system

Abstract

We provide the system. [Solution] A means of acquiring real-time data via a communication network in the event of a disaster, A means for standardizing the aforementioned real-time data and inputting it into a generating artificial intelligence model, The aforementioned artificial intelligence model analyzes the current disaster situation using past disaster data and generates a recovery plan; A means of presenting the generated recovery plan to the user, and re-evaluating and adjusting the plan based on user feedback, A means to support disaster recovery activities based on approved recovery plans and to monitor progress in real time, 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 method for controlling a persona chatbot, which is performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; 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] In the event of a disaster, the situation changes moment by moment, and prompt and accurate responses are required. However, conventional disaster countermeasures have problems in that it takes time to formulate a recovery plan and sufficient efficiency cannot be demonstrated due to delays in data collection and analysis and the complexity of the decision-making process. In addition, it is difficult to create a plan that reflects the on-site situation in real time, which may lead to an expansion of damage and a delay in the recovery work. Against this background, there is a need for a system that can quickly generate an optimal recovery plan after a disaster and support efficient recovery activities.

Means for Solving the Problems

[0005] This invention provides a means for acquiring real-time data via a communication network in the event of a disaster. This allows for a rapid understanding of the situation on site. It also includes a means for standardizing the acquired data and inputting it into a generating artificial intelligence model, which is used to analyze the current disaster situation while referring to past disaster data. Furthermore, it provides a means for generating an optimal recovery plan based on the analysis results. This plan is presented to the user and can be re-evaluated and adjusted based on user feedback. Finally, by providing a means to support disaster recovery activities based on the approved recovery plan and to monitor progress in real time, it enables a rapid and efficient response.

[0006] "Real-time data" refers to the latest situational information collected immediately from the scene when a disaster occurs, and is processed rapidly via data communication.

[0007] A "generative artificial intelligence model" refers to an artificial intelligence model that has an algorithm that analyzes data based on past disaster data and automatically generates the optimal recovery plan.

[0008] A "recovery plan" outlines the optimal response measures after a disaster occurs and includes detailed instructions regarding the design of evacuation routes, the distribution of emergency relief supplies, and the deployment of necessary personnel.

[0009] A "user" refers to an individual or organization that can access the disaster recovery system to present and adjust recovery plans.

[0010] "Feedback" refers to comments and correction requests provided by users based on the recovery plan presented, and serves as information for the system to readjust the plan.

[0011] "Monitoring" refers to the process of continuously monitoring the implementation of a recovery plan and tracking its progress, which enables rapid problem resolution. [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] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0015] In the following embodiments, a tagged processor (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 tagged RAM (Random Access Memory) 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 tagged storage 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, etc.

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

[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, a 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] As an embodiment of this invention, a system is provided that performs data collection, analysis, plan generation, and implementation support in real time during a disaster.

[0034] When a disaster occurs, the server automatically collects real-time data from sensor devices and drones on-site. This data includes earthquake intensity, weather conditions, traffic information, and video footage of the affected area. The terminal also receives information from local users, including the latest updates on the extent of damage and the safety of evacuation centers.

[0035] The server centrally manages the acquired real-time data and inputs it into an artificial intelligence model in a standardized format. The AI ​​model analyzes the current situation by referring to past disaster data and generates an optimal recovery plan to effectively advance disaster response. This plan includes detailed instructions such as the design of evacuation routes, the deployment of emergency medical support, and the installation of communication infrastructure.

[0036] The generated recovery plan is presented to the user via the terminal. The user can review this plan and provide feedback tailored to the specific situation on-site. The server re-evaluates the plan based on the user's feedback and makes adjustments as needed.

[0037] Based on the final approved plan, the server monitors the progress of recovery activities in real time and maintains constant communication with field personnel via terminals. This increases the efficiency of recovery operations and allows for immediate solutions to be provided if problems arise.

[0038] Specific example

[0039] For example, when a large-scale typhoon occurs, the server retrieves data on the typhoon's path and wind speed from weather information systems. Terminals send reports from residents on-site about flooding and traffic disruptions. The generative artificial intelligence model analyzes this data to determine areas that need evacuation and prioritize them. It also sets evacuation routes that take into account the location of evacuation shelters and identifies areas that require emergency assistance. Users can review this plan and provide feedback if there are any changes on-site, further refining the plan. In this way, all stakeholders can cooperate to implement a swift and accurate disaster response.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] When the server detects a disaster, it immediately collects real-time data from sensor devices and drones. This data includes weather information, earthquake intensity, traffic conditions, and on-site video.

[0043] Step 2:

[0044] The server standardizes the collected data and unifies the data format. In this process, it filters out noisy data and prepares it for analysis.

[0045] Step 3:

[0046] The server inputs standardized data into a generating artificial intelligence model and analyzes the situation by comparing it with historical data from similar disasters. This analysis determines the prediction of damage and the prioritization of response measures.

[0047] Step 4:

[0048] The server generates a recovery plan based on the analysis results. The plan will include specific details such as evacuation routes, delivery destinations for relief supplies, and locations for communication infrastructure.

[0049] Step 5:

[0050] The server presents the generated recovery plan to the user via the terminal. The user reviews the plan and provides situation-based feedback as needed.

[0051] Step 6:

[0052] The server receives user feedback and re-evaluates and adjusts the recovery plan. It then finalizes the newly approved plan and prepares to implement it in field operations.

[0053] Step 7:

[0054] The server monitors the progress of the execution phase in real time, based on the adjusted recovery plan. If a problem occurs, it immediately provides alternative solutions or additional instructions to ensure smooth operation.

[0055] Step 8:

[0056] The terminal continuously receives situation reports from field personnel and immediately transmits them to the server, maintaining up-to-date information. This allows the server to monitor recovery activities more accurately.

[0057] (Example 1)

[0058] 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."

[0059] In recent years, the frequency and scale of natural disasters have increased, highlighting the growing need for rapid and effective information gathering and response planning at disaster sites. Conventional systems have struggled to collect data in real time and generate and adjust recovery plans based on that data. Furthermore, immediate plan adjustments in response to changing conditions on the ground have also been a significant challenge.

[0060] 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.

[0061] In this invention, the server includes means for acquiring dynamic data via a communication medium during a disaster, means for unifying the dynamic data and inputting it into a generative intelligence model, and means for interpreting the current disaster situation using past disaster information with the generative intelligence model and creating a recovery plan. This enables rapid and accurate information gathering and immediate plan adjustment for disaster response.

[0062] "Disaster" refers to a period of emergency caused by natural phenomena such as weather or earthquakes that affect human lives and property.

[0063] A "communication medium" refers to a physical or wireless device or network system used as a means to enable the transmission and reception of information.

[0064] "Dynamic data" refers to information that is constantly changing in real time, and includes numerical data and video footage collected from sensor devices and drones.

[0065] "Standardization" refers to the process of converting data from different formats or specifications into a standard format.

[0066] A "generative intelligence model" is a system that includes algorithms to analyze the current situation based on past data and derive optimal responses and plans.

[0067] A "recovery plan" refers to a set of specific action guidelines formulated with the aim of restoring the social and physical environment after a disaster.

[0068] A "detector device" is a general term for devices that detect physical or chemical changes in the environment and generate data from them.

[0069] "Local equipment" is a general term for devices installed in areas where a disaster has occurred in order to collect or transmit information.

[0070] An "evacuation route" refers to a designated path used to evacuate to a safe place during a disaster.

[0071] "Emergency supplies" refers to the goods and equipment needed in the event of a disaster, including food, water, and medical supplies.

[0072] "Staff" refers to personnel deployed to carry out plans and provide support in disaster response.

[0073] This invention provides a system in which servers, terminals, and users cooperate with each other to efficiently collect information, formulate response plans, and implement them during disasters.

[0074] The server first acquires dynamic data using communication media during a disaster. This data collection utilizes existing external data sources such as weather information APIs and earthquake early warning systems, and also incorporates data from sensors and drones deployed on-site. General-purpose server equipment and network connectivity devices are likely to be used as hardware.

[0075] Next, the server unifies the acquired dynamic data. It converts data in different formats into a standard format so that it can be smoothly input into the generated AI model. Database management systems and data conversion software are used in this process.

[0076] The server inputs standardized data into a generative AI model. This generative AI model analyzes the current situation based on data from past disasters and creates an appropriate recovery plan. An example of a prompt used in this process is, "Generate the optimal disaster response plan based on the current data."

[0077] The generated recovery plan is presented to the user via a device. The user can review the plan received on the device and provide feedback based on their knowledge gained from the disaster site. The device can be a smartphone, tablet, or laptop.

[0078] The server receives feedback from users and re-evaluates and adjusts the recovery plan as needed. This ensures that the plan is executed in a way that is responsive to the actual situation on site.

[0079] As a concrete example, let's consider the operation when a typhoon approaches. The server obtains typhoon path and wind speed information from weather information provision systems, and terminals transmit information on flooding conditions and traffic disruptions from local residents. The generated AI model analyzes this information, identifies areas requiring evacuation, and presents evacuation routes and priority support areas. Users can then use this information to take quick and appropriate action.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server detects the occurrence of a disaster and acquires dynamic data through communication media. Specifically, it receives information on earthquake intensity and typhoon paths from weather information APIs and earthquake early warning systems. It also collects video data of the affected area from sensors and drones deployed on-site. Inputs are various data from external information services and on-site devices, and output is a collection of raw data including this data.

[0083] Step 2:

[0084] The server unifies the acquired dynamic data. Specifically, it standardizes the format of each data point and converts it into a format that can be input into the generating AI model. For example, it integrates different data formats (JSON, XML, etc.) and converts units for numerical data. The input is the raw data obtained in step 1, and the output is the standardized dataset.

[0085] Step 3:

[0086] The server inputs standardized data into a generating AI model. Using the prompt "Generate the optimal disaster response plan based on the current data," the model analyzes the current situation and creates a recovery plan by comparing it with past disaster data. The input is the standardized data obtained in step 2, and the output is the recovery plan generated by the generating AI model.

[0087] Step 4:

[0088] The server presents the generated recovery plan to the user via the terminal. The user can review the plan on the terminal and input opinions and feedback based on the situation on site. Specifically, they can review each element of the plan through the UI and add comments based on its feasibility. The input is the recovery plan obtained in step 3, and the output is a revised plan including the user's feedback.

[0089] Step 5:

[0090] The server re-evaluates and adjusts the recovery plan based on user feedback. It then utilizes the generated AI model again to modify and optimize the plan as needed. The input is the user feedback and initial recovery plan obtained in step 4, and the output is the approved plan after final adjustments.

[0091] Step 6:

[0092] The server monitors recovery activities based on the approved plan. It checks progress in real time and maintains communication between users and field personnel through terminals. Specifically, it checks the completion status of each task and quickly sends countermeasures when problems occur. The input is the final recovery plan, and the output is the progress of the recovery activities and coordination information.

[0093] (Application Example 1)

[0094] 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."

[0095] In the event of a disaster within a logistics facility, rapid and efficient data collection and analysis are required. However, conventional systems lack real-time capabilities and accuracy, making it difficult to provide optimal recovery plans. Against this backdrop, there is a need for immediate information collection during disasters and the provision of optimal recovery procedures based on that information.

[0096] 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.

[0097] In this invention, the server includes means for acquiring real-time data through an information technology network in the event of a disaster, means for standardizing the real-time data and inputting it into a generated artificial intelligence model, and means for effectively collecting and analyzing internal state data of a logistics facility and providing optimal recovery procedures. This makes it possible to quickly and efficiently grasp the situation inside a logistics facility even in the event of a disaster and accurately execute the necessary recovery procedures.

[0098] An "information technology network" is a system for exchanging and transmitting information via the internet or communication networks.

[0099] "Real-time data" refers to data that is acquired at the exact moment an event occurs and is immediately available for use.

[0100] "Standardization" refers to the process of converting data obtained in different formats into a unified standard format.

[0101] A "generative artificial intelligence model" is a machine learning model trained to perform a specific task based on a large amount of data.

[0102] A "logistics facility" is a general term for places or buildings used for storing, sorting, and shipping goods.

[0103] "Status data" refers to a collection of information that indicates the physical and environmental conditions of a logistics facility at a specific point in time.

[0104] "Recovery procedures" refer to the specific methods and steps taken to restore the system to a normal state in the event of a disaster or malfunction.

[0105] This invention is implemented as a system to support rapid and efficient recovery activities in the event of a disaster at a logistics facility. The server acquires real-time data from multiple sensor devices inside and outside the logistics facility and aggregates this data via an information technology network. The server normalizes the data acquired from the sensor devices and inputs it into a generated artificial intelligence model to derive effective recovery procedures. TENSORFLOW® and PyTorch are used for the AI ​​model.

[0106] The terminal presents the generated recovery plan to the user and accepts user feedback on changes in the logistics facility. This user feedback is then sent back to the server and used to re-evaluate and adjust the plan.

[0107] As a concrete example, consider a recovery scenario for a logistics facility during an earthquake. The server receives vibration information and temperature changes within the facility from detection devices, and an artificial intelligence model analyzes this information to assess safety. Simultaneously, the user's smart device records information obtained from staff within the facility, identifying disruptions in logistics and damage to goods. Based on this, an optimal recovery plan is generated.

[0108] This invention allows logistics facility managers to quickly grasp the situation after a disaster and issue effective instructions. For example, a possible prompt message could be: "Based on the current state of the logistics facility, generate the optimal recovery procedure and specify which areas should be prioritized for recovery."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server acquires real-time data from multiple sensor devices placed inside and outside the logistics facility. Inputs include vibration information, temperature, humidity, and location information. This data is collected and then standardized so that it can be processed in the next step.

[0112] Step 2:

[0113] The server normalizes the acquired real-time data. Here, data obtained from different sensor devices is converted into a common format to ensure data consistency. The output is normalized data, which improves the accuracy of subsequent AI model inputs.

[0114] Step 3:

[0115] The server inputs standardized data into an artificial intelligence model. Machine learning frameworks such as TensorFlow and PyTorch are used for the AI ​​model. Data processing here involves analyzing historical disaster data and real-time data to generate recovery procedures suitable for logistics facilities. The output is a concrete recovery plan.

[0116] Step 4:

[0117] The terminal presents the generated recovery plan to the user. The user can send feedback about changes in the situation within the logistics facility. The function here is to provide an interface that visualizes the contents of the recovery plan in an easy-to-understand way, enabling the user to make accurate decisions.

[0118] Step 5:

[0119] The server receives user feedback and re-evaluates the recovery plan, adjusting it as needed. The input includes text data representing user feedback. The server then inputs this back into an artificial intelligence model, generating prompts, and produces an adjusted recovery plan. The output is the updated recovery plan.

[0120] Step 6:

[0121] The server monitors the recovery progress of the logistics facility in real time and maintains constant communication with the terminals. It continuously acquires new data from sensor devices to confirm that progress is on schedule, and quickly derives countermeasures if problems occur. The output here is the latest recovery status report and necessary countermeasures.

[0122] 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.

[0123] This invention combines an emotion engine with a system that collects and analyzes data in real time during a disaster. By adding a function to recognize the user's emotions, this system enables more appropriate information provision and support.

[0124] First, when the server detects a disaster, it collects real-time data from sensor devices and on-site terminals. This data includes weather conditions, the extent of damage, and photos and videos of the scene. Terminals collect information directly entered by users on-site. In addition to this user information, data is also collected to determine emotions from the user's facial expressions and tone of voice.

[0125] The server standardizes this data and inputs it into a generating artificial intelligence model. This AI model analyzes the current situation by referring to past disaster data and automatically generates an optimal recovery plan. This recovery plan includes specific instructions such as evacuation routes, distribution plans for necessary materials, and personnel deployment.

[0126] Furthermore, by incorporating an emotion engine, the system recognizes the user's emotional state in real time. The emotion engine determines the user's stress and anxiety levels and adjusts the pace and content of the recovery plan presentation according to the user's psychological state. In this way, the plan is presented in a format that is easiest for the user to understand.

[0127] For example, if a user who has received an evacuation order is in a state of high stress, the emotion engine will recognize this and provide a plan with calmer language and enhanced visual support. The user's response is then fed back to the server via the device, where the emotional changes are recorded.

[0128] Ultimately, based on the approved recovery plan, the server continuously monitors the ongoing disaster recovery activities. User sentiment information is used as important feedback to improve on-site work efficiency, ultimately enhancing the quality of recovery efforts.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server collects real-time data from sensor devices and drones via the network during a disaster. This includes weather data from the affected area, earthquake vibration data, traffic conditions, and on-site video footage.

[0132] Step 2:

[0133] The device collects information from local users. Users report the extent of the damage and the need for evacuation through a specific application. The device also uses its camera and microphone to record the user's facial expressions and tone of voice, generating emotional data.

[0134] Step 3:

[0135] The server standardizes the collected real-time data and user sentiment data. This unifies the format and prepares a dataset suitable for analysis.

[0136] Step 4:

[0137] The server inputs standardized data into a generating artificial intelligence model and analyzes the current situation by referencing past disaster data. This analysis is a process that predicts damage, prioritizes emergency assistance, and generates an optimal recovery plan.

[0138] Step 5:

[0139] The server uses an emotion engine to analyze the user's emotional state. Based on this analysis, it adjusts the method of presenting the recovery plan and selects a feedback format that is appropriate for the user's psychological state.

[0140] Step 6:

[0141] The server presents the generated recovery plan to the user via the terminal. When communicating this to the user, the tone of the instructions and the presence or absence of visual assistance are adjusted according to the user's stress level.

[0142] Step 7:

[0143] The user reviews the presented recovery plan and sends feedback to the server via their device. This feedback includes comments on the plan's content and additional information from the field.

[0144] Step 8:

[0145] The server receives feedback from the user, re-evaluates the plan as needed, and proposes a revised plan. It also simultaneously records changes in the user's emotions, which are used for subsequent analysis.

[0146] Step 9:

[0147] The server monitors field activities in real time based on the approved recovery plan. This includes checking the progress of recovery work and responding immediately to any new failures.

[0148] Step 10:

[0149] The terminal continuously receives progress reports from field personnel and provides the latest information to the server, thereby improving the overall system's response speed and accuracy.

[0150] (Example 2)

[0151] 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".

[0152] During a disaster, a complex web of information becomes chaotic, making it difficult to provide swift and accurate recovery support. Furthermore, simply presenting information without considering the psychological state of users can exacerbate confusion. Therefore, it is essential to accurately process diverse information and provide recovery information to users in an appropriate format to streamline disaster recovery activities and alleviate user anxiety.

[0153] 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.

[0154] In this invention, the server includes means for acquiring real-time information through a communication infrastructure when a disaster occurs, means for unifying the real-time information and supplying it to a generation AI model, and means for displaying the generated recovery plan to the user, obtaining user feedback, and re-evaluating and adjusting the plan. This enables the automatic generation of an appropriate recovery plan according to the disaster situation and the presentation of information according to the user's emotional state.

[0155] "Communication infrastructure" refers to the entire network infrastructure that enables real-time data collection and information transmission during disasters.

[0156] "Real-time information" refers to the latest data and events that reflect the current situation as the disaster progresses.

[0157] A "generative AI model" refers to an artificial intelligence model that analyzes the current situation based on past disaster data and automatically generates the optimal recovery plan.

[0158] A "recovery plan" is a plan aimed at effective recovery from a disaster, which includes specific instructions regarding the design of evacuation routes, the distribution of materials, and the deployment of personnel.

[0159] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions and voice, and optimizes the way information is presented according to that situation.

[0160] This invention is a system for effective information gathering and recovery support during disasters. Upon detecting a disaster, the server acquires real-time information from sensor devices and local terminals via a communication infrastructure. The hardware used includes high-precision weather sensors and highly durable communication modules. The terminals are equipped with cameras and microphones to analyze the user's facial expressions and voice in real time and collect emotional data.

[0161] The server unifies the acquired real-time information into a format that facilitates AI data analysis and supplies it to the generated AI model. This model analyzes the situation by referring to past disaster cases and automatically generates an optimal recovery plan for evacuation routes and material distribution. Specific examples of AI models include deep learning frameworks such as "TensorFlow" and "PyTorch".

[0162] Furthermore, the server uses an emotion engine to analyze the user's psychological state and presents the recovery plan in a format that is easy for the user to understand. For users in a high-stress state, the plan is presented with calming language and enhanced visual support. In this way, information is delivered more effectively and with less psychological burden.

[0163] As a concrete example, consider a scenario involving a large-scale flood. The server collects water level rise data from sensors and receives evacuation completion reports from users via on-site terminals. An AI model issues a prompt message asking, "Is it necessary to strengthen evacuation orders?" and updates the plan according to the user's situation. This mechanism makes it possible to improve the overall efficiency and quality of recovery efforts.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] When the server detects a disaster, it collects real-time information from sensor devices and on-site terminals. Inputs include weather data and images / videos showing the extent of damage. The server centrally aggregates this data through a communication infrastructure. Specifically, the server receives wind speed and precipitation data from sensors and downloads image data from on-site terminals. The output is a dataset saved in a unified format.

[0167] Step 2:

[0168] The server standardizes the collected real-time information. The input consists of raw data in various formats; the server performs format conversion to create a consistent dataset suitable for input to the generated AI model. Specifically, the server converts the data into CSV or JSON format, preparing it for efficient analysis by the model. The output is data ready for analysis.

[0169] Step 3:

[0170] The server inputs standardized data into a generating AI model to analyze the disaster situation. The input consists of past disaster cases and real-time standardized data, and the AI ​​model automatically generates a recovery plan using machine learning algorithms. Specifically, the AI ​​model calculates optimal scenarios for evacuation routes, material distribution, and personnel deployment. The output is a detailed recovery plan.

[0171] Step 4:

[0172] The server uses an emotion engine to analyze the user's psychological state and determine how to present the recovery plan. Input consists of facial expression data and voice tone transmitted from the terminal, which the server analyzes to determine the user's stress and anxiety levels. Specifically, if the emotion engine detects high user stress, it presents the recovery plan using gentler language and enhanced visual support. The output is the optimized information presentation method.

[0173] Step 5:

[0174] The device presents the user with a recovery plan and sends the user's response as feedback to the server. The input is optimized content using an emotion engine, and the device presents it in an easy-to-understand manner for the user. Specifically, for users in a high-stress state, the device displays a visually highlighted evacuation route map. The output is the user's response and feedback information.

[0175] Step 6:

[0176] The server re-evaluates and adjusts the recovery plan based on user feedback and monitors disaster recovery activities as they progress. The input is user feedback data, which the server uses to revise the recovery plan. Specifically, the server resends updated evacuation route information to the terminal based on the feedback. The output is the latest recovery plan and monitoring data of its progress.

[0177] (Application Example 2)

[0178] 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".

[0179] In the event of a disaster, a challenge exists in providing optimal information and guidance tailored to the emotional state of individual users when implementing and supporting rapid and effective recovery activities. Conventional systems sometimes fail to create an environment where users can fully understand and act with confidence by providing uniform information without considering their psychological state.

[0180] 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.

[0181] In this invention, the server includes means for acquiring immediate data through an information and communication infrastructure in the event of a disaster, means for standardizing the immediate data and inputting it into an artificial intelligence model, and means for recognizing the user's emotional state and customizing a recovery plan generated based on that emotion to present to the user. This makes it possible to provide an optimal recovery plan that takes into account the user's emotional state in the event of a disaster, thereby improving the user's sense of security and the certainty of their actions.

[0182] "Information and communication infrastructure" refers to networks and digital infrastructure used for sending and receiving data.

[0183] "Real-time data" refers to information obtained in real time, specifically data collected instantaneously under certain circumstances.

[0184] An "artificial intelligence model" refers to a set of algorithms used to learn from past data and analyze the current situation.

[0185] "Means of recognizing emotional states" refers to technologies that analyze a user's facial expressions and tone of voice to determine their psychological state.

[0186] "Customizing a recovery plan" refers to the process of adjusting and adapting a standard recovery plan to suit the individual user's needs and circumstances.

[0187] "Means for immediate monitoring of progress" refers to technologies and tools that allow for real-time confirmation of the recovery efforts and rapid response to the situation.

[0188] The system for implementing this invention is built using an information and communication infrastructure, an artificial intelligence model, and emotion recognition technology to enable rapid response in the event of a disaster. When a disaster occurs, the server immediately uses the information and communication infrastructure to acquire data from detection devices and on-site terminals. This data includes information on weather conditions and damage, as well as on-site video and audio. This collected data is first standardized before being input into the artificial intelligence model.

[0189] The artificial intelligence model utilizes deep learning frameworks such as TensorFlow to analyze the current situation based on past disaster data. Based on this analysis, the server generates a recovery plan that includes appropriate evacuation actions, supply distribution, and personnel deployment. Furthermore, the server recognizes each user's emotional state in real time through the terminal. This allows the emotion engine to adjust the information presentation method according to the user's psychological state, providing information in a format that is easiest for the user to understand and feel comfortable with.

[0190] Specifically, for example, if a user is experiencing high levels of stress, the server will present a customized plan using visual maps and gentle language to facilitate understanding. This tailored plan is then displayed on the user's device, and feedback is gathered to further improve the system. This feedback loop ensures that recovery efforts are always optimized.

[0191] Example of a prompt:

[0192] "Using the user's facial expressions and voice tone data as input, analyze the user's current emotional state and generate appropriate evacuation instructions."

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] When a disaster occurs, the server immediately collects data using the information and communication infrastructure. Inputs include weather conditions, damage status, video, and audio data from detection equipment and on-site terminals. Outputs are datasets containing this raw data. To standardize the data, data in different formats is integrated and converted into a format that can be analyzed.

[0196] Step 2:

[0197] The server inputs standardized data into an artificial intelligence model. The input is the standardized data processed in Step 1. The output is the result of analyzing the disaster situation. Using a deep learning framework such as TensorFlow, the current situation is analyzed based on past disaster data, and key parameters are extracted.

[0198] Step 3:

[0199] The server generates a recovery plan based on the AI ​​analysis results. The input is the analysis results output in step 2. The output is a recovery plan concerning evacuation actions, supply distribution, and personnel deployment. The generated AI model is used to create a plan that includes the most efficient recovery procedures.

[0200] Step 4:

[0201] The device senses the user's facial expressions and voice tone in real time and analyzes their emotional state. The input is raw emotional data obtained through the camera and microphone. The output is an evaluation of the user's emotional state. An emotion recognition algorithm is used to determine the user's psychological state.

[0202] Step 5:

[0203] The server customizes the recovery plan based on the sentiment assessment results from step 4 and presents it to the user. The inputs are the recovery plan and the user's sentiment assessment results. The output is a customized plan presented in a format suitable for the user. The plan is adjusted to provide information that is easiest for the user to understand and feel comfortable with.

[0204] Step 6:

[0205] User feedback is sent to the server via the terminal. The input is the feedback data provided by the user. The output is a dataset for improvement that the server handles. The feedback is analyzed, the effectiveness of the recovery plan is evaluated, and the plan is adjusted as needed.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] As an embodiment of this invention, a system is provided that performs data collection, analysis, plan generation, and implementation support in real time during a disaster.

[0223] When a disaster occurs, the server automatically collects real-time data from sensor devices and drones on-site. This data includes earthquake intensity, weather conditions, traffic information, and video footage of the affected area. The terminal also receives information from local users, including the latest updates on the extent of damage and the safety of evacuation centers.

[0224] The server centrally manages the acquired real-time data and inputs it into an artificial intelligence model in a standardized format. The AI ​​model analyzes the current situation by referring to past disaster data and generates an optimal recovery plan to effectively advance disaster response. This plan includes detailed instructions such as the design of evacuation routes, the deployment of emergency medical support, and the installation of communication infrastructure.

[0225] The generated recovery plan is presented to the user via the terminal. The user can review this plan and provide feedback tailored to the specific situation on-site. The server re-evaluates the plan based on the user's feedback and makes adjustments as needed.

[0226] Based on the final approved plan, the server monitors the progress of recovery activities in real time and maintains constant communication with field personnel via terminals. This increases the efficiency of recovery operations and allows for immediate solutions to be provided if problems arise.

[0227] Specific example

[0228] For example, when a large-scale typhoon occurs, the server retrieves data on the typhoon's path and wind speed from weather information systems. Terminals send reports from residents on-site about flooding and traffic disruptions. The generative artificial intelligence model analyzes this data to determine areas that need evacuation and prioritize them. It also sets evacuation routes that take into account the location of evacuation shelters and identifies areas that require emergency assistance. Users can review this plan and provide feedback if there are any changes on-site, further refining the plan. In this way, all stakeholders can cooperate to implement a swift and accurate disaster response.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] When the server detects a disaster, it immediately collects real-time data from sensor devices and drones. This data includes weather information, earthquake intensity, traffic conditions, and on-site video.

[0232] Step 2:

[0233] The server standardizes the collected data and unifies the data format. In this process, it filters out noisy data and prepares it for analysis.

[0234] Step 3:

[0235] The server inputs standardized data into a generating artificial intelligence model and analyzes the situation by comparing it with historical data from similar disasters. This analysis determines the prediction of damage and the prioritization of response measures.

[0236] Step 4:

[0237] The server generates a recovery plan based on the analysis results. The plan will include specific details such as evacuation routes, delivery destinations for relief supplies, and locations for communication infrastructure.

[0238] Step 5:

[0239] The server presents the generated recovery plan to the user via the terminal. The user reviews the plan and provides situation-based feedback as needed.

[0240] Step 6:

[0241] The server receives user feedback and re-evaluates and adjusts the recovery plan. It then finalizes the newly approved plan and prepares to implement it in field operations.

[0242] Step 7:

[0243] The server monitors the progress of the execution phase in real time, based on the adjusted recovery plan. If a problem occurs, it immediately provides alternative solutions or additional instructions to ensure smooth operation.

[0244] Step 8:

[0245] The terminal continuously receives situation reports from field personnel and immediately transmits them to the server, maintaining up-to-date information. This allows the server to monitor recovery activities more accurately.

[0246] (Example 1)

[0247] 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."

[0248] In recent years, the frequency and scale of natural disasters have increased, highlighting the growing need for rapid and effective information gathering and response planning at disaster sites. Conventional systems have struggled to collect data in real time and generate and adjust recovery plans based on that data. Furthermore, immediate plan adjustments in response to changing conditions on the ground have also been a significant challenge.

[0249] 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.

[0250] In this invention, the server includes means for acquiring dynamic data via a communication medium during a disaster, means for unifying the dynamic data and inputting it into a generative intelligence model, and means for interpreting the current disaster situation using past disaster information with the generative intelligence model and creating a recovery plan. This enables rapid and accurate information gathering and immediate plan adjustment for disaster response.

[0251] "Disaster" refers to a period of emergency caused by natural phenomena such as weather or earthquakes that affect human lives and property.

[0252] A "communication medium" refers to a physical or wireless device or network system used as a means to enable the transmission and reception of information.

[0253] "Dynamic data" refers to information that is constantly changing in real time, and includes numerical data and video footage collected from sensor devices and drones.

[0254] "Standardization" refers to the process of converting data from different formats or specifications into a standard format.

[0255] A "generative intelligence model" is a system that includes algorithms to analyze the current situation based on past data and derive optimal responses and plans.

[0256] A "recovery plan" refers to a set of specific action guidelines formulated with the aim of restoring the social and physical environment after a disaster.

[0257] A "detector device" is a general term for devices that detect physical or chemical changes in the environment and generate data from them.

[0258] "Local equipment" is a general term for devices installed in areas where a disaster has occurred in order to collect or transmit information.

[0259] An "evacuation route" refers to a designated path used to evacuate to a safe place during a disaster.

[0260] "Emergency supplies" refers to the goods and equipment needed in the event of a disaster, including food, water, and medical supplies.

[0261] "Staff" refers to personnel deployed to carry out plans and provide support in disaster response.

[0262] This invention provides a system in which servers, terminals, and users cooperate with each other to efficiently collect information, formulate response plans, and implement them during disasters.

[0263] The server first acquires dynamic data using communication media during a disaster. This data collection utilizes existing external data sources such as weather information APIs and earthquake early warning systems, and also incorporates data from sensors and drones deployed on-site. General-purpose server equipment and network connectivity devices are likely to be used as hardware.

[0264] Next, the server unifies the acquired dynamic data. It converts data in different formats into a standard format so that it can be smoothly input into the generated AI model. Database management systems and data conversion software are used in this process.

[0265] The server inputs standardized data into a generative AI model. This generative AI model analyzes the current situation based on data from past disasters and creates an appropriate recovery plan. An example of a prompt used in this process is, "Generate the optimal disaster response plan based on the current data."

[0266] The generated recovery plan is presented to the user via a device. The user can review the plan received on the device and provide feedback based on their knowledge gained from the disaster site. The device can be a smartphone, tablet, or laptop.

[0267] The server receives feedback from users and re-evaluates and adjusts the recovery plan as needed. This ensures that the plan is executed in a way that is responsive to the actual situation on site.

[0268] As a concrete example, let's consider the operation when a typhoon approaches. The server obtains typhoon path and wind speed information from weather information provision systems, and terminals transmit information on flooding conditions and traffic disruptions from local residents. The generated AI model analyzes this information, identifies areas requiring evacuation, and presents evacuation routes and priority support areas. Users can then use this information to take quick and appropriate action.

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] The server detects the occurrence of a disaster and acquires dynamic data through communication media. Specifically, it receives information on earthquake intensity and typhoon paths from weather information APIs and earthquake early warning systems. It also collects video data of the affected area from sensors and drones deployed on-site. Inputs are various data from external information services and on-site devices, and output is a collection of raw data including this data.

[0272] Step 2:

[0273] The server unifies the acquired dynamic data. Specifically, it standardizes the format of each data point and converts it into a format that can be input into the generating AI model. For example, it integrates different data formats (JSON, XML, etc.) and converts units for numerical data. The input is the raw data obtained in step 1, and the output is the standardized dataset.

[0274] Step 3:

[0275] The server inputs standardized data into a generating AI model. Using the prompt "Generate the optimal disaster response plan based on the current data," the model analyzes the current situation and creates a recovery plan by comparing it with past disaster data. The input is the standardized data obtained in step 2, and the output is the recovery plan generated by the generating AI model.

[0276] Step 4:

[0277] The server presents the generated recovery plan to the user through the terminal. The user can check the plan on the terminal and input opinions and feedback according to the on-site situation. Specifically, each element of the plan can be checked through the UI, and comments can be added based on its feasibility. The input is the recovery plan obtained in step 3, and the output is a proposed modification including the user's feedback.

[0278] Step 5:

[0279] The server re-evaluates and adjusts the recovery plan upon receiving feedback from the user. The generation AI model is utilized again to modify and optimize the plan as necessary. The input is the user feedback and the initial recovery plan obtained in step 4, and the output is the approved plan after final adjustment.

[0280] Step 6:

[0281] The server monitors the recovery activities based on the approved plan. It checks the progress status in real time and maintains communication between the user and the on-site staff through the terminal. Specifically, it checks the completion status of each task and sends prompt countermeasures when problems occur. The input is the final recovery plan, and the output is the progress status of the recovery activities and adjustment information.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] In the event of a disaster in a logistics facility, rapid and efficient data collection and analysis are required. However, conventional systems lack real-time performance and accuracy and have difficulty providing an optimal recovery plan. Against this background, there is a need for immediate information collection during a disaster and the provision of an optimal recovery procedure based on it.

[0285] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes means for acquiring real-time data through an information technology network when a disaster occurs, means for normalizing the real-time data and inputting it into a generated artificial intelligence model, and means for effectively collecting and analyzing the state data inside the logistics facility and providing an optimal recovery procedure. Thereby, even in case of a disaster, it is possible to quickly and efficiently grasp the situation inside the logistics facility and accurately execute the necessary recovery procedures.

[0287] The "information technology network" is a system for exchanging and transmitting information via the Internet or a communication network.

[0288] "Real-time data" is data that is acquired at the moment an event occurs and is immediately available for use.

[0289] "Normalization" refers to converting data obtained in different formats into a unified standard format.

[0290] The "generated artificial intelligence model" is a machine learning model trained to execute a specific task based on a large amount of data.

[0291] A "logistics facility" is a general term for places or buildings for storing, sorting, and shipping goods.

[0292] "State data" is a set of information indicating the physical and environmental situation of a logistics facility at a specific point in time.

[0293] A "recovery procedure" refers to a specific method or process for returning to a normal state when a disaster or failure occurs.

[0294] This invention is implemented as a system to support rapid and efficient recovery activities in the event of a disaster at a logistics facility. The server acquires real-time data from multiple sensor devices inside and outside the logistics facility and aggregates this data via an information technology network. The server normalizes the data acquired from the sensor devices and inputs it into a generated artificial intelligence model to derive effective recovery procedures. TensorFlow and PyTorch are used for the AI ​​model.

[0295] The terminal presents the generated recovery plan to the user and accepts user feedback on changes in the logistics facility. This user feedback is then sent back to the server and used to re-evaluate and adjust the plan.

[0296] As a concrete example, consider a recovery scenario for a logistics facility during an earthquake. The server receives vibration information and temperature changes within the facility from detection devices, and an artificial intelligence model analyzes this information to assess safety. Simultaneously, the user's smart device records information obtained from staff within the facility, identifying disruptions in logistics and damage to goods. Based on this, an optimal recovery plan is generated.

[0297] This invention allows logistics facility managers to quickly grasp the situation after a disaster and issue effective instructions. For example, a possible prompt message could be: "Based on the current state of the logistics facility, generate the optimal recovery procedure and specify which areas should be prioritized for recovery."

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The server acquires real-time data from multiple sensor devices placed inside and outside the logistics facility. Inputs include vibration information, temperature, humidity, and location information. This data is collected and then standardized so that it can be processed in the next step.

[0301] Step 2:

[0302] The server normalizes the acquired real-time data. Here, data obtained from different sensor devices is converted into a common format to ensure data consistency. As output, normalized data is obtained. This improves the accuracy of the subsequent AI model input.

[0303] Step 3:

[0304] The server inputs the normalized data into a generative artificial intelligence model. Machine learning frameworks such as TensorFlow or PyTorch are used for the AI model. The data processing here combines past disaster data and real-time data for analysis and generates recovery procedures suitable for logistics facilities. As output, a specific recovery plan is obtained.

[0305] Step 4:

[0306] The terminal presents the generated recovery plan to the user. The user can send feedback on the situation changes within the logistics facility. The operation here provides an interface to visualize the content of the recovery plan clearly so that the user can make accurate judgments.

[0307] Step 5:

[0308] The server receives feedback from the user, re-evaluates the recovery plan, and adjusts it as necessary. The input includes text data as the user's feedback. The server re-enters this as a prompt text into the generative artificial intelligence model and generates an adjusted recovery plan. As output, an updated recovery plan is obtained.

[0309] Step 6:

[0310] The server monitors the recovery progress of the logistics facility in real time and maintains constant communication with the terminals. It continuously acquires new data from sensor devices to confirm that progress is on schedule, and quickly derives countermeasures if problems occur. The output here is the latest recovery status report and necessary countermeasures.

[0311] 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.

[0312] This invention combines an emotion engine with a system that collects and analyzes data in real time during a disaster. By adding a function to recognize the user's emotions, this system enables more appropriate information provision and support.

[0313] First, when the server detects a disaster, it collects real-time data from sensor devices and on-site terminals. This data includes weather conditions, the extent of damage, and photos and videos of the scene. Terminals collect information directly entered by users on-site. In addition to this user information, data is also collected to determine emotions from the user's facial expressions and tone of voice.

[0314] The server standardizes this data and inputs it into a generating artificial intelligence model. This AI model analyzes the current situation by referring to past disaster data and automatically generates an optimal recovery plan. This recovery plan includes specific instructions such as evacuation routes, distribution plans for necessary materials, and personnel deployment.

[0315] Furthermore, by incorporating an emotion engine, the system recognizes the user's emotional state in real time. The emotion engine determines the user's stress and anxiety levels and adjusts the pace and content of the recovery plan presentation according to the user's psychological state. In this way, the plan is presented in a format that is easiest for the user to understand.

[0316] For example, if a user who has received an evacuation order is in a state of high stress, the emotion engine will recognize this and provide a plan with calmer language and enhanced visual support. The user's response is then fed back to the server via the device, where the emotional changes are recorded.

[0317] Ultimately, based on the approved recovery plan, the server continuously monitors the ongoing disaster recovery activities. User sentiment information is used as important feedback to improve on-site work efficiency, ultimately enhancing the quality of recovery efforts.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] The server collects real-time data from sensor devices and drones via the network during a disaster. This includes weather data from the affected area, earthquake vibration data, traffic conditions, and on-site video footage.

[0321] Step 2:

[0322] The device collects information from local users. Users report the extent of the damage and the need for evacuation through a specific application. The device also uses its camera and microphone to record the user's facial expressions and tone of voice, generating emotional data.

[0323] Step 3:

[0324] The server standardizes the collected real-time data and user sentiment data. This unifies the format and prepares a dataset suitable for analysis.

[0325] Step 4:

[0326] The server inputs standardized data into a generating artificial intelligence model and analyzes the current situation by referencing past disaster data. This analysis is a process that predicts damage, prioritizes emergency assistance, and generates an optimal recovery plan.

[0327] Step 5:

[0328] The server uses an emotion engine to analyze the user's emotional state. Based on this analysis, it adjusts the method of presenting the recovery plan and selects a feedback format that is appropriate for the user's psychological state.

[0329] Step 6:

[0330] The server presents the generated recovery plan to the user via the terminal. When communicating this to the user, the tone of the instructions and the presence or absence of visual assistance are adjusted according to the user's stress level.

[0331] Step 7:

[0332] The user reviews the presented recovery plan and sends feedback to the server via their device. This feedback includes comments on the plan's content and additional information from the field.

[0333] Step 8:

[0334] The server receives feedback from the user, re-evaluates the plan as needed, and proposes a revised plan. It also simultaneously records changes in the user's emotions, which are used for subsequent analysis.

[0335] Step 9:

[0336] The server monitors field activities in real time based on the approved recovery plan. This includes checking the progress of recovery work and responding immediately to any new failures.

[0337] Step 10:

[0338] The terminal continuously receives progress reports from field personnel and provides the latest information to the server, thereby improving the overall system's response speed and accuracy.

[0339] (Example 2)

[0340] 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".

[0341] During a disaster, a complex web of information becomes chaotic, making it difficult to provide swift and accurate recovery support. Furthermore, simply presenting information without considering the psychological state of users can exacerbate confusion. Therefore, it is essential to accurately process diverse information and provide recovery information to users in an appropriate format to streamline disaster recovery activities and alleviate user anxiety.

[0342] 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.

[0343] In this invention, the server includes means for acquiring real-time information through a communication infrastructure when a disaster occurs, means for unifying the real-time information and supplying it to a generation AI model, and means for displaying the generated recovery plan to the user, obtaining user feedback, and re-evaluating and adjusting the plan. This enables the automatic generation of an appropriate recovery plan according to the disaster situation and the presentation of information according to the user's emotional state.

[0344] "Communication infrastructure" refers to the entire network infrastructure that enables real-time data collection and information transmission during disasters.

[0345] "Real-time information" refers to the latest data and events that reflect the current situation as the disaster progresses.

[0346] A "generative AI model" refers to an artificial intelligence model that analyzes the current situation based on past disaster data and automatically generates the optimal recovery plan.

[0347] A "recovery plan" is a plan aimed at effective recovery from a disaster, which includes specific instructions regarding the design of evacuation routes, the distribution of materials, and the deployment of personnel.

[0348] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions and voice, and optimizes the way information is presented according to that situation.

[0349] This invention is a system for effective information gathering and recovery support during disasters. Upon detecting a disaster, the server acquires real-time information from sensor devices and local terminals via a communication infrastructure. The hardware used includes high-precision weather sensors and highly durable communication modules. The terminals are equipped with cameras and microphones to analyze the user's facial expressions and voice in real time and collect emotional data.

[0350] The server unifies the acquired real-time information into a format that facilitates AI data analysis and supplies it to the generated AI model. This model analyzes the situation by referring to past disaster cases and automatically generates an optimal recovery plan for evacuation routes and material distribution. Specific examples of AI models include deep learning frameworks such as "TensorFlow" and "PyTorch".

[0351] Furthermore, the server uses an emotion engine to analyze the user's psychological state and presents the recovery plan in a format that is easy for the user to understand. For users in a high-stress state, the plan is presented with calming language and enhanced visual support. In this way, information is delivered more effectively and with less psychological burden.

[0352] As a concrete example, consider a scenario involving a large-scale flood. The server collects water level rise data from sensors and receives evacuation completion reports from users via on-site terminals. An AI model issues a prompt message asking, "Is it necessary to strengthen evacuation orders?" and updates the plan according to the user's situation. This mechanism makes it possible to improve the overall efficiency and quality of recovery efforts.

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] When the server detects a disaster, it collects real-time information from sensor devices and on-site terminals. Inputs include weather data and images / videos showing the extent of damage. The server centrally aggregates this data through a communication infrastructure. Specifically, the server receives wind speed and precipitation data from sensors and downloads image data from on-site terminals. The output is a dataset saved in a unified format.

[0356] Step 2:

[0357] The server standardizes the collected real-time information. The input consists of raw data in various formats; the server performs format conversion to create a consistent dataset suitable for input to the generated AI model. Specifically, the server converts the data into CSV or JSON format, preparing it for efficient analysis by the model. The output is data ready for analysis.

[0358] Step 3:

[0359] The server inputs standardized data into a generating AI model to analyze the disaster situation. The input consists of past disaster cases and real-time standardized data, and the AI ​​model automatically generates a recovery plan using machine learning algorithms. Specifically, the AI ​​model calculates optimal scenarios for evacuation routes, material distribution, and personnel deployment. The output is a detailed recovery plan.

[0360] Step 4:

[0361] The server uses an emotion engine to analyze the user's psychological state and determine how to present the recovery plan. Input consists of facial expression data and voice tone transmitted from the terminal, which the server analyzes to determine the user's stress and anxiety levels. Specifically, if the emotion engine detects high user stress, it presents the recovery plan using gentler language and enhanced visual support. The output is the optimized information presentation method.

[0362] Step 5:

[0363] The device presents the user with a recovery plan and sends the user's response as feedback to the server. The input is optimized content using an emotion engine, and the device presents it in an easy-to-understand manner for the user. Specifically, for users in a high-stress state, the device displays a visually highlighted evacuation route map. The output is the user's response and feedback information.

[0364] Step 6:

[0365] The server re-evaluates and adjusts the recovery plan based on user feedback and monitors disaster recovery activities as they progress. The input is user feedback data, which the server uses to revise the recovery plan. Specifically, the server resends updated evacuation route information to the terminal based on the feedback. The output is the latest recovery plan and monitoring data of its progress.

[0366] (Application Example 2)

[0367] 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."

[0368] In the event of a disaster, a challenge exists in providing optimal information and guidance tailored to the emotional state of individual users when implementing and supporting rapid and effective recovery activities. Conventional systems sometimes fail to create an environment where users can fully understand and act with confidence by providing uniform information without considering their psychological state.

[0369] 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.

[0370] In this invention, the server includes means for acquiring immediate data through an information and communication infrastructure in the event of a disaster, means for standardizing the immediate data and inputting it into an artificial intelligence model, and means for recognizing the user's emotional state and customizing a recovery plan generated based on that emotion to present to the user. This makes it possible to provide an optimal recovery plan that takes into account the user's emotional state in the event of a disaster, thereby improving the user's sense of security and the certainty of their actions.

[0371] "Information and communication infrastructure" refers to networks and digital infrastructure used for sending and receiving data.

[0372] "Real-time data" refers to information obtained in real time, specifically data collected instantaneously under certain circumstances.

[0373] An "artificial intelligence model" refers to a set of algorithms used to learn from past data and analyze the current situation.

[0374] "Means of recognizing emotional states" refers to technologies that analyze a user's facial expressions and tone of voice to determine their psychological state.

[0375] "Customizing a recovery plan" refers to the process of adjusting and adapting a standard recovery plan to suit the individual user's needs and circumstances.

[0376] "Means for immediate monitoring of progress" refers to technologies and tools that allow for real-time confirmation of the recovery efforts and rapid response to the situation.

[0377] The system for implementing this invention is built using an information and communication infrastructure, an artificial intelligence model, and emotion recognition technology to enable rapid response in the event of a disaster. When a disaster occurs, the server immediately uses the information and communication infrastructure to acquire data from detection devices and on-site terminals. This data includes information on weather conditions and damage, as well as on-site video and audio. This collected data is first standardized before being input into the artificial intelligence model.

[0378] The artificial intelligence model utilizes deep learning frameworks such as TensorFlow to analyze the current situation based on past disaster data. Based on this analysis, the server generates a recovery plan that includes appropriate evacuation actions, supply distribution, and personnel deployment. Furthermore, the server recognizes each user's emotional state in real time through the terminal. This allows the emotion engine to adjust the information presentation method according to the user's psychological state, providing information in a format that is easiest for the user to understand and feel comfortable with.

[0379] Specifically, for example, if a user is experiencing high levels of stress, the server will present a customized plan using visual maps and gentle language to facilitate understanding. This tailored plan is then displayed on the user's device, and feedback is gathered to further improve the system. This feedback loop ensures that recovery efforts are always optimized.

[0380] Example of a prompt:

[0381] "Using the user's facial expressions and voice tone data as input, analyze the user's current emotional state and generate appropriate evacuation instructions."

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] When a disaster occurs, the server immediately collects data using the information and communication infrastructure. Inputs include weather conditions, damage status, video, and audio data from detection equipment and on-site terminals. Outputs are datasets containing this raw data. To standardize the data, data in different formats is integrated and converted into a format that can be analyzed.

[0385] Step 2:

[0386] The server inputs standardized data into an artificial intelligence model. The input is the standardized data processed in Step 1. The output is the result of analyzing the disaster situation. Using a deep learning framework such as TensorFlow, the current situation is analyzed based on past disaster data, and key parameters are extracted.

[0387] Step 3:

[0388] The server generates a recovery plan based on the AI ​​analysis results. The input is the analysis results output in step 2. The output is a recovery plan concerning evacuation actions, supply distribution, and personnel deployment. The generated AI model is used to create a plan that includes the most efficient recovery procedures.

[0389] Step 4:

[0390] The device senses the user's facial expressions and voice tone in real time and analyzes their emotional state. The input is raw emotional data obtained through the camera and microphone. The output is an evaluation of the user's emotional state. An emotion recognition algorithm is used to determine the user's psychological state.

[0391] Step 5:

[0392] The server customizes the recovery plan based on the sentiment assessment results from step 4 and presents it to the user. The inputs are the recovery plan and the user's sentiment assessment results. The output is a customized plan presented in a format suitable for the user. The plan is adjusted to provide information that is easiest for the user to understand and feel comfortable with.

[0393] Step 6:

[0394] User feedback is sent to the server via the terminal. The input is the feedback data provided by the user. The output is a dataset for improvement that the server handles. The feedback is analyzed, the effectiveness of the recovery plan is evaluated, and the plan is adjusted as needed.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] [Third Embodiment]

[0399] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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".

[0411] As an embodiment of this invention, a system is provided that performs data collection, analysis, plan generation, and implementation support in real time during a disaster.

[0412] When a disaster occurs, the server automatically collects real-time data from sensor devices and drones on-site. This data includes earthquake intensity, weather conditions, traffic information, and video footage of the affected area. The terminal also receives information from local users, including the latest updates on the extent of damage and the safety of evacuation centers.

[0413] The server centrally manages the acquired real-time data and inputs it into an artificial intelligence model in a standardized format. The AI ​​model analyzes the current situation by referring to past disaster data and generates an optimal recovery plan to effectively advance disaster response. This plan includes detailed instructions such as the design of evacuation routes, the deployment of emergency medical support, and the installation of communication infrastructure.

[0414] The generated recovery plan is presented to the user via the terminal. The user can review this plan and provide feedback tailored to the specific situation on-site. The server re-evaluates the plan based on the user's feedback and makes adjustments as needed.

[0415] Based on the final approved plan, the server monitors the progress of recovery activities in real time and maintains constant communication with field personnel via terminals. This increases the efficiency of recovery operations and allows for immediate solutions to be provided if problems arise.

[0416] Specific example

[0417] For example, when a large-scale typhoon occurs, the server retrieves data on the typhoon's path and wind speed from weather information systems. Terminals send reports from residents on-site about flooding and traffic disruptions. The generative artificial intelligence model analyzes this data to determine areas that need evacuation and prioritize them. It also sets evacuation routes that take into account the location of evacuation shelters and identifies areas that require emergency assistance. Users can review this plan and provide feedback if there are any changes on-site, further refining the plan. In this way, all stakeholders can cooperate to implement a swift and accurate disaster response.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] When the server detects a disaster, it immediately collects real-time data from sensor devices and drones. This data includes weather information, earthquake intensity, traffic conditions, and on-site video.

[0421] Step 2:

[0422] The server standardizes the collected data and unifies the data format. In this process, it filters out noisy data and prepares it for analysis.

[0423] Step 3:

[0424] The server inputs standardized data into a generating artificial intelligence model and analyzes the situation by comparing it with historical data from similar disasters. This analysis determines the prediction of damage and the prioritization of response measures.

[0425] Step 4:

[0426] The server generates a recovery plan based on the analysis results. The plan will include specific details such as evacuation routes, delivery destinations for relief supplies, and locations for communication infrastructure.

[0427] Step 5:

[0428] The server presents the generated recovery plan to the user via the terminal. The user reviews the plan and provides situation-based feedback as needed.

[0429] Step 6:

[0430] The server receives user feedback and re-evaluates and adjusts the recovery plan. It then finalizes the newly approved plan and prepares to implement it in field operations.

[0431] Step 7:

[0432] The server monitors the progress of the execution phase in real time, based on the adjusted recovery plan. If a problem occurs, it immediately provides alternative solutions or additional instructions to ensure smooth operation.

[0433] Step 8:

[0434] The terminal continuously receives situation reports from field personnel and immediately transmits them to the server, maintaining up-to-date information. This allows the server to monitor recovery activities more accurately.

[0435] (Example 1)

[0436] 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."

[0437] In recent years, the frequency and scale of natural disasters have increased, highlighting the growing need for rapid and effective information gathering and response planning at disaster sites. Conventional systems have struggled to collect data in real time and generate and adjust recovery plans based on that data. Furthermore, immediate plan adjustments in response to changing conditions on the ground have also been a significant challenge.

[0438] 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.

[0439] In this invention, the server includes means for acquiring dynamic data via a communication medium during a disaster, means for unifying the dynamic data and inputting it into a generative intelligence model, and means for interpreting the current disaster situation using past disaster information with the generative intelligence model and creating a recovery plan. This enables rapid and accurate information gathering and immediate plan adjustment for disaster response.

[0440] "Disaster" refers to a period of emergency caused by natural phenomena such as weather or earthquakes that affect human lives and property.

[0441] A "communication medium" refers to a physical or wireless device or network system used as a means to enable the transmission and reception of information.

[0442] "Dynamic data" refers to information that is constantly changing in real time, and includes numerical data and video footage collected from sensor devices and drones.

[0443] "Standardization" refers to the process of converting data from different formats or specifications into a standard format.

[0444] A "generative intelligence model" is a system that includes algorithms to analyze the current situation based on past data and derive optimal responses and plans.

[0445] A "recovery plan" refers to a set of specific action guidelines formulated with the aim of restoring the social and physical environment after a disaster.

[0446] A "detector device" is a general term for devices that detect physical or chemical changes in the environment and generate data from them.

[0447] "Local equipment" is a general term for devices installed in areas where a disaster has occurred in order to collect or transmit information.

[0448] An "evacuation route" refers to a designated path used to evacuate to a safe place during a disaster.

[0449] "Emergency supplies" refers to the goods and equipment needed in the event of a disaster, including food, water, and medical supplies.

[0450] "Staff" refers to personnel deployed to carry out plans and provide support in disaster response.

[0451] This invention provides a system in which servers, terminals, and users cooperate with each other to efficiently collect information, formulate response plans, and implement them during disasters.

[0452] The server first acquires dynamic data using communication media during a disaster. This data collection utilizes existing external data sources such as weather information APIs and earthquake early warning systems, and also incorporates data from sensors and drones deployed on-site. General-purpose server equipment and network connectivity devices are likely to be used as hardware.

[0453] Next, the server unifies the acquired dynamic data. It converts data in different formats into a standard format so that it can be smoothly input into the generated AI model. Database management systems and data conversion software are used in this process.

[0454] The server inputs standardized data into a generative AI model. This generative AI model analyzes the current situation based on data from past disasters and creates an appropriate recovery plan. An example of a prompt used in this process is, "Generate the optimal disaster response plan based on the current data."

[0455] The generated recovery plan is presented to the user via a device. The user can review the plan received on the device and provide feedback based on their knowledge gained from the disaster site. The device can be a smartphone, tablet, or laptop.

[0456] The server receives feedback from users and re-evaluates and adjusts the recovery plan as needed. This ensures that the plan is executed in a way that is responsive to the actual situation on site.

[0457] As a concrete example, let's consider the operation when a typhoon approaches. The server obtains typhoon path and wind speed information from weather information provision systems, and terminals transmit information on flooding conditions and traffic disruptions from local residents. The generated AI model analyzes this information, identifies areas requiring evacuation, and presents evacuation routes and priority support areas. Users can then use this information to take quick and appropriate action.

[0458] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0459] Step 1:

[0460] The server detects the occurrence of a disaster and acquires dynamic data through communication media. Specifically, it receives information on earthquake intensity and typhoon paths from weather information APIs and earthquake early warning systems. It also collects video data of the affected area from sensors and drones deployed on-site. Inputs are various data from external information services and on-site devices, and output is a collection of raw data including this data.

[0461] Step 2:

[0462] The server unifies the acquired dynamic data. Specifically, it standardizes the format of each data point and converts it into a format that can be input into the generating AI model. For example, it integrates different data formats (JSON, XML, etc.) and converts units for numerical data. The input is the raw data obtained in step 1, and the output is the standardized dataset.

[0463] Step 3:

[0464] The server inputs standardized data into a generating AI model. Using the prompt "Generate the optimal disaster response plan based on the current data," the model analyzes the current situation and creates a recovery plan by comparing it with past disaster data. The input is the standardized data obtained in step 2, and the output is the recovery plan generated by the generating AI model.

[0465] Step 4:

[0466] The server presents the generated recovery plan to the user via the terminal. The user can review the plan on the terminal and input opinions and feedback based on the situation on site. Specifically, they can review each element of the plan through the UI and add comments based on its feasibility. The input is the recovery plan obtained in step 3, and the output is a revised plan including the user's feedback.

[0467] Step 5:

[0468] The server re-evaluates and adjusts the recovery plan based on user feedback. It then utilizes the generated AI model again to modify and optimize the plan as needed. The input is the user feedback and initial recovery plan obtained in step 4, and the output is the approved plan after final adjustments.

[0469] Step 6:

[0470] The server monitors recovery activities based on the approved plan. It checks progress in real time and maintains communication between users and field personnel through terminals. Specifically, it checks the completion status of each task and quickly sends countermeasures when problems occur. The input is the final recovery plan, and the output is the progress of the recovery activities and coordination information.

[0471] (Application Example 1)

[0472] 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."

[0473] In the event of a disaster within a logistics facility, rapid and efficient data collection and analysis are required. However, conventional systems lack real-time capabilities and accuracy, making it difficult to provide optimal recovery plans. Against this backdrop, there is a need for immediate information collection during disasters and the provision of optimal recovery procedures based on that information.

[0474] 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.

[0475] In this invention, the server includes means for acquiring real-time data through an information technology network in the event of a disaster, means for standardizing the real-time data and inputting it into a generated artificial intelligence model, and means for effectively collecting and analyzing internal state data of a logistics facility and providing optimal recovery procedures. This makes it possible to quickly and efficiently grasp the situation inside a logistics facility even in the event of a disaster and accurately execute the necessary recovery procedures.

[0476] An "information technology network" is a system for exchanging and transmitting information via the internet or communication networks.

[0477] "Real-time data" refers to data that is acquired at the exact moment an event occurs and is immediately available for use.

[0478] "Standardization" refers to the process of converting data obtained in different formats into a unified standard format.

[0479] A "generative artificial intelligence model" is a machine learning model trained to perform a specific task based on a large amount of data.

[0480] A "logistics facility" is a general term for places or buildings used for storing, sorting, and shipping goods.

[0481] "Status data" refers to a collection of information that indicates the physical and environmental conditions of a logistics facility at a specific point in time.

[0482] "Recovery procedures" refer to the specific methods and steps taken to restore the system to a normal state in the event of a disaster or malfunction.

[0483] This invention is implemented as a system to support rapid and efficient recovery activities in the event of a disaster at a logistics facility. The server acquires real-time data from multiple sensor devices inside and outside the logistics facility and aggregates this data via an information technology network. The server normalizes the data acquired from the sensor devices and inputs it into a generated artificial intelligence model to derive effective recovery procedures. TensorFlow and PyTorch are used for the AI ​​model.

[0484] The terminal presents the generated recovery plan to the user and accepts user feedback on changes in the logistics facility. This user feedback is then sent back to the server and used to re-evaluate and adjust the plan.

[0485] As a concrete example, consider a recovery scenario for a logistics facility during an earthquake. The server receives vibration information and temperature changes within the facility from detection devices, and an artificial intelligence model analyzes this information to assess safety. Simultaneously, the user's smart device records information obtained from staff within the facility, identifying disruptions in logistics and damage to goods. Based on this, an optimal recovery plan is generated.

[0486] This invention allows logistics facility managers to quickly grasp the situation after a disaster and issue effective instructions. For example, a possible prompt message could be: "Based on the current state of the logistics facility, generate the optimal recovery procedure and specify which areas should be prioritized for recovery."

[0487] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0488] Step 1:

[0489] The server acquires real-time data from multiple sensor devices placed inside and outside the logistics facility. Inputs include vibration information, temperature, humidity, and location information. This data is collected and then standardized so that it can be processed in the next step.

[0490] Step 2:

[0491] The server normalizes the acquired real-time data. Here, data obtained from different sensor devices is converted into a common format to ensure data consistency. The output is normalized data, which improves the accuracy of subsequent AI model inputs.

[0492] Step 3:

[0493] The server inputs standardized data into an artificial intelligence model. Machine learning frameworks such as TensorFlow and PyTorch are used for the AI ​​model. Data processing here involves analyzing historical disaster data and real-time data to generate recovery procedures suitable for logistics facilities. The output is a concrete recovery plan.

[0494] Step 4:

[0495] The terminal presents the generated recovery plan to the user. The user can send feedback about changes in the situation within the logistics facility. The function here is to provide an interface that visualizes the contents of the recovery plan in an easy-to-understand way, enabling the user to make accurate decisions.

[0496] Step 5:

[0497] The server receives user feedback and re-evaluates the recovery plan, adjusting it as needed. The input includes text data representing user feedback. The server then inputs this back into an artificial intelligence model, generating prompts, and produces an adjusted recovery plan. The output is the updated recovery plan.

[0498] Step 6:

[0499] The server monitors the recovery progress of the logistics facility in real time and maintains constant communication with the terminals. It continuously acquires new data from sensor devices to confirm that progress is on schedule, and quickly derives countermeasures if problems occur. The output here is the latest recovery status report and necessary countermeasures.

[0500] 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.

[0501] This invention combines an emotion engine with a system that collects and analyzes data in real time during a disaster. By adding a function to recognize the user's emotions, this system enables more appropriate information provision and support.

[0502] First, when the server detects a disaster, it collects real-time data from sensor devices and on-site terminals. This data includes weather conditions, the extent of damage, and photos and videos of the scene. Terminals collect information directly entered by users on-site. In addition to this user information, data is also collected to determine emotions from the user's facial expressions and tone of voice.

[0503] The server standardizes this data and inputs it into a generating artificial intelligence model. This AI model analyzes the current situation by referring to past disaster data and automatically generates an optimal recovery plan. This recovery plan includes specific instructions such as evacuation routes, distribution plans for necessary materials, and personnel deployment.

[0504] Furthermore, by incorporating an emotion engine, the system recognizes the user's emotional state in real time. The emotion engine determines the user's stress and anxiety levels and adjusts the pace and content of the recovery plan presentation according to the user's psychological state. In this way, the plan is presented in a format that is easiest for the user to understand.

[0505] For example, if a user who has received an evacuation order is in a state of high stress, the emotion engine will recognize this and provide a plan with calmer language and enhanced visual support. The user's response is then fed back to the server via the device, where the emotional changes are recorded.

[0506] Ultimately, based on the approved recovery plan, the server continuously monitors the ongoing disaster recovery activities. User sentiment information is used as important feedback to improve on-site work efficiency, ultimately enhancing the quality of recovery efforts.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] The server collects real-time data from sensor devices and drones via the network during a disaster. This includes weather data from the affected area, earthquake vibration data, traffic conditions, and on-site video footage.

[0510] Step 2:

[0511] The device collects information from local users. Users report the extent of the damage and the need for evacuation through a specific application. The device also uses its camera and microphone to record the user's facial expressions and tone of voice, generating emotional data.

[0512] Step 3:

[0513] The server standardizes the collected real-time data and user sentiment data. This unifies the format and prepares a dataset suitable for analysis.

[0514] Step 4:

[0515] The server inputs standardized data into a generating artificial intelligence model and analyzes the current situation by referencing past disaster data. This analysis is a process that predicts damage, prioritizes emergency assistance, and generates an optimal recovery plan.

[0516] Step 5:

[0517] The server uses an emotion engine to analyze the user's emotional state. Based on this analysis, it adjusts the method of presenting the recovery plan and selects a feedback format that is appropriate for the user's psychological state.

[0518] Step 6:

[0519] The server presents the generated recovery plan to the user via the terminal. When communicating this to the user, the tone of the instructions and the presence or absence of visual assistance are adjusted according to the user's stress level.

[0520] Step 7:

[0521] The user reviews the presented recovery plan and sends feedback to the server via their device. This feedback includes comments on the plan's content and additional information from the field.

[0522] Step 8:

[0523] The server receives feedback from the user, re-evaluates the plan as needed, and proposes a revised plan. It also simultaneously records changes in the user's emotions, which are used for subsequent analysis.

[0524] Step 9:

[0525] The server monitors field activities in real time based on the approved recovery plan. This includes checking the progress of recovery work and responding immediately to any new failures.

[0526] Step 10:

[0527] The terminal continuously receives progress reports from field personnel and provides the latest information to the server, thereby improving the overall system's response speed and accuracy.

[0528] (Example 2)

[0529] 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."

[0530] During a disaster, a complex web of information becomes chaotic, making it difficult to provide swift and accurate recovery support. Furthermore, simply presenting information without considering the psychological state of users can exacerbate confusion. Therefore, it is essential to accurately process diverse information and provide recovery information to users in an appropriate format to streamline disaster recovery activities and alleviate user anxiety.

[0531] 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.

[0532] In this invention, the server includes means for acquiring real-time information through a communication infrastructure when a disaster occurs, means for unifying the real-time information and supplying it to a generation AI model, and means for displaying the generated recovery plan to the user, obtaining user feedback, and re-evaluating and adjusting the plan. This enables the automatic generation of an appropriate recovery plan according to the disaster situation and the presentation of information according to the user's emotional state.

[0533] "Communication infrastructure" refers to the entire network infrastructure that enables real-time data collection and information transmission during disasters.

[0534] "Real-time information" refers to the latest data and events that reflect the current situation as the disaster progresses.

[0535] A "generative AI model" refers to an artificial intelligence model that analyzes the current situation based on past disaster data and automatically generates the optimal recovery plan.

[0536] A "recovery plan" is a plan aimed at effective recovery from a disaster, which includes specific instructions regarding the design of evacuation routes, the distribution of materials, and the deployment of personnel.

[0537] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions and voice, and optimizes the way information is presented according to that situation.

[0538] This invention is a system for effective information gathering and recovery support during disasters. Upon detecting a disaster, the server acquires real-time information from sensor devices and local terminals via a communication infrastructure. The hardware used includes high-precision weather sensors and highly durable communication modules. The terminals are equipped with cameras and microphones to analyze the user's facial expressions and voice in real time and collect emotional data.

[0539] The server unifies the acquired real-time information into a format that facilitates AI data analysis and supplies it to the generated AI model. This model analyzes the situation by referring to past disaster cases and automatically generates an optimal recovery plan for evacuation routes and material distribution. Specific examples of AI models include deep learning frameworks such as "TensorFlow" and "PyTorch".

[0540] Furthermore, the server uses an emotion engine to analyze the user's psychological state and presents the recovery plan in a format that is easy for the user to understand. For users in a high-stress state, the plan is presented with calming language and enhanced visual support. In this way, information is delivered more effectively and with less psychological burden.

[0541] As a concrete example, consider a scenario involving a large-scale flood. The server collects water level rise data from sensors and receives evacuation completion reports from users via on-site terminals. An AI model issues a prompt message asking, "Is it necessary to strengthen evacuation orders?" and updates the plan according to the user's situation. This mechanism makes it possible to improve the overall efficiency and quality of recovery efforts.

[0542] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0543] Step 1:

[0544] When the server detects a disaster, it collects real-time information from sensor devices and on-site terminals. Inputs include weather data and images / videos showing the extent of damage. The server centrally aggregates this data through a communication infrastructure. Specifically, the server receives wind speed and precipitation data from sensors and downloads image data from on-site terminals. The output is a dataset saved in a unified format.

[0545] Step 2:

[0546] The server standardizes the collected real-time information. The input consists of raw data in various formats; the server performs format conversion to create a consistent dataset suitable for input to the generated AI model. Specifically, the server converts the data into CSV or JSON format, preparing it for efficient analysis by the model. The output is data ready for analysis.

[0547] Step 3:

[0548] The server inputs standardized data into a generating AI model to analyze the disaster situation. The input consists of past disaster cases and real-time standardized data, and the AI ​​model automatically generates a recovery plan using machine learning algorithms. Specifically, the AI ​​model calculates optimal scenarios for evacuation routes, material distribution, and personnel deployment. The output is a detailed recovery plan.

[0549] Step 4:

[0550] The server uses an emotion engine to analyze the user's psychological state and determine how to present the recovery plan. Input consists of facial expression data and voice tone transmitted from the terminal, which the server analyzes to determine the user's stress and anxiety levels. Specifically, if the emotion engine detects high user stress, it presents the recovery plan using gentler language and enhanced visual support. The output is the optimized information presentation method.

[0551] Step 5:

[0552] The device presents the user with a recovery plan and sends the user's response as feedback to the server. The input is optimized content using an emotion engine, and the device presents it in an easy-to-understand manner for the user. Specifically, for users in a high-stress state, the device displays a visually highlighted evacuation route map. The output is the user's response and feedback information.

[0553] Step 6:

[0554] The server re-evaluates and adjusts the recovery plan based on user feedback and monitors disaster recovery activities as they progress. The input is user feedback data, which the server uses to revise the recovery plan. Specifically, the server resends updated evacuation route information to the terminal based on the feedback. The output is the latest recovery plan and monitoring data of its progress.

[0555] (Application Example 2)

[0556] 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."

[0557] In the event of a disaster, a challenge exists in providing optimal information and guidance tailored to the emotional state of individual users when implementing and supporting rapid and effective recovery activities. Conventional systems sometimes fail to create an environment where users can fully understand and act with confidence by providing uniform information without considering their psychological state.

[0558] 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.

[0559] In this invention, the server includes means for acquiring immediate data through an information and communication infrastructure in the event of a disaster, means for standardizing the immediate data and inputting it into an artificial intelligence model, and means for recognizing the user's emotional state and customizing a recovery plan generated based on that emotion to present to the user. This makes it possible to provide an optimal recovery plan that takes into account the user's emotional state in the event of a disaster, thereby improving the user's sense of security and the certainty of their actions.

[0560] "Information and communication infrastructure" refers to networks and digital infrastructure used for sending and receiving data.

[0561] "Real-time data" refers to information obtained in real time, specifically data collected instantaneously under certain circumstances.

[0562] An "artificial intelligence model" refers to a set of algorithms used to learn from past data and analyze the current situation.

[0563] "Means of recognizing emotional states" refers to technologies that analyze a user's facial expressions and tone of voice to determine their psychological state.

[0564] "Customizing a recovery plan" refers to the process of adjusting and adapting a standard recovery plan to suit the individual user's needs and circumstances.

[0565] "Means for immediate monitoring of progress" refers to technologies and tools that allow for real-time confirmation of the recovery efforts and rapid response to the situation.

[0566] The system for implementing this invention is built using an information and communication infrastructure, an artificial intelligence model, and emotion recognition technology to enable rapid response in the event of a disaster. When a disaster occurs, the server immediately uses the information and communication infrastructure to acquire data from detection devices and on-site terminals. This data includes information on weather conditions and damage, as well as on-site video and audio. This collected data is first standardized before being input into the artificial intelligence model.

[0567] The artificial intelligence model utilizes deep learning frameworks such as TensorFlow to analyze the current situation based on past disaster data. Based on this analysis, the server generates a recovery plan that includes appropriate evacuation actions, supply distribution, and personnel deployment. Furthermore, the server recognizes each user's emotional state in real time through the terminal. This allows the emotion engine to adjust the information presentation method according to the user's psychological state, providing information in a format that is easiest for the user to understand and feel comfortable with.

[0568] Specifically, for example, if a user is experiencing high levels of stress, the server will present a customized plan using visual maps and gentle language to facilitate understanding. This tailored plan is then displayed on the user's device, and feedback is gathered to further improve the system. This feedback loop ensures that recovery efforts are always optimized.

[0569] Example of a prompt:

[0570] "Using the user's facial expressions and voice tone data as input, analyze the user's current emotional state and generate appropriate evacuation instructions."

[0571] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0572] Step 1:

[0573] When a disaster occurs, the server immediately collects data using the information and communication infrastructure. Inputs include weather conditions, damage status, video, and audio data from detection equipment and on-site terminals. Outputs are datasets containing this raw data. To standardize the data, data in different formats is integrated and converted into a format that can be analyzed.

[0574] Step 2:

[0575] The server inputs standardized data into an artificial intelligence model. The input is the standardized data processed in Step 1. The output is the result of analyzing the disaster situation. Using a deep learning framework such as TensorFlow, the current situation is analyzed based on past disaster data, and key parameters are extracted.

[0576] Step 3:

[0577] The server generates a recovery plan based on the AI ​​analysis results. The input is the analysis results output in step 2. The output is a recovery plan concerning evacuation actions, supply distribution, and personnel deployment. The generated AI model is used to create a plan that includes the most efficient recovery procedures.

[0578] Step 4:

[0579] The device senses the user's facial expressions and voice tone in real time and analyzes their emotional state. The input is raw emotional data obtained through the camera and microphone. The output is an evaluation of the user's emotional state. An emotion recognition algorithm is used to determine the user's psychological state.

[0580] Step 5:

[0581] The server customizes the recovery plan based on the sentiment assessment results from step 4 and presents it to the user. The inputs are the recovery plan and the user's sentiment assessment results. The output is a customized plan presented in a format suitable for the user. The plan is adjusted to provide information that is easiest for the user to understand and feel comfortable with.

[0582] Step 6:

[0583] User feedback is sent to the server via the terminal. The input is the feedback data provided by the user. The output is a dataset for improvement that the server handles. The feedback is analyzed, the effectiveness of the recovery plan is evaluated, and the plan is adjusted as needed.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] [Fourth Embodiment]

[0588] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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".

[0601] As an embodiment of this invention, a system is provided that performs data collection, analysis, plan generation, and implementation support in real time during a disaster.

[0602] When a disaster occurs, the server automatically collects real-time data from sensor devices and drones on-site. This data includes earthquake intensity, weather conditions, traffic information, and video footage of the affected area. The terminal also receives information from local users, including the latest updates on the extent of damage and the safety of evacuation centers.

[0603] The server centrally manages the acquired real-time data and inputs it into an artificial intelligence model in a standardized format. The AI ​​model analyzes the current situation by referring to past disaster data and generates an optimal recovery plan to effectively advance disaster response. This plan includes detailed instructions such as the design of evacuation routes, the deployment of emergency medical support, and the installation of communication infrastructure.

[0604] The generated recovery plan is presented to the user via the terminal. The user can review this plan and provide feedback tailored to the specific situation on-site. The server re-evaluates the plan based on the user's feedback and makes adjustments as needed.

[0605] Based on the final approved plan, the server monitors the progress of recovery activities in real time and maintains constant communication with field personnel via terminals. This increases the efficiency of recovery operations and allows for immediate solutions to be provided if problems arise.

[0606] Specific example

[0607] For example, when a large-scale typhoon occurs, the server retrieves data on the typhoon's path and wind speed from weather information systems. Terminals send reports from residents on-site about flooding and traffic disruptions. The generative artificial intelligence model analyzes this data to determine areas that need evacuation and prioritize them. It also sets evacuation routes that take into account the location of evacuation shelters and identifies areas that require emergency assistance. Users can review this plan and provide feedback if there are any changes on-site, further refining the plan. In this way, all stakeholders can cooperate to implement a swift and accurate disaster response.

[0608] The following describes the processing flow.

[0609] Step 1:

[0610] When the server detects a disaster, it immediately collects real-time data from sensor devices and drones. This data includes weather information, earthquake intensity, traffic conditions, and on-site video.

[0611] Step 2:

[0612] The server standardizes the collected data and unifies the data format. In this process, it filters out noisy data and prepares it for analysis.

[0613] Step 3:

[0614] The server inputs standardized data into a generating artificial intelligence model and analyzes the situation by comparing it with historical data from similar disasters. This analysis determines the prediction of damage and the prioritization of response measures.

[0615] Step 4:

[0616] The server generates a recovery plan based on the analysis results. The plan will include specific details such as evacuation routes, delivery destinations for relief supplies, and locations for communication infrastructure.

[0617] Step 5:

[0618] The server presents the generated recovery plan to the user via the terminal. The user reviews the plan and provides situation-based feedback as needed.

[0619] Step 6:

[0620] The server receives user feedback and re-evaluates and adjusts the recovery plan. It then finalizes the newly approved plan and prepares to implement it in field operations.

[0621] Step 7:

[0622] The server monitors the progress of the execution phase in real time, based on the adjusted recovery plan. If a problem occurs, it immediately provides alternative solutions or additional instructions to ensure smooth operation.

[0623] Step 8:

[0624] The terminal continuously receives situation reports from field personnel and immediately transmits them to the server, maintaining up-to-date information. This allows the server to monitor recovery activities more accurately.

[0625] (Example 1)

[0626] 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".

[0627] In recent years, the frequency and scale of natural disasters have increased, highlighting the growing need for rapid and effective information gathering and response planning at disaster sites. Conventional systems have struggled to collect data in real time and generate and adjust recovery plans based on that data. Furthermore, immediate plan adjustments in response to changing conditions on the ground have also been a significant challenge.

[0628] 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.

[0629] In this invention, the server includes means for acquiring dynamic data via a communication medium during a disaster, means for unifying the dynamic data and inputting it into a generative intelligence model, and means for interpreting the current disaster situation using past disaster information with the generative intelligence model and creating a recovery plan. This enables rapid and accurate information gathering and immediate plan adjustment for disaster response.

[0630] "Disaster" refers to a period of emergency caused by natural phenomena such as weather or earthquakes that affect human lives and property.

[0631] A "communication medium" refers to a physical or wireless device or network system used as a means to enable the transmission and reception of information.

[0632] "Dynamic data" refers to information that is constantly changing in real time, and includes numerical data and video footage collected from sensor devices and drones.

[0633] "Standardization" refers to the process of converting data from different formats or specifications into a standard format.

[0634] A "generative intelligence model" is a system that includes algorithms to analyze the current situation based on past data and derive optimal responses and plans.

[0635] A "recovery plan" refers to a set of specific action guidelines formulated with the aim of restoring the social and physical environment after a disaster.

[0636] A "detector device" is a general term for devices that detect physical or chemical changes in the environment and generate data from them.

[0637] "Local equipment" is a general term for devices installed in areas where a disaster has occurred in order to collect or transmit information.

[0638] An "evacuation route" refers to a designated path used to evacuate to a safe place during a disaster.

[0639] "Emergency supplies" refers to the goods and equipment needed in the event of a disaster, including food, water, and medical supplies.

[0640] "Staff" refers to personnel deployed to carry out plans and provide support in disaster response.

[0641] This invention provides a system in which servers, terminals, and users cooperate with each other to efficiently collect information, formulate response plans, and implement them during disasters.

[0642] The server first acquires dynamic data using communication media during a disaster. This data collection utilizes existing external data sources such as weather information APIs and earthquake early warning systems, and also incorporates data from sensors and drones deployed on-site. General-purpose server equipment and network connectivity devices are likely to be used as hardware.

[0643] Next, the server unifies the acquired dynamic data. It converts data in different formats into a standard format so that it can be smoothly input into the generated AI model. Database management systems and data conversion software are used in this process.

[0644] The server inputs standardized data into a generative AI model. This generative AI model analyzes the current situation based on data from past disasters and creates an appropriate recovery plan. An example of a prompt used in this process is, "Generate the optimal disaster response plan based on the current data."

[0645] The generated recovery plan is presented to the user via a device. The user can review the plan received on the device and provide feedback based on their knowledge gained from the disaster site. The device can be a smartphone, tablet, or laptop.

[0646] The server receives feedback from users and re-evaluates and adjusts the recovery plan as needed. This ensures that the plan is executed in a way that is responsive to the actual situation on site.

[0647] As a concrete example, let's consider the operation when a typhoon approaches. The server obtains typhoon path and wind speed information from weather information provision systems, and terminals transmit information on flooding conditions and traffic disruptions from local residents. The generated AI model analyzes this information, identifies areas requiring evacuation, and presents evacuation routes and priority support areas. Users can then use this information to take quick and appropriate action.

[0648] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0649] Step 1:

[0650] The server detects the occurrence of a disaster and acquires dynamic data through communication media. Specifically, it receives information on earthquake intensity and typhoon paths from weather information APIs and earthquake early warning systems. It also collects video data of the affected area from sensors and drones deployed on-site. Inputs are various data from external information services and on-site devices, and output is a collection of raw data including this data.

[0651] Step 2:

[0652] The server unifies the acquired dynamic data. Specifically, it standardizes the format of each data point and converts it into a format that can be input into the generating AI model. For example, it integrates different data formats (JSON, XML, etc.) and converts units for numerical data. The input is the raw data obtained in step 1, and the output is the standardized dataset.

[0653] Step 3:

[0654] The server inputs standardized data into a generating AI model. Using the prompt "Generate the optimal disaster response plan based on the current data," the model analyzes the current situation and creates a recovery plan by comparing it with past disaster data. The input is the standardized data obtained in step 2, and the output is the recovery plan generated by the generating AI model.

[0655] Step 4:

[0656] The server presents the generated recovery plan to the user via the terminal. The user can review the plan on the terminal and input opinions and feedback based on the situation on site. Specifically, they can review each element of the plan through the UI and add comments based on its feasibility. The input is the recovery plan obtained in step 3, and the output is a revised plan including the user's feedback.

[0657] Step 5:

[0658] The server re-evaluates and adjusts the recovery plan based on user feedback. It then utilizes the generated AI model again to modify and optimize the plan as needed. The input is the user feedback and initial recovery plan obtained in step 4, and the output is the approved plan after final adjustments.

[0659] Step 6:

[0660] The server monitors recovery activities based on the approved plan. It checks progress in real time and maintains communication between users and field personnel through terminals. Specifically, it checks the completion status of each task and quickly sends countermeasures when problems occur. The input is the final recovery plan, and the output is the progress of the recovery activities and coordination information.

[0661] (Application Example 1)

[0662] 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".

[0663] In the event of a disaster within a logistics facility, rapid and efficient data collection and analysis are required. However, conventional systems lack real-time capabilities and accuracy, making it difficult to provide optimal recovery plans. Against this backdrop, there is a need for immediate information collection during disasters and the provision of optimal recovery procedures based on that information.

[0664] 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.

[0665] In this invention, the server includes means for acquiring real-time data through an information technology network in the event of a disaster, means for standardizing the real-time data and inputting it into a generated artificial intelligence model, and means for effectively collecting and analyzing internal state data of a logistics facility and providing optimal recovery procedures. This makes it possible to quickly and efficiently grasp the situation inside a logistics facility even in the event of a disaster and accurately execute the necessary recovery procedures.

[0666] An "information technology network" is a system for exchanging and transmitting information via the internet or communication networks.

[0667] "Real-time data" refers to data that is acquired at the exact moment an event occurs and is immediately available for use.

[0668] "Standardization" refers to the process of converting data obtained in different formats into a unified standard format.

[0669] A "generative artificial intelligence model" is a machine learning model trained to perform a specific task based on a large amount of data.

[0670] A "logistics facility" is a general term for places or buildings used for storing, sorting, and shipping goods.

[0671] "Status data" refers to a collection of information that indicates the physical and environmental conditions of a logistics facility at a specific point in time.

[0672] "Recovery procedures" refer to the specific methods and steps taken to restore the system to a normal state in the event of a disaster or malfunction.

[0673] This invention is implemented as a system to support rapid and efficient recovery activities in the event of a disaster at a logistics facility. The server acquires real-time data from multiple sensor devices inside and outside the logistics facility and aggregates this data via an information technology network. The server normalizes the data acquired from the sensor devices and inputs it into a generated artificial intelligence model to derive effective recovery procedures. TensorFlow and PyTorch are used for the AI ​​model.

[0674] The terminal presents the generated recovery plan to the user and accepts user feedback on changes in the logistics facility. This user feedback is then sent back to the server and used to re-evaluate and adjust the plan.

[0675] As a concrete example, consider a recovery scenario for a logistics facility during an earthquake. The server receives vibration information and temperature changes within the facility from detection devices, and an artificial intelligence model analyzes this information to assess safety. Simultaneously, the user's smart device records information obtained from staff within the facility, identifying disruptions in logistics and damage to goods. Based on this, an optimal recovery plan is generated.

[0676] This invention allows logistics facility managers to quickly grasp the situation after a disaster and issue effective instructions. For example, a possible prompt message could be: "Based on the current state of the logistics facility, generate the optimal recovery procedure and specify which areas should be prioritized for recovery."

[0677] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0678] Step 1:

[0679] The server acquires real-time data from multiple sensor devices placed inside and outside the logistics facility. Inputs include vibration information, temperature, humidity, and location information. This data is collected and then standardized so that it can be processed in the next step.

[0680] Step 2:

[0681] The server normalizes the acquired real-time data. Here, data obtained from different sensor devices is converted into a common format to ensure data consistency. The output is normalized data, which improves the accuracy of subsequent AI model inputs.

[0682] Step 3:

[0683] The server inputs standardized data into an artificial intelligence model. Machine learning frameworks such as TensorFlow and PyTorch are used for the AI ​​model. Data processing here involves analyzing historical disaster data and real-time data to generate recovery procedures suitable for logistics facilities. The output is a concrete recovery plan.

[0684] Step 4:

[0685] The terminal presents the generated recovery plan to the user. The user can send feedback about changes in the situation within the logistics facility. The function here is to provide an interface that visualizes the contents of the recovery plan in an easy-to-understand way, enabling the user to make accurate decisions.

[0686] Step 5:

[0687] The server receives user feedback and re-evaluates the recovery plan, adjusting it as needed. The input includes text data representing user feedback. The server then inputs this back into an artificial intelligence model, generating prompts, and produces an adjusted recovery plan. The output is the updated recovery plan.

[0688] Step 6:

[0689] The server monitors the recovery progress of the logistics facility in real time and maintains constant communication with the terminals. It continuously acquires new data from sensor devices to confirm that progress is on schedule, and quickly derives countermeasures if problems occur. The output here is the latest recovery status report and necessary countermeasures.

[0690] 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.

[0691] This invention combines an emotion engine with a system that collects and analyzes data in real time during a disaster. By adding a function to recognize the user's emotions, this system enables more appropriate information provision and support.

[0692] First, when the server detects a disaster, it collects real-time data from sensor devices and on-site terminals. This data includes weather conditions, the extent of damage, and photos and videos of the scene. Terminals collect information directly entered by users on-site. In addition to this user information, data is also collected to determine emotions from the user's facial expressions and tone of voice.

[0693] The server standardizes this data and inputs it into a generating artificial intelligence model. This AI model analyzes the current situation by referring to past disaster data and automatically generates an optimal recovery plan. This recovery plan includes specific instructions such as evacuation routes, distribution plans for necessary materials, and personnel deployment.

[0694] Furthermore, by incorporating an emotion engine, the system recognizes the user's emotional state in real time. The emotion engine determines the user's stress and anxiety levels and adjusts the pace and content of the recovery plan presentation according to the user's psychological state. In this way, the plan is presented in a format that is easiest for the user to understand.

[0695] For example, if a user who has received an evacuation order is in a state of high stress, the emotion engine will recognize this and provide a plan with calmer language and enhanced visual support. The user's response is then fed back to the server via the device, where the emotional changes are recorded.

[0696] Ultimately, based on the approved recovery plan, the server continuously monitors the ongoing disaster recovery activities. User sentiment information is used as important feedback to improve on-site work efficiency, ultimately enhancing the quality of recovery efforts.

[0697] The following describes the processing flow.

[0698] Step 1:

[0699] The server collects real-time data from sensor devices and drones via the network during a disaster. This includes weather data from the affected area, earthquake vibration data, traffic conditions, and on-site video footage.

[0700] Step 2:

[0701] The device collects information from local users. Users report the extent of the damage and the need for evacuation through a specific application. The device also uses its camera and microphone to record the user's facial expressions and tone of voice, generating emotional data.

[0702] Step 3:

[0703] The server standardizes the collected real-time data and user sentiment data. This unifies the format and prepares a dataset suitable for analysis.

[0704] Step 4:

[0705] The server inputs standardized data into a generating artificial intelligence model and analyzes the current situation by referencing past disaster data. This analysis is a process that predicts damage, prioritizes emergency assistance, and generates an optimal recovery plan.

[0706] Step 5:

[0707] The server uses an emotion engine to analyze the user's emotional state. Based on this analysis, it adjusts the method of presenting the recovery plan and selects a feedback format that is appropriate for the user's psychological state.

[0708] Step 6:

[0709] The server presents the generated recovery plan to the user via the terminal. When communicating this to the user, the tone of the instructions and the presence or absence of visual assistance are adjusted according to the user's stress level.

[0710] Step 7:

[0711] The user reviews the presented recovery plan and sends feedback to the server via their device. This feedback includes comments on the plan's content and additional information from the field.

[0712] Step 8:

[0713] The server receives feedback from the user, re-evaluates the plan as needed, and proposes a revised plan. It also simultaneously records changes in the user's emotions, which are used for subsequent analysis.

[0714] Step 9:

[0715] The server monitors field activities in real time based on the approved recovery plan. This includes checking the progress of recovery work and responding immediately to any new failures.

[0716] Step 10:

[0717] The terminal continuously receives progress reports from field personnel and provides the latest information to the server, thereby improving the overall system's response speed and accuracy.

[0718] (Example 2)

[0719] 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".

[0720] During a disaster, a complex web of information becomes chaotic, making it difficult to provide swift and accurate recovery support. Furthermore, simply presenting information without considering the psychological state of users can exacerbate confusion. Therefore, it is essential to accurately process diverse information and provide recovery information to users in an appropriate format to streamline disaster recovery activities and alleviate user anxiety.

[0721] 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.

[0722] In this invention, the server includes means for acquiring real-time information through a communication infrastructure when a disaster occurs, means for unifying the real-time information and supplying it to a generation AI model, and means for displaying the generated recovery plan to the user, obtaining user feedback, and re-evaluating and adjusting the plan. This enables the automatic generation of an appropriate recovery plan according to the disaster situation and the presentation of information according to the user's emotional state.

[0723] "Communication infrastructure" refers to the entire network infrastructure that enables real-time data collection and information transmission during disasters.

[0724] "Real-time information" refers to the latest data and events that reflect the current situation as the disaster progresses.

[0725] A "generative AI model" refers to an artificial intelligence model that analyzes the current situation based on past disaster data and automatically generates the optimal recovery plan.

[0726] A "recovery plan" is a plan aimed at effective recovery from a disaster, which includes specific instructions regarding the design of evacuation routes, the distribution of materials, and the deployment of personnel.

[0727] An "emotion engine" refers to a system that analyzes a user's emotional state from their facial expressions and voice, and optimizes the way information is presented according to that situation.

[0728] This invention is a system for effective information gathering and recovery support during disasters. Upon detecting a disaster, the server acquires real-time information from sensor devices and local terminals via a communication infrastructure. The hardware used includes high-precision weather sensors and highly durable communication modules. The terminals are equipped with cameras and microphones to analyze the user's facial expressions and voice in real time and collect emotional data.

[0729] The server unifies the acquired real-time information into a format that facilitates AI data analysis and supplies it to the generated AI model. This model analyzes the situation by referring to past disaster cases and automatically generates an optimal recovery plan for evacuation routes and material distribution. Specific examples of AI models include deep learning frameworks such as "TensorFlow" and "PyTorch".

[0730] Furthermore, the server uses an emotion engine to analyze the user's psychological state and presents the recovery plan in a format that is easy for the user to understand. For users in a high-stress state, the plan is presented with calming language and enhanced visual support. In this way, information is delivered more effectively and with less psychological burden.

[0731] As a concrete example, consider a scenario involving a large-scale flood. The server collects water level rise data from sensors and receives evacuation completion reports from users via on-site terminals. An AI model issues a prompt message asking, "Is it necessary to strengthen evacuation orders?" and updates the plan according to the user's situation. This mechanism makes it possible to improve the overall efficiency and quality of recovery efforts.

[0732] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0733] Step 1:

[0734] When the server detects a disaster, it collects real-time information from sensor devices and on-site terminals. Inputs include weather data and images / videos showing the extent of damage. The server centrally aggregates this data through a communication infrastructure. Specifically, the server receives wind speed and precipitation data from sensors and downloads image data from on-site terminals. The output is a dataset saved in a unified format.

[0735] Step 2:

[0736] The server standardizes the collected real-time information. The input consists of raw data in various formats; the server performs format conversion to create a consistent dataset suitable for input to the generated AI model. Specifically, the server converts the data into CSV or JSON format, preparing it for efficient analysis by the model. The output is data ready for analysis.

[0737] Step 3:

[0738] The server inputs standardized data into a generating AI model to analyze the disaster situation. The input consists of past disaster cases and real-time standardized data, and the AI ​​model automatically generates a recovery plan using machine learning algorithms. Specifically, the AI ​​model calculates optimal scenarios for evacuation routes, material distribution, and personnel deployment. The output is a detailed recovery plan.

[0739] Step 4:

[0740] The server uses an emotion engine to analyze the user's psychological state and determine how to present the recovery plan. Input consists of facial expression data and voice tone transmitted from the terminal, which the server analyzes to determine the user's stress and anxiety levels. Specifically, if the emotion engine detects high user stress, it presents the recovery plan using gentler language and enhanced visual support. The output is the optimized information presentation method.

[0741] Step 5:

[0742] The device presents the user with a recovery plan and sends the user's response as feedback to the server. The input is optimized content using an emotion engine, and the device presents it in an easy-to-understand manner for the user. Specifically, for users in a high-stress state, the device displays a visually highlighted evacuation route map. The output is the user's response and feedback information.

[0743] Step 6:

[0744] The server re-evaluates and adjusts the recovery plan based on user feedback and monitors disaster recovery activities as they progress. The input is user feedback data, which the server uses to revise the recovery plan. Specifically, the server resends updated evacuation route information to the terminal based on the feedback. The output is the latest recovery plan and monitoring data of its progress.

[0745] (Application Example 2)

[0746] 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".

[0747] In the event of a disaster, a challenge exists in providing optimal information and guidance tailored to the emotional state of individual users when implementing and supporting rapid and effective recovery activities. Conventional systems sometimes fail to create an environment where users can fully understand and act with confidence by providing uniform information without considering their psychological state.

[0748] 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.

[0749] In this invention, the server includes means for acquiring immediate data through an information and communication infrastructure in the event of a disaster, means for standardizing the immediate data and inputting it into an artificial intelligence model, and means for recognizing the user's emotional state and customizing a recovery plan generated based on that emotion to present to the user. This makes it possible to provide an optimal recovery plan that takes into account the user's emotional state in the event of a disaster, thereby improving the user's sense of security and the certainty of their actions.

[0750] "Information and communication infrastructure" refers to networks and digital infrastructure used for sending and receiving data.

[0751] "Real-time data" refers to information obtained in real time, specifically data collected instantaneously under certain circumstances.

[0752] An "artificial intelligence model" refers to a set of algorithms used to learn from past data and analyze the current situation.

[0753] "Means of recognizing emotional states" refers to technologies that analyze a user's facial expressions and tone of voice to determine their psychological state.

[0754] "Customizing a recovery plan" refers to the process of adjusting and adapting a standard recovery plan to suit the individual user's needs and circumstances.

[0755] "Means for immediate monitoring of progress" refers to technologies and tools that allow for real-time confirmation of the recovery efforts and rapid response to the situation.

[0756] The system for implementing this invention is built using an information and communication infrastructure, an artificial intelligence model, and emotion recognition technology to enable rapid response in the event of a disaster. When a disaster occurs, the server immediately uses the information and communication infrastructure to acquire data from detection devices and on-site terminals. This data includes information on weather conditions and damage, as well as on-site video and audio. This collected data is first standardized before being input into the artificial intelligence model.

[0757] The artificial intelligence model utilizes deep learning frameworks such as TensorFlow to analyze the current situation based on past disaster data. Based on this analysis, the server generates a recovery plan that includes appropriate evacuation actions, supply distribution, and personnel deployment. Furthermore, the server recognizes each user's emotional state in real time through the terminal. This allows the emotion engine to adjust the information presentation method according to the user's psychological state, providing information in a format that is easiest for the user to understand and feel comfortable with.

[0758] Specifically, for example, if a user is experiencing high levels of stress, the server will present a customized plan using visual maps and gentle language to facilitate understanding. This tailored plan is then displayed on the user's device, and feedback is gathered to further improve the system. This feedback loop ensures that recovery efforts are always optimized.

[0759] Example of a prompt:

[0760] "Using the user's facial expressions and voice tone data as input, analyze the user's current emotional state and generate appropriate evacuation instructions."

[0761] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0762] Step 1:

[0763] When a disaster occurs, the server immediately collects data using the information and communication infrastructure. Inputs include weather conditions, damage status, video, and audio data from detection equipment and on-site terminals. Outputs are datasets containing this raw data. To standardize the data, data in different formats is integrated and converted into a format that can be analyzed.

[0764] Step 2:

[0765] The server inputs standardized data into an artificial intelligence model. The input is the standardized data processed in Step 1. The output is the result of analyzing the disaster situation. Using a deep learning framework such as TensorFlow, the current situation is analyzed based on past disaster data, and key parameters are extracted.

[0766] Step 3:

[0767] The server generates a recovery plan based on the AI ​​analysis results. The input is the analysis results output in step 2. The output is a recovery plan concerning evacuation actions, supply distribution, and personnel deployment. The generated AI model is used to create a plan that includes the most efficient recovery procedures.

[0768] Step 4:

[0769] The device senses the user's facial expressions and voice tone in real time and analyzes their emotional state. The input is raw emotional data obtained through the camera and microphone. The output is an evaluation of the user's emotional state. An emotion recognition algorithm is used to determine the user's psychological state.

[0770] Step 5:

[0771] The server customizes the recovery plan based on the sentiment assessment results from step 4 and presents it to the user. The inputs are the recovery plan and the user's sentiment assessment results. The output is a customized plan presented in a format suitable for the user. The plan is adjusted to provide information that is easiest for the user to understand and feel comfortable with.

[0772] Step 6:

[0773] User feedback is sent to the server via the terminal. The input is the feedback data provided by the user. The output is a dataset for improvement that the server handles. The feedback is analyzed, the effectiveness of the recovery plan is evaluated, and the plan is adjusted as needed.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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."

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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 to be incorporated by reference.

[0795] The following is further disclosed regarding the embodiments described above.

[0796] (Claim 1)

[0797] A means of acquiring real-time data via a communication network in the event of a disaster,

[0798] A means for standardizing the aforementioned real-time data and inputting it into a generating artificial intelligence model,

[0799] The aforementioned artificial intelligence model analyzes the current disaster situation using past disaster data and generates a recovery plan;

[0800] A means of presenting the generated recovery plan to the user, and re-evaluating and adjusting the plan based on user feedback,

[0801] A means to support disaster recovery activities based on approved recovery plans and to monitor progress in real time,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, wherein the real-time data is acquired from a sensor device and a local terminal.

[0805] (Claim 3)

[0806] The system according to claim 1, wherein the recovery plan includes information regarding the design of evacuation routes, the distribution of emergency supplies, and the deployment of personnel.

[0807] "Example 1"

[0808] (Claim 1)

[0809] A means of acquiring dynamic data via communication media during a disaster,

[0810] A means for unifying the aforementioned dynamic data and inputting it into a generative intelligence model,

[0811] The aforementioned generative intelligence model provides a means for interpreting the current disaster situation using past disaster information and creating a recovery plan,

[0812] A means of presenting the created recovery plan to users, and re-evaluating and adjusting the plan based on user feedback,

[0813] A means to support disaster recovery activities based on approved recovery plans and to dynamically monitor progress,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, wherein the dynamic data is obtained from a sensing device and a field device.

[0817] (Claim 3)

[0818] The system according to claim 1, wherein the recovery plan includes information regarding the design of evacuation routes, the allocation of emergency supplies, and the deployment of personnel.

[0819] "Application Example 1"

[0820] (Claim 1)

[0821] A means of acquiring real-time data through an information technology network in the event of a disaster,

[0822] A means for normalizing the aforementioned real-time data and inputting it into a generative artificial intelligence model,

[0823] The aforementioned artificial intelligence model analyzes the current disaster state using historical disaster data and generates a recovery plan;

[0824] A means of presenting the generated recovery plan to the user, and re-evaluating and adjusting the plan based on feedback from the user,

[0825] A means to support disaster recovery activities based on approved recovery plans and to monitor their progress in real time,

[0826] A means to effectively collect and analyze internal condition data of logistics facilities and provide optimal recovery procedures,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, wherein the real-time data is acquired from a detection device and a local terminal.

[0830] (Claim 3)

[0831] The system according to claim 1, wherein the recovery plan includes information regarding the design of evacuation routes, the distribution of emergency supplies, and the deployment of workers.

[0832] "Example 2 of combining an emotion engine"

[0833] (Claim 1)

[0834] A means of obtaining real-time information through the communication infrastructure when a disaster occurs,

[0835] A means for unifying the aforementioned real-time information and supplying it to the generated AI model,

[0836] The aforementioned AI model generates a means for determining the current disaster situation by referring to past disaster cases and creating a recovery plan,

[0837] A means of displaying the generated recovery plan to the user, obtaining user feedback, and re-evaluating and adjusting the plan,

[0838] A means to support disaster recovery activities based on approved recovery plans and to monitor progress in real time,

[0839] A means of analyzing the user's psychological state using an emotion engine and adapting the presentation of a recovery plan accordingly,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, wherein the real-time information is acquired from a sensor device and a local terminal, and includes the user's psychological information.

[0843] (Claim 3)

[0844] The system according to claim 1, wherein the recovery plan includes information regarding the design of evacuation routes, the distribution of emergency supplies, the allocation of personnel, and adaptive information according to the emotional state of users.

[0845] "Application example 2 when combining with an emotional engine"

[0846] (Claim 1)

[0847] A means of acquiring data immediately through the information and communication infrastructure in the event of a disaster,

[0848] A means for standardizing the aforementioned real-time data and inputting it into an artificial intelligence model,

[0849] The aforementioned artificial intelligence model analyzes the current disaster situation using past disaster data and generates a recovery plan;

[0850] A means of recognizing the user's emotional state and presenting a customized recovery plan generated based on those emotions to the user,

[0851] A means of re-evaluating and adjusting the plan based on user feedback,

[0852] A means to support disaster recovery activities based on approved recovery plans and to monitor progress immediately,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, wherein the aforementioned real-time data is acquired from a detection device and a local terminal.

[0856] (Claim 3)

[0857] The system according to claim 1, wherein the recovery plan includes information regarding the design of evacuation routes, the allocation of emergency resources, and the deployment of workers. [Explanation of Symbols]

[0858] 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. A means of acquiring real-time data via a communication network in the event of a disaster, A means for standardizing the aforementioned real-time data and inputting it into a generating artificial intelligence model, The aforementioned artificial intelligence model analyzes the current disaster situation using past disaster data and generates a recovery plan; A means of presenting the generated recovery plan to the user, and re-evaluating and adjusting the plan based on user feedback, A means to support disaster recovery activities based on approved recovery plans and to monitor progress in real time, A system that includes this.

2. The system according to claim 1, wherein the real-time data is acquired from a sensor device and a local terminal.

3. The system according to claim 1, wherein the recovery plan includes information regarding the design of evacuation routes, the distribution of emergency supplies, and the deployment of personnel.

Images