system

Abstract

Provide a system. [Solution] A means for collecting disaster-related information from social media; A means for identifying key locations from the collected information; A means for calculating a priority of a base station based on the identified important location; A system comprising: means for generating a restoration plan for a base station based on priority.

Description

[Technical Field]

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

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

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

[0004] When multiple base stations are down during a disaster, it is necessary to determine which base station should be prioritized for restoration in order to restore service quickly and efficiently. However, conventional systems have difficulty collecting and analyzing the information needed to make such decisions, which can result in delays in the restoration of important base stations. In particular, identifying locations that urgently require communications, such as evacuation shelters, and creating specific restoration plans are major challenges. [Means for solving the problem]

[0005] The system of the present invention first includes a means for collecting disaster-related information from social media. The collected information is then organized by a means for identifying important locations, and evacuation shelters and unavailable locations are identified. A means for calculating the priority of base stations based on the identified important locations is introduced. Finally, by including a means for generating a base station restoration plan based on the priority, efficient and rapid restoration is achieved. The present invention allows important locations to be quickly identified and an optimal restoration order to be planned, thereby effectively restoring communications during a disaster.

[0006] "Social media" is a general term for online platforms that allow users to share information and communicate via the Internet.

[0007] "Disaster" is a general term for events caused by natural phenomena or man-made factors that have a significant impact on human life, property, and daily life.

[0008] "Important locations" refer to locations where communication is particularly necessary during a disaster, including, for example, evacuation shelters and medical facilities.

[0009] A "base station" is a relay device for communicating with terminals in a wireless communication system, and covers a specific geographical area.

[0010] "Priority" is an indicator that indicates the importance or urgency of an action or process based on specific criteria, and is a measure used to determine which base station should be restored first in disaster recovery.

[0011] A "restoration plan" is a detailed outline of the procedures and work to be done to effectively restore downed base stations and communications infrastructure. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

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

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0033] The present invention relates to a system for collecting disaster-related information from social media, analyzing the information, and identifying base stations that should be prioritized for restoration. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a restoration plan generation module.

[0034] The device first uses a social media data collection module to collect disaster-related tweets. In this case, it connects to social media platforms using an API key and secret to collect tweets containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[0035] The collected tweets are then analyzed by the server using a critical location identification module. This module extracts information about evacuation shelters and other critical locations from the tweets. For example, if a tweet says "X-shelter is unavailable," the module analyzes it and identifies X-shelter as a critical location.

[0036] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the traffic information of the base station and other criteria (e.g., geographic importance).

[0037] The server also operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. This module determines the restoration order of base stations based on the analyzed data and issues restoration instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, with the highest priority, and notifies the corresponding worker.

[0038] Examples:

[0039] 1. The device connects to social media using the API key and secret and collects tweets with the keywords "shelter" and "unusable."

[0040] 2. The server identifies tweets saying "XX shelter is unavailable" and adds that shelter to the list as an "important location."

[0041] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[0042] 4. The server generates a plan to restore base station A as the top priority and issues the instruction "Restore base station A" to the corresponding worker. This plan aims to provide fast and efficient communication services to disaster victims by prioritizing support for locations that require urgent response.

[0043] In this way, the system of the present invention makes it possible to collect appropriate information during a disaster, quickly identify important locations, and generate effective recovery plans based on priorities, thereby significantly improving the efficiency of disaster recovery.

[0044] The processing flow will be explained below.

[0045] Step 1:

[0046] The device connects to the social media platform using an API key and secret, performs API authentication, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then used in subsequent processing steps.

[0047] Step 2:

[0048] The server analyzes the collected tweets to identify important locations. In this step, it analyzes the text content of the tweets and checks whether they correspond to evacuation shelters or other important locations registered in advance. For example, if a tweet says "XX evacuation shelter is unavailable," it adds this evacuation shelter to the list of important locations.

[0049] Step 3:

[0050] The server calculates the priority of base stations based on the identified important locations. In this stage, it identifies base stations around the identified important locations and evaluates their priority based on traffic information and other factors. If a base station has a high traffic volume, it will be given a high priority.

[0051] Step 4:

[0052] The server generates a restoration plan based on the priority calculation results. It lists base stations in order of priority and creates a plan including specific restoration procedures. This plan includes information such as which base stations should be restored, when, and which workers will be responsible for the restoration.

[0053] Step 5:

[0054] The server then sends instructions to the workers to execute the generated restoration plan. Specifically, it issues restoration instructions to the base station with the highest priority, allowing the workers to respond quickly. The notification includes the base station's location information and specific restoration procedures.

[0055] Step 6:

[0056] The user (worker) receives the notification and begins work to restore the base station. The worker acts according to the restoration plan provided by the server, and proceeds with the work in order of priority for the base station that needs to be restored. Information about base stations that have been restored is reported to the server.

[0057] Example 1

[0058] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0059] In the event of a disaster, rapid and effective restoration of communications infrastructure is crucial for supporting victims. However, with current systems, it is difficult to determine which base stations should be restored first, and it is also difficult to grasp the situation in real time. Therefore, it is necessary to identify evacuation shelters and important base stations, prioritize base station restoration, and efficiently generate restoration plans.

[0060] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0061] In this invention, the server includes means for collecting disaster-related information from social media, means for analyzing the collected information using a natural language processing model to identify important locations, means for calculating the priority of base stations based on the identified important locations, and means for generating a base station recovery plan based on the calculated priority. This makes it possible to grasp the disaster situation in real time, identify important locations, and generate a base station recovery plan efficiently and quickly.

[0062] "Social media" is a platform on the Internet where users can share information and interact with each other.

[0063] "Disaster-related information" refers to information about the situation, damage, evacuation sites, relief activities, etc. related to natural disasters and man-made disasters.

[0064] "Means of collection" refers to the technologies and processes used to obtain posts containing specific keywords from social media, including the use of APIs.

[0065] A "natural language processing model" is an artificial intelligence technology for analyzing and understanding human language, such as BERT and GPT-3 (registered trademark).

[0066] "Important bases" are locations that are particularly important for rescue operations and support for evacuees during disasters, and include evacuation shelters and medical institutions.

[0067] The "means of identification" is a method of analyzing information collected from social media using a natural language processing model and extracting important information.

[0068] The "base station priority" indicates the priority of which base station should be restored first among a plurality of base stations.

[0069] The "calculating means" is a method for determining the priority of base stations based on the collected information and analysis results.

[0070] A "recovery plan" is a specific action plan for restoring communications infrastructure to its original state in the event of a disaster.

[0071] The "means for generating" is a method for creating specific recovery procedures and work instructions based on the calculated priorities.

[0072] The system aims to collect appropriate information during disasters, quickly identify important locations, and generate effective recovery plans based on priorities. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a recovery plan generation module.

[0073] Social Media Data Collection Module

[0074] The device first collects disaster-related information using a social media data collection module. This is done using the Twitter API, and authentication is performed using an API key and secret. Then, by collecting tweets containing specific keywords (e.g., "shelter" or "unavailable"), the device grasps the real-time disaster situation.

[0075] Example: Collect tweets saying "The shelters are full and unusable."

[0076] Important location identification module

[0077] The server then passes the collected tweets to a critical location identification module, which uses natural language processing models (e.g., BERT or GPT-3) to analyze the content of the tweets and identify evacuation centers and other critical locations.

[0078] Example: Analyzing tweets such as "XX shelter is unusable" and identifying XX shelter as an important base.

[0079] Priority Calculation Module

[0080] The server activates a priority calculation module that calculates the priority of the base station based on the identified important locations, taking into account the traffic information and geographical importance of the base station to determine the priority.

[0081] Example: You notice that base station A is handling three times the normal amount of traffic and decide that base station A should be restored as a top priority.

[0082] Recovery Plan Generation Module

[0083] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities, and this module determines the restoration order of each base station based on the analyzed data and the priority list, and generates specific restoration instructions.

[0084] Example: Notify the worker of the instruction to "restore base station A as a top priority."

[0085] This system supports the rapid restoration of communications infrastructure in the event of a disaster, and by utilizing collected social media data and advanced natural language processing technology, it is possible to generate efficient and effective restoration plans. Specific examples of prompt sentences include the following:

[0086] Prompt Sentence Examples

[0087] "Collect tweets related to disaster information, identify important evacuation centers, and generate a plan to prioritize the restoration of base stations around those evacuation centers. First, collect tweets using an API key and secret, and extract evacuation center information using natural language processing. Then, evaluate base station traffic information to calculate restoration priority, and generate and notify a restoration plan."

[0088] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0089] Step 1:

[0090] The device connects to the Twitter API using a social media data collection module.

[0091] Specifically, it authenticates with Twitter using the API key and secret. If authentication is successful, it collects tweets containing specific keywords such as "shelter" and "unusable" and stores them in a database.

[0092] The input includes the API key and secret, and the search keywords, and the output is the collected tweet data.

[0093] Step 2:

[0094] The server passes the collected tweet data to the important location identification module for analysis.

[0095] Specifically, it uses a natural language processing model (e.g., GPT-3) to analyze the content of tweets and identify evacuation shelters and other important locations. Through this analysis, it extracts important information, such as "____ evacuation shelter," from the text data of tweets.

[0096] The input includes collected tweet data and the output is a list of identified important locations.

[0097] Step 3:

[0098] The server launches a priority calculation module that calculates the priority of the base station based on the identified important locations.

[0099] Specifically, the system collects a list of base stations and their traffic information, evaluates their geographic importance, and determines the priority of each base station.

[0100] The input includes a list of important locations and traffic information of base stations, and the output is a priority list of each base station.

[0101] Step 4:

[0102] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priority.

[0103] Specifically, the restoration order is determined based on the analyzed priority list, and specific restoration instructions are generated, which in turn generate instructions for restoration work for each base station.

[0104] The input includes a priority list, and the output is a specific recovery plan and work instructions.

[0105] Step 5:

[0106] The server notifies the corresponding worker of the generated recovery plan.

[0107] Specifically, the system uses email or messaging systems to send instructions to workers such as "Restore base station A as a top priority."

[0108] The input includes a recovery plan and the output is a notification to the workers.

[0109] (Application example 1)

[0110] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0111] When a disaster occurs, rapid restoration of communications infrastructure is required. However, in order to efficiently utilize limited resources, it is important to identify base stations that should be restored as a priority. Conventional technologies have limitations in collecting disaster information in real time and generating base station restoration plans that incorporate user situation reports. Furthermore, they are not sufficient in providing information to users or visualizing the progress of restoration. This has led to problems such as not receiving necessary information in a timely manner during a disaster, and the condition of evacuation centers and the communications environment not improving. Therefore, there is a need for a system that enables efficient restoration of communications infrastructure during a disaster and provides users with real-time information.

[0112] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0113] In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating the priority of base stations based on the identified important locations, means for generating a base station recovery plan based on the priority, means for collecting user situation reports using smartphones, means for notifying users of disaster information in real time, and means for visualizing the progress of recovery on user terminals. This not only enables rapid and efficient recovery of communication infrastructure in the event of a disaster, but also makes it possible to provide users with timely important information and visualize the status of improvements to evacuation centers and the communication environment.

[0114] "Social media" is an online platform for collecting information about disasters in real time.

[0115] "Important locations" are key locations such as evacuation shelters and locations close to base stations that should be restored as a priority in the event of a disaster.

[0116] "Priority" is a standard for indicating the order and importance of restoration, and is calculated based on traffic information and needs at a specific location.

[0117] A "base station" is an infrastructure facility that supports user communications in a mobile communications network.

[0118] A "recovery plan" is a specific work schedule formulated based on priorities in order to restore communications infrastructure efficiently and quickly in the event of a disaster.

[0119] A "smartphone" is a portable information terminal that users use to collect and report disaster information.

[0120] "Real-time" refers to the timing when information is acquired, processed, and notified almost simultaneously.

[0121] "Progress" is information that indicates the degree of completion of each stage of restoration work and the progress of the construction work.

[0122] "Users" refers to people who use the system to receive disaster information and report their own situations.

[0123] This invention relates to a system and method for quickly and efficiently restoring communications infrastructure after a disaster. Specifically, this system collects and analyzes disaster-related information from social media, identifies key locations, prioritizes base stations based on that information, and generates a restoration plan. This system also includes the collection of situation reports from users using smartphones, real-time information notifications, and visualization of restoration progress.

[0124] The server first collects disaster-related posts using a social media data collection module. In this case, it connects to social media platforms using an API key and secret to collect posts containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[0125] The collected posts are then analyzed using a critical location identification module. The server extracts information about evacuation shelters and other critical locations from the posts. For example, if a post says "X-shelter is unavailable," the server analyzes it and identifies X-shelter as a critical location.

[0126] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the base station's traffic information and other criteria (e.g., geographic importance). For example, areas with high traffic or many evacuation shelters will have higher priority.

[0127] The server also operates a recovery plan generation module that generates a recovery plan based on the calculated priorities. This module determines the order in which base stations should be restored based on the analyzed data and issues recovery instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, as the highest priority, and notifies the appropriate worker. The purpose of this plan is to provide disaster victims with fast and efficient communication services by prioritizing support for locations requiring urgent response.

[0128] Users can also report their own situation using their smartphones, and these reports are collected on a server. Specifically, users can report specific information from the scene, such as the status of evacuation shelters and traffic information, in real time. This information is used as additional data to understand the overall picture of disaster response.

[0129] The server also has a function to notify users of collected information and restoration progress in real time. This allows users to receive disaster information via their smartphones and quickly take evacuation and safety measures. The restoration progress is also visualized on a map, allowing users to see which base stations are currently undergoing restoration work or have been restored.

[0130] Examples:

[0131] 1. The server connects to social media using the API key and secret and collects posts containing the keywords "shelter" and "unavailable."

[0132] 2. The post contains information that "XX evacuation shelter is unavailable," and this is added to the list as an important location.

[0133] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[0134] 4. The server generates a plan to restore base station A as the top priority and instructs the corresponding worker to "restore base station A."

[0135] 5. Users use their smartphones to report that "there is a water shortage at XX evacuation shelter," and the information is collected on the server.

[0136] 6. The server notifies the user of the collected information in real time and visualizes the progress of recovery on a map.

[0137] Example prompt sentence:

[0138] "Collect tweets about the disaster and identify important evacuation centers from tweets containing keywords such as 'evacuation center' or 'unavailable.' Based on this, create a Python program to calculate the priority of base stations and generate a recovery plan."

[0139] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0140] Step 1:

[0141] The server uses a social media data collection module to collect disaster-related posts. Specifically, it connects to social media platforms using an API key and secret to retrieve posts containing keywords such as "shelter" and "unavailable" in real time. The input is the API key, secret, and search keywords, and the output is the retrieved post data. This allows for a wealth of real-time information about the disaster.

[0142] Step 2:

[0143] The server analyzes the collected posts using an important location identification module. Specifically, it uses text mining technology to extract important location information from posts containing keywords such as "shelter" and "unusable." The input is the collected post data, and the output is a list of extracted important locations. This allows important evacuation centers and key locations to be identified.

[0144] Step 3:

[0145] The server launches a priority calculation module that calculates the priority of base stations based on the identified important locations. Specifically, it references a list of base stations around the important locations and quantifies the priority of each base station by taking into account traffic information and geographical importance. The inputs are the list of important locations, the list of base stations, and traffic information, and the output is a priority list for each base station. This makes it possible to determine which base stations should be prioritized for restoration.

[0146] Step 4:

[0147] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. Specifically, it determines the restoration order for each base station and creates a plan to issue restoration instructions starting with the base station with the highest priority. The input is a priority list, and the output is a specific restoration plan. This allows for the formulation of an efficient restoration work plan.

[0148] Step 5:

[0149] Users report their own situation using their smartphones. Specifically, they use a dedicated application to input the status of the evacuation shelter where they are currently located and the surrounding area. The input is the situation report entered by the user, and the output is report data that is aggregated on the server. This allows real-time information from the scene to be collected.

[0150] Step 6:

[0151] The server aggregates users' situation reports and notifies them in real time through the disaster information notification module. Specifically, it sends push notifications to smartphones to provide important disaster information and evacuation shelter information. The input is the aggregated situation report data, and the output is push notifications to users. This allows users to receive the latest disaster information in a timely manner.

[0152] Step 7:

[0153] The server runs a progress visualization module that visualizes the restoration progress on the user's device. Specifically, it displays the restoration progress on a map, showing which base stations are currently being restored or have been restored. The input is the restoration plan and progress data, and the output is a progress map displayed on the user's device. This allows the user to see at a glance which base stations have been restored.

[0154] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0155] The present invention relates to a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, the present invention has the function of evaluating the reliability of the collected information and adjusting the priority of important base stations by combining it with an emotion engine that recognizes user emotions.

[0156] The system includes the following modules:

[0157] 1. Social Media Data Collection Module: The device connects to social media platforms using the API key and secret to collect tweets related to the disaster, such as tweets containing keywords like "shelter" and "unavailable."

[0158] 2. Important Location Identification Module: The server analyzes the collected tweets and extracts information about evacuation centers and other important locations. For example, it analyzes tweets that say "XX evacuation center is unavailable" and adds them to the list of important locations.

[0159] 3. Priority calculation module: The server identifies base stations around the identified critical location and evaluates their priority based on traffic information and other factors. Base stations with particularly high traffic volumes are given a high priority.

[0160] 4. Emotion Engine: The server analyzes user emotions. This engine analyzes the emotional tone of tweets and recognizes positive, negative, and neutral emotions. This allows the reliability of collected information to be evaluated and information with high emotional intensity to be prioritized. It is also possible to adjust the priority of important points based on emotional information.

[0161] 5. Recovery plan generation module: The server generates a base station recovery plan based on the priority. It lists base stations in order of priority and creates specific recovery procedures. The plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station.

[0162] Explaining program processing in natural language

[0163] The device first uses a social media data collection module to collect disaster-related tweets. At this stage, it connects to social media platforms using an API key and secret, and collects keywords such as "shelter" and "unavailable."

[0164] The server then analyzes the collected tweets using an important location identification module, which scans the text in the tweets and adds the location to a list of important locations if it matches a pre-registered location name or keyword.

[0165] Next, the server launches a priority calculation module to identify base stations around the identified important locations, obtains traffic information and geographical importance of the base stations from a database, and calculates the priority of the base stations based on this information.

[0166] Furthermore, the server uses a sentiment engine to analyze the emotional tone of the collected tweets. The sentiment engine is used to evaluate the positive, negative, and neutral sentiment of the tweets and increase the reliability of the information. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[0167] Finally, the server uses the restoration plan generation module to create a priority-based restoration plan, which includes the restoration procedures and priorities for each base station and notifies the operator, thereby ensuring fast and efficient restoration of the base stations.

[0168] Examples:

[0169] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[0170] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[0171] 3. The server obtains information about base stations around the important location and sets the priority of base station A high based on traffic information.

[0172] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[0173] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[0174] The processing flow will be explained below.

[0175] Step 1:

[0176] The device connects to the social media platform using a social media data collection module, authenticates using an API key and secret, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then stored in a database for analysis in the next step.

[0177] Step 2:

[0178] The server analyzes the collected tweets using an important location identification module. Specifically, it scans the text of the tweets and extracts information about evacuation shelters and other important locations. For example, it analyzes a tweet that says "XX evacuation shelter is unavailable" and adds that location to a list of "important locations."

[0179] Step 3:

[0180] The server analyzes the emotional tone of collected tweets using an emotion engine. The emotion engine identifies positive, negative, and neutral emotions from the tweet content and evaluates the reliability of the information. Tweets with strong emotions are considered to have high reliability and are used to calculate priorities in the next step.

[0181] Step 4:

[0182] The server calculates the priority of base stations based on the key locations and the results of sentiment analysis. Using the priority calculation module, the server sets specific priorities, taking into account the traffic information and geographic importance of base stations around key locations. For example, if base station A near a certain evacuation shelter has a lot of traffic and many tweets with negative sentiment, the server sets the priority of that base station A high.

[0183] Step 5:

[0184] The server uses the restoration plan generation module to create a restoration plan based on priority. It determines the restoration procedure for the base station with the highest priority, and formulates a plan including specific work content and personnel. This plan is notified to the workers in the next step.

[0185] Step 6:

[0186] The server then notifies the workers of the generated restoration plan, which includes the specific locations, priorities, and work procedures of the base stations that need to be restored. Based on this information, the workers can quickly respond and proceed with the restoration work in order of priority.

[0187] Step 7:

[0188] The user (worker) receives the notification and begins work to restore the base station. The worker carries out the work in order of priority, following the restoration plan provided by the server. Information about base stations that have completed restoration is reported to the server, and progress is managed in real time.

[0189] Example 2

[0190] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0191] In modern natural disasters, while the rapid recovery of affected areas is required, determining which bases should be prioritized for recovery can be difficult. In particular, as the situation in the affected areas changes in real time, formulating an efficient recovery plan is difficult, and it is necessary to evaluate priorities while ensuring the reliability of information.

[0192] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0193] In this invention, the server includes means for collecting disaster-related data from social media, means for identifying important locations from the collected data, means for calculating the priority of communication bases based on the identified important locations, means for analyzing user sentiment and evaluating the reliability of the data, and means for generating a recovery plan for the communication bases based on the priority. This makes it possible to formulate an efficient recovery plan using reliable data in real time based on information from social media.

[0194] "Social media" refers to platforms that allow users to share and exchange information online.

[0195] A "disaster" is an emergency caused by a natural phenomenon that causes damage to large numbers of people and infrastructure.

[0196] "Data" refers to information for processing and analysis by a computer.

[0197] "Important locations" refer to locations that function as evacuation routes or evacuation facilities in the event of a disaster, or locations that are necessary for maintaining social functions.

[0198] "Communication base" means a facility for providing a mobile communication network.

[0199] "Priority" refers to the level of importance or urgency that is applied after evaluating multiple targets.

[0200] A "recovery plan" refers to a plan that includes specific steps and schedules for restoring infrastructure in a disaster-stricken area to its original state.

[0201] "User sentiment" refers to the emotional responses (positive, negative, and neutral emotions) expressed by users on social media.

[0202] "Analysis" refers to the process of investigating and interpreting data and information in detail to gain useful insights.

[0203] "Reliability" refers to the degree to which information or data is accurate and useful.

[0204] MODE FOR CARRYING OUT THE INVENTION

[0205] This invention is a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, this system combines an emotion engine that recognizes user emotions to evaluate the reliability of the collected information and adjust the priority of important base stations.

[0206] The system includes the following modules:

[0207] 1. Social Media Data Collection Module:

[0208] The device connects to social media platforms using an API key and secret to collect tweets related to the disaster, specifically tweets containing keywords such as "shelter" and "unavailable." The software used includes the Twitter API and Facebook Graph API.

[0209] 2. Critical Location Identification Module:

[0210] The server analyzes the collected tweets and extracts information about important locations. It scans the text in the tweets and, if it matches pre-registered place names or keywords, adds the location to a list of important locations. It uses natural language processing tools such as NLTK and SpaCy.

[0211] 3. Priority Calculation Module:

[0212] The server identifies communication base stations in the vicinity of the identified important base station and evaluates their priority based on traffic information and other factors. MySQL (registered trademark) and PostgreSQL are used as the database, and base stations with particularly high traffic volumes are set to a high priority.

[0213] 4. Emotion Engine:

[0214] The server analyzes the emotional tone of tweets. The engine evaluates positive, negative, and neutral sentiment and is used to increase the reliability of the collected information. Tools used include SentiStrength and VADER.

[0215] 5. Recovery Plan Generation Module:

[0216] The server generates a recovery plan for the communication base stations based on the priority. It lists the base stations in order of priority and creates specific recovery procedures. This plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station. JIRA and Trello are used as work management systems.

[0217] Specific examples

[0218] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[0219] In this example, the keyword "shelter" is the target of collection.

[0220] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[0221] Tweets containing the word "shelter" are identified and added to a list along with the location name.

[0222] 3. The server obtains information about communication base stations surrounding the important base station and sets the priority of base station A high based on traffic information.

[0223] Base station A is in an area with heavy traffic, so it is set to a high priority.

[0224] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[0225] Negative tweets such as "It's terrible, XX shelter is completely unusable" are analyzed and reflected in the priorities.

[0226] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[0227] Finally, a plan is created to restore base station A as the top priority, and specific instructions are sent to the workers.

[0228] Prompt Sentence Examples

[0229] Sample prompt 1: "Please explain in detail the steps of the system that collects social media data and calculates the priority of key locations and their surrounding base stations in the event of a disaster."

[0230] Sample prompt 2: "What are the specific steps to use the Twitter API to collect disaster-related tweets, analyze them, and generate a base station recovery plan?"

[0231] The above is a specific example of an embodiment of the present invention, which makes it possible to formulate an efficient recovery plan using highly reliable data in real time.

[0232] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0233] Step 1:

[0234] The device uses a social media data collection module to collect disaster-related tweets by connecting to social media platforms using an API key and secret, and collecting keywords such as "shelter" and "unavailable."

[0235] Input: Connection information to social media API (e.g. Twitter API) and collection keywords.

[0236] Specific behavior:

[0237] 1. The device connects to the Twitter API using the API key and secret.

[0238] 2. Set "shelter" and "unusable" as keywords.

[0239] 3. Collect tweets containing these keywords and store the acquired data in local storage (e.g., SQLite database).

[0240] Output: Tweet data that matches the keywords.

[0241] Step 2:

[0242] The server analyzes the collected tweets and extracts information about important locations. To do this, it uses natural language processing tools (e.g., NLTK, SpaCy) to scan the tweet text and, if it matches a pre-registered place name or keyword, adds that place to a list of important locations.

[0243] Input: Collected tweet data.

[0244] Specific behavior:

[0245] 1. The server retrieves tweet data from the SQLite database.

[0246] 2. Analyze tweet text using natural language processing tools.

[0247] 3. Add locations containing keywords that correspond to important locations (e.g., "○○ evacuation shelter") to the list.

[0248] Output: A list of important locations.

[0249] Step 3:

[0250] The server identifies communication base stations around key locations, retrieves traffic information and geographical importance of those base stations from a database, and evaluates their priority. Based on this evaluation, the server sets the priority of the base stations.

[0251] Input: List of key locations and base station traffic information.

[0252] Specific behavior:

[0253] 1. The server retrieves base station traffic data from a database (e.g., PostgreSQL).

[0254] 2. Evaluate the traffic volume and geographical conditions of each base station.

[0255] 3. Set the priority of the base station and generate a priority list.

[0256] Output: Base station priority list.

[0257] Step 4:

[0258] The server uses an emotion engine to analyze the emotional tone of collected tweets. This analysis evaluates positive, negative, and neutral sentiment, which is used to increase the reliability of the data. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[0259] Input: Collected tweet data.

[0260] Specific behavior:

[0261] 1. The server applies a sentiment analysis tool (e.g., SentiStrength, VADER) to analyze the emotional tone of the tweet.

[0262] 2. Calculate positive, negative, and neutral sentiment scores for each tweet.

[0263] 3. Update the base station's priority list based on tweets with high emotional intensity.

[0264] Output: Updated base station priority list.

[0265] Step 5:

[0266] The server generates a restoration plan for the communication base station based on the priority, which includes the restoration procedures and priorities for the base station and is notified to the operator.

[0267] Input: Updated base station priority list.

[0268] Specific behavior:

[0269] 1. The server creates a recovery plan based on a priority list.

[0270] 2. The restoration plan will include specific procedures for which base stations should be restored and when.

[0271] 3. Notify workers of the recovery plan and work instructions using a work management system (e.g., JIRA, Trello).

[0272] Output: Recovery plan communicated to workers.

[0273] (Application example 2)

[0274] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0275] In the event of a disaster, it is necessary to quickly and accurately identify important evacuation shelters and unusable locations, and to develop effective recovery plans. However, current systems have difficulty evaluating the reliability of information taking user emotions into account, and there is a lack of means to notify emergency information in real time, which makes it difficult to respond quickly.

[0276] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating priorities based on the identified important locations, means for generating a recovery plan based on the priorities, means for evaluating the reliability and urgency of the information using a sentiment analysis engine, and means for notifying users and response teams of emergency information. This makes it possible to accurately evaluate the reliability and urgency of the information based on sentiment analysis, and to quickly and effectively develop a recovery plan and notify emergency information.

[0277] "Social media" refers to internet-based platforms that users use to disseminate and share information.

[0278] A "disaster" refers to a situation in which human life and property are put at risk due to natural phenomena or man-made factors.

[0279] "Information collection means" refers to devices and software used to collect relevant data from various data sources.

[0280] "Important locations" refer to locations or facilities where protection and restoration are considered particularly important in the event of a disaster.

[0281] A "priority calculation means" is a device or software that evaluates and ranks the importance and urgency of tasks based on specific criteria.

[0282] A "recovery plan" is a document that outlines the procedures and schedule for improving the situation after a disaster and returning to normal.

[0283] An "emotion analysis engine" is software that automatically analyzes human emotions (positive, negative, neutral, etc.) from text and voice.

[0284] "Reliability of information" is an indicator that evaluates whether the collected data is true.

[0285] "Emergency information" refers to important information that must be communicated in the event of a disaster and requires a prompt response.

[0286] A "response team" is a group of people with specialized skills and knowledge for disaster response.

[0287] This invention provides a system that quickly identifies important bases and evaluates their priorities in the event of a disaster, creates a recovery plan based on that information, and notifies relevant teams and users of emergency information. A specific example of the system is described below.

[0288] Generating a Program

[0289] 1. Real-time data collection:

[0290] The server collects posts containing disaster-related keywords such as "shelter" and "help" in real time using social media APIs, specifically Twitter API and Facebook Graph API.

[0291] 2. Data Analysis:

[0292] The server analyzes the collected posts using natural language processing tools (e.g., Google® Cloud Natural Language API), which allows it to identify important evacuation shelters and unavailable locations.

[0293] 3. Emotion analysis:

[0294] The server uses a sentiment analysis engine (e.g., IBM Watson® Natural Language Understanding) to assess the emotional tone of posts, recognizing positive, negative, and neutral sentiment to enhance the credibility and urgency of information.

[0295] 4. Priority Calculation:

[0296] The server calculates the priority by taking into account traffic information and resource usage around the identified important locations. This is done using traffic information stored in a database (e.g., MySQL).

[0297] 5. Recovery plan generation:

[0298] Based on the priorities, a recovery plan is generated, which includes details on which locations should be restored and in what order.

[0299] 6. Notifications and Guidance:

[0300] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify emergency teams and users of emergency information. At the same time, users are also provided with guidance information such as evacuation procedures and safe routes.

[0301] Hardware and software usage examples

[0302] Hardware:

[0303] Smartphone (iOS or ANDROID (registered trademark))

[0304] Server (Cloud service: AWS (registered trademark), Google Cloud)

[0305] software:

[0306] Social Media APIs (Twitter API, Facebook Graph API)

[0307] Sentiment analysis engine (IBM Watson Natural Language Understanding, Google Cloud Natural Language API)

[0308] Database (MySQL, PostgreSQL)

[0309] Cloud storage (AWS S3, Google Cloud Storage)

[0310] Push notification service (Firebase Cloud Messaging)

[0311] Specific examples

[0312] Specific examples are given below:

[0313] 1. Data Collection:

[0314] The server uses the Twitter API to collect tweets containing keywords such as "shelter" and "help."

[0315] 2. Data Analysis:

[0316] The server uses the Google Cloud Natural Language API to extract information such as "XX shelter is unavailable" from the collected tweets and adds XX shelter to a list as an important location.

[0317] 3. Emotion analysis:

[0318] The server uses IBM Watson to analyze the emotional tone of tweets, giving more weight to tweets that display a strong negative sentiment.

[0319] 4. Priority Calculation:

[0320] Based on the traffic information stored in the MySQL database, the server calculates the priority of base stations around the XX evacuation shelter and lists them in order of importance.

[0321] 5. Recovery plan generation:

[0322] Based on the priority, the base station that should be restored with the highest priority is identified, and specific restoration procedures are created.

[0323] 6. Notifications and Guidance:

[0324] Notify emergency response teams with emergency information and provide evacuation instructions and safe routes to users using Firebase Cloud Messaging.

[0325] Prompt Sentence Examples

[0326] Example of input sentence to generative AI model:

[0327] How can I collect disaster-related information from user posts, analyze that information, and assess its urgency?

[0328] Input data:

[0329] 1. Tweet text collected from social media platforms

[0330] 2. Keyword list (shelter, help, unusable, in trouble)

[0331] 3. User sentiment (positive, negative, neutral)

[0332] Output data:

[0333] 1. List of important shelters and points

[0334] 2. Prioritizing by cumulative emotional tone

[0335] 3. Notification to the response team

[0336] 4. User evacuation guide

[0337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0338] Step 1:

[0339] The device uses social media APIs to collect posts containing disaster-related keywords (e.g., "shelter" and "help") in real time. It connects to the social media platform (e.g., Twitter) using an API key and secret, and sends the collected post data to the server. The input is the keywords and API connection information, and the output is the collected social media post data.

[0340] Step 2:

[0341] The server analyzes the received social media post data using natural language processing tools (e.g., Google Cloud Natural Language API). It extracts posts containing specific keywords and phrases and identifies important evacuation shelters and unusable locations. The input is the collected social media post data, and the output is a list of important evacuation shelters and unusable locations.

[0342] Step 3:

[0343] The server applies a sentiment analysis engine (e.g., IBM Watson Natural Language Understanding) to information about important evacuation shelters and unavailable locations to evaluate the emotional tone of the posts. It recognizes positive, negative, and neutral emotions and evaluates the reliability and urgency of the information. The input is post data about identified evacuation shelters and locations, and the output is the sentiment evaluation results for each post.

[0344] Step 4:

[0345] The server calculates the priority of the identified important locations based on the emotional tone and traffic information. The server obtains traffic information stored in a database (e.g., MySQL) and combines it with the emotional evaluation results. The inputs are the emotional evaluation results and traffic information, and the output is a priority list of important locations.

[0346] Step 5:

[0347] The server generates a recovery plan based on the priority list. This plan includes specific instructions and a schedule for which sites should be restored and in what order. The input is the priority list, and the output is a recovery plan document.

[0348] Step 6:

[0349] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify response teams and users of emergency information, including a summary of the recovery plan and evacuation guide information. The input is the recovery plan document and emergency information, and the output is a push notification message.

[0350] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0351] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0352] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0353] [Second embodiment]

[0354] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0355] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0356] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0357] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0358] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0359] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0360] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0361] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0362] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0363] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0364] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0365] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0366] The present invention relates to a system for collecting disaster-related information from social media, analyzing the information, and identifying base stations that should be prioritized for restoration. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a restoration plan generation module.

[0367] The device first uses a social media data collection module to collect disaster-related tweets. In this case, it connects to social media platforms using an API key and secret to collect tweets containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[0368] The collected tweets are then analyzed by the server using a critical location identification module. This module extracts information about evacuation shelters and other critical locations from the tweets. For example, if a tweet says "X-shelter is unavailable," the module analyzes it and identifies X-shelter as a critical location.

[0369] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the traffic information of the base station and other criteria (e.g., geographic importance).

[0370] The server also operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. This module determines the restoration order of base stations based on the analyzed data and issues restoration instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, with the highest priority, and notifies the corresponding worker.

[0371] Examples:

[0372] 1. The device connects to social media using the API key and secret and collects tweets with the keywords "shelter" and "unusable."

[0373] 2. The server identifies tweets saying "XX shelter is unavailable" and adds that shelter to the list as an "important location."

[0374] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[0375] 4. The server generates a plan to restore base station A as the top priority and issues the instruction "Restore base station A" to the corresponding worker. This plan aims to provide fast and efficient communication services to disaster victims by prioritizing support for locations that require urgent response.

[0376] In this way, the system of the present invention makes it possible to collect appropriate information during a disaster, quickly identify important locations, and generate effective recovery plans based on priorities, thereby significantly improving the efficiency of disaster recovery.

[0377] The processing flow will be explained below.

[0378] Step 1:

[0379] The device connects to the social media platform using an API key and secret, performs API authentication, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then used in subsequent processing steps.

[0380] Step 2:

[0381] The server analyzes the collected tweets to identify important locations. In this step, it analyzes the text content of the tweets and checks whether they correspond to evacuation shelters or other important locations registered in advance. For example, if a tweet says "XX evacuation shelter is unavailable," it adds this evacuation shelter to the list of important locations.

[0382] Step 3:

[0383] The server calculates the priority of base stations based on the identified important locations. In this stage, it identifies base stations around the identified important locations and evaluates their priority based on traffic information and other factors. If a base station has a high traffic volume, it will be given a high priority.

[0384] Step 4:

[0385] The server generates a restoration plan based on the priority calculation results. It lists base stations in order of priority and creates a plan including specific restoration procedures. This plan includes information such as which base stations should be restored, when, and which workers will be responsible for the restoration.

[0386] Step 5:

[0387] The server then sends instructions to the workers to execute the generated restoration plan. Specifically, it issues restoration instructions to the base station with the highest priority, allowing the workers to respond quickly. The notification includes the base station's location information and specific restoration procedures.

[0388] Step 6:

[0389] The user (worker) receives the notification and begins work to restore the base station. The worker acts according to the restoration plan provided by the server, and proceeds with the work in order of priority for the base station that needs to be restored. Information about base stations that have been restored is reported to the server.

[0390] Example 1

[0391] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0392] In the event of a disaster, rapid and effective restoration of communications infrastructure is crucial for supporting victims. However, with current systems, it is difficult to determine which base stations should be restored first, and it is also difficult to grasp the situation in real time. Therefore, it is necessary to identify evacuation shelters and important base stations, prioritize base station restoration, and efficiently generate restoration plans.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0394] In this invention, the server includes means for collecting disaster-related information from social media, means for analyzing the collected information using a natural language processing model to identify important locations, means for calculating the priority of base stations based on the identified important locations, and means for generating a base station recovery plan based on the calculated priority. This makes it possible to grasp the disaster situation in real time, identify important locations, and generate a base station recovery plan efficiently and quickly.

[0395] "Social media" is a platform on the Internet where users can share information and interact with each other.

[0396] "Disaster-related information" refers to information about the situation, damage, evacuation sites, relief activities, etc. related to natural disasters and man-made disasters.

[0397] "Means of collection" refers to the technologies and processes used to obtain posts containing specific keywords from social media, including the use of APIs.

[0398] A "natural language processing model" is an artificial intelligence technology for analyzing and understanding human language, such as BERT and GPT-3.

[0399] "Important bases" are locations that are particularly important for rescue operations and support for evacuees during disasters, and include evacuation shelters and medical institutions.

[0400] The "means of identification" is a method of analyzing information collected from social media using a natural language processing model and extracting important information.

[0401] The "base station priority" indicates the priority of which base station should be restored first among a plurality of base stations.

[0402] The "calculating means" is a method for determining the priority of base stations based on the collected information and analysis results.

[0403] A "recovery plan" is a specific action plan for restoring communications infrastructure to its original state in the event of a disaster.

[0404] The "means for generating" is a method for creating specific recovery procedures and work instructions based on the calculated priorities.

[0405] The system aims to collect appropriate information during disasters, quickly identify important locations, and generate effective recovery plans based on priorities. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a recovery plan generation module.

[0406] Social Media Data Collection Module

[0407] The device first collects disaster-related information using a social media data collection module. This is done using the Twitter API, and authentication is performed using an API key and secret. Then, by collecting tweets containing specific keywords (e.g., "shelter" or "unavailable"), the device grasps the real-time disaster situation.

[0408] Example: Collect tweets saying "The shelters are full and unusable."

[0409] Important location identification module

[0410] The server then passes the collected tweets to a critical location identification module, which uses natural language processing models (e.g., BERT or GPT-3) to analyze the content of the tweets and identify evacuation centers and other critical locations.

[0411] Example: Analyzing tweets such as "XX shelter is unusable" and identifying XX shelter as an important base.

[0412] Priority Calculation Module

[0413] The server activates a priority calculation module that calculates the priority of the base station based on the identified important locations, taking into account the traffic information and geographical importance of the base station to determine the priority.

[0414] Example: You notice that base station A is handling three times the normal amount of traffic and decide that base station A should be restored as a top priority.

[0415] Recovery Plan Generation Module

[0416] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities, and this module determines the restoration order of each base station based on the analyzed data and the priority list, and generates specific restoration instructions.

[0417] Example: Notify the worker of the instruction to "restore base station A as a top priority."

[0418] This system supports the rapid restoration of communications infrastructure in the event of a disaster, and by utilizing collected social media data and advanced natural language processing technology, it is possible to generate efficient and effective restoration plans. Specific examples of prompt sentences include the following:

[0419] Prompt Sentence Examples

[0420] "Collect tweets related to disaster information, identify important evacuation centers, and generate a plan to prioritize the restoration of base stations around those evacuation centers. First, collect tweets using an API key and secret, and extract evacuation center information using natural language processing. Then, evaluate base station traffic information to calculate restoration priority, and generate and notify a restoration plan."

[0421] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0422] Step 1:

[0423] The device connects to the Twitter API using a social media data collection module.

[0424] Specifically, it authenticates with Twitter using the API key and secret. If authentication is successful, it collects tweets containing specific keywords such as "shelter" and "unusable" and stores them in a database.

[0425] The input includes the API key and secret, and the search keywords, and the output is the collected tweet data.

[0426] Step 2:

[0427] The server passes the collected tweet data to the important location identification module for analysis.

[0428] Specifically, it uses a natural language processing model (e.g., GPT-3) to analyze the content of tweets and identify evacuation shelters and other important locations. Through this analysis, it extracts important information, such as "____ evacuation shelter," from the text data of tweets.

[0429] The input includes collected tweet data and the output is a list of identified important locations.

[0430] Step 3:

[0431] The server launches a priority calculation module that calculates the priority of the base station based on the identified important locations.

[0432] Specifically, the system collects a list of base stations and their traffic information, evaluates their geographic importance, and determines the priority of each base station.

[0433] The input includes a list of important locations and traffic information of base stations, and the output is a priority list of each base station.

[0434] Step 4:

[0435] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priority.

[0436] Specifically, the restoration order is determined based on the analyzed priority list, and specific restoration instructions are generated, which in turn generate instructions for restoration work for each base station.

[0437] The input includes a priority list, and the output is a specific recovery plan and work instructions.

[0438] Step 5:

[0439] The server notifies the corresponding worker of the generated recovery plan.

[0440] Specifically, the system uses email or messaging systems to send instructions to workers such as "Restore base station A as a top priority."

[0441] The input includes a recovery plan and the output is a notification to the workers.

[0442] (Application example 1)

[0443] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0444] When a disaster occurs, rapid restoration of communications infrastructure is required. However, in order to efficiently utilize limited resources, it is important to identify base stations that should be restored as a priority. Conventional technologies have limitations in collecting disaster information in real time and generating base station restoration plans that incorporate user situation reports. Furthermore, they are not sufficient in providing information to users or visualizing the progress of restoration. This has led to problems such as not receiving necessary information in a timely manner during a disaster, and the condition of evacuation centers and the communications environment not improving. Therefore, there is a need for a system that enables efficient restoration of communications infrastructure during a disaster and provides users with real-time information.

[0445] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0446] In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating the priority of base stations based on the identified important locations, means for generating a base station recovery plan based on the priority, means for collecting user situation reports using smartphones, means for notifying users of disaster information in real time, and means for visualizing the progress of recovery on user terminals. This not only enables rapid and efficient recovery of communication infrastructure in the event of a disaster, but also makes it possible to provide users with timely important information and visualize the status of improvements to evacuation centers and the communication environment.

[0447] "Social media" is an online platform for collecting information about disasters in real time.

[0448] "Important locations" are key locations such as evacuation shelters and locations close to base stations that should be restored as a priority in the event of a disaster.

[0449] "Priority" is a standard for indicating the order and importance of restoration, and is calculated based on traffic information and needs at a specific location.

[0450] A "base station" is an infrastructure facility that supports user communications in a mobile communications network.

[0451] A "recovery plan" is a specific work schedule formulated based on priorities in order to restore communications infrastructure efficiently and quickly in the event of a disaster.

[0452] A "smartphone" is a portable information terminal that users use to collect and report disaster information.

[0453] "Real-time" refers to the timing when information is acquired, processed, and notified almost simultaneously.

[0454] "Progress" is information that indicates the degree of completion of each stage of restoration work and the progress of the construction work.

[0455] "Users" refers to people who use the system to receive disaster information and report their own situations.

[0456] This invention relates to a system and method for quickly and efficiently restoring communications infrastructure after a disaster. Specifically, this system collects and analyzes disaster-related information from social media, identifies key locations, prioritizes base stations based on that information, and generates a restoration plan. This system also includes the collection of situation reports from users using smartphones, real-time information notifications, and visualization of restoration progress.

[0457] The server first collects disaster-related posts using a social media data collection module. In this case, it connects to social media platforms using an API key and secret to collect posts containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[0458] The collected posts are then analyzed using a critical location identification module. The server extracts information about evacuation shelters and other critical locations from the posts. For example, if a post says "X-shelter is unavailable," the server analyzes it and identifies X-shelter as a critical location.

[0459] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the base station's traffic information and other criteria (e.g., geographic importance). For example, areas with high traffic or many evacuation shelters will have higher priority.

[0460] The server also operates a recovery plan generation module that generates a recovery plan based on the calculated priorities. This module determines the order in which base stations should be restored based on the analyzed data and issues recovery instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, as the highest priority, and notifies the appropriate worker. The purpose of this plan is to provide disaster victims with fast and efficient communication services by prioritizing support for locations requiring urgent response.

[0461] Users can also report their own situation using their smartphones, and these reports are collected on a server. Specifically, users can report specific information from the scene, such as the status of evacuation shelters and traffic information, in real time. This information is used as additional data to understand the overall picture of disaster response.

[0462] The server also has a function to notify users of collected information and restoration progress in real time. This allows users to receive disaster information via their smartphones and quickly take evacuation and safety measures. The restoration progress is also visualized on a map, allowing users to see which base stations are currently undergoing restoration work or have been restored.

[0463] Examples:

[0464] 1. The server connects to social media using the API key and secret and collects posts containing the keywords "shelter" and "unavailable."

[0465] 2. The post contains information that "XX evacuation shelter is unavailable," and this is added to the list as an important location.

[0466] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[0467] 4. The server generates a plan to restore base station A as the top priority and instructs the corresponding worker to "restore base station A."

[0468] 5. Users use their smartphones to report that "there is a water shortage at XX evacuation shelter," and the information is collected on the server.

[0469] 6. The server notifies the user of the collected information in real time and visualizes the progress of recovery on a map.

[0470] Example prompt sentence:

[0471] "Collect tweets about the disaster and identify important evacuation centers from tweets containing keywords such as 'evacuation center' or 'unavailable.' Based on this, create a Python program to calculate the priority of base stations and generate a recovery plan."

[0472] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0473] Step 1:

[0474] The server uses a social media data collection module to collect disaster-related posts. Specifically, it connects to social media platforms using an API key and secret to retrieve posts containing keywords such as "shelter" and "unavailable" in real time. The input is the API key, secret, and search keywords, and the output is the retrieved post data. This allows for a wealth of real-time information about the disaster.

[0475] Step 2:

[0476] The server analyzes the collected posts using an important location identification module. Specifically, it uses text mining technology to extract important location information from posts containing keywords such as "shelter" and "unusable." The input is the collected post data, and the output is a list of extracted important locations. This allows important evacuation centers and key locations to be identified.

[0477] Step 3:

[0478] The server launches a priority calculation module that calculates the priority of base stations based on the identified important locations. Specifically, it references a list of base stations around the important locations and quantifies the priority of each base station by taking into account traffic information and geographical importance. The inputs are the list of important locations, the list of base stations, and traffic information, and the output is a priority list for each base station. This makes it possible to determine which base stations should be prioritized for restoration.

[0479] Step 4:

[0480] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. Specifically, it determines the restoration order for each base station and creates a plan to issue restoration instructions starting with the base station with the highest priority. The input is a priority list, and the output is a specific restoration plan. This allows for the formulation of an efficient restoration work plan.

[0481] Step 5:

[0482] Users report their own situation using their smartphones. Specifically, they use a dedicated application to input the status of the evacuation shelter where they are currently located and the surrounding area. The input is the situation report entered by the user, and the output is report data that is aggregated on the server. This allows real-time information from the scene to be collected.

[0483] Step 6:

[0484] The server aggregates users' situation reports and notifies them in real time through the disaster information notification module. Specifically, it sends push notifications to smartphones to provide important disaster information and evacuation shelter information. The input is the aggregated situation report data, and the output is push notifications to users. This allows users to receive the latest disaster information in a timely manner.

[0485] Step 7:

[0486] The server runs a progress visualization module that visualizes the restoration progress on the user's device. Specifically, it displays the restoration progress on a map, showing which base stations are currently being restored or have been restored. The input is the restoration plan and progress data, and the output is a progress map displayed on the user's device. This allows the user to see at a glance which base stations have been restored.

[0487] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0488] The present invention relates to a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, the present invention has the function of evaluating the reliability of the collected information and adjusting the priority of important base stations by combining it with an emotion engine that recognizes user emotions.

[0489] The system includes the following modules:

[0490] 1. Social Media Data Collection Module: The device connects to social media platforms using the API key and secret to collect tweets related to the disaster, such as tweets containing keywords like "shelter" and "unavailable."

[0491] 2. Important Location Identification Module: The server analyzes the collected tweets and extracts information about evacuation centers and other important locations. For example, it analyzes tweets that say "XX evacuation center is unavailable" and adds them to the list of important locations.

[0492] 3. Priority calculation module: The server identifies base stations around the identified critical location and evaluates their priority based on traffic information and other factors. Base stations with particularly high traffic volumes are given a high priority.

[0493] 4. Emotion Engine: The server analyzes user emotions. This engine analyzes the emotional tone of tweets and recognizes positive, negative, and neutral emotions. This allows the reliability of collected information to be evaluated and information with high emotional intensity to be prioritized. It is also possible to adjust the priority of important points based on emotional information.

[0494] 5. Recovery plan generation module: The server generates a base station recovery plan based on the priority. It lists base stations in order of priority and creates specific recovery procedures. The plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station.

[0495] Explaining program processing in natural language

[0496] The device first uses a social media data collection module to collect disaster-related tweets. At this stage, it connects to social media platforms using an API key and secret, and collects keywords such as "shelter" and "unavailable."

[0497] The server then analyzes the collected tweets using an important location identification module, which scans the text in the tweets and adds the location to a list of important locations if it matches a pre-registered location name or keyword.

[0498] Next, the server launches a priority calculation module to identify base stations around the identified important locations, obtains traffic information and geographical importance of the base stations from a database, and calculates the priority of the base stations based on this information.

[0499] Furthermore, the server uses a sentiment engine to analyze the emotional tone of the collected tweets. The sentiment engine is used to evaluate the positive, negative, and neutral sentiment of the tweets and increase the reliability of the information. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[0500] Finally, the server uses the restoration plan generation module to create a priority-based restoration plan, which includes the restoration procedures and priorities for each base station and notifies the operator, thereby ensuring fast and efficient restoration of the base stations.

[0501] Examples:

[0502] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[0503] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[0504] 3. The server obtains information about base stations around the important location and sets the priority of base station A high based on traffic information.

[0505] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[0506] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[0507] The processing flow will be explained below.

[0508] Step 1:

[0509] The device connects to the social media platform using a social media data collection module, authenticates using an API key and secret, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then stored in a database for analysis in the next step.

[0510] Step 2:

[0511] The server analyzes the collected tweets using an important location identification module. Specifically, it scans the text of the tweets and extracts information about evacuation shelters and other important locations. For example, it analyzes a tweet that says "XX evacuation shelter is unavailable" and adds that location to a list of "important locations."

[0512] Step 3:

[0513] The server analyzes the emotional tone of collected tweets using an emotion engine. The emotion engine identifies positive, negative, and neutral emotions from the tweet content and evaluates the reliability of the information. Tweets with strong emotions are considered to have high reliability and are used to calculate priorities in the next step.

[0514] Step 4:

[0515] The server calculates the priority of base stations based on the key locations and the results of sentiment analysis. Using the priority calculation module, the server sets specific priorities, taking into account the traffic information and geographic importance of base stations around key locations. For example, if base station A near a certain evacuation shelter has a lot of traffic and many tweets with negative sentiment, the server sets the priority of that base station A high.

[0516] Step 5:

[0517] The server uses the restoration plan generation module to create a restoration plan based on priority. It determines the restoration procedure for the base station with the highest priority, and formulates a plan including specific work content and personnel. This plan is notified to the workers in the next step.

[0518] Step 6:

[0519] The server then notifies the workers of the generated restoration plan, which includes the specific locations, priorities, and work procedures of the base stations that need to be restored. Based on this information, the workers can quickly respond and proceed with the restoration work in order of priority.

[0520] Step 7:

[0521] The user (worker) receives the notification and begins work to restore the base station. The worker carries out the work in order of priority, following the restoration plan provided by the server. Information about base stations that have completed restoration is reported to the server, and progress is managed in real time.

[0522] Example 2

[0523] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0524] In modern natural disasters, while the rapid recovery of affected areas is required, determining which bases should be prioritized for recovery can be difficult. In particular, as the situation in the affected areas changes in real time, formulating an efficient recovery plan is difficult, and it is necessary to evaluate priorities while ensuring the reliability of information.

[0525] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0526] In this invention, the server includes means for collecting disaster-related data from social media, means for identifying important locations from the collected data, means for calculating the priority of communication bases based on the identified important locations, means for analyzing user sentiment and evaluating the reliability of the data, and means for generating a recovery plan for the communication bases based on the priority. This makes it possible to formulate an efficient recovery plan using reliable data in real time based on information from social media.

[0527] "Social media" refers to platforms that allow users to share and exchange information online.

[0528] A "disaster" is an emergency caused by a natural phenomenon that causes damage to large numbers of people and infrastructure.

[0529] "Data" refers to information for processing and analysis by a computer.

[0530] "Important locations" refer to locations that function as evacuation routes or evacuation facilities in the event of a disaster, or locations that are necessary for maintaining social functions.

[0531] "Communication base" means a facility for providing a mobile communication network.

[0532] "Priority" refers to the level of importance or urgency that is applied after evaluating multiple targets.

[0533] A "recovery plan" refers to a plan that includes specific steps and schedules for restoring infrastructure in a disaster-stricken area to its original state.

[0534] "User sentiment" refers to the emotional responses (positive, negative, and neutral emotions) expressed by users on social media.

[0535] "Analysis" refers to the process of investigating and interpreting data and information in detail to gain useful insights.

[0536] "Reliability" refers to the degree to which information or data is accurate and useful.

[0537] MODE FOR CARRYING OUT THE INVENTION

[0538] This invention is a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, this system combines an emotion engine that recognizes user emotions to evaluate the reliability of the collected information and adjust the priority of important base stations.

[0539] The system includes the following modules:

[0540] 1. Social Media Data Collection Module:

[0541] The device connects to social media platforms using an API key and secret to collect tweets related to the disaster, specifically tweets containing keywords such as "shelter" and "unavailable." The software used includes the Twitter API and Facebook Graph API.

[0542] 2. Critical Location Identification Module:

[0543] The server analyzes the collected tweets and extracts information about important locations. It scans the text in the tweets and, if it matches pre-registered place names or keywords, adds the location to a list of important locations. It uses natural language processing tools such as NLTK and SpaCy.

[0544] 3. Priority Calculation Module:

[0545] The server identifies communication base stations in the vicinity of the identified important base station and evaluates their priority based on traffic information and other factors. MySQL or PostgreSQL is used as the database, and base stations with particularly high traffic volumes are given a high priority.

[0546] 4. Emotion Engine:

[0547] The server analyzes the emotional tone of tweets. The engine evaluates positive, negative, and neutral sentiment and is used to increase the reliability of the collected information. Tools used include SentiStrength and VADER.

[0548] 5. Recovery Plan Generation Module:

[0549] The server generates a recovery plan for the communication base stations based on the priority. It lists the base stations in order of priority and creates specific recovery procedures. This plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station. JIRA and Trello are used as work management systems.

[0550] Specific examples

[0551] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[0552] In this example, the keyword "shelter" is the target of collection.

[0553] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[0554] Tweets containing the word "shelter" are identified and added to a list along with the location name.

[0555] 3. The server obtains information about communication base stations surrounding the important base station and sets the priority of base station A high based on traffic information.

[0556] Base station A is in an area with heavy traffic, so it is set to a high priority.

[0557] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[0558] Negative tweets such as "It's terrible, XX shelter is completely unusable" are analyzed and reflected in the priorities.

[0559] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[0560] Finally, a plan is created to restore base station A as the top priority, and specific instructions are sent to the workers.

[0561] Prompt Sentence Examples

[0562] Sample prompt 1: "Please explain in detail the steps of the system that collects social media data and calculates the priority of key locations and their surrounding base stations in the event of a disaster."

[0563] Sample prompt 2: "What are the specific steps to use the Twitter API to collect disaster-related tweets, analyze them, and generate a base station recovery plan?"

[0564] The above is a specific example of an embodiment of the present invention, which makes it possible to formulate an efficient recovery plan using highly reliable data in real time.

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

[0566] Step 1:

[0567] The device uses a social media data collection module to collect disaster-related tweets by connecting to social media platforms using an API key and secret, and collecting keywords such as "shelter" and "unavailable."

[0568] Input: Connection information to social media API (e.g. Twitter API) and collection keywords.

[0569] Specific behavior:

[0570] 1. The device connects to the Twitter API using the API key and secret.

[0571] 2. Set "shelter" and "unusable" as keywords.

[0572] 3. Collect tweets containing these keywords and store the acquired data in local storage (e.g., SQLite database).

[0573] Output: Tweet data that matches the keywords.

[0574] Step 2:

[0575] The server analyzes the collected tweets and extracts information about important locations. To do this, it uses natural language processing tools (e.g., NLTK, SpaCy) to scan the tweet text and, if it matches a pre-registered place name or keyword, adds that place to a list of important locations.

[0576] Input: Collected tweet data.

[0577] Specific behavior:

[0578] 1. The server retrieves tweet data from the SQLite database.

[0579] 2. Analyze tweet text using natural language processing tools.

[0580] 3. Add locations containing keywords that correspond to important locations (e.g., "○○ evacuation shelter") to the list.

[0581] Output: A list of important locations.

[0582] Step 3:

[0583] The server identifies communication base stations around key locations, retrieves traffic information and geographical importance of those base stations from a database, and evaluates their priority. Based on this evaluation, the server sets the priority of the base stations.

[0584] Input: List of key locations and base station traffic information.

[0585] Specific behavior:

[0586] 1. The server retrieves base station traffic data from a database (e.g., PostgreSQL).

[0587] 2. Evaluate the traffic volume and geographical conditions of each base station.

[0588] 3. Set the priority of the base station and generate a priority list.

[0589] Output: Base station priority list.

[0590] Step 4:

[0591] The server uses an emotion engine to analyze the emotional tone of collected tweets. This analysis evaluates positive, negative, and neutral sentiment, which is used to increase the reliability of the data. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[0592] Input: Collected tweet data.

[0593] Specific behavior:

[0594] 1. The server applies a sentiment analysis tool (e.g., SentiStrength, VADER) to analyze the emotional tone of the tweet.

[0595] 2. Calculate positive, negative, and neutral sentiment scores for each tweet.

[0596] 3. Update the base station's priority list based on tweets with high emotional intensity.

[0597] Output: Updated base station priority list.

[0598] Step 5:

[0599] The server generates a restoration plan for the communication base station based on the priority, which includes the restoration procedures and priorities for the base station and is notified to the operator.

[0600] Input: Updated base station priority list.

[0601] Specific behavior:

[0602] 1. The server creates a recovery plan based on a priority list.

[0603] 2. The restoration plan will include specific procedures for which base stations should be restored and when.

[0604] 3. Notify workers of the recovery plan and work instructions using a work management system (e.g., JIRA, Trello).

[0605] Output: Recovery plan communicated to workers.

[0606] (Application example 2)

[0607] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0608] In the event of a disaster, it is necessary to quickly and accurately identify important evacuation shelters and unusable locations, and to develop effective recovery plans. However, current systems have difficulty evaluating the reliability of information taking user emotions into account, and there is a lack of means to notify emergency information in real time, which makes it difficult to respond quickly.

[0609] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating priorities based on the identified important locations, means for generating a recovery plan based on the priorities, means for evaluating the reliability and urgency of the information using a sentiment analysis engine, and means for notifying users and response teams of emergency information. This makes it possible to accurately evaluate the reliability and urgency of the information based on sentiment analysis, and to quickly and effectively develop a recovery plan and notify emergency information.

[0610] "Social media" refers to internet-based platforms that users use to disseminate and share information.

[0611] A "disaster" refers to a situation in which human life and property are put at risk due to natural phenomena or man-made factors.

[0612] "Information collection means" refers to devices and software used to collect relevant data from various data sources.

[0613] "Important locations" refer to locations or facilities where protection and restoration are considered particularly important in the event of a disaster.

[0614] A "priority calculation means" is a device or software that evaluates and ranks the importance and urgency of tasks based on specific criteria.

[0615] A "recovery plan" is a document that outlines the procedures and schedule for improving the situation after a disaster and returning to normal.

[0616] An "emotion analysis engine" is software that automatically analyzes human emotions (positive, negative, neutral, etc.) from text and voice.

[0617] "Reliability of information" is an indicator that evaluates whether the collected data is true.

[0618] "Emergency information" refers to important information that must be communicated in the event of a disaster and requires a prompt response.

[0619] A "response team" is a group of people with specialized skills and knowledge for disaster response.

[0620] This invention provides a system that quickly identifies important bases and evaluates their priorities in the event of a disaster, creates a recovery plan based on that information, and notifies relevant teams and users of emergency information. A specific example of the system is described below.

[0621] Generating a Program

[0622] 1. Real-time data collection:

[0623] The server collects posts containing disaster-related keywords such as "shelter" and "help" in real time using social media APIs, specifically Twitter API and Facebook Graph API.

[0624] 2. Data Analysis:

[0625] The server analyzes the collected posts using natural language processing tools (e.g., Google Cloud Natural Language API), which allows it to identify important evacuation sites and unavailable locations.

[0626] 3. Emotion analysis:

[0627] The server uses a sentiment analysis engine (e.g., IBM Watson Natural Language Understanding) to evaluate the emotional tone of posts, recognizing positive, negative, and neutral sentiment and increasing the credibility and urgency of information.

[0628] 4. Priority Calculation:

[0629] The server calculates the priority by taking into account traffic information and resource usage around the identified important locations. This is done using traffic information stored in a database (e.g., MySQL).

[0630] 5. Recovery plan generation:

[0631] Based on the priorities, a recovery plan is generated, which includes details on which locations should be restored and in what order.

[0632] 6. Notifications and Guidance:

[0633] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify emergency teams and users of emergency information. At the same time, users are also provided with guidance information such as evacuation procedures and safe routes.

[0634] Hardware and software usage examples

[0635] Hardware:

[0636] Smartphone (iOS or Android)

[0637] Server (Cloud service: AWS, Google Cloud)

[0638] software:

[0639] Social Media APIs (Twitter API, Facebook Graph API)

[0640] Sentiment analysis engine (IBM Watson Natural Language Understanding, Google Cloud Natural Language API)

[0641] Database (MySQL, PostgreSQL)

[0642] Cloud storage (AWS S3, Google Cloud Storage)

[0643] Push notification service (Firebase Cloud Messaging)

[0644] Specific examples

[0645] Specific examples are given below:

[0646] 1. Data Collection:

[0647] The server uses the Twitter API to collect tweets containing keywords such as "shelter" and "help."

[0648] 2. Data Analysis:

[0649] The server uses the Google Cloud Natural Language API to extract information such as "XX shelter is unavailable" from the collected tweets and adds XX shelter to a list as an important location.

[0650] 3. Emotion analysis:

[0651] The server uses IBM Watson to analyze the emotional tone of tweets, giving more weight to tweets that display a strong negative sentiment.

[0652] 4. Priority Calculation:

[0653] Based on the traffic information stored in the MySQL database, the server calculates the priority of base stations around the XX evacuation shelter and lists them in order of importance.

[0654] 5. Recovery plan generation:

[0655] Based on the priority, the base station that should be restored with the highest priority is identified, and specific restoration procedures are created.

[0656] 6. Notifications and Guidance:

[0657] Notify emergency response teams with emergency information and provide evacuation instructions and safe routes to users using Firebase Cloud Messaging.

[0658] Prompt Sentence Examples

[0659] Example of input sentence to generative AI model:

[0660] How can I collect disaster-related information from user posts, analyze that information, and assess its urgency?

[0661] Input data:

[0662] 1. Tweet text collected from social media platforms

[0663] 2. Keyword list (shelter, help, unusable, in trouble)

[0664] 3. User sentiment (positive, negative, neutral)

[0665] Output data:

[0666] 1. List of important shelters and points

[0667] 2. Prioritizing by cumulative emotional tone

[0668] 3. Notification to the response team

[0669] 4. User evacuation guide

[0670] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0671] Step 1:

[0672] The device uses social media APIs to collect posts containing disaster-related keywords (e.g., "shelter" and "help") in real time. It connects to the social media platform (e.g., Twitter) using an API key and secret, and sends the collected post data to the server. The input is the keywords and API connection information, and the output is the collected social media post data.

[0673] Step 2:

[0674] The server analyzes the received social media post data using natural language processing tools (e.g., Google Cloud Natural Language API). It extracts posts containing specific keywords and phrases and identifies important evacuation shelters and unusable locations. The input is the collected social media post data, and the output is a list of important evacuation shelters and unusable locations.

[0675] Step 3:

[0676] The server applies a sentiment analysis engine (e.g., IBM Watson Natural Language Understanding) to information about important evacuation shelters and unavailable locations to evaluate the emotional tone of the posts. It recognizes positive, negative, and neutral emotions and evaluates the reliability and urgency of the information. The input is post data about identified evacuation shelters and locations, and the output is the sentiment evaluation results for each post.

[0677] Step 4:

[0678] The server calculates the priority of the identified important locations based on the emotional tone and traffic information. The server obtains traffic information stored in a database (e.g., MySQL) and combines it with the emotional evaluation results. The inputs are the emotional evaluation results and traffic information, and the output is a priority list of important locations.

[0679] Step 5:

[0680] The server generates a recovery plan based on the priority list. This plan includes specific instructions and a schedule for which sites should be restored and in what order. The input is the priority list, and the output is a recovery plan document.

[0681] Step 6:

[0682] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify response teams and users of emergency information, including a summary of the recovery plan and evacuation guide information. The input is the recovery plan document and emergency information, and the output is a push notification message.

[0683] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0684] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0685] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0686] [Third embodiment]

[0687] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0688] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0689] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0690] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0691] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0692] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0693] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0694] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0695] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0696] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0697] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0698] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0699] The present invention relates to a system for collecting disaster-related information from social media, analyzing the information, and identifying base stations that should be prioritized for restoration. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a restoration plan generation module.

[0700] The device first uses a social media data collection module to collect disaster-related tweets. In this case, it connects to social media platforms using an API key and secret to collect tweets containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[0701] The collected tweets are then analyzed by the server using a critical location identification module. This module extracts information about evacuation shelters and other critical locations from the tweets. For example, if a tweet says "X-shelter is unavailable," the module analyzes it and identifies X-shelter as a critical location.

[0702] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the traffic information of the base station and other criteria (e.g., geographic importance).

[0703] The server also operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. This module determines the restoration order of base stations based on the analyzed data and issues restoration instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, with the highest priority, and notifies the corresponding worker.

[0704] Examples:

[0705] 1. The device connects to social media using the API key and secret and collects tweets with the keywords "shelter" and "unusable."

[0706] 2. The server identifies tweets saying "XX shelter is unavailable" and adds that shelter to the list as an "important location."

[0707] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[0708] 4. The server generates a plan to restore base station A as the top priority and issues the instruction "Restore base station A" to the corresponding worker. This plan aims to provide fast and efficient communication services to disaster victims by prioritizing support for locations that require urgent response.

[0709] In this way, the system of the present invention makes it possible to collect appropriate information during a disaster, quickly identify important locations, and generate effective recovery plans based on priorities, thereby significantly improving the efficiency of disaster recovery.

[0710] The processing flow will be explained below.

[0711] Step 1:

[0712] The device connects to the social media platform using an API key and secret, performs API authentication, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then used in subsequent processing steps.

[0713] Step 2:

[0714] The server analyzes the collected tweets to identify important locations. In this step, it analyzes the text content of the tweets and checks whether they correspond to evacuation shelters or other important locations registered in advance. For example, if a tweet says "XX evacuation shelter is unavailable," it adds this evacuation shelter to the list of important locations.

[0715] Step 3:

[0716] The server calculates the priority of base stations based on the identified important locations. In this stage, it identifies base stations around the identified important locations and evaluates their priority based on traffic information and other factors. If a base station has a high traffic volume, it will be given a high priority.

[0717] Step 4:

[0718] The server generates a restoration plan based on the priority calculation results. It lists base stations in order of priority and creates a plan including specific restoration procedures. This plan includes information such as which base stations should be restored, when, and which workers will be responsible for the restoration.

[0719] Step 5:

[0720] The server then sends instructions to the workers to execute the generated restoration plan. Specifically, it issues restoration instructions to the base station with the highest priority, allowing the workers to respond quickly. The notification includes the base station's location information and specific restoration procedures.

[0721] Step 6:

[0722] The user (worker) receives the notification and begins work to restore the base station. The worker acts according to the restoration plan provided by the server, and proceeds with the work in order of priority for the base station that needs to be restored. Information about base stations that have been restored is reported to the server.

[0723] Example 1

[0724] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0725] In the event of a disaster, rapid and effective restoration of communications infrastructure is crucial for supporting victims. However, with current systems, it is difficult to determine which base stations should be restored first, and it is also difficult to grasp the situation in real time. Therefore, it is necessary to identify evacuation shelters and important base stations, prioritize base station restoration, and efficiently generate restoration plans.

[0726] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0727] In this invention, the server includes means for collecting disaster-related information from social media, means for analyzing the collected information using a natural language processing model to identify important locations, means for calculating the priority of base stations based on the identified important locations, and means for generating a base station recovery plan based on the calculated priority. This makes it possible to grasp the disaster situation in real time, identify important locations, and generate a base station recovery plan efficiently and quickly.

[0728] "Social media" is a platform on the Internet where users can share information and interact with each other.

[0729] "Disaster-related information" refers to information about the situation, damage, evacuation sites, relief activities, etc. related to natural disasters and man-made disasters.

[0730] "Means of collection" refers to the technologies and processes used to obtain posts containing specific keywords from social media, including the use of APIs.

[0731] A "natural language processing model" is an artificial intelligence technology for analyzing and understanding human language, such as BERT and GPT-3.

[0732] "Important bases" are locations that are particularly important for rescue operations and support for evacuees during disasters, and include evacuation shelters and medical institutions.

[0733] The "means of identification" is a method of analyzing information collected from social media using a natural language processing model and extracting important information.

[0734] The "base station priority" indicates the priority of which base station should be restored first among a plurality of base stations.

[0735] The "calculating means" is a method for determining the priority of base stations based on the collected information and analysis results.

[0736] A "recovery plan" is a specific action plan for restoring communications infrastructure to its original state in the event of a disaster.

[0737] The "means for generating" is a method for creating specific recovery procedures and work instructions based on the calculated priorities.

[0738] The system aims to collect appropriate information during disasters, quickly identify important locations, and generate effective recovery plans based on priorities. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a recovery plan generation module.

[0739] Social Media Data Collection Module

[0740] The device first collects disaster-related information using a social media data collection module. This is done using the Twitter API, and authentication is performed using an API key and secret. Then, by collecting tweets containing specific keywords (e.g., "shelter" or "unavailable"), the device grasps the real-time disaster situation.

[0741] Example: Collect tweets saying "The shelters are full and unusable."

[0742] Important location identification module

[0743] The server then passes the collected tweets to a critical location identification module, which uses natural language processing models (e.g., BERT or GPT-3) to analyze the content of the tweets and identify evacuation centers and other critical locations.

[0744] Example: Analyzing tweets such as "XX shelter is unusable" and identifying XX shelter as an important base.

[0745] Priority Calculation Module

[0746] The server activates a priority calculation module that calculates the priority of the base station based on the identified important locations, taking into account the traffic information and geographical importance of the base station to determine the priority.

[0747] Example: You notice that base station A is handling three times the normal amount of traffic and decide that base station A should be restored as a top priority.

[0748] Recovery Plan Generation Module

[0749] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities, and this module determines the restoration order of each base station based on the analyzed data and the priority list, and generates specific restoration instructions.

[0750] Example: Notify the worker of the instruction to "restore base station A as a top priority."

[0751] This system supports the rapid restoration of communications infrastructure in the event of a disaster, and by utilizing collected social media data and advanced natural language processing technology, it is possible to generate efficient and effective restoration plans. Specific examples of prompt sentences include the following:

[0752] Prompt Sentence Examples

[0753] "Collect tweets related to disaster information, identify important evacuation centers, and generate a plan to prioritize the restoration of base stations around those evacuation centers. First, collect tweets using an API key and secret, and extract evacuation center information using natural language processing. Then, evaluate base station traffic information to calculate restoration priority, and generate and notify a restoration plan."

[0754] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0755] Step 1:

[0756] The device connects to the Twitter API using a social media data collection module.

[0757] Specifically, it authenticates with Twitter using the API key and secret. If authentication is successful, it collects tweets containing specific keywords such as "shelter" and "unusable" and stores them in a database.

[0758] The input includes the API key and secret, and the search keywords, and the output is the collected tweet data.

[0759] Step 2:

[0760] The server passes the collected tweet data to the important location identification module for analysis.

[0761] Specifically, it uses a natural language processing model (e.g., GPT-3) to analyze the content of tweets and identify evacuation shelters and other important locations. Through this analysis, it extracts important information, such as "____ evacuation shelter," from the text data of tweets.

[0762] The input includes collected tweet data and the output is a list of identified important locations.

[0763] Step 3:

[0764] The server launches a priority calculation module that calculates the priority of the base station based on the identified important locations.

[0765] Specifically, the system collects a list of base stations and their traffic information, evaluates their geographic importance, and determines the priority of each base station.

[0766] The input includes a list of important locations and traffic information of base stations, and the output is a priority list of each base station.

[0767] Step 4:

[0768] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priority.

[0769] Specifically, the restoration order is determined based on the analyzed priority list, and specific restoration instructions are generated, which in turn generate instructions for restoration work for each base station.

[0770] The input includes a priority list, and the output is a specific recovery plan and work instructions.

[0771] Step 5:

[0772] The server notifies the corresponding worker of the generated recovery plan.

[0773] Specifically, the system uses email or messaging systems to send instructions to workers such as "Restore base station A as a top priority."

[0774] The input includes a recovery plan and the output is a notification to the workers.

[0775] (Application example 1)

[0776] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0777] When a disaster occurs, rapid restoration of communications infrastructure is required. However, in order to efficiently utilize limited resources, it is important to identify base stations that should be restored as a priority. Conventional technologies have limitations in collecting disaster information in real time and generating base station restoration plans that incorporate user situation reports. Furthermore, they are not sufficient in providing information to users or visualizing the progress of restoration. This has led to problems such as not receiving necessary information in a timely manner during a disaster, and the condition of evacuation centers and the communications environment not improving. Therefore, there is a need for a system that enables efficient restoration of communications infrastructure during a disaster and provides users with real-time information.

[0778] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0779] In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating the priority of base stations based on the identified important locations, means for generating a base station recovery plan based on the priority, means for collecting user situation reports using smartphones, means for notifying users of disaster information in real time, and means for visualizing the progress of recovery on user terminals. This not only enables rapid and efficient recovery of communication infrastructure in the event of a disaster, but also makes it possible to provide users with timely important information and visualize the status of improvements to evacuation centers and the communication environment.

[0780] "Social media" is an online platform for collecting information about disasters in real time.

[0781] "Important locations" are key locations such as evacuation shelters and locations close to base stations that should be restored as a priority in the event of a disaster.

[0782] "Priority" is a standard for indicating the order and importance of restoration, and is calculated based on traffic information and needs at a specific location.

[0783] A "base station" is an infrastructure facility that supports user communications in a mobile communications network.

[0784] A "recovery plan" is a specific work schedule formulated based on priorities in order to restore communications infrastructure efficiently and quickly in the event of a disaster.

[0785] A "smartphone" is a portable information terminal that users use to collect and report disaster information.

[0786] "Real-time" refers to the timing when information is acquired, processed, and notified almost simultaneously.

[0787] "Progress" is information that indicates the degree of completion of each stage of restoration work and the progress of the construction work.

[0788] "Users" refers to people who use the system to receive disaster information and report their own situations.

[0789] This invention relates to a system and method for quickly and efficiently restoring communications infrastructure after a disaster. Specifically, this system collects and analyzes disaster-related information from social media, identifies key locations, prioritizes base stations based on that information, and generates a restoration plan. This system also includes the collection of situation reports from users using smartphones, real-time information notifications, and visualization of restoration progress.

[0790] The server first collects disaster-related posts using a social media data collection module. In this case, it connects to social media platforms using an API key and secret to collect posts containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[0791] The collected posts are then analyzed using a critical location identification module. The server extracts information about evacuation shelters and other critical locations from the posts. For example, if a post says "X-shelter is unavailable," the server analyzes it and identifies X-shelter as a critical location.

[0792] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the base station's traffic information and other criteria (e.g., geographic importance). For example, areas with high traffic or many evacuation shelters will have higher priority.

[0793] The server also operates a recovery plan generation module that generates a recovery plan based on the calculated priorities. This module determines the order in which base stations should be restored based on the analyzed data and issues recovery instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, as the highest priority, and notifies the appropriate worker. The purpose of this plan is to provide disaster victims with fast and efficient communication services by prioritizing support for locations requiring urgent response.

[0794] Users can also report their own situation using their smartphones, and these reports are collected on a server. Specifically, users can report specific information from the scene, such as the status of evacuation shelters and traffic information, in real time. This information is used as additional data to understand the overall picture of disaster response.

[0795] The server also has a function to notify users of collected information and restoration progress in real time. This allows users to receive disaster information via their smartphones and quickly take evacuation and safety measures. The restoration progress is also visualized on a map, allowing users to see which base stations are currently undergoing restoration work or have been restored.

[0796] Examples:

[0797] 1. The server connects to social media using the API key and secret and collects posts containing the keywords "shelter" and "unavailable."

[0798] 2. The post contains information that "XX evacuation shelter is unavailable," and this is added to the list as an important location.

[0799] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[0800] 4. The server generates a plan to restore base station A as the top priority and instructs the corresponding worker to "restore base station A."

[0801] 5. Users use their smartphones to report that "there is a water shortage at XX evacuation shelter," and the information is collected on the server.

[0802] 6. The server notifies the user of the collected information in real time and visualizes the progress of recovery on a map.

[0803] Example prompt sentence:

[0804] "Collect tweets about the disaster and identify important evacuation centers from tweets containing keywords such as 'evacuation center' or 'unavailable.' Based on this, create a Python program to calculate the priority of base stations and generate a recovery plan."

[0805] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0806] Step 1:

[0807] The server uses a social media data collection module to collect disaster-related posts. Specifically, it connects to social media platforms using an API key and secret to retrieve posts containing keywords such as "shelter" and "unavailable" in real time. The input is the API key, secret, and search keywords, and the output is the retrieved post data. This allows for a wealth of real-time information about the disaster.

[0808] Step 2:

[0809] The server analyzes the collected posts using an important location identification module. Specifically, it uses text mining technology to extract important location information from posts containing keywords such as "shelter" and "unusable." The input is the collected post data, and the output is a list of extracted important locations. This allows important evacuation centers and key locations to be identified.

[0810] Step 3:

[0811] The server launches a priority calculation module that calculates the priority of base stations based on the identified important locations. Specifically, it references a list of base stations around the important locations and quantifies the priority of each base station by taking into account traffic information and geographical importance. The inputs are the list of important locations, the list of base stations, and traffic information, and the output is a priority list for each base station. This makes it possible to determine which base stations should be prioritized for restoration.

[0812] Step 4:

[0813] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. Specifically, it determines the restoration order for each base station and creates a plan to issue restoration instructions starting with the base station with the highest priority. The input is a priority list, and the output is a specific restoration plan. This allows for the formulation of an efficient restoration work plan.

[0814] Step 5:

[0815] Users report their own situation using their smartphones. Specifically, they use a dedicated application to input the status of the evacuation shelter where they are currently located and the surrounding area. The input is the situation report entered by the user, and the output is report data that is aggregated on the server. This allows real-time information from the scene to be collected.

[0816] Step 6:

[0817] The server aggregates users' situation reports and notifies them in real time through the disaster information notification module. Specifically, it sends push notifications to smartphones to provide important disaster information and evacuation shelter information. The input is the aggregated situation report data, and the output is push notifications to users. This allows users to receive the latest disaster information in a timely manner.

[0818] Step 7:

[0819] The server runs a progress visualization module that visualizes the restoration progress on the user's device. Specifically, it displays the restoration progress on a map, showing which base stations are currently being restored or have been restored. The input is the restoration plan and progress data, and the output is a progress map displayed on the user's device. This allows the user to see at a glance which base stations have been restored.

[0820] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0821] The present invention relates to a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, the present invention has the function of evaluating the reliability of the collected information and adjusting the priority of important base stations by combining it with an emotion engine that recognizes user emotions.

[0822] The system includes the following modules:

[0823] 1. Social Media Data Collection Module: The device connects to social media platforms using the API key and secret to collect tweets related to the disaster, such as tweets containing keywords like "shelter" and "unavailable."

[0824] 2. Important Location Identification Module: The server analyzes the collected tweets and extracts information about evacuation centers and other important locations. For example, it analyzes tweets that say "XX evacuation center is unavailable" and adds them to the list of important locations.

[0825] 3. Priority calculation module: The server identifies base stations around the identified critical location and evaluates their priority based on traffic information and other factors. Base stations with particularly high traffic volumes are given a high priority.

[0826] 4. Emotion Engine: The server analyzes user emotions. This engine analyzes the emotional tone of tweets and recognizes positive, negative, and neutral emotions. This allows the reliability of collected information to be evaluated and information with high emotional intensity to be prioritized. It is also possible to adjust the priority of important points based on emotional information.

[0827] 5. Recovery plan generation module: The server generates a base station recovery plan based on the priority. It lists base stations in order of priority and creates specific recovery procedures. The plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station.

[0828] Explaining program processing in natural language

[0829] The device first uses a social media data collection module to collect disaster-related tweets. At this stage, it connects to social media platforms using an API key and secret, and collects keywords such as "shelter" and "unavailable."

[0830] The server then analyzes the collected tweets using an important location identification module, which scans the text in the tweets and adds the location to a list of important locations if it matches a pre-registered location name or keyword.

[0831] Next, the server launches a priority calculation module to identify base stations around the identified important locations, obtains traffic information and geographical importance of the base stations from a database, and calculates the priority of the base stations based on this information.

[0832] Furthermore, the server uses a sentiment engine to analyze the emotional tone of the collected tweets. The sentiment engine is used to evaluate the positive, negative, and neutral sentiment of the tweets and increase the reliability of the information. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[0833] Finally, the server uses the restoration plan generation module to create a priority-based restoration plan, which includes the restoration procedures and priorities for each base station and notifies the operator, thereby ensuring fast and efficient restoration of the base stations.

[0834] Examples:

[0835] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[0836] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[0837] 3. The server obtains information about base stations around the important location and sets the priority of base station A high based on traffic information.

[0838] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[0839] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[0840] The processing flow will be explained below.

[0841] Step 1:

[0842] The device connects to the social media platform using a social media data collection module, authenticates using an API key and secret, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then stored in a database for analysis in the next step.

[0843] Step 2:

[0844] The server analyzes the collected tweets using an important location identification module. Specifically, it scans the text of the tweets and extracts information about evacuation shelters and other important locations. For example, it analyzes a tweet that says "XX evacuation shelter is unavailable" and adds that location to a list of "important locations."

[0845] Step 3:

[0846] The server analyzes the emotional tone of collected tweets using an emotion engine. The emotion engine identifies positive, negative, and neutral emotions from the tweet content and evaluates the reliability of the information. Tweets with strong emotions are considered to have high reliability and are used to calculate priorities in the next step.

[0847] Step 4:

[0848] The server calculates the priority of base stations based on the key locations and the results of sentiment analysis. Using the priority calculation module, the server sets specific priorities, taking into account the traffic information and geographic importance of base stations around key locations. For example, if base station A near a certain evacuation shelter has a lot of traffic and many tweets with negative sentiment, the server sets the priority of that base station A high.

[0849] Step 5:

[0850] The server uses the restoration plan generation module to create a restoration plan based on priority. It determines the restoration procedure for the base station with the highest priority, and formulates a plan including specific work content and personnel. This plan is notified to the workers in the next step.

[0851] Step 6:

[0852] The server then notifies the workers of the generated restoration plan, which includes the specific locations, priorities, and work procedures of the base stations that need to be restored. Based on this information, the workers can quickly respond and proceed with the restoration work in order of priority.

[0853] Step 7:

[0854] The user (worker) receives the notification and begins work to restore the base station. The worker carries out the work in order of priority, following the restoration plan provided by the server. Information about base stations that have completed restoration is reported to the server, and progress is managed in real time.

[0855] Example 2

[0856] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0857] In modern natural disasters, while the rapid recovery of affected areas is required, determining which bases should be prioritized for recovery can be difficult. In particular, as the situation in the affected areas changes in real time, formulating an efficient recovery plan is difficult, and it is necessary to evaluate priorities while ensuring the reliability of information.

[0858] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0859] In this invention, the server includes means for collecting disaster-related data from social media, means for identifying important locations from the collected data, means for calculating the priority of communication bases based on the identified important locations, means for analyzing user sentiment and evaluating the reliability of the data, and means for generating a recovery plan for the communication bases based on the priority. This makes it possible to formulate an efficient recovery plan using reliable data in real time based on information from social media.

[0860] "Social media" refers to platforms that allow users to share and exchange information online.

[0861] A "disaster" is an emergency caused by a natural phenomenon that causes damage to large numbers of people and infrastructure.

[0862] "Data" refers to information for processing and analysis by a computer.

[0863] "Important locations" refer to locations that function as evacuation routes or evacuation facilities in the event of a disaster, or locations that are necessary for maintaining social functions.

[0864] "Communication base" means a facility for providing a mobile communication network.

[0865] "Priority" refers to the level of importance or urgency that is applied after evaluating multiple targets.

[0866] A "recovery plan" refers to a plan that includes specific steps and schedules for restoring infrastructure in a disaster-stricken area to its original state.

[0867] "User sentiment" refers to the emotional responses (positive, negative, and neutral emotions) expressed by users on social media.

[0868] "Analysis" refers to the process of investigating and interpreting data and information in detail to gain useful insights.

[0869] "Reliability" refers to the degree to which information or data is accurate and useful.

[0870] MODE FOR CARRYING OUT THE INVENTION

[0871] This invention is a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, this system combines an emotion engine that recognizes user emotions to evaluate the reliability of the collected information and adjust the priority of important base stations.

[0872] The system includes the following modules:

[0873] 1. Social Media Data Collection Module:

[0874] The device connects to social media platforms using an API key and secret to collect tweets related to the disaster, specifically tweets containing keywords such as "shelter" and "unavailable." The software used includes the Twitter API and Facebook Graph API.

[0875] 2. Critical Location Identification Module:

[0876] The server analyzes the collected tweets and extracts information about important locations. It scans the text in the tweets and, if it matches pre-registered place names or keywords, adds the location to a list of important locations. It uses natural language processing tools such as NLTK and SpaCy.

[0877] 3. Priority Calculation Module:

[0878] The server identifies communication base stations in the vicinity of the identified important base station and evaluates their priority based on traffic information and other factors. MySQL or PostgreSQL is used as the database, and base stations with particularly high traffic volumes are given a high priority.

[0879] 4. Emotion Engine:

[0880] The server analyzes the emotional tone of tweets. The engine evaluates positive, negative, and neutral sentiment and is used to increase the reliability of the collected information. Tools used include SentiStrength and VADER.

[0881] 5. Recovery Plan Generation Module:

[0882] The server generates a recovery plan for the communication base stations based on the priority. It lists the base stations in order of priority and creates specific recovery procedures. This plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station. JIRA and Trello are used as work management systems.

[0883] Specific examples

[0884] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[0885] In this example, the keyword "shelter" is the target of collection.

[0886] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[0887] Tweets containing the word "shelter" are identified and added to a list along with the location name.

[0888] 3. The server obtains information about communication base stations surrounding the important base station and sets the priority of base station A high based on traffic information.

[0889] Base station A is in an area with heavy traffic, so it is set to a high priority.

[0890] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[0891] Negative tweets such as "It's terrible, XX shelter is completely unusable" are analyzed and reflected in the priorities.

[0892] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[0893] Finally, a plan is created to restore base station A as the top priority, and specific instructions are sent to the workers.

[0894] Prompt Sentence Examples

[0895] Sample prompt 1: "Please explain in detail the steps of the system that collects social media data and calculates the priority of key locations and their surrounding base stations in the event of a disaster."

[0896] Sample prompt 2: "What are the specific steps to use the Twitter API to collect disaster-related tweets, analyze them, and generate a base station recovery plan?"

[0897] The above is a specific example of an embodiment of the present invention, which makes it possible to formulate an efficient recovery plan using highly reliable data in real time.

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

[0899] Step 1:

[0900] The device uses a social media data collection module to collect disaster-related tweets by connecting to social media platforms using an API key and secret, and collecting keywords such as "shelter" and "unavailable."

[0901] Input: Connection information to social media API (e.g. Twitter API) and collection keywords.

[0902] Specific behavior:

[0903] 1. The device connects to the Twitter API using the API key and secret.

[0904] 2. Set "shelter" and "unusable" as keywords.

[0905] 3. Collect tweets containing these keywords and store the acquired data in local storage (e.g., SQLite database).

[0906] Output: Tweet data that matches the keywords.

[0907] Step 2:

[0908] The server analyzes the collected tweets and extracts information about important locations. To do this, it uses natural language processing tools (e.g., NLTK, SpaCy) to scan the tweet text and, if it matches a pre-registered place name or keyword, adds that place to a list of important locations.

[0909] Input: Collected tweet data.

[0910] Specific behavior:

[0911] 1. The server retrieves tweet data from the SQLite database.

[0912] 2. Analyze tweet text using natural language processing tools.

[0913] 3. Add locations containing keywords that correspond to important locations (e.g., "○○ evacuation shelter") to the list.

[0914] Output: A list of important locations.

[0915] Step 3:

[0916] The server identifies communication base stations around key locations, retrieves traffic information and geographical importance of those base stations from a database, and evaluates their priority. Based on this evaluation, the server sets the priority of the base stations.

[0917] Input: List of key locations and base station traffic information.

[0918] Specific behavior:

[0919] 1. The server retrieves base station traffic data from a database (e.g., PostgreSQL).

[0920] 2. Evaluate the traffic volume and geographical conditions of each base station.

[0921] 3. Set the priority of the base station and generate a priority list.

[0922] Output: Base station priority list.

[0923] Step 4:

[0924] The server uses an emotion engine to analyze the emotional tone of collected tweets. This analysis evaluates positive, negative, and neutral sentiment, which is used to increase the reliability of the data. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[0925] Input: Collected tweet data.

[0926] Specific behavior:

[0927] 1. The server applies a sentiment analysis tool (e.g., SentiStrength, VADER) to analyze the emotional tone of the tweet.

[0928] 2. Calculate positive, negative, and neutral sentiment scores for each tweet.

[0929] 3. Update the base station's priority list based on tweets with high emotional intensity.

[0930] Output: Updated base station priority list.

[0931] Step 5:

[0932] The server generates a restoration plan for the communication base station based on the priority, which includes the restoration procedures and priorities for the base station and is notified to the operator.

[0933] Input: Updated base station priority list.

[0934] Specific behavior:

[0935] 1. The server creates a recovery plan based on a priority list.

[0936] 2. The restoration plan will include specific procedures for which base stations should be restored and when.

[0937] 3. Notify workers of the recovery plan and work instructions using a work management system (e.g., JIRA, Trello).

[0938] Output: Recovery plan communicated to workers.

[0939] (Application example 2)

[0940] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0941] In the event of a disaster, it is necessary to quickly and accurately identify important evacuation shelters and unusable locations, and to develop effective recovery plans. However, current systems have difficulty evaluating the reliability of information taking user emotions into account, and there is a lack of means to notify emergency information in real time, which makes it difficult to respond quickly.

[0942] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating priorities based on the identified important locations, means for generating a recovery plan based on the priorities, means for evaluating the reliability and urgency of the information using a sentiment analysis engine, and means for notifying users and response teams of emergency information. This makes it possible to accurately evaluate the reliability and urgency of the information based on sentiment analysis, and to quickly and effectively develop a recovery plan and notify emergency information.

[0943] "Social media" refers to internet-based platforms that users use to disseminate and share information.

[0944] A "disaster" refers to a situation in which human life and property are put at risk due to natural phenomena or man-made factors.

[0945] "Information collection means" refers to devices and software used to collect relevant data from various data sources.

[0946] "Important locations" refer to locations or facilities where protection and restoration are considered particularly important in the event of a disaster.

[0947] A "priority calculation means" is a device or software that evaluates and ranks the importance and urgency of tasks based on specific criteria.

[0948] A "recovery plan" is a document that outlines the procedures and schedule for improving the situation after a disaster and returning to normal.

[0949] An "emotion analysis engine" is software that automatically analyzes human emotions (positive, negative, neutral, etc.) from text and voice.

[0950] "Reliability of information" is an indicator that evaluates whether the collected data is true.

[0951] "Emergency information" refers to important information that must be communicated in the event of a disaster and requires a prompt response.

[0952] A "response team" is a group of people with specialized skills and knowledge for disaster response.

[0953] This invention provides a system that quickly identifies important bases and evaluates their priorities in the event of a disaster, creates a recovery plan based on that information, and notifies relevant teams and users of emergency information. A specific example of the system is described below.

[0954] Generating a Program

[0955] 1. Real-time data collection:

[0956] The server collects posts containing disaster-related keywords such as "shelter" and "help" in real time using social media APIs, specifically Twitter API and Facebook Graph API.

[0957] 2. Data Analysis:

[0958] The server analyzes the collected posts using natural language processing tools (e.g., Google Cloud Natural Language API), which allows it to identify important evacuation sites and unavailable locations.

[0959] 3. Emotion analysis:

[0960] The server uses a sentiment analysis engine (e.g., IBM Watson Natural Language Understanding) to evaluate the emotional tone of posts, recognizing positive, negative, and neutral sentiment and increasing the credibility and urgency of information.

[0961] 4. Priority Calculation:

[0962] The server calculates the priority by taking into account traffic information and resource usage around the identified important locations. This is done using traffic information stored in a database (e.g., MySQL).

[0963] 5. Recovery plan generation:

[0964] Based on the priorities, a recovery plan is generated, which includes details on which locations should be restored and in what order.

[0965] 6. Notifications and Guidance:

[0966] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify emergency teams and users of emergency information. At the same time, users are also provided with guidance information such as evacuation procedures and safe routes.

[0967] Hardware and software usage examples

[0968] Hardware:

[0969] Smartphone (iOS or Android)

[0970] Server (Cloud service: AWS, Google Cloud)

[0971] software:

[0972] Social Media APIs (Twitter API, Facebook Graph API)

[0973] Sentiment analysis engine (IBM Watson Natural Language Understanding, Google Cloud Natural Language API)

[0974] Database (MySQL, PostgreSQL)

[0975] Cloud storage (AWS S3, Google Cloud Storage)

[0976] Push notification service (Firebase Cloud Messaging)

[0977] Specific examples

[0978] Specific examples are given below:

[0979] 1. Data Collection:

[0980] The server uses the Twitter API to collect tweets containing keywords such as "shelter" and "help."

[0981] 2. Data Analysis:

[0982] The server uses the Google Cloud Natural Language API to extract information such as "XX shelter is unavailable" from the collected tweets and adds XX shelter to a list as an important location.

[0983] 3. Emotion analysis:

[0984] The server uses IBM Watson to analyze the emotional tone of tweets, giving more weight to tweets that display a strong negative sentiment.

[0985] 4. Priority Calculation:

[0986] Based on the traffic information stored in the MySQL database, the server calculates the priority of base stations around the XX evacuation shelter and lists them in order of importance.

[0987] 5. Recovery plan generation:

[0988] Based on the priority, the base station that should be restored with the highest priority is identified, and specific restoration procedures are created.

[0989] 6. Notifications and Guidance:

[0990] Notify emergency response teams with emergency information and provide evacuation instructions and safe routes to users using Firebase Cloud Messaging.

[0991] Prompt Sentence Examples

[0992] Example of input sentence to generative AI model:

[0993] How can I collect disaster-related information from user posts, analyze that information, and assess its urgency?

[0994] Input data:

[0995] 1. Tweet text collected from social media platforms

[0996] 2. Keyword list (shelter, help, unusable, in trouble)

[0997] 3. User sentiment (positive, negative, neutral)

[0998] Output data:

[0999] 1. List of important shelters and points

[1000] 2. Prioritizing by cumulative emotional tone

[1001] 3. Notification to the response team

[1002] 4. User evacuation guide

[1003] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1004] Step 1:

[1005] The device uses social media APIs to collect posts containing disaster-related keywords (e.g., "shelter" and "help") in real time. It connects to the social media platform (e.g., Twitter) using an API key and secret, and sends the collected post data to the server. The input is the keywords and API connection information, and the output is the collected social media post data.

[1006] Step 2:

[1007] The server analyzes the received social media post data using natural language processing tools (e.g., Google Cloud Natural Language API). It extracts posts containing specific keywords and phrases and identifies important evacuation shelters and unusable locations. The input is the collected social media post data, and the output is a list of important evacuation shelters and unusable locations.

[1008] Step 3:

[1009] The server applies a sentiment analysis engine (e.g., IBM Watson Natural Language Understanding) to information about important evacuation shelters and unavailable locations to evaluate the emotional tone of the posts. It recognizes positive, negative, and neutral emotions and evaluates the reliability and urgency of the information. The input is post data about identified evacuation shelters and locations, and the output is the sentiment evaluation results for each post.

[1010] Step 4:

[1011] The server calculates the priority of the identified important locations based on the emotional tone and traffic information. The server obtains traffic information stored in a database (e.g., MySQL) and combines it with the emotional evaluation results. The inputs are the emotional evaluation results and traffic information, and the output is a priority list of important locations.

[1012] Step 5:

[1013] The server generates a recovery plan based on the priority list. This plan includes specific instructions and a schedule for which sites should be restored and in what order. The input is the priority list, and the output is a recovery plan document.

[1014] Step 6:

[1015] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify response teams and users of emergency information, including a summary of the recovery plan and evacuation guide information. The input is the recovery plan document and emergency information, and the output is a push notification message.

[1016] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1017] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1018] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1019] [Fourth embodiment]

[1020] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1021] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1023] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1024] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1025] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1027] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1028] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1029] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1031] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1033] The present invention relates to a system for collecting disaster-related information from social media, analyzing the information, and identifying base stations that should be prioritized for restoration. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a restoration plan generation module.

[1034] The device first uses a social media data collection module to collect disaster-related tweets. In this case, it connects to social media platforms using an API key and secret to collect tweets containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[1035] The collected tweets are then analyzed by the server using a critical location identification module. This module extracts information about evacuation shelters and other critical locations from the tweets. For example, if a tweet says "X-shelter is unavailable," the module analyzes it and identifies X-shelter as a critical location.

[1036] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the traffic information of the base station and other criteria (e.g., geographic importance).

[1037] The server also operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. This module determines the restoration order of base stations based on the analyzed data and issues restoration instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, with the highest priority, and notifies the corresponding worker.

[1038] Examples:

[1039] 1. The device connects to social media using the API key and secret and collects tweets with the keywords "shelter" and "unusable."

[1040] 2. The server identifies tweets saying "XX shelter is unavailable" and adds that shelter to the list as an "important location."

[1041] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[1042] 4. The server generates a plan to restore base station A as the top priority and issues the instruction "Restore base station A" to the corresponding worker. This plan aims to provide fast and efficient communication services to disaster victims by prioritizing support for locations that require urgent response.

[1043] In this way, the system of the present invention makes it possible to collect appropriate information during a disaster, quickly identify important locations, and generate effective recovery plans based on priorities, thereby significantly improving the efficiency of disaster recovery.

[1044] The processing flow will be explained below.

[1045] Step 1:

[1046] The device connects to the social media platform using an API key and secret, performs API authentication, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then used in subsequent processing steps.

[1047] Step 2:

[1048] The server analyzes the collected tweets to identify important locations. In this step, it analyzes the text content of the tweets and checks whether they correspond to evacuation shelters or other important locations registered in advance. For example, if a tweet says "XX evacuation shelter is unavailable," it adds this evacuation shelter to the list of important locations.

[1049] Step 3:

[1050] The server calculates the priority of base stations based on the identified important locations. In this stage, it identifies base stations around the identified important locations and evaluates their priority based on traffic information and other factors. If a base station has a high traffic volume, it will be given a high priority.

[1051] Step 4:

[1052] The server generates a restoration plan based on the priority calculation results. It lists base stations in order of priority and creates a plan including specific restoration procedures. This plan includes information such as which base stations should be restored, when, and which workers will be responsible for the restoration.

[1053] Step 5:

[1054] The server then sends instructions to the workers to execute the generated restoration plan. Specifically, it issues restoration instructions to the base station with the highest priority, allowing the workers to respond quickly. The notification includes the base station's location information and specific restoration procedures.

[1055] Step 6:

[1056] The user (worker) receives the notification and begins work to restore the base station. The worker acts according to the restoration plan provided by the server, and works on the base station that needs to be restored first. Information on base stations that have been restored is reported to the server.

[1057] Example 1

[1058] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1059] In the event of a disaster, rapid and effective restoration of communications infrastructure is crucial for supporting victims. However, with current systems, it is difficult to determine which base stations should be restored first, and it is also difficult to grasp the situation in real time. Therefore, it is necessary to identify evacuation shelters and important base stations, prioritize base station restoration, and efficiently generate restoration plans.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1061] In this invention, the server includes means for collecting disaster-related information from social media, means for analyzing the collected information using a natural language processing model to identify important locations, means for calculating the priority of base stations based on the identified important locations, and means for generating a base station recovery plan based on the calculated priority. This makes it possible to grasp the disaster situation in real time, identify important locations, and generate a base station recovery plan efficiently and quickly.

[1062] "Social media" is a platform on the Internet where users can share information and interact with each other.

[1063] "Disaster-related information" refers to information about the situation, damage, evacuation sites, relief activities, etc. related to natural disasters and man-made disasters.

[1064] "Means of collection" refers to the technologies and processes used to obtain posts containing specific keywords from social media, including the use of APIs.

[1065] A "natural language processing model" is an artificial intelligence technology for analyzing and understanding human language, such as BERT and GPT-3.

[1066] "Important bases" are locations that are particularly important for rescue operations and support for evacuees during disasters, and include evacuation shelters and medical institutions.

[1067] The "means of identification" is a method of analyzing information collected from social media using a natural language processing model and extracting important information.

[1068] The "base station priority" indicates the priority of which base station should be restored first among a plurality of base stations.

[1069] The "calculating means" is a method for determining the priority of base stations based on the collected information and analysis results.

[1070] A "recovery plan" is a specific action plan for restoring communications infrastructure to its original state in the event of a disaster.

[1071] The "means for generating" is a method for creating specific recovery procedures and work instructions based on the calculated priorities.

[1072] The system aims to collect appropriate information during disasters, quickly identify important locations, and generate effective recovery plans based on priorities. The system includes a social media data collection module, a critical location identification module, a priority calculation module, and a recovery plan generation module.

[1073] Social Media Data Collection Module

[1074] The device first collects disaster-related information using a social media data collection module. This is done using the Twitter API, and authentication is performed using an API key and secret. Then, by collecting tweets containing specific keywords (e.g., "shelter" or "unavailable"), the device grasps the real-time disaster situation.

[1075] Example: Collect tweets saying "The shelters are full and unusable."

[1076] Important location identification module

[1077] The server then passes the collected tweets to a critical location identification module, which uses natural language processing models (e.g., BERT or GPT-3) to analyze the content of the tweets and identify evacuation centers and other critical locations.

[1078] Example: Analyzing tweets such as "XX shelter is unusable" and identifying XX shelter as an important base.

[1079] Priority Calculation Module

[1080] The server activates a priority calculation module that calculates the priority of the base station based on the identified important locations, taking into account the traffic information and geographical importance of the base station to determine the priority.

[1081] Example: You notice that base station A is handling three times the normal amount of traffic and decide that base station A should be restored as a top priority.

[1082] Recovery Plan Generation Module

[1083] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities, and this module determines the restoration order of each base station based on the analyzed data and the priority list, and generates specific restoration instructions.

[1084] Example: Notify the worker of the instruction to "restore base station A as a top priority."

[1085] This system supports the rapid restoration of communications infrastructure in the event of a disaster, and by utilizing collected social media data and advanced natural language processing technology, it is possible to generate efficient and effective restoration plans. Specific examples of prompt sentences include the following:

[1086] Prompt Sentence Examples

[1087] "Collect tweets related to disaster information, identify important evacuation centers, and generate a plan to prioritize the restoration of base stations around those evacuation centers. First, collect tweets using an API key and secret, and extract evacuation center information using natural language processing. Then, evaluate base station traffic information to calculate restoration priority, and generate and notify a restoration plan."

[1088] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1089] Step 1:

[1090] The device connects to the Twitter API using a social media data collection module.

[1091] Specifically, it authenticates with Twitter using the API key and secret. If authentication is successful, it collects tweets containing specific keywords such as "shelter" and "unusable" and stores them in a database.

[1092] The input includes the API key and secret, and the search keywords, and the output is the collected tweet data.

[1093] Step 2:

[1094] The server passes the collected tweet data to the important location identification module for analysis.

[1095] Specifically, it uses a natural language processing model (e.g., GPT-3) to analyze the content of tweets and identify evacuation shelters and other important locations. Through this analysis, it extracts important information, such as "____ evacuation shelter," from the text data of tweets.

[1096] The input includes collected tweet data and the output is a list of identified important locations.

[1097] Step 3:

[1098] The server launches a priority calculation module that calculates the priority of the base station based on the identified important locations.

[1099] Specifically, the system collects a list of base stations and their traffic information, evaluates their geographic importance, and determines the priority of each base station.

[1100] The input includes a list of important locations and traffic information of base stations, and the output is a priority list of each base station.

[1101] Step 4:

[1102] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priority.

[1103] Specifically, the restoration order is determined based on the analyzed priority list, and specific restoration instructions are generated, which in turn generate instructions for restoration work for each base station.

[1104] The input includes a priority list, and the output is a specific recovery plan and work instructions.

[1105] Step 5:

[1106] The server notifies the corresponding worker of the generated recovery plan.

[1107] Specifically, the system uses email or messaging systems to send instructions to workers such as "Restore base station A as a top priority."

[1108] The input includes a recovery plan and the output is a notification to the workers.

[1109] (Application example 1)

[1110] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1111] When a disaster occurs, rapid restoration of communications infrastructure is required. However, in order to efficiently utilize limited resources, it is important to identify base stations that should be prioritized for restoration. Conventional technologies have limitations in collecting disaster information in real time and generating base station restoration plans that incorporate user situation reports. Furthermore, they are not sufficient in providing information to users or visualizing the progress of restoration. This has led to problems such as not receiving necessary information in a timely manner during a disaster, and the condition of evacuation centers and the communications environment not improving. Therefore, there is a need for a system that enables efficient restoration of communications infrastructure during a disaster and provides users with real-time information.

[1112] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1113] In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating the priority of base stations based on the identified important locations, means for generating a base station recovery plan based on the priority, means for collecting user situation reports using smartphones, means for notifying users of disaster information in real time, and means for visualizing the progress of recovery on user terminals. This not only enables rapid and efficient recovery of communication infrastructure in the event of a disaster, but also makes it possible to provide users with timely important information and visualize the status of improvements to evacuation centers and the communication environment.

[1114] "Social media" is an online platform for collecting information about disasters in real time.

[1115] "Important locations" are key locations such as evacuation shelters and locations close to base stations that should be restored as a priority in the event of a disaster.

[1116] "Priority" is a standard for indicating the order and importance of restoration, and is calculated based on traffic information and needs at a specific location.

[1117] A "base station" is an infrastructure facility that supports user communications in a mobile communications network.

[1118] A "recovery plan" is a specific work schedule formulated based on priorities in order to efficiently and quickly restore communications infrastructure in the event of a disaster.

[1119] A "smartphone" is a portable information terminal that users use to collect and report disaster information.

[1120] "Real-time" refers to the timing when information is acquired, processed, and notified almost simultaneously.

[1121] "Progress" is information that indicates the degree of completion of each stage of restoration work and the progress of the construction work.

[1122] "Users" refers to people who use the system to receive disaster information and report their own situations.

[1123] This invention relates to a system and method for quickly and efficiently restoring communications infrastructure after a disaster. Specifically, this system collects and analyzes disaster-related information from social media, identifies key locations, prioritizes base stations based on that information, and generates a restoration plan. This system also includes the collection of situation reports from users using smartphones, real-time information notifications, and visualization of restoration progress.

[1124] The server first collects disaster-related posts using a social media data collection module. In this case, it connects to social media platforms using an API key and secret to collect posts containing keywords such as "shelter" and "unavailable." This allows it to aggregate a large amount of real-time information about the disaster situation.

[1125] The collected posts are then analyzed using a critical location identification module. The server extracts information about evacuation shelters and other critical locations from the posts. For example, if a post says "X-shelter is unavailable," the server analyzes it and identifies X-shelter as a critical location.

[1126] Next, the server launches a priority calculation module to calculate the priority of base stations based on critical locations. Base stations near critical locations should be restored with higher priority than other base stations. This priority is calculated by taking into account the base station's traffic information and other criteria (e.g., geographic importance). For example, areas with high traffic or many evacuation shelters will have higher priority.

[1127] The server also operates a recovery plan generation module that generates a recovery plan based on the calculated priorities. This module determines the order in which base stations should be restored based on the analyzed data and issues recovery instructions to each base station. For example, it creates an instruction to restore base station A, which is located near the XX evacuation shelter, as the highest priority, and notifies the appropriate worker. The purpose of this plan is to provide disaster victims with fast and efficient communication services by prioritizing support for locations requiring urgent response.

[1128] Users can also report their own situation using their smartphones, and these reports are collected on a server. Specifically, users can report specific information from the scene, such as the status of evacuation shelters and traffic information, in real time. This information is used as additional data to understand the overall picture of disaster response.

[1129] The server also has a function to notify users of collected information and restoration progress in real time. This allows users to receive disaster information via their smartphones and quickly take evacuation and safety measures. The restoration progress is also visualized on a map, allowing users to see which base stations are currently undergoing restoration work or have been restored.

[1130] Examples:

[1131] 1. The server connects to social media using the API key and secret and collects posts containing the keywords "shelter" and "unavailable."

[1132] 2. The post contains information that "XX evacuation shelter is unavailable," and this is added to the list as an important location.

[1133] 3. The server queries the list of base stations around the shelter and finds that base station A has particularly high traffic.

[1134] 4. The server generates a plan to restore base station A as the top priority and instructs the corresponding worker to "restore base station A."

[1135] 5. Users use their smartphones to report that "there is a water shortage at XX evacuation shelter," and the information is collected on the server.

[1136] 6. The server notifies the user of the collected information in real time and visualizes the progress of recovery on a map.

[1137] Example prompt sentence:

[1138] "Collect tweets about the disaster and identify important evacuation centers from tweets containing keywords such as 'evacuation center' or 'unavailable.' Based on this, create a Python program to calculate the priority of base stations and generate a recovery plan."

[1139] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1140] Step 1:

[1141] The server uses a social media data collection module to collect disaster-related posts. Specifically, it connects to social media platforms using an API key and secret to retrieve posts containing keywords such as "shelter" and "unavailable" in real time. The input is the API key, secret, and search keywords, and the output is the retrieved post data. This allows for a wealth of real-time information about the disaster.

[1142] Step 2:

[1143] The server analyzes the collected posts using an important location identification module. Specifically, it uses text mining technology to extract important location information from posts containing keywords such as "shelter" and "unusable." The input is the collected post data, and the output is a list of extracted important locations. This allows important evacuation centers and key locations to be identified.

[1144] Step 3:

[1145] The server launches a priority calculation module that calculates the priority of base stations based on the identified important locations. Specifically, it references a list of base stations around the important locations and quantifies the priority of each base station by taking into account traffic information and geographical importance. The inputs are the list of important locations, the list of base stations, and traffic information, and the output is a priority list for each base station. This makes it possible to determine which base stations should be prioritized for restoration.

[1146] Step 4:

[1147] The server operates a restoration plan generation module that generates a restoration plan based on the calculated priorities. Specifically, it determines the restoration order for each base station and creates a plan to issue restoration instructions starting with the base station with the highest priority. The input is a priority list, and the output is a specific restoration plan. This allows for the formulation of an efficient restoration work plan.

[1148] Step 5:

[1149] Users report their own situation using their smartphones. Specifically, they use a dedicated application to input the status of the evacuation shelter where they are currently located and the surrounding area. The input is the situation report entered by the user, and the output is report data that is aggregated on the server. This allows real-time information from the scene to be collected.

[1150] Step 6:

[1151] The server aggregates users' situation reports and notifies them in real time through the disaster information notification module. Specifically, it sends push notifications to smartphones to provide important disaster information and evacuation shelter information. The input is the aggregated situation report data, and the output is push notifications to users. This allows users to receive the latest disaster information in a timely manner.

[1152] Step 7:

[1153] The server runs a progress visualization module that visualizes the restoration progress on the user's device. Specifically, it displays the restoration progress on a map, showing which base stations are currently being restored or have been restored. The input is the restoration plan and progress data, and the output is a progress map displayed on the user's device. This allows the user to see at a glance which base stations have been restored.

[1154] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1155] The present invention relates to a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, the present invention has the function of evaluating the reliability of the collected information and adjusting the priority of important base stations by combining it with an emotion engine that recognizes user emotions.

[1156] The system includes the following modules:

[1157] 1. Social Media Data Collection Module: The device connects to social media platforms using the API key and secret to collect tweets related to the disaster, such as tweets containing keywords like "shelter" and "unavailable."

[1158] 2. Important Location Identification Module: The server analyzes the collected tweets and extracts information about evacuation centers and other important locations. For example, it analyzes tweets that say "XX evacuation center is unavailable" and adds them to the list of important locations.

[1159] 3. Priority calculation module: The server identifies base stations around the identified critical location and evaluates their priority based on traffic information and other factors. Base stations with particularly high traffic volumes are given a high priority.

[1160] 4. Emotion Engine: The server analyzes user emotions. This engine analyzes the emotional tone of tweets and recognizes positive, negative, and neutral emotions. This allows the reliability of collected information to be evaluated and information with high emotional intensity to be prioritized. It is also possible to adjust the priority of important points based on emotional information.

[1161] 5. Recovery plan generation module: The server generates a base station recovery plan based on the priority. It lists base stations in order of priority and creates specific recovery procedures. The plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station.

[1162] Explaining program processing in natural language

[1163] The device first uses a social media data collection module to collect disaster-related tweets. At this stage, it connects to social media platforms using an API key and secret, and collects keywords such as "shelter" and "unavailable."

[1164] The server then analyzes the collected tweets using an important location identification module, which scans the text in the tweets and adds the location to a list of important locations if it matches a pre-registered location name or keyword.

[1165] Next, the server launches a priority calculation module to identify base stations around the identified important locations, obtains traffic information and geographical importance of the base stations from a database, and calculates the priority of the base stations based on this information.

[1166] Furthermore, the server uses a sentiment engine to analyze the emotional tone of the collected tweets. The sentiment engine is used to evaluate the positive, negative, and neutral sentiment of the tweets and increase the reliability of the information. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[1167] Finally, the server uses the restoration plan generation module to create a priority-based restoration plan, which includes the restoration procedures and priorities for each base station and notifies the operator, thereby ensuring fast and efficient restoration of the base stations.

[1168] Examples:

[1169] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[1170] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[1171] 3. The server obtains information about base stations around the important location and sets the priority of base station A high based on traffic information.

[1172] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[1173] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[1174] The processing flow will be explained below.

[1175] Step 1:

[1176] The device connects to the social media platform using a social media data collection module, authenticates using an API key and secret, and collects tweets containing keywords such as "shelter" and "unavailable." The collected tweets are then stored in a database for analysis in the next step.

[1177] Step 2:

[1178] The server analyzes the collected tweets using an important location identification module. Specifically, it scans the text of the tweets and extracts information about evacuation shelters and other important locations. For example, it analyzes a tweet that says "XX evacuation shelter is unavailable" and adds that location to a list of "important locations."

[1179] Step 3:

[1180] The server analyzes the emotional tone of collected tweets using an emotion engine. The emotion engine identifies positive, negative, and neutral emotions from the tweet content and evaluates the reliability of the information. Tweets with strong emotions are considered to have high reliability and are used to calculate priorities in the next step.

[1181] Step 4:

[1182] The server calculates the priority of base stations based on the key locations and the results of sentiment analysis. Using the priority calculation module, the server sets specific priorities, taking into account the traffic information and geographic importance of base stations around key locations. For example, if base station A near a certain evacuation shelter has a lot of traffic and many tweets with negative sentiment, the server sets the priority of that base station A high.

[1183] Step 5:

[1184] The server uses the restoration plan generation module to create a restoration plan based on priority. It determines the restoration procedure for the base station with the highest priority, and formulates a plan including specific work content and personnel. This plan is then notified to the workers in the next step.

[1185] Step 6:

[1186] The server then notifies the workers of the generated restoration plan, which includes the specific locations, priorities, and work procedures of the base stations that need to be restored. Based on this information, the workers can quickly respond and proceed with the restoration work in order of priority.

[1187] Step 7:

[1188] The user (worker) receives the notification and begins work to restore the base station. The worker carries out the work in order of priority, following the restoration plan provided by the server. Information about base stations that have completed restoration is reported to the server, and progress is managed in real time.

[1189] Example 2

[1190] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1191] In modern natural disasters, while the rapid recovery of affected areas is required, determining which bases should be prioritized for recovery can be difficult. In particular, as the situation in the affected areas changes in real time, formulating an efficient recovery plan is difficult, and it is necessary to evaluate priorities while ensuring the reliability of information.

[1192] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1193] In this invention, the server includes means for collecting disaster-related data from social media, means for identifying important locations from the collected data, means for calculating the priority of communication bases based on the identified important locations, means for analyzing user sentiment and evaluating the reliability of the data, and means for generating a recovery plan for the communication bases based on the priority. This makes it possible to formulate an efficient recovery plan using reliable data in real time based on information from social media.

[1194] "Social media" refers to platforms that allow users to share and exchange information online.

[1195] A "disaster" is an emergency caused by a natural phenomenon that causes damage to large numbers of people and infrastructure.

[1196] "Data" refers to information for processing and analysis by a computer.

[1197] "Important locations" refer to locations that function as evacuation routes or evacuation facilities in the event of a disaster, or locations that are necessary for maintaining social functions.

[1198] "Communication base" means a facility for providing a mobile communication network.

[1199] "Priority" refers to the level of importance or urgency that is applied after evaluating multiple targets.

[1200] A "recovery plan" refers to a plan that includes specific steps and schedules for restoring infrastructure in a disaster-stricken area to its original state.

[1201] "User sentiment" refers to the emotional responses (positive, negative, and neutral emotions) expressed by users on social media.

[1202] "Analysis" refers to the process of investigating and interpreting data and information in detail to gain useful insights.

[1203] "Reliability" refers to the degree to which information or data is accurate and useful.

[1204] MODE FOR CARRYING OUT THE INVENTION

[1205] This invention is a system that collects disaster-related information from social media, analyzes that information, and identifies base stations that should be prioritized for restoration. In particular, this system combines an emotion engine that recognizes user emotions to evaluate the reliability of the collected information and adjust the priority of important base stations.

[1206] The system includes the following modules:

[1207] 1. Social Media Data Collection Module:

[1208] The device connects to social media platforms using an API key and secret to collect tweets related to the disaster, specifically tweets containing keywords such as "shelter" and "unavailable." The software used includes the Twitter API and Facebook Graph API.

[1209] 2. Critical Location Identification Module:

[1210] The server analyzes the collected tweets and extracts information about important locations. It scans the text in the tweets and, if it matches pre-registered place names or keywords, adds the location to a list of important locations. It uses natural language processing tools such as NLTK and SpaCy.

[1211] 3. Priority Calculation Module:

[1212] The server identifies communication base stations in the vicinity of the identified important base station and evaluates their priority based on traffic information and other factors. MySQL or PostgreSQL is used as the database, and base stations with particularly high traffic volumes are given a high priority.

[1213] 4. Emotion Engine:

[1214] The server analyzes the emotional tone of tweets. The engine evaluates positive, negative, and neutral sentiment and is used to increase the reliability of the collected information. Tools used include SentiStrength and VADER.

[1215] 5. Recovery Plan Generation Module:

[1216] The server generates a recovery plan for the communication base stations based on the priority. It lists the base stations in order of priority and creates specific recovery procedures. This plan includes details on which base stations should be restored, when, and what recovery work workers should perform at each base station. JIRA and Trello are used as work management systems.

[1217] Specific examples

[1218] 1. The device collects tweets containing the keywords "shelter" and "unusable" from social media via an API.

[1219] In this example, the keyword "shelter" is the target of collection.

[1220] 2. The server analyzes the tweet and, based on the information that "XX shelter is unavailable," adds XX shelter to the list as an important location.

[1221] Tweets containing the word "shelter" are identified and added to a list along with the location name.

[1222] 3. The server obtains information about communication base stations surrounding the important base station and sets the priority of base station A high based on traffic information.

[1223] Base station A is in an area with heavy traffic, so it is set to a high priority.

[1224] 4. The server uses an emotion engine to analyze the emotional tone of the tweets, for example, giving more weight to tweets with a strong negative sentiment, further strengthening the priority of base station A.

[1225] Negative tweets such as "It's terrible, XX shelter is completely unusable" are analyzed and reflected in the priorities.

[1226] 5. The server uses the restoration plan generation module to create a plan to restore base station A as the top priority, and notifies the worker of the instruction to "restore base station A."

[1227] Finally, a plan is created to restore base station A as the top priority, and specific instructions are sent to the workers.

[1228] Prompt Sentence Examples

[1229] Sample prompt 1: "Please explain in detail the steps of the system that collects social media data and calculates the priority of key locations and their surrounding base stations in the event of a disaster."

[1230] Sample prompt 2: "What are the specific steps to use the Twitter API to collect disaster-related tweets, analyze them, and generate a base station recovery plan?"

[1231] The above is a specific example of an embodiment of the present invention, which makes it possible to formulate an efficient recovery plan using highly reliable data in real time.

[1232] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1233] Step 1:

[1234] The device uses a social media data collection module to collect disaster-related tweets by connecting to social media platforms using an API key and secret, and collecting keywords such as "shelter" and "unavailable."

[1235] Input: Connection information to social media API (e.g. Twitter API) and collection keywords.

[1236] Specific behavior:

[1237] 1. The device connects to the Twitter API using the API key and secret.

[1238] 2. Set "shelter" and "unusable" as keywords.

[1239] 3. Collect tweets containing these keywords and store the acquired data in local storage (e.g., SQLite database).

[1240] Output: Tweet data that matches the keywords.

[1241] Step 2:

[1242] The server analyzes the collected tweets and extracts information about important locations. To do this, it uses natural language processing tools (e.g., NLTK, SpaCy) to scan the tweet text and, if it matches a pre-registered place name or keyword, adds that place to a list of important locations.

[1243] Input: Collected tweet data.

[1244] Specific behavior:

[1245] 1. The server retrieves tweet data from the SQLite database.

[1246] 2. Analyze tweet text using natural language processing tools.

[1247] 3. Add locations containing keywords that correspond to important locations (e.g., "○○ evacuation shelter") to the list.

[1248] Output: A list of important locations.

[1249] Step 3:

[1250] The server identifies communication base stations around key locations, retrieves traffic information and geographical importance of those base stations from a database, and evaluates their priority. Based on this evaluation, the server sets the priority of the base stations.

[1251] Input: List of key locations and base station traffic information.

[1252] Specific behavior:

[1253] 1. The server retrieves base station traffic data from a database (e.g., PostgreSQL).

[1254] 2. Evaluate the traffic volume and geographical conditions of each base station.

[1255] 3. Set the priority of the base station and generate a priority list.

[1256] Output: Base station priority list.

[1257] Step 4:

[1258] The server uses an emotion engine to analyze the emotional tone of collected tweets. This analysis evaluates positive, negative, and neutral sentiment, which is used to increase the reliability of the data. Tweets with high emotional intensity are considered more reliable and influence the priority calculation.

[1259] Input: Collected tweet data.

[1260] Specific behavior:

[1261] 1. The server applies a sentiment analysis tool (e.g., SentiStrength, VADER) to analyze the emotional tone of the tweet.

[1262] 2. Calculate positive, negative, and neutral sentiment scores for each tweet.

[1263] 3. Update the base station's priority list based on tweets with high emotional intensity.

[1264] Output: Updated base station priority list.

[1265] Step 5:

[1266] The server generates a restoration plan for the communication base station based on the priority, which includes the restoration procedures and priorities for the base station and is notified to the operator.

[1267] Input: Updated base station priority list.

[1268] Specific behavior:

[1269] 1. The server creates a recovery plan based on a priority list.

[1270] 2. The restoration plan will include specific procedures for which base stations should be restored and when.

[1271] 3. Notify workers of the recovery plan and work instructions using a work management system (e.g., JIRA, Trello).

[1272] Output: Recovery plan communicated to workers.

[1273] (Application example 2)

[1274] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1275] In the event of a disaster, it is necessary to quickly and accurately identify important evacuation shelters and unusable locations, and to develop effective recovery plans. However, current systems have difficulty evaluating the reliability of information taking user emotions into account, and there is a lack of means to notify emergency information in real time, which makes it difficult to respond quickly.

[1276] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting disaster-related information from social media, means for identifying important locations from the collected information, means for calculating priorities based on the identified important locations, means for generating a recovery plan based on the priorities, means for evaluating the reliability and urgency of the information using a sentiment analysis engine, and means for notifying users and response teams of emergency information. This makes it possible to accurately evaluate the reliability and urgency of the information based on sentiment analysis, and to quickly and effectively develop a recovery plan and notify emergency information.

[1277] "Social media" refers to internet-based platforms that users use to disseminate and share information.

[1278] A "disaster" refers to a situation in which human life and property are put at risk due to natural phenomena or man-made factors.

[1279] "Information collection means" refers to devices and software used to collect relevant data from various data sources.

[1280] "Important locations" refer to locations or facilities where protection and restoration are considered particularly important in the event of a disaster.

[1281] A "priority calculation means" is a device or software that evaluates and ranks the importance and urgency of tasks based on specific criteria.

[1282] A "recovery plan" is a document that outlines the procedures and schedule for improving the situation after a disaster and returning to normal.

[1283] An "emotion analysis engine" is software that automatically analyzes human emotions (positive, negative, neutral, etc.) from text and voice.

[1284] "Reliability of information" is an indicator that evaluates whether the collected data is true.

[1285] "Emergency information" refers to important information that must be communicated in the event of a disaster and requires a prompt response.

[1286] A "response team" is a group of people with specialized skills and knowledge for disaster response.

[1287] This invention provides a system that quickly identifies important bases and evaluates their priorities in the event of a disaster, creates a recovery plan based on that information, and notifies relevant teams and users of emergency information. A specific example of the system is described below.

[1288] Generating a Program

[1289] 1. Real-time data collection:

[1290] The server collects posts containing disaster-related keywords such as "shelter" and "help" in real time using social media APIs, specifically Twitter API and Facebook Graph API.

[1291] 2. Data Analysis:

[1292] The server analyzes the collected posts using natural language processing tools (e.g., Google Cloud Natural Language API), which allows it to identify important evacuation sites and unavailable locations.

[1293] 3. Emotion analysis:

[1294] The server uses a sentiment analysis engine (e.g., IBM Watson Natural Language Understanding) to evaluate the emotional tone of posts, recognizing positive, negative, and neutral sentiment and increasing the credibility and urgency of information.

[1295] 4. Priority Calculation:

[1296] The server calculates the priority by taking into account traffic information and resource usage around the identified important locations. This is done using traffic information stored in a database (e.g., MySQL).

[1297] 5. Recovery plan generation:

[1298] Based on the priorities, a recovery plan is generated, which includes details on which locations should be restored and in what order.

[1299] 6. Notifications and Guidance:

[1300] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify emergency teams and users of emergency information. At the same time, users are also provided with guidance information such as evacuation procedures and safe routes.

[1301] Hardware and software usage examples

[1302] Hardware:

[1303] Smartphone (iOS or Android)

[1304] Server (Cloud service: AWS, Google Cloud)

[1305] software:

[1306] Social Media APIs (Twitter API, Facebook Graph API)

[1307] Sentiment analysis engine (IBM Watson Natural Language Understanding, Google Cloud Natural Language API)

[1308] Database (MySQL, PostgreSQL)

[1309] Cloud storage (AWS S3, Google Cloud Storage)

[1310] Push notification service (Firebase Cloud Messaging)

[1311] Specific examples

[1312] Specific examples are given below:

[1313] 1. Data Collection:

[1314] The server uses the Twitter API to collect tweets containing keywords such as "shelter" and "help."

[1315] 2. Data Analysis:

[1316] The server uses the Google Cloud Natural Language API to extract information such as "XX shelter is unavailable" from the collected tweets and adds XX shelter to a list as an important location.

[1317] 3. Emotion analysis:

[1318] The server uses IBM Watson to analyze the emotional tone of tweets, giving more weight to tweets that display a strong negative sentiment.

[1319] 4. Priority Calculation:

[1320] Based on the traffic information stored in the MySQL database, the server calculates the priority of base stations around the XX evacuation shelter and lists them in order of importance.

[1321] 5. Recovery plan generation:

[1322] Based on the priority, the base station that should be restored with the highest priority is identified, and specific restoration procedures are created.

[1323] 6. Notifications and Guidance:

[1324] Notify emergency response teams with emergency information and provide evacuation instructions and safe routes to users using Firebase Cloud Messaging.

[1325] Prompt Sentence Examples

[1326] Example of input sentence to generative AI model:

[1327] How can I collect disaster-related information from user posts, analyze that information, and assess its urgency?

[1328] Input data:

[1329] 1. Tweet text collected from social media platforms

[1330] 2. Keyword list (shelter, help, unusable, in trouble)

[1331] 3. User sentiment (positive, negative, neutral)

[1332] Output data:

[1333] 1. List of important shelters and points

[1334] 2. Prioritizing by cumulative emotional tone

[1335] 3. Notification to the response team

[1336] 4. User evacuation guide

[1337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1338] Step 1:

[1339] The device uses social media APIs to collect posts containing disaster-related keywords (e.g., "shelter" and "help") in real time. It connects to the social media platform (e.g., Twitter) using an API key and secret, and sends the collected post data to the server. The input is the keywords and API connection information, and the output is the collected social media post data.

[1340] Step 2:

[1341] The server analyzes the received social media post data using natural language processing tools (e.g., Google Cloud Natural Language API). It extracts posts containing specific keywords and phrases and identifies important evacuation shelters and unusable locations. The input is the collected social media post data, and the output is a list of important evacuation shelters and unusable locations.

[1342] Step 3:

[1343] The server applies a sentiment analysis engine (e.g., IBM Watson Natural Language Understanding) to information about important evacuation shelters and unavailable locations to evaluate the emotional tone of the posts. It recognizes positive, negative, and neutral emotions and evaluates the reliability and urgency of the information. The input is post data about identified evacuation shelters and locations, and the output is the sentiment evaluation results for each post.

[1344] Step 4:

[1345] The server calculates the priority of the identified important locations based on the emotional tone and traffic information. The server obtains traffic information stored in a database (e.g., MySQL) and combines it with the emotional evaluation results. The inputs are the emotional evaluation results and traffic information, and the output is a priority list of important locations.

[1346] Step 5:

[1347] The server generates a recovery plan based on the priority list. This plan includes specific instructions and a schedule for which sites should be restored and in what order. The input is the priority list, and the output is a recovery plan document.

[1348] Step 6:

[1349] The server uses a push notification service (e.g., Firebase Cloud Messaging) to notify response teams and users of emergency information, including a summary of the recovery plan and evacuation guide information. The input is the recovery plan document and emergency information, and the output is a push notification message.

[1350] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1351] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1352] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1353] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1354] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1355] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1356] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1357] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1358] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1359] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1360] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1361] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1362] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1363] 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.

[1364] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1365] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1366] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1367] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1368] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1369] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1370] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1371] The following is further disclosed regarding the above embodiment.

[1372] (Claim 1)

[1373] A means of collecting disaster-related information from social media;

[1374] A means for identifying key locations from the collected information;

[1375] A means for calculating a priority of a base station based on the identified important location;

[1376] A system comprising: means for generating a restoration plan for a base station based on priority.

[1377] (Claim 2)

[1378] 10. The system of claim 1, further comprising means for identifying evacuation shelters and unusable locations from information collected from social media.

[1379] (Claim 3)

[1380] 10. The system of claim 1, further comprising means for determining a priority of a base station based on traffic information.

[1381] "Example 1"

[1382] (Claim 1)

[1383] A means of collecting disaster-related information from social media;

[1384] A means of analyzing the collected information using a natural language processing model to identify important locations;

[1385] A means for calculating a priority of a base station based on the identified important location;

[1386] The system includes means for generating a restoration plan for the base station based on the determined priorities.

[1387] (Claim 2)

[1388] 10. The system of claim 1, further comprising means for identifying evacuation sites as important locations from information collected from social media.

[1389] (Claim 3)

[1390] 10. The system of claim 1, further comprising means for determining a priority of a base station based on traffic information and geographic importance.

[1391] "Application Example 1"

[1392] (Claim 1)

[1393] A means of collecting disaster-related information from social media;

[1394] A means for identifying key locations from the collected information;

[1395] A means for calculating a priority of a base station based on the identified important location;

[1396] means for generating a restoration plan for the base station based on the priority;

[1397] A means for collecting status reports from users using a smartphone;

[1398] A means of notifying users of disaster information in real time,

[1399] A system that includes a means for visualizing the progress of recovery on a user's device.

[1400] (Claim 2)

[1401] 10. The system of claim 1, further comprising means for identifying evacuation shelters and unusable locations from information collected from social media.

[1402] (Claim 3)

[1403] 10. The system of claim 1, further comprising means for determining a priority of a base station based on traffic information.

[1404] "Example 2: Combining Emotion Engines"

[1405] (Claim 1)

[1406] A means of collecting disaster-related data from social media; and

[1407] a means of identifying significant locations from the collected data;

[1408] means for calculating a priority of communication sites based on the identified critical locations;

[1409] means for generating a restoration plan for the communication base based on the priority;

[1410] A system including means for analyzing user sentiment and assessing the reliability of data.

[1411] (Claim 2)

[1412] 10. The system of claim 1, further comprising means for identifying evacuation shelters and unavailable locations from data collected from social media.

[1413] (Claim 3)

[1414] 2. The system according to claim 1, further comprising means for calculating a priority of the communication base based on communication traffic information.

[1415] "Application example 2 when combining emotion engines"

[1416] (Claim 1)

[1417] A means of collecting disaster-related information from social media;

[1418] A means for identifying key locations from the collected information;

[1419] A means for calculating a priority based on the identified critical locations;

[1420] means for generating a recovery plan based on the priority;

[1421] a means for assessing the credibility and urgency of information using a sentiment analysis engine;

[1422] A system that includes a means of notifying users and response teams of emergency information.

[1423] (Claim 2)

[1424] 10. The system of claim 1, further comprising means for identifying evacuation shelters and unavailable locations from information collected from social media.

[1425] (Claim 3)

[1426] 2. The system according to claim 1, further comprising means for setting priorities based on information on peripheral resources of the identified important locations, and generating an emergency response plan based on the priorities. [Explanation of symbols]

[1427] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting disaster-related information from social media; A means for identifying key locations from the collected information; A means for calculating a priority of a base station based on the identified important location; A system comprising: means for generating a restoration plan for a base station based on priority.

2. The system of claim 1 , further comprising means for identifying evacuation shelters and unusable locations from information collected from social media.

3. 2. The system of claim 1, further comprising means for determining a priority of a base station based on traffic information.

Images