consists of geographical information and disaster history obtained in step 1, which are then input into the model to perform predictive calculations. The output is data showing geographical areas at risk of disaster. Specifically, it predicts the expected collapse of buildings and changes in terrain during a disaster and visualizes the risk areas on a map based on these predictions.

[0671] Step 3:

[0672] The server calculates the optimal evacuation route that avoids risk areas and creates this route information. The input is map information of the risk areas identified in step 2. A route optimization algorithm is used to calculate a safe route. The output is customized evacuation route information provided to the user. Specifically, it calculates a route that avoids risks while reaching a shelter in the shortest possible time.

[0673] Step 4:

[0674] The server pre-distributes the generated evacuation route information to the user's terminal. The input is the evacuation route data generated in step 3, which is sent to the terminal via a communication protocol. The output is the terminal's storage holding the evacuation route information. Specifically, the server sends the data to the terminal via the communication line and saves it locally.

[0675] Step 5:

[0676] When the user launches the app, the device starts navigation based on saved evacuation route information. The input is the user's current location, which is obtained using GPS. Using this information, the device provides real-time voice instructions and displays progress while comparing it with the saved route. The output is navigation information to help the user safely navigate the evacuation route. Specifically, it starts voice guidance along with a map display and provides visual and auditory feedback to the user according to their progress.

[0677] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0678] This invention provides a system combining an information processing device, an emotion engine, and a user terminal to support evacuation during disasters. This system is implemented as follows.

[0679] Server Operation: The server first collects geographical information and historical disaster data from an external database. Based on this data, it uses machine learning algorithms to analyze the area where damage is expected during a disaster and calculates the optimal evacuation route to avoid that area. The server also performs structural analysis of buildings and generates data to predict the risk of damage. Furthermore, it generates optimized evacuation route information for each user and distributes it to their terminals.

[0680] Emotional Engine Operation: The emotional engine recognizes the user's emotional state by analyzing the user's voice and operation data. For example, it measures anxiety and stress levels in real time through voice analysis. Based on these results, the emotional engine dynamically adjusts the evacuation route guidance method to suit the user's state.

[0681] Terminal Operation: The terminal stores evacuation route information delivered from the server and modifies the way it guides the user based on feedback provided by the emotion engine. Specifically, if the user is experiencing high levels of anxiety, the terminal provides more detailed guidance and words of encouragement via voice. Also, if the user's stress level is high, it recalculates the evacuation route to recommend rest points and suggests them to the user.

[0682] User Usage: When a disaster occurs, users launch the app on their device to check evacuation routes. For example, if a user is in an area where river flooding is a concern, the app will refer to pre-stored data and suggest a safe detour route. At the same time, the device continuously monitors the user's emotions and provides flexible guidance as needed.

[0683] As a result, users can receive evacuation information customized to their emotional state, enabling them to evacuate with peace of mind. This system provides a comprehensive solution to reduce stress during disasters and support safe evacuation.

[0684] The following describes the processing flow.

[0685] Step 1:

[0686] The server accesses multiple external databases to collect the latest geographical information and disaster history data. This collection includes local weather data, infrastructure conditions, and records of past disasters.

[0687] Step 2:

[0688] The server runs machine learning algorithms based on the collected data to analyze areas where danger is expected during a disaster. This analysis displays specific areas where damage is predicted on a map.

[0689] Step 3:

[0690] The server works with the analysis results to calculate the optimal evacuation route. This route calculation takes into account the location of evacuation sites, the available road network, and bridge conditions. The calculated evacuation route is customized to suit the user's place of residence and mode of transportation.

[0691] Step 4:

[0692] The emotion engine analyzes the user's voice input and device sensor information to evaluate the user's emotional state. The emotion engine identifies the user's level of anxiety and stress in real time based on the tone of voice and word choice.

[0693] Step 5:

[0694] The server pre-distributes calculated evacuation route information to the user's terminal. This distribution includes not only the evacuation route but also settings for guidance methods tailored to the user's emotional state, as analyzed by the emotion engine.

[0695] Step 6:

[0696] The device stores received evacuation information locally and prepares guidance methods tailored to the user's emotional state. Based on evacuation route information, it adjusts screen displays and voice guidance to provide flexible directions to the user.

[0697] Step 7:

[0698] The user launches an app on their device to check the current evacuation route. If the device determines that the user is experiencing high stress, it provides encouraging messages and detailed guides via voice.

[0699] Step 8:

[0700] The device continuously updates location information even after the user begins evacuating, providing real-time guidance for safe routes. It also monitors the user's emotional state and updates or recalculates route guidance as needed to support safe evacuation.

[0701] (Example 2)

[0702] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0703] Evacuation during disasters is often prone to confusion, and there is a problem in that people may not be able to take appropriate evacuation actions, especially when their emotional state is unstable. Furthermore, conventional evacuation route guidance systems cannot provide flexible route guidance that takes emotions into account, making safe and secure evacuation difficult.

[0704] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0705] In this invention, the server includes means for collecting spatial information and past disaster history from external information sources, means for analyzing the spatial information and past disaster history using a machine learning algorithm to identify areas expected to be affected during a disaster, and means for acquiring the user's emotional state and adapting the route guidance unit based on that emotional state. As a result, users can obtain evacuation information optimized to their own emotional state.

[0706] "External information sources" is a general term for databases and repositories that systems use to acquire disaster-related information, including geographical information and disaster history.

[0707] "Spatial information" refers to information about geographical location, regional structure, topography, etc.

[0708] "Past disaster history" refers to record data regarding the type, scale, and scope of impact of disasters that have occurred in the past.

[0709] A "machine learning algorithm" is a collection of programs used to analyze large amounts of data and perform pattern recognition and prediction.

[0710] "User terminal" refers to electronic devices such as mobile phones, tablets, and PCs that users directly operate to obtain information.

[0711] "Emotional state" refers to the user's mental state, mood, stress levels, and anxiety levels.

[0712] The "route guidance section" refers to the functions and components within a system that present evacuation routes to users and provide navigation.

[0713] This system is designed to support evacuation during disasters by combining an information processing device, an emotion analysis mechanism, and user terminals.

[0714] The server first collects spatial information and historical disaster data from external sources. Based on this data, the server uses machine learning algorithms to analyze areas expected to be affected during a disaster. By using the Python Scikit-learn library for machine learning, the server can quickly and accurately analyze large amounts of data and identify the extent of the impact. The server also uses a map API to calculate the optimal evacuation route based on the user's location and delivers it to the user's terminal.

[0715] The emotion analysis mechanism monitors the user's voice data and operation history to analyze their emotional state in real time. This analysis uses a natural language processing framework (e.g., Transformers) as the emotion analysis model. This allows for the measurement of the user's anxiety and stress levels, and the adjustment of evacuation route guidance methods as needed.

[0716] The terminal stores evacuation route information distributed from the server and provides it to users through structured visual and audio interfaces in the event of a disaster. The terminal can also adapt its guidance based on feedback from an emotion analysis mechanism. For example, if the user is highly anxious, the terminal will reinforce the guidance with reassuring language.

[0717] When signs of a disaster appear, users can use their devices to check evacuation routes. An example of a prompt related to suggesting evacuation routes is, "Please tell me the best evacuation route in an area where river flooding is expected." By inputting this prompt into a generating AI model, more appropriate evacuation information can be obtained quickly.

[0718] Based on the above, the system can provide a concrete form of support for safe and secure evacuation that takes into account the emotional state of the users.

[0719] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0720] Step 1:

[0721] The server collects spatial information and historical disaster data from external sources. Inputs include geographic location information and access to historical disaster databases. This allows the server to utilize a Geographic Information System (GIS) to store this information in a database.

[0722] Step 2:

[0723] The server analyzes collected spatial information and past disaster history using machine learning algorithms. The input is the geographic information and disaster data collected in the previous step. The server uses this information to extract risk areas using Scikit-learn. The output generates identification of areas expected to be affected and candidate evacuation routes.

[0724] Step 3:

[0725] The server receives the user's current location information as input and calculates the optimal evacuation route. This utilizes location data confirmed in real time via a map API. The server generates route information to provide the user with the calculation results and delivers it as output to the user's terminal.

[0726] Step 4:

[0727] The emotion engine monitors voice data and operation logs obtained when the user operates the device in real time. Inputs include voice samples and screen operation history. The emotion engine analyzes these and determines the emotional state through a natural language processing framework. The output is the result of the emotional state analysis.

[0728] Step 5:

[0729] The terminal provides the user with evacuation route information received from the server. Input to the terminal consists of structured data and audio from the server. The terminal uses this information to provide guidance through visual and audio interfaces. Output is evacuation route information that the user can visually confirm and is also navigated by voice.

[0730] Step 6:

[0731] The user checks the evacuation route information provided on the device and actually begins evacuating according to that route. Inputs include route information from the device and emotion-based guidance provided by the device. Based on this information, the user can safely evacuate from the disaster area. The output is simply the user reaching a safe location.

[0732] (Application Example 2)

[0733] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0734] Providing appropriate evacuation routes during disasters is crucial, but flexible responses that take into account the emotional state of users are required. Furthermore, the current lack of systems for evacuation support using autonomous vehicles makes it difficult to evacuate with peace of mind. Additionally, technology for analyzing user emotions from voice data and dynamically adjusting evacuation guidance based on the results is insufficient. Therefore, a system is needed that provides appropriate evacuation guidance tailored to emotions, ensuring safe and secure evacuation.

[0735] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0736] In this invention, the server includes means for collecting geographical information and disaster history from an external database; means for analyzing the geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster; means for calculating evacuation routes that avoid the identified area; means for pre-distributing the evacuation route information to a user terminal; means for storing the evacuation route information on the user terminal and providing the evacuation route when a disaster occurs; means for evaluating voice data for analyzing the user's emotional state; and means for dynamically adjusting evacuation route guidance based on the user's emotional state. This enables flexible evacuation guidance that responds to the user's emotions, allowing for safe and secure evacuation.

[0737] An "external database" is an external source of information that stores geographical information and disaster history information.

[0738] "Geographic information" refers to data about the physical characteristics of a particular area, such as its topography, transportation, and building layout.

[0739] "Disaster history" refers to record data regarding the types, scope, and impact of disasters that have occurred in the past.

[0740] A "machine learning algorithm" is a computational method that automatically learns patterns and rules from large amounts of data to perform decision-making and classification.

[0741] "Areas where damage is expected" refers to geographical areas identified as having a high probability of property damage and personal injury during a disaster.

[0742] An "evacuation route" is a path that indicates the route and steps to take to move to a safe place in the event of a disaster.

[0743] A "user terminal" refers to a digital device such as a smartphone or tablet owned by a user.

[0744] "Emotional state" refers to the psychological situation and emotional level inferred from the user's voice and other actions.

[0745] "Voice data" refers to information recorded in digital format using the user's voice.

[0746] To realize this invention, the server efficiently collects and analyzes information necessary during a disaster. Specifically, the server obtains geographical information and past disaster history through an external database, and uses machine learning algorithms based on this information to identify the area where damage is expected. This can be achieved using machine learning libraries such as TensorFlow. Furthermore, based on the analysis results, the server calculates the optimal evacuation route and delivers that information to user terminals.

[0747] The terminal receives evacuation route information distributed from the server and displays it appropriately to the user. Furthermore, the terminal is equipped with an emotion engine that acquires the user's voice data and evaluates their emotional state in real time. Natural language processing tools are used for voice analysis, and the method of evacuation guidance is dynamically adjusted based on the emotional state obtained. If the user shows anxiety, detailed guides and encouraging messages are provided to reassure them.

[0748] Users can use their devices to check evacuation routes during a disaster. For example, if a user is in an area at risk of flooding, the app will provide a safe alternative route based on previously saved data. If the user is feeling anxious, the device will display a message such as, "Don't worry, this is a safe route, please stay calm."

[0749] The system utilizes a generative AI model to generate guidance text that is tailored to the user's emotions. Examples of prompt text include the following:

[0750] "Disaster relief evacuation support app for autonomous vehicles: We will build a system that evaluates the user's emotions based on voice data, provides the optimal evacuation route, and offers reassuring navigation. How will this be implemented?"

[0751] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0752] Step 1:

[0753] The server collects geographical information and disaster history from an external database. In this step, the server retrieves the necessary data via an API, collecting geographical information such as regional topography and road information, and disaster history data such as past disaster locations. The input is the API endpoint, and the output is a dataset containing this information.

[0754] Step 2:

[0755] The server uses a machine learning algorithm to identify the area where damage is expected in the event of a disaster. The server takes the dataset collected in step 1 as input and uses a specific algorithm (e.g., random forest) to predict the risk area. The output specifies the geographical area where damage is expected.

[0756] Step 3:

[0757] The system calculates evacuation routes to avoid identified risk areas for the server. Here, geolocation data is used as input, and a suitable mapping tool (e.g., Google Maps API) is used to generate safe evacuation routes. The output is route information for the evacuation routes.

[0758] Step 4:

[0759] The server distributes the calculated evacuation route information to the user terminal. The server uses the route information generated in the previous step as input and sends data to the user terminal. The output is route information accessible on the user terminal.

[0760] Step 5:

[0761] The terminal stores evacuation route information received from the server and displays it to the user. In this step, the terminal processes the received route information and visualizes it as a map on the interface. The input is evacuation route data, and the output is the display on the user interface.

[0762] Step 6:

[0763] The device acquires the user's voice data and analyzes their emotional state using an emotion engine. Here, the device uses a microphone to collect the user's voice as input and utilizes NLP (Natural Language Processing) to evaluate their emotional state. The output is the result of the user's emotional state analysis.

[0764] Step 7:

[0765] The device dynamically adjusts evacuation instructions based on the user's emotional state. It uses the results of the emotional analysis as input to generate appropriate navigation instructions and provide them to the user. Specifically, if the user is showing anxiety, it plays an encouraging message via voice. The output is the adjusted guidance instructions.

[0766] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0767] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0768] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0769] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0770] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0771] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0772] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0773] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0774] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0775] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0776] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0777] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0778] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0779] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0780] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0781] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0782] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0783] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0784] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0785] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0786] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0787] The following is further disclosed regarding the embodiments described above.

[0788] (Claim 1)

[0789] In an information processing device that provides evacuation routes during a disaster,

[0790] A means of collecting geographical information and disaster history from an external database,

[0791] A means for analyzing geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster,

[0792] Means for calculating evacuation routes that avoid the identified area,

[0793] A means for distributing the evacuation route information to the user terminal in advance,

[0794] A means for storing the evacuation route information on the user terminal and providing the evacuation route in the event of a disaster,

[0795] A system that includes this.

[0796] (Claim 2)

[0797] The system according to claim 1, wherein the information processing device performs damage risk prediction, including structural analysis of buildings.

[0798] (Claim 3)

[0799] The system according to claim 1, which predicts the time required for evacuation based on the user's means of transportation and the number of people evacuating, and provides an optimized evacuation route.

[0800] "Example 1"

[0801] (Claim 1)

[0802] Means for collecting domain information and event history from general sources,

[0803] A means for analyzing the region information and the event history using a data analysis algorithm to identify the region where damage is expected at the time of the event,

[0804] Means for calculating a path that avoids the identified area,

[0805] A means for distributing the route information to the user's device in advance,

[0806] Means for storing the route information in the user's device and providing the route when an event occurs,

[0807] Means for providing visual and audible instructions on a display device for the generated route information,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, wherein the information processing device performs risk prediction, including structural strength analysis.

[0811] (Claim 3)

[0812] The system according to claim 1, which predicts the time required for evacuation based on the user's means of transportation and the number of people evacuating, and provides an optimized route.

[0813] "Application Example 1"

[0814] (Claim 1)

[0815] In an information processing device that provides evacuation routes during a disaster,

[0816] A means of collecting geographical information and disaster history from an external database,

[0817] A means for analyzing geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster,

[0818] Means for calculating evacuation routes that avoid the identified area,

[0819] A means for distributing the evacuation route information to the user terminal in advance,

[0820] A means for storing the evacuation route information on the user terminal and providing the evacuation route in the event of a disaster,

[0821] A means of providing both voice instructions and a real-time display of progress,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, wherein the information processing device performs damage risk prediction, including durability analysis of buildings.

[0825] (Claim 3)

[0826] The system according to claim 1, which predicts the time required for evacuation based on the user's means of transportation and the number of evacuees, provides an optimized evacuation route, and further updates information in accordance with changes in the surrounding terrain.

[0827] "Example 2 of combining an emotion engine"

[0828] (Claim 1)

[0829] Means for collecting spatial information and past disaster history from external sources,

[0830] A means for analyzing spatial information and past disaster history using machine learning algorithms to identify areas expected to be affected during a disaster,

[0831] Means for calculating a route that avoids the identified area,

[0832] A means for supplying the route information to the user terminal in advance,

[0833] A means for storing the route information on the user's terminal and providing the route in the event of a disaster,

[0834] A means for acquiring the user's emotional state and adapting the route guidance unit based on that emotional state,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, wherein the information processing device performs risk prediction including structural strength analysis of the building and adapts the route based on the user's emotional data.

[0838] (Claim 3)

[0839] The system according to claim 1, which predicts the time required for evacuation based on the user's means of transportation and the number of people evacuating, and provides an optimized route based on the emotional state of the user.

[0840] "Application example 2 when combining with an emotional engine"

[0841] (Claim 1)

[0842] A means of collecting geographical information and disaster history from an external database,

[0843] A means for analyzing geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster,

[0844] Means for calculating evacuation routes that avoid the identified area,

[0845] A means for distributing the evacuation route information to the user terminal in advance,

[0846] A means for storing the evacuation route information on the user terminal and providing the evacuation route in the event of a disaster,

[0847] A means for evaluating audio data to analyze the emotional state of a user,

[0848] A means for dynamically adjusting evacuation route guidance based on the user's emotional state,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, wherein the information processing device performs damage risk prediction, including structural analysis of buildings.

[0852] (Claim 3)

[0853] The system according to claim 1, which predicts the time required for evacuation based on the user's means of transportation and the number of people evacuating, and provides an optimized evacuation route. [Explanation of Symbols]

[0854] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. In an information processing device that provides evacuation routes during a disaster, A means of collecting geographical information and disaster history from an external database, A means for analyzing geographical information and disaster history using a machine learning algorithm to identify the area where damage is expected during a disaster, Means for calculating evacuation routes that avoid the identified area, A means for distributing the evacuation route information to the user terminal in advance, A means for storing the evacuation route information on the user terminal and providing the evacuation route in the event of a disaster, A system that includes this.

2. The system according to claim 1, wherein the information processing device performs damage risk prediction, including structural analysis of the building.

3. The system according to claim 1, which predicts the time required for evacuation based on the user's means of transportation and the number of people evacuating, and provides an optimized evacuation route.

Images