System

Abstract

A system is provided.SOLUTION: The system includes a means for scraping social media data, a generation system artificial intelligence means for analyzing the collected social media data, a means for predicting communication traffic in real time on the basis of an analysis result, a means for providing communication traffic prediction data to a communication carrier or a disaster countermeasure organization, and a means for executing area tuning on the basis of the provided communication traffic prediction data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, with the increase in social media users, sudden increases in communication traffic during disasters and large-scale events have become a problem. This sudden increase can overload communication networks and cause communication failures. Furthermore, while rapid and accurate information provision and countermeasures are required during disasters, current prediction methods have issues with real-timeness and accuracy. For this reason, there is a need for a real-time communication traffic prediction system that will enable communication carriers and disaster response organizations to respond quickly. [Means for solving the problem]

[0005] The present invention provides a means for scraping and collecting social media data, a means for analyzing the collected data using generative artificial intelligence, and a means for predicting communication traffic in real time based on the analysis results. This allows communication traffic prediction data to be provided to telecommunications carriers and disaster response organizations, enabling enhanced area tuning and facility monitoring. The system also includes a means for classifying the collected data and assigning importance scores, thereby improving the accuracy of predictions. Furthermore, a dashboard is provided that displays the provided prediction data on a user interface, allowing for a visual understanding of the situation and enabling rapid response.

[0006] "Social Media Data" refers to information posted by users on social media platforms, including published text, images, videos, reactions, etc.

[0007] "Scraping" is a technique that uses a program to automatically obtain data from websites and applications on the Internet.

[0008] "Generative AI" is a type of AI technology that learns patterns based on large amounts of data and makes predictions and generates data. It is used to analyze natural language and generate data.

[0009] "Communication traffic" refers to the amount and flow of data sent and received over a communication network, and indicates the network usage and load.

[0010] "Area tuning" refers to adjusting communication network settings and resource allocation for a specific geographic area, as a means of responding to increases or decreases in traffic.

[0011] "Data classification" is the process of organizing and grouping collected data according to specific criteria or categories.

[0012] An "importance score" is a numerical indicator that evaluates the priority and importance of data based on its content and relevance.

[0013] "User interface" refers to all points of contact, such as screens and operating methods, that are used to exchange information between the user and the system.

[0014] A "dashboard" is an interface that visually displays important data and information to support quick decision-making. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[0037] Social Media Data Collection

[0038] server:

[0039] The server uses the APIs of social media platforms to collect relevant data. For example, the server uses the APIs of Twitter and Facebook to retrieve posts matching keywords such as "power outage," "live," and "earthquake." The retrieved data is stored in an internal database and prepared for analysis.

[0040] Data analysis

[0041] server:

[0042] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The generative AI uses natural language processing (NLP) technology to analyze the posts and classify them into categories (disasters, events, etc.).

[0043] Examples:

[0044] A post such as "Power outage in XX city" is classified as a "disaster" category, and the generative AI will rate its importance highly. In contrast, a post such as "Live concert at YY venue" is classified as an "event" category, and is considered a factor in increasing communication traffic.

[0045] Communications traffic forecast

[0046] server:

[0047] The server applies a traffic prediction model based on the results of the generative AI analysis. This predictive model combines historical traffic data with real-time posting data. It uses machine learning algorithms to predict future traffic fluctuations.

[0048] Examples:

[0049] If there are many posts such as "There was a power outage in XX City," the server will refer to similar cases in past data, predict a sudden increase in communication traffic in XX City, and propose load reduction measures for this area.

[0050] Providing forecast data

[0051] server:

[0052] The server provides forecast data to telecommunications carriers and disaster response organizations, which then display the data in real time via dashboards and APIs, allowing personnel to take immediate action.

[0053] Device:

[0054] The carrier's terminals receive the forecast data provided by the server and perform area tuning and strengthen equipment monitoring, thereby maintaining an optimal communication environment.

[0055] User:

[0056] General users can receive notifications from disaster response organizations and telecommunications carriers and take necessary actions. For example, information is provided that encourages appropriate actions depending on the situation, such as evacuation orders and refraining from using telecommunications.

[0057] Examples:

[0058] Based on the collected data and predicted communication traffic, disaster response organizations will issue emergency notifications and request users to take prompt action. Users will also be notified of measures such as limiting communication speeds to reduce communication load in specific areas.

[0059] As described above, the present invention is a system that analyzes social media data in real time to predict communication traffic and respond appropriately, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[0060] The processing flow will be explained below.

[0061] Step 1: Collect social media data

[0062] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[0063] Step 2: Preprocessing the data

[0064] Server: Removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process includes text normalization.

[0065] Step 3: Analyze the data

[0066] Server: Analyzes pre-processed data using generative artificial intelligence (AI). Specifically, it uses natural language processing (NLP) technology to classify posts into categories (disasters, events, etc.) and assigns an importance score to each post.

[0067] Step 4: Generate a predictive model for communication traffic

[0068] Server: Integrates historical communication traffic data with real-time social media data and uses machine learning algorithms to build a communication traffic prediction model. The server trains the prediction model using a training dataset and verifies the accuracy of the model.

[0069] Step 5: Generate prediction data

[0070] Server: Using the constructed prediction model, it predicts communication traffic based on collected and analyzed real-time data. The prediction results show specific increases or decreases in traffic for specific areas.

[0071] Step 6: Provide traffic forecast data

[0072] Server: Provides forecast data to telecommunications carriers and disaster response organizations. The server updates a dashboard that displays the forecast data in a user interface and provides data through an API endpoint.

[0073] Step 7: Area Tuning

[0074] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. For example, it allocates additional network resources to specific areas to reduce communication load.

[0075] Step 8: Receive and respond to notifications

[0076] Users: General users receive notifications from disaster response organizations and telecommunications carriers. For example, they can take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[0077] Step 9: Building a feedback loop

[0078] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[0079] These are the specific processing steps of this system. This system analyzes social media data in real time and predicts increases in communication traffic, enabling quick and effective responses.

[0080] Example 1

[0081] 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."

[0082] There is a need to effectively utilize real-time information on social media to quickly and accurately predict communication traffic and encourage appropriate responses from telecommunications carriers and disaster response organizations. However, conventional technologies have not fully automated the collection and analysis of social media data, making it difficult to predict communication traffic in real time and implement appropriate responses.

[0083] 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.

[0084] In this invention, the server includes means for acquiring social media data, means using a generative artificial intelligence module to analyze the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing the predicted communication traffic data to a telecommunications carrier or a disaster response organization, and means for performing area tuning based on the provided communication traffic prediction data, thereby enabling real-time analysis of the collected data and rapid prediction and response to communication traffic.

[0085] "Social media data" refers to digital content, such as text, images, and videos, that users post or share on online platforms, such as social networking services.

[0086] "Means of collection" refers to devices or software programs used to collect data from social media platforms using APIs or scraping techniques based on specific keywords or hashtags.

[0087] "Generative AI Module" refers to software or systems that implement artificial intelligence techniques used to process and analyze collected data and make classifications and predictions.

[0088] "Natural language processing" refers to the technology of analyzing human language and understanding and extracting its meaning, and is used to analyze and classify text data.

[0089] "Communications traffic" refers to the amount of data passing through a particular network or communication line, usually measured in units of time.

[0090] "Prediction means" refers to a device or program that uses machine learning or statistical models to estimate future fluctuations in communication traffic based on collected and analyzed data.

[0091] "Means of providing" refers to the equipment or system that presents and transmits collected, analyzed, and predicted data to telecommunications carriers and disaster response organizations.

[0092] "Area tuning" refers to adjustments to optimize the communications infrastructure in a specific area based on predictive data, such as base station placement and bandwidth allocation.

[0093] A "dashboard" refers to a user interface that visualizes collected and analyzed data and displays it to relevant parties in real time.

[0094] "API" stands for Application Program Interface, which provides a way for software applications to communicate with other software services.

[0095] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[0096] Social Media Data Collection

[0097] server:

[0098] The server collects relevant data using APIs of social media platforms, specifically, posts based on keywords such as "power outage," "live," and "earthquake" via Twitter and other social media APIs, and stores the data in an internal database for subsequent analysis.

[0099] Data analysis

[0100] server:

[0101] The server sends the collected social media data to a generative artificial intelligence (AI) module, which analyzes the content of posts using natural language processing (NLP) technology. This generative AI module classifies the retrieved posts into categories such as "disaster" and "event," and then scores the importance of each post. For example, a post about "power outage in XX city" would be classified in the disaster category and assigned a high importance rating.

[0102] Communications traffic forecast

[0103] server:

[0104] Based on the analyzed data, the server applies a predictive model that combines past communication traffic data with real-time posted data. A machine learning algorithm is used to predict future fluctuations in communication traffic. This prediction allows communication carriers and disaster response organizations to take measures in advance. For example, if there are many posts saying "There was a power outage in XX city," the server will predict a sudden increase in communication traffic in XX city based on similar cases in the past and propose load reduction measures for this area.

[0105] Providing forecast data

[0106] server:

[0107] The server provides predicted communication traffic data to telecommunications carriers and disaster response organizations. The data is displayed and shared in real time via a dashboard and API. Alerts are also sent to encourage specific countermeasures.

[0108] Device:

[0109] The carrier's terminals acquire the forecast data provided by the server and perform area tuning and enhanced monitoring of the communications infrastructure to maintain an optimal communications environment. Based on the acquired forecast data, the terminals perform specific resource management such as base station placement and bandwidth adjustment.

[0110] User:

[0111] Ordinary users receive notifications from disaster response organizations and telecommunications carriers. These notifications include evacuation orders and recommended actions such as refraining from using communications. This allows users to take prompt and appropriate action. As a specific example, disaster response organizations issue emergency notifications based on collected data and predicted communications traffic, requesting users to respond promptly. In addition, users are notified of measures such as limiting communication speeds to reduce communications load in specific areas.

[0112] Example prompt sentence:

[0113] "There have been reports of a power outage in XX city. Please tell me the expected communication traffic and countermeasures."

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] server:

[0117] Collects social media data. The server queries the API of a social media platform using specific keywords (e.g., "power outage," "live," "earthquake"). A list of keywords and a timestamp are used as input. The post data returned from the API is received and stored in a database. The output is the stored social media data. Specifically, the query is run every minute to collect new posts.

[0118] Step 2:

[0119] server:

[0120] The collected data is analyzed. The server retrieves the collected social media data from its internal database and sends it to the generative AI module. The input is the collected social media data. The generative AI module uses natural language processing (NLP) technology to analyze the content of posts, classifying them into categories such as "disaster" and "event," and assigning an importance score to each post. The output is the categorized and importance-assigned analysis result data. Specifically, the generative AI module classifies the post "Power outage in XX city" into the disaster category and assigns a high importance score.

[0121] Step 3:

[0122] server:

[0123] Predicts communication traffic. The server applies a predictive model based on the analysis results of the generative AI module. The input is categorized social media data and past communication traffic data. A machine learning algorithm (e.g., random forest, LSTM) is used to predict future fluctuations in communication traffic. The output is predicted communication traffic data. Specifically, it analyzes a large number of posted data items saying "A power outage has occurred in XX city" and predicts a sudden increase in communication traffic in that area.

[0124] Step 4:

[0125] server:

[0126] Provides predicted communication traffic data. The server prepares a dashboard and API to provide predicted data to telecommunications carriers and disaster response organizations. The input is predicted communication traffic data. The output is real-time data displayed through the dashboard and API. Specifically, the predicted communication traffic data is displayed on the dashboard and updated in real time.

[0127] Step 5:

[0128] Device:

[0129] The carrier's terminal obtains the forecast data provided by the server and performs area tuning. The input is the forecast data provided by the server. The output is an optimized communications infrastructure. Specifically, the system readjusts the placement of communications base stations and bandwidth based on the forecast data to maintain communications quality in real time.

[0130] Step 6:

[0131] User:

[0132] Ordinary users receive notifications from telecommunications carriers and disaster response organizations and take the necessary action. The input is the received notification. The output is the specific action the user takes (e.g., evacuation, refraining from using communications). Specifically, if a disaster response organization notifies the user that "There is a power outage in XX city, so please evacuate to a safe location," the user will evacuate promptly.

[0133] (Application example 1)

[0134] 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."

[0135] In modern society, with the spread of social media, a huge amount of information is being circulated in real time. It is extremely important to utilize this information to predict communication traffic and local security situations and take appropriate measures. However, with conventional methods, it has been difficult to efficiently collect and analyze this data and realize real-time predictions and responses. Furthermore, there has been no established method for quickly notifying and responding to sudden increases in communication traffic or sudden changes in security situations.

[0136] 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.

[0137] In this invention, the server includes a means for scraping social media data, a generative artificial intelligence means for analyzing the collected social media data, a means for predicting communication traffic in real time based on the analysis results, and a means for sending notifications to users based on the predicted local security situation, thereby enabling real-time communication traffic prediction and local security situation prediction and appropriate responses based on the predictions.

[0138] "Social media data" refers to digital information such as text, images, and videos posted by users on social media platforms such as Twitter, Facebook, and Instagram.

[0139] "Scraping" is a technique for automatically extracting and collecting specific data from a website.

[0140] "Generative AI means" refers to algorithms or models that use AI technology to analyze input data and generate new information from the results.

[0141] "Analysis" is the process of classifying and organizing collected data according to a specific purpose and discovering meanings and trends.

[0142] "Communication traffic" refers to the amount of data sent and received over a communication network within a given period of time.

[0143] "Forecasting" is the act of estimating possible future events or situations based on current and past data.

[0144] "Telecommunications carrier" refers to a company or organization that provides communications services such as internet and telephone.

[0145] A "disaster management organization" is a public or private organization that works to mitigate damage and ensure rapid recovery when natural or man-made disasters occur.

[0146] "Area tuning" is the process of optimizing communication network settings in a specific area.

[0147] "Regional security situation" refers to information about safety in a particular area, such as the crime rate and frequency of accidents.

[0148] "Notification" is the act of sending a message to inform a target person of specific information.

[0149] "User" refers to an individual or organization that uses this system.

[0150] A "user interface" is the means and display screen through which a computer system and its users interact with information.

[0151] "Dashboard" refers to a display screen that visually displays data in real time to facilitate monitoring and management.

[0152] This invention relates to a system that utilizes social media data to predict communication traffic and local security situations in real time and take appropriate measures. This system is realized by using the following multiple means.

[0153] First, the server uses scraping technology to collect data from social media platforms such as Twitter and Facebook. For example, it uses the Twitter API or Facebook Graph API to collect posts that match specific keywords (e.g., "power outage," "crime," "accident"), and stores the collected data in an internal database, ready for subsequent analysis.

[0154] The collected social media data is then analyzed by a generative artificial intelligence (AI) tool. This invention includes an analysis system that uses natural language processing (NLP) techniques, such as NLP libraries like spacy or NLTK. The AI ​​classifies these posts into categories ("Disaster," "Security," "Other") and assigns an importance score to each category.

[0155] Based on the analysis results, the server makes a prediction of communication traffic. This prediction is made using a machine learning algorithm that combines past traffic data with real-time posting data. For example, machine learning libraries such as Scikit-Learn and TensorFlow are used. The machine learning model analyzes past traffic patterns related to specific keywords and predicts future fluctuations in communication traffic.

[0156] Furthermore, local security situation predictions are also performed using the same method. The server analyzes the collected data and predicts the likelihood of crimes or accidents occurring in a specific area. Based on the results, appropriate notifications are sent to users. Notifications can be provided in the form of push notifications, email notifications, etc.

[0157] For example, if a large number of posts are collected stating "There is a power outage in XX city," the server can compare them with past data and predict a sudden increase in communication traffic in XX city. Also, if there are many posts about "crimes" or "accidents" in a particular area, a warning notification will be sent to users staying in that area.

[0158] Examples of prompts to use include:

[0159] "The latest information on power outages, crimes, and accidents is collected and analyzed using natural language processing. Each tweet is classified into a category (disaster, security, etc.) and the importance of each category is evaluated. Communication traffic is predicted based on past and real-time data, and countermeasures are proposed."

[0160] This allows users to understand the situation in real time and take appropriate action.By combining the server, generative AI, scraping technology, and natural language processing technology, an efficient and effective real-time prediction system is realized.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] Social Media Data Collection

[0164] The server uses the API of a social media platform (e.g., Twitter or Facebook) to collect relevant data. Specifically, it retrieves posts based on specific keywords (e.g., "power outage," "crime," or "accident"). The input to this process is the parameters of the API request, and the output is the retrieved post data. The server stores this data in an internal database.

[0165] Step 2:

[0166] Data analysis

[0167] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The input for this process is the post data obtained in step 1, and the output is the analysis results. Specifically, the generative AI uses natural language processing (NLP) technology to analyze the content of the posts, classifying each post into a category ("Disaster," "Security," "Other"), and assigning an importance score to each. This process uses an NLP library (e.g., spacy or NLTK).

[0168] Step 3:

[0169] Communications traffic forecast

[0170] The server applies a communication traffic prediction model based on the analysis results of the generative AI. The inputs to this process are the analysis results from step 2 and past traffic data, and the output is predicted communication traffic data. Specifically, a machine learning algorithm (e.g., Scikit-Learn or TensorFlow) is used to predict how communication traffic will fluctuate in the future.

[0171] Step 4:

[0172] Predicting the security situation

[0173] The server analyzes the collected data and predicts the frequency of crimes and accidents in a specific area. The input to this process is the social media data from step 1 and the analysis results from step 2, and the output is the predicted security situation in the area. The server analyzes the content of posts about "crimes" and "accidents" in a specific area to identify occurrence frequencies and trends.

[0174] Step 5:

[0175] Providing forecast data

[0176] The server provides the forecast data to telecommunications carriers and disaster response organizations. The input to this process is the forecast data from Steps 3 and 4, and the output is the provided forecast data. The server displays this data in real time via a dashboard or API, allowing personnel to take immediate action.

[0177] Step 6:

[0178] User Notification

[0179] The server sends a notification to the user based on the predicted local security situation. The input to this process is the security prediction data from step 4, and the output is a notification message to the user. The server provides users with risk information using push notifications and email notifications, encouraging them to take prompt action.

[0180] 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.

[0181] The present invention relates to a system that combines social media data, generative artificial intelligence, and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[0182] The following describes how to implement this system specifically.

[0183] Social Media Data Collection

[0184] server:

[0185] The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter, Facebook, etc. to obtain posts based on keywords (e.g., "power outage," "live," "earthquake"), and stores the obtained data in an internal database.

[0186] Data Preprocessing

[0187] server:

[0188] Remove unnecessary information from collected social media data, such as filtering out spam posts and duplicate data, and converting it into a format suitable for analysis. This process involves text normalization.

[0189] Data analysis

[0190] server:

[0191] The server analyzes the preprocessed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters, events, etc.) and assign an importance score to each post. In addition, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[0192] Examples:

[0193] A post such as "There is a power outage in XX city" is classified as a "disaster" category, and the generative AI gives it a high importance. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns it an emotion score.

[0194] Communications traffic forecast

[0195] server:

[0196] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[0197] Examples:

[0198] If there are many posts saying "There was a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[0199] Providing forecast data

[0200] server:

[0201] The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via a dashboard and API, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[0202] Device:

[0203] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[0204] User:

[0205] General users will receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and information to encourage appropriate actions depending on the situation, such as refraining from using telecommunications.

[0206] Examples:

[0207] Based on the collected data with high emotion scores and traffic forecast data, disaster response organizations can issue emergency notifications, requesting users to take prompt action, and notify users of measures such as limiting communication speeds to reduce communication load in specific areas.

[0208] As described above, the present invention is a system that uses social media data and an emotion engine to predict communication traffic and respond quickly, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[0209] The processing flow will be explained below.

[0210] Step 1: Collect social media data

[0211] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[0212] Step 2: Preprocessing the data

[0213] Server: This removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process involves techniques such as text normalization.

[0214] Step 3: Analyze the data

[0215] Server: The server uses a generative artificial intelligence (AI) and emotion engine to analyze the preprocessed data. The generative AI uses natural language processing (NLP) to classify posts into categories (disasters, events, etc.) and assign an importance score to each post. Meanwhile, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from posts and assigns an emotion score.

[0216] Examples:

[0217] A post saying "There is a power outage in XX city" is classified as a "disaster" and the generative AI rates it as important. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns a high emotion score.

[0218] Step 4: Traffic forecast

[0219] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model integrates historical traffic data with real-time posting data and uses machine learning algorithms to predict traffic fluctuations. Emotion scores are also incorporated into this model to improve prediction accuracy.

[0220] Examples:

[0221] If there are many posts saying "There is a power outage in XX city," the system will refer to past data and sentiment scores to predict a sudden increase in communication traffic in XX city.

[0222] Step 5: Generate prediction data

[0223] Server: Generates future traffic fluctuation data based on a predictive model. This data specifically indicates increases or decreases in traffic in specific areas.

[0224] Step 6: Provide traffic forecast data

[0225] Server: Provides predictive data to telecommunications carriers and disaster response organizations via dashboards and API endpoints. The dashboard also displays the results of the emotion engine's recognition, helping personnel understand the detailed situation.

[0226] Step 7: Area Tuning

[0227] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. Specifically, it allocates additional network resources to specific areas to avoid overload.

[0228] Step 8: Receive and respond to notifications

[0229] Users: General users receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and instructions to refrain from using communications.

[0230] Examples:

[0231] Disaster response agencies can use data with high emotion scores, such as anxiety and anger, to quickly send emergency notifications and encourage users to take prompt action.

[0232] Step 9: Building a feedback loop

[0233] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[0234] The above are the specific processing steps for implementing the present invention. This system enables real-time communication traffic prediction and rapid response by utilizing social media data and an emotion engine.

[0235] Example 2

[0236] 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."

[0237] In recent years, the amount of information disseminated on social media has increased, and during disasters and large-scale events, a large number of posts are often made in real time. This has resulted in a sudden increase in communication traffic, increasing the risk of communication networks becoming overloaded. However, conventional communication traffic management systems have had difficulty making real-time predictions and responding quickly. In particular, they were unable to predict traffic taking into account user emotions and the importance of information, and only inaccurate countermeasures could be implemented. For this reason, communication carriers and disaster response organizations are required to respond quickly and appropriately to prevent communication traffic overload.

[0238] 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.

[0239] In this invention, the server includes means for scraping social media data, means for preprocessing the collected social media data, means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing communication traffic prediction data to telecommunications carriers and disaster response organizations, and means for performing area tuning based on the provided communication traffic prediction data. This makes it possible to predict communication traffic in real time based on the analysis results of the social media data and provide highly accurate prediction data that takes into account importance scores and sentiment scores. This allows telecommunications carriers and disaster response organizations to respond quickly and appropriately and prevent communication network overload.

[0240] "Social media data" refers to content such as text, images, videos, and links posted by users on social networking services (SNS) and online platforms.

[0241] "Scraping" refers to the automated capture and extraction of website data, including using the APIs of social media platforms to gather data.

[0242] "Preprocessing" refers to the process of removing spam and duplicate data from collected data and converting it into a format suitable for analysis, including text normalization.

[0243] "Generative artificial intelligence (AI)" refers to machine learning algorithms that are trained to perform specific tasks, including analyzing social media data using natural language processing (NLP) techniques.

[0244] "Real-time" refers to processing and analysis occurring close to the moment data is generated, with extremely little delay.

[0245] "Communication traffic forecasting" refers to predicting future fluctuations in data transfer volume within a communication network based on collected and analyzed data.

[0246] "Telecommunications carrier" refers to a company or organization that provides and operates a telecommunications network, including fixed-line and mobile communications.

[0247] "Disaster response agencies" refer to public institutions and organizations that take response measures in response to natural disasters such as earthquakes and typhoons, as well as man-made disasters.

[0248] "Area Tuning" refers to the process of adjusting communication settings in a particular geographic area, including increasing or limiting communication capacity.

[0249] The "importance score" is a number that indicates how important a particular post is in the collected social media data. For example, posts in the "disaster" category are given a high score.

[0250] "Emotion score" refers to the numerical value of the intensity of emotions (e.g., joy, sadness, anger) extracted from social media posts. It is assigned by the emotion engine.

[0251] "User interface" refers to the screens and methods of operation that allow users to interact with a system, including dashboards.

[0252] A "dashboard" is an interface that visually displays multiple data points and analysis results, allowing managers to understand the situation in real time.

[0253] This invention is a system that collects social media data, predicts communication traffic in real time, and provides the results to telecommunications carriers and disaster response organizations. How to implement this system in concrete terms is explained below.

[0254] Social Media Data Collection

[0255] server:

[0256] The server collects relevant data using the APIs of social media platforms (e.g., Twitter and Facebook) in the following manner:

[0257] 1. Authentication to the API: The server uses the API key or access token of each social media to authenticate access to the API.

[0258] 2. Setting up keyword filters: The server sets up specific keywords such as "power outage," "live," and "earthquake."

[0259] 3. Performing data collection: The server collects relevant posts based on the set keywords and stores the acquired data in an internal database.

[0260] Data Preprocessing

[0261] server:

[0262] The server pre-processes the collected social media data. The specific details of the pre-processing are as follows:

[0263] 1. Spam filtering: The server detects and removes spam posts, for example, filtering out posts with repetitive content and advertisements.

[0264] 2. Removing duplicate data: Removing duplicates to make data collected in multiple places unique.

[0265] 3. Text normalization: The server corrects variations and typos in the text data and formats it consistently.

[0266] Data analysis

[0267] server:

[0268] The server analyzes the pre-processed data using generative artificial intelligence (AI) and an emotion engine. The specific analysis is as follows:

[0269] 1. Natural Language Processing (NLP): Generative AI uses natural language processing techniques to analyze posts and classify them into categories (e.g., disasters, events, etc.).

[0270] 2. Assigning importance scores: Each post is assigned an importance score. For example, "Power outage in XX city" is assigned a high importance score.

[0271] 3. Sentiment Analysis: The emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from collected posts and assigns an emotion score to each post.

[0272] Example: A generative AI classifies a post such as "There was a power outage in XX city" into the "disaster" category, and the emotion engine recognizes "anxiety" or "anger" from the post and assigns it an emotion score.

[0273] Communications traffic forecast

[0274] server:

[0275] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[0276] 1. Data integration: Integrate the analysis results of generative AI and emotion engines.

[0277] 2. Applying machine learning algorithms: Using the integrated data, we build a predictive model for communication traffic. We combine historical traffic data with real-time data and perform analysis.

[0278] 3. Bias verification and correction: Balance the predictive model as necessary to ensure it is not biased towards specific data.

[0279] Example: The server combines past traffic data for XX city with currently collected post data with high importance and high sentiment scores, such as "There was a power outage in XX city," to predict a sudden increase in traffic.

[0280] Providing forecast data

[0281] server:

[0282] The server provides the forecast data to telecommunications carriers and disaster response organizations. The specific procedure is as follows:

[0283] 1. Build a dashboard: Build a dashboard that can visualize the forecast data and set it up so that the data is updated in real time.

[0284] 2. API disclosure: We will publish an API endpoint to provide forecast data to telecommunications carriers and disaster response organizations.

[0285] 3. Alert function: Receives an alert when certain conditions are met (e.g., high sentiment score, traffic forecast exceeds a critical value).

[0286] Device:

[0287] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[0288] 1. Receiving data: Obtaining prediction data via API.

[0289] 2. Area Tuning: Adjust communication settings in specific areas based on predictive data.

[0290] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are expected.

[0291] User:

[0292] General users receive notifications from disaster response organizations and telecommunications carriers. The specific procedure is as follows:

[0293] 1. Receive emergency notifications: Receive emergency notifications on your smartphone or email.

[0294] 2. Promoting action: Based on the notification, take necessary actions such as evacuation and refraining from communication.

[0295] Example: Disaster management organizations send emergency notifications and instruct users to evacuate based on "power outage" data with a high emotional score and traffic forecast data. Telecommunications carriers also limit communication speeds in specific areas to reduce traffic loads.

[0296] Prompt Sentence Examples

[0297] Below are some example prompts to input to a generative AI model:

[0298] "Please collect data about outages from Twitter, assign a sentiment score to it, and predict traffic and display the results on a dashboard."

[0299] By using this prompt statement, you can check how the system processes and what data it will ultimately output.

[0300] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0301] Step 1:

[0302] Social Media Data Collection

[0303] server:

[0304] The server collects data using the APIs of social media platforms (e.g., Twitter, Facebook). The specific steps are as follows:

[0305] 1. Authentication to the API: The server authenticates using an API key and an access token. The input is the API key and the access token, and the output is an authentication token.

[0306] 2. Keyword filter setting: The server sets keywords such as "power outage," "live," "earthquake," etc. The input is a list of keywords, and the output is the filter conditions.

[0307] 3. Execute data collection: The server retrieves social media posts based on the set keywords. The input is the filter conditions, and the output is the collected post data. Specifically, it uses the Twitter API to collect tweets containing the keyword "power outage" in real time and saves them in a database.

[0308] Step 2:

[0309] Data Preprocessing

[0310] server:

[0311] The server pre-processes the collected social media data. The specific details of the pre-processing are as follows:

[0312] 1. Spam filtering: The server detects and removes spam submissions. The input is the collected submission data, and the output is the spam-cleaned data.

[0313] 2. Duplicate Data Removal: The server removes duplicate data. The input is the spam filtered data, and the output is the unique data.

[0314] 3. Text normalization: The server converts text data into a consistent format. The input is unique data, and the output is normalized data. As a specific operation, it arranges so that "power outage" can be correctly recognized even in different formats such as "teiden" or "power outage."

[0315] Step 3:

[0316] Analysis of data

[0317] Server:

[0318] The server analyzes data using generative artificial intelligence (AI) and an emotion engine. The specific content of the analysis is as follows.

[0319] 1. Natural language processing (NLP): The generative AI uses natural language processing technology to analyze the posted content and classify it into categories (e.g., disasters, events, etc.). The input is normalized data, and the output is categorized data.

[0320] [[ID=2?]] 2. Assignment of importance scores: The server assigns an importance score to each post. The input is categorized data, and the output is data with an assigned importance score.

[0321] 3. Sentiment analysis: The emotion engine recognizes the user's emotion from each post and assigns an emotion score. The input is data with an assigned importance score, and the output is data with an assigned emotion score. As a specific example, a post such as "A power outage occurred in XX City" is given a high importance and high emotion scores such as "uneasiness" and "anger."

[0322] Step 4:

[0323] Prediction of communication traffic

[0324] Server:

[0325] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[0326] 1. Data integration: Integrate the analysis results of the generative AI and the emotion engine. The input is data with importance and emotion scores, and the output is the integrated data.

[0327] 2. Applying machine learning algorithms: The server uses the integrated data to create a communication traffic prediction model. The input is the integrated data, and the output is the communication traffic prediction model.

[0328] 3. Bias verification and correction: The server adjusts the balance so that the prediction model is not biased towards specific data. The input is the prediction model, and the output is the balanced prediction model. As a specific example, the server uses past traffic data for XX city and real-time collected data such as "A power outage has occurred in XX city" to predict a sudden increase in traffic.

[0329] Step 5:

[0330] Providing forecast data

[0331] server:

[0332] The server provides the forecast data to telecommunications carriers and disaster response organizations. The procedure is as follows:

[0333] 1. Building a dashboard: We build a dashboard that can visualize the forecast data. The input is the communication traffic forecast model, and the output is a dashboard that is updated in real time.

[0334] 2. Exposing API: The server exposes an API endpoint for providing prediction data. The input is the traffic prediction model, and the output is the API endpoint.

[0335] 3. Alert function: The server sends an alert notification when a specific condition occurs (e.g., the sentiment score is high, or the traffic prediction exceeds a critical value). The input is the prediction data, and the output is the alert notification.

[0336] Device:

[0337] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[0338] 1. Receiving data: Receive prediction data through the API. The input is the API endpoint and the output is the prediction data.

[0339] 2. Area Tuning: Adjusting communication settings in a specific area based on predicted data. The input is the predicted data, and the output is the adjusted communication settings.

[0340] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are predicted. The input is forecast data, and the output is an enhanced monitoring system.

[0341] User:

[0342] General users will receive notifications from disaster response organizations and telecommunications carriers and take the following actions:

[0343] 1. Receiving emergency notifications: Receive emergency notifications via smartphone or email. The input is the alert notification, and the output is the notification content.

[0344] 2. Promoting action: Based on the content of the notification, actions such as evacuation or limiting communication are taken. The input is the notification content, and the output is the user's action. As a specific example, a disaster response organization sends out an emergency notification based on "power outage" data with a high emotional score and traffic prediction data, instructing users to evacuate quickly or limit communication.

[0345] (Application example 2)

[0346] 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."

[0347] In recent years, there has been an increasing number of cases of sudden increases in communication traffic due to disasters and large-scale events, and there is a need for an appropriate prediction system to respond quickly to these situations. A notification mechanism is also needed to prompt general users to take appropriate action in real time. Conventional systems have inadequate means for predicting communication traffic by combining social media data and users' emotional responses, making it difficult to respond appropriately to sudden increases in traffic.

[0348] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting social media data, generative artificial intelligence means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results and an emotion score by an emotion engine, means for providing communication traffic prediction data to a telecommunications carrier or a disaster response organization, means for performing area tuning based on the provided communication traffic prediction data and the real-time importance score, and means for sending a real-time notification to a user. This enables a quick and appropriate response to a sudden increase in communication traffic, improving the safety of users and the communication network.

[0349] "Social Media Data" refers to information such as user posts and comments obtained from social media platforms such as Twitter and Facebook.

[0350] "Generative AI means" refers to AI that uses natural language processing techniques to analyze data, particularly for text classification and sentiment analysis.

[0351] An "emotion engine" is an algorithm or software that recognizes a user's emotions (happiness, sadness, anger, etc.) from collected data and assigns an emotion score.

[0352] "Communication traffic forecasting" is the process of combining historical communication data with real-time posting data and using machine learning algorithms to predict future fluctuations in communication traffic.

[0353] A "communications carrier" is a company or organization that provides communications services such as telephone and internet.

[0354] "Disaster response agencies" are public institutions and organizations that take measures in the event of disasters such as earthquakes, floods, and typhoons.

[0355] "Area tuning" refers to dynamically changing and optimizing the settings and configuration of a communication network in a specific area.

[0356] The "importance score" is an index that quantitatively evaluates the urgency and importance of collected data.

[0357] "Real-time notification" is a function that provides users with information immediately when a specific event or situation occurs.

[0358] The present invention relates to a system that uses social media data, generative artificial intelligence (AI), and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[0359] Social Media Data Collection

[0360] Server: The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter and Facebook to retrieve posts based on specific keywords (e.g., "power outage," "live," "earthquake") and stores the retrieved data in an internal database.

[0361] Data Preprocessing

[0362] Server: Removes unnecessary information from collected social media data. Specifically, it filters out spam posts and duplicate data and converts it into a format suitable for analysis. This process includes text normalization.

[0363] Data analysis

[0364] Server: The server analyzes the preprocessed data using generative artificial intelligence (AI) and an emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters or events) and assigns an importance score to each post. Furthermore, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[0365] Communications traffic forecast

[0366] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[0367] Providing forecast data

[0368] Server: The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via dashboards and APIs, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[0369] Performing area tuning

[0370] Telecommunications carrier's terminal: The telecommunications carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communications environment.

[0371] Sending real-time notifications

[0372] Server and user device: The server sends real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[0373] Hardware and software used

[0374] Hardware: Cloud server, smartphone (iOS or Android)

[0375] Software: Python, Flask, Tweepy (server side), React Native, Axios (client side)

[0376] Specific examples

[0377] For example, if there are many posts saying "There is a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[0378] Prompt Sentence Examples

[0379] "Analyze data collected from social media based on keywords such as 'power outage,' 'earthquake,' and 'event,' and calculate a sentiment score and importance."

[0380] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0381] Step 1:

[0382] Social Media Data Collection

[0383] The server collects relevant data using APIs of social media platforms, such as Twitter and Facebook, to retrieve posts based on specific keywords (e.g., "power outage," "live," and "earthquake") and store them in an internal database.

[0384] Input: Social media platform API, specific keywords

[0385] Output: Collected social media data

[0386] What it does: The program uses the API key to retrieve social media data and saves it in JSON format.

[0387] Step 2:

[0388] Data Preprocessing

[0389] The server removes unnecessary information from the collected social media data, for example filtering out spam posts and duplicate data, and converts it into a format suitable for analysis. Text normalization also takes place at this stage.

[0390] Input: Collected social media data

[0391] Output: Preprocessed social media data

[0392] What you will do: Clean data using regular expressions and filtering algorithms to build a valid dataset.

[0393] Step 3:

[0394] Data analysis

[0395] The server analyzes the pre-processed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses NLP techniques to classify posts into categories (e.g., disasters or events) and assign importance scores. At the same time, the emotion engine recognizes users' emotions (e.g., joy, sadness, anger, etc.) and assigns emotion scores.

[0396] Input: Preprocessed social media data

[0397] Output: Analysis results (category classification, importance score, sentiment score)

[0398] What it does: Analyzes text using an NLP model to calculate categories and scores.

[0399] Step 4:

[0400] Communications traffic forecast

[0401] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. Past traffic data and real-time posting data are input into a machine learning algorithm to predict future traffic fluctuations.

[0402] Input: Analysis results, past traffic data

[0403] Output: Communication traffic forecast data

[0404] What it does: It uses machine learning algorithms to learn from data and generate predictive models.

[0405] Step 5:

[0406] Providing forecast data

[0407] The server provides telecommunications carriers and disaster response organizations with traffic forecast data, which is displayed in real time via a dashboard and API.

[0408] Input: Communication traffic forecast data

[0409] Output: Dashboard display data, API communication data

[0410] What it does: Formats the data, displays it in a dashboard, and serves it to an API endpoint.

[0411] Step 6:

[0412] Performing area tuning

[0413] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[0414] Input: Communication traffic forecast data

[0415] Output: Optimized communication network

[0416] Specific operation: Dynamically adjusts communication network settings based on predictive data to maintain optimal conditions.

[0417] Step 7:

[0418] Sending real-time notifications

[0419] The server and user device send real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[0420] Input: Importance score, sentiment score

[0421] Output: Real-time notification

[0422] Specific Actions: Use notifications to alert the user and provide specific instructions.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] [Second embodiment]

[0427] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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."

[0439] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[0440] Social Media Data Collection

[0441] server:

[0442] The server uses the APIs of social media platforms to collect relevant data. For example, the server uses the APIs of Twitter and Facebook to retrieve posts matching keywords such as "power outage," "live," and "earthquake." The retrieved data is stored in an internal database and prepared for analysis.

[0443] Data analysis

[0444] server:

[0445] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The generative AI uses natural language processing (NLP) technology to analyze the posts and classify them into categories (disasters, events, etc.).

[0446] Examples:

[0447] A post such as "Power outage in XX city" is classified as a "disaster" category, and the generative AI will rate its importance highly. In contrast, a post such as "Live concert at YY venue" is classified as an "event" category, and is considered a factor in increasing communication traffic.

[0448] Communications traffic forecast

[0449] server:

[0450] The server applies a traffic prediction model based on the results of the generative AI analysis. This predictive model combines historical traffic data with real-time posting data. It uses machine learning algorithms to predict future traffic fluctuations.

[0451] Examples:

[0452] If there are many posts such as "There was a power outage in XX City," the server will refer to similar cases in past data, predict a sudden increase in communication traffic in XX City, and propose load reduction measures for this area.

[0453] Providing forecast data

[0454] server:

[0455] The server provides forecast data to telecommunications carriers and disaster response organizations, which then display the data in real time via dashboards and APIs, allowing personnel to take immediate action.

[0456] Device:

[0457] The carrier's terminals receive the forecast data provided by the server and perform area tuning and strengthen equipment monitoring, thereby maintaining an optimal communication environment.

[0458] User:

[0459] General users can receive notifications from disaster response organizations and telecommunications carriers and take necessary actions. For example, information is provided that encourages appropriate actions depending on the situation, such as evacuation orders and refraining from using telecommunications.

[0460] Examples:

[0461] Based on the collected data and predicted communication traffic, disaster response organizations will issue emergency notifications and request users to take prompt action. Users will also be notified of measures such as limiting communication speeds to reduce communication load in specific areas.

[0462] As described above, the present invention is a system that analyzes social media data in real time to predict communication traffic and respond appropriately, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[0463] The processing flow will be explained below.

[0464] Step 1: Collect social media data

[0465] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[0466] Step 2: Preprocessing the data

[0467] Server: Removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process includes text normalization.

[0468] Step 3: Analyze the data

[0469] Server: Analyzes pre-processed data using generative artificial intelligence (AI). Specifically, it uses natural language processing (NLP) technology to classify posts into categories (disasters, events, etc.) and assigns an importance score to each post.

[0470] Step 4: Generate a predictive model for communication traffic

[0471] Server: Integrates historical communication traffic data with real-time social media data and uses machine learning algorithms to build a communication traffic prediction model. The server trains the prediction model using a training dataset and verifies the accuracy of the model.

[0472] Step 5: Generate prediction data

[0473] Server: Using the constructed prediction model, it predicts communication traffic based on collected and analyzed real-time data. The prediction results show specific increases or decreases in traffic for specific areas.

[0474] Step 6: Provide traffic forecast data

[0475] Server: Provides forecast data to telecommunications carriers and disaster response organizations. The server updates a dashboard that displays the forecast data in a user interface and provides data through an API endpoint.

[0476] Step 7: Area Tuning

[0477] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. For example, it allocates additional network resources to specific areas to reduce communication load.

[0478] Step 8: Receive and respond to notifications

[0479] Users: General users receive notifications from disaster response organizations and telecommunications carriers. For example, they can take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[0480] Step 9: Building a feedback loop

[0481] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[0482] These are the specific processing steps of this system. This system analyzes social media data in real time and predicts increases in communication traffic, enabling quick and effective responses.

[0483] Example 1

[0484] 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."

[0485] There is a need to effectively utilize real-time information on social media to quickly and accurately predict communication traffic and encourage appropriate responses from telecommunications carriers and disaster response organizations. However, conventional technologies have not fully automated the collection and analysis of social media data, making it difficult to predict communication traffic in real time and implement appropriate responses.

[0486] 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.

[0487] In this invention, the server includes means for acquiring social media data, means using a generative artificial intelligence module to analyze the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing the predicted communication traffic data to a telecommunications carrier or a disaster response organization, and means for performing area tuning based on the provided communication traffic prediction data, thereby enabling real-time analysis of the collected data and rapid prediction and response to communication traffic.

[0488] "Social media data" refers to digital content, such as text, images, and videos, that users post or share on online platforms, such as social networking services.

[0489] "Means of collection" refers to devices or software programs used to collect data from social media platforms using APIs or scraping techniques based on specific keywords or hashtags.

[0490] "Generative AI Module" refers to software or systems that implement artificial intelligence techniques used to process and analyze collected data and make classifications and predictions.

[0491] "Natural language processing" refers to the technology of analyzing human language and understanding and extracting its meaning, and is used to analyze and classify text data.

[0492] "Communications traffic" refers to the amount of data passing through a particular network or communication line, usually measured in units of time.

[0493] "Prediction means" refers to a device or program that uses machine learning or statistical models to estimate future fluctuations in communication traffic based on collected and analyzed data.

[0494] "Means of providing" refers to the equipment or system that presents and transmits collected, analyzed, and predicted data to telecommunications carriers and disaster response organizations.

[0495] "Area tuning" refers to adjustments to optimize the communications infrastructure in a specific area based on predictive data, such as base station placement and bandwidth allocation.

[0496] A "dashboard" refers to a user interface that visualizes collected and analyzed data and displays it to relevant parties in real time.

[0497] "API" stands for Application Program Interface, which provides a way for software applications to communicate with other software services.

[0498] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[0499] Social Media Data Collection

[0500] server:

[0501] The server collects relevant data using APIs of social media platforms, specifically, posts based on keywords such as "power outage," "live," and "earthquake" via Twitter and other social media APIs, and stores the data in an internal database for subsequent analysis.

[0502] Data analysis

[0503] server:

[0504] The server sends the collected social media data to a generative artificial intelligence (AI) module, which analyzes the content of posts using natural language processing (NLP) technology. This generative AI module classifies the retrieved posts into categories such as "disaster" and "event," and then scores the importance of each post. For example, a post about "power outage in XX city" would be classified in the disaster category and assigned a high importance rating.

[0505] Communications traffic forecast

[0506] server:

[0507] Based on the analyzed data, the server applies a predictive model that combines past communication traffic data with real-time posted data. A machine learning algorithm is used to predict future fluctuations in communication traffic. This prediction allows communication carriers and disaster response organizations to take measures in advance. For example, if there are many posts saying "There was a power outage in XX city," the server will predict a sudden increase in communication traffic in XX city based on similar cases in the past and propose load reduction measures for this area.

[0508] Providing forecast data

[0509] server:

[0510] The server provides predicted communication traffic data to telecommunications carriers and disaster response organizations. The data is displayed and shared in real time via a dashboard and API. Alerts are also sent to encourage specific countermeasures.

[0511] Device:

[0512] The carrier's terminals acquire the forecast data provided by the server and perform area tuning and enhanced monitoring of the communications infrastructure to maintain an optimal communications environment. Based on the acquired forecast data, the terminals perform specific resource management such as base station placement and bandwidth adjustment.

[0513] User:

[0514] Ordinary users receive notifications from disaster response organizations and telecommunications carriers. These notifications include evacuation orders and recommended actions such as refraining from using communications. This allows users to take prompt and appropriate action. As a specific example, disaster response organizations issue emergency notifications based on collected data and predicted communications traffic, requesting users to respond promptly. In addition, users are notified of measures such as limiting communication speeds to reduce communications load in specific areas.

[0515] Example prompt sentence:

[0516] "There have been reports of a power outage in XX city. Please tell me the expected communication traffic and countermeasures."

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

[0518] Step 1:

[0519] server:

[0520] Collects social media data. The server queries the API of a social media platform using specific keywords (e.g., "power outage," "live," "earthquake"). A list of keywords and a timestamp are used as input. The post data returned from the API is received and stored in a database. The output is the stored social media data. Specifically, the query is run every minute to collect new posts.

[0521] Step 2:

[0522] server:

[0523] The collected data is analyzed. The server retrieves the collected social media data from its internal database and sends it to the generative AI module. The input is the collected social media data. The generative AI module uses natural language processing (NLP) technology to analyze the content of posts, classifying them into categories such as "disaster" and "event," and assigning an importance score to each post. The output is the categorized and importance-assigned analysis result data. Specifically, the generative AI module classifies the post "Power outage in XX city" into the disaster category and assigns a high importance score.

[0524] Step 3:

[0525] server:

[0526] Predicts communication traffic. The server applies a predictive model based on the analysis results of the generative AI module. The input is categorized social media data and past communication traffic data. A machine learning algorithm (e.g., random forest, LSTM) is used to predict future fluctuations in communication traffic. The output is predicted communication traffic data. Specifically, it analyzes a large number of posted data items saying "A power outage has occurred in XX city" and predicts a sudden increase in communication traffic in that area.

[0527] Step 4:

[0528] server:

[0529] Provides predicted communication traffic data. The server prepares a dashboard and API to provide predicted data to telecommunications carriers and disaster response organizations. The input is predicted communication traffic data. The output is real-time data displayed through the dashboard and API. Specifically, the predicted communication traffic data is displayed on the dashboard and updated in real time.

[0530] Step 5:

[0531] Device:

[0532] The carrier's terminal obtains the forecast data provided by the server and performs area tuning. The input is the forecast data provided by the server. The output is an optimized communications infrastructure. Specifically, the system readjusts the placement of communications base stations and bandwidth based on the forecast data to maintain communications quality in real time.

[0533] Step 6:

[0534] User:

[0535] Ordinary users receive notifications from telecommunications carriers and disaster response organizations and take the necessary action. The input is the received notification. The output is the specific action the user takes (e.g., evacuation, refraining from using communications). Specifically, if a disaster response organization notifies the user that "There is a power outage in XX city, so please evacuate to a safe location," the user will evacuate promptly.

[0536] (Application example 1)

[0537] 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."

[0538] In modern society, with the spread of social media, a huge amount of information is being circulated in real time. It is extremely important to utilize this information to predict communication traffic and local security situations and take appropriate measures. However, with conventional methods, it has been difficult to efficiently collect and analyze this data and realize real-time predictions and responses. Furthermore, there has been no established method for quickly notifying and responding to sudden increases in communication traffic or sudden changes in security situations.

[0539] 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.

[0540] In this invention, the server includes a means for scraping social media data, a generative artificial intelligence means for analyzing the collected social media data, a means for predicting communication traffic in real time based on the analysis results, and a means for sending notifications to users based on the predicted local security situation, thereby enabling real-time communication traffic prediction and local security situation prediction and appropriate responses based on the predictions.

[0541] "Social media data" refers to digital information such as text, images, and videos posted by users on social media platforms such as Twitter, Facebook, and Instagram.

[0542] "Scraping" is a technique for automatically extracting and collecting specific data from a website.

[0543] "Generative AI means" refers to algorithms or models that use AI technology to analyze input data and generate new information from the results.

[0544] "Analysis" is the process of classifying and organizing collected data according to a specific purpose and discovering meanings and trends.

[0545] "Communication traffic" refers to the amount of data sent and received over a communication network within a given period of time.

[0546] "Forecasting" is the act of estimating possible future events or situations based on current and past data.

[0547] "Telecommunications carrier" refers to a company or organization that provides communications services such as internet and telephone.

[0548] A "disaster management organization" is a public or private organization that works to mitigate damage and ensure rapid recovery when natural or man-made disasters occur.

[0549] "Area tuning" is the process of optimizing communication network settings in a specific area.

[0550] "Regional security situation" refers to information about safety in a particular area, such as the crime rate and frequency of accidents.

[0551] "Notification" is the act of sending a message to inform a target person of specific information.

[0552] "User" refers to an individual or organization that uses this system.

[0553] A "user interface" is the means and display screen through which a computer system and its users interact with information.

[0554] "Dashboard" refers to a display screen that visually displays data in real time to facilitate monitoring and management.

[0555] This invention relates to a system that utilizes social media data to predict communication traffic and local security situations in real time and take appropriate measures. This system is realized by using the following multiple means.

[0556] First, the server uses scraping technology to collect data from social media platforms such as Twitter and Facebook. For example, it uses the Twitter API or Facebook Graph API to collect posts that match specific keywords (e.g., "power outage," "crime," "accident"), and stores the collected data in an internal database, ready for subsequent analysis.

[0557] The collected social media data is then analyzed by a generative artificial intelligence (AI) tool. This invention includes an analysis system that uses natural language processing (NLP) techniques, such as NLP libraries like spacy or NLTK. The AI ​​classifies these posts into categories ("Disaster," "Security," "Other") and assigns an importance score to each category.

[0558] Based on the analysis results, the server makes a prediction of communication traffic. This prediction is made using a machine learning algorithm that combines past traffic data with real-time posting data. For example, machine learning libraries such as Scikit-Learn and TensorFlow are used. The machine learning model analyzes past traffic patterns related to specific keywords and predicts future fluctuations in communication traffic.

[0559] Furthermore, local security situation predictions are also performed using the same method. The server analyzes the collected data and predicts the likelihood of crimes or accidents occurring in a specific area. Based on the results, appropriate notifications are sent to users. Notifications can be provided in the form of push notifications, email notifications, etc.

[0560] For example, if a large number of posts are collected stating "There is a power outage in XX city," the server can compare them with past data and predict a sudden increase in communication traffic in XX city. Also, if there are many posts about "crimes" or "accidents" in a particular area, a warning notification will be sent to users staying in that area.

[0561] Examples of prompts to use include:

[0562] "The latest information on power outages, crimes, and accidents is collected and analyzed using natural language processing. Each tweet is classified into a category (disaster, security, etc.) and the importance of each category is evaluated. Communication traffic is predicted based on past and real-time data, and countermeasures are proposed."

[0563] This allows users to understand the situation in real time and take appropriate action.By combining the server, generative AI, scraping technology, and natural language processing technology, an efficient and effective real-time prediction system is realized.

[0564] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0565] Step 1:

[0566] Social Media Data Collection

[0567] The server uses the API of a social media platform (e.g., Twitter or Facebook) to collect relevant data. Specifically, it retrieves posts based on specific keywords (e.g., "power outage," "crime," or "accident"). The input to this process is the parameters of the API request, and the output is the retrieved post data. The server stores this data in an internal database.

[0568] Step 2:

[0569] Data analysis

[0570] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The input for this process is the post data obtained in step 1, and the output is the analysis results. Specifically, the generative AI uses natural language processing (NLP) technology to analyze the content of the posts, classifying each post into a category ("Disaster," "Security," "Other"), and assigning an importance score to each. This process uses an NLP library (e.g., spacy or NLTK).

[0571] Step 3:

[0572] Communications traffic forecast

[0573] The server applies a communication traffic prediction model based on the analysis results of the generative AI. The inputs to this process are the analysis results from step 2 and past traffic data, and the output is predicted communication traffic data. Specifically, a machine learning algorithm (e.g., Scikit-Learn or TensorFlow) is used to predict how communication traffic will fluctuate in the future.

[0574] Step 4:

[0575] Predicting the security situation

[0576] The server analyzes the collected data and predicts the frequency of crimes and accidents in a specific area. The input to this process is the social media data from step 1 and the analysis results from step 2, and the output is the predicted security situation in the area. The server analyzes the content of posts about "crimes" and "accidents" in a specific area to identify occurrence frequencies and trends.

[0577] Step 5:

[0578] Providing forecast data

[0579] The server provides the forecast data to telecommunications carriers and disaster response organizations. The input to this process is the forecast data from Steps 3 and 4, and the output is the provided forecast data. The server displays this data in real time via a dashboard or API, allowing personnel to take immediate action.

[0580] Step 6:

[0581] User Notification

[0582] The server sends a notification to the user based on the predicted local security situation. The input to this process is the security prediction data from step 4, and the output is a notification message to the user. The server provides users with risk information using push notifications and email notifications, encouraging them to take prompt action.

[0583] 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.

[0584] The present invention relates to a system that combines social media data, generative artificial intelligence, and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[0585] The following describes how to implement this system specifically.

[0586] Social Media Data Collection

[0587] server:

[0588] The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter, Facebook, etc. to obtain posts based on keywords (e.g., "power outage," "live," "earthquake"), and stores the obtained data in an internal database.

[0589] Data Preprocessing

[0590] server:

[0591] Remove unnecessary information from collected social media data, such as filtering out spam posts and duplicate data, and converting it into a format suitable for analysis. This process involves text normalization.

[0592] Data analysis

[0593] server:

[0594] The server analyzes the preprocessed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters, events, etc.) and assign an importance score to each post. In addition, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[0595] Examples:

[0596] A post such as "There is a power outage in XX city" is classified as a "disaster" category, and the generative AI gives it a high importance. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns it an emotion score.

[0597] Communications traffic forecast

[0598] server:

[0599] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[0600] Examples:

[0601] If there are many posts saying "There was a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[0602] Providing forecast data

[0603] server:

[0604] The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via a dashboard and API, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[0605] Device:

[0606] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[0607] User:

[0608] General users will receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and information to encourage appropriate actions depending on the situation, such as refraining from using telecommunications.

[0609] Examples:

[0610] Based on the collected data with high emotion scores and traffic forecast data, disaster response organizations can issue emergency notifications, requesting users to take prompt action, and notify users of measures such as limiting communication speeds to reduce communication load in specific areas.

[0611] As described above, the present invention is a system that uses social media data and an emotion engine to predict communication traffic and respond quickly, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[0612] The processing flow will be explained below.

[0613] Step 1: Collect social media data

[0614] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[0615] Step 2: Preprocessing the data

[0616] Server: This removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process involves techniques such as text normalization.

[0617] Step 3: Analyze the data

[0618] Server: The server uses a generative artificial intelligence (AI) and emotion engine to analyze the preprocessed data. The generative AI uses natural language processing (NLP) to classify posts into categories (disasters, events, etc.) and assign an importance score to each post. Meanwhile, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from posts and assigns an emotion score.

[0619] Examples:

[0620] A post saying "There is a power outage in XX city" is classified as a "disaster" and the generative AI rates it as important. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns a high emotion score.

[0621] Step 4: Traffic forecast

[0622] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model integrates historical traffic data with real-time posting data and uses machine learning algorithms to predict traffic fluctuations. Emotion scores are also incorporated into this model to improve prediction accuracy.

[0623] Examples:

[0624] If there are many posts saying "There is a power outage in XX city," the system will refer to past data and sentiment scores to predict a sudden increase in communication traffic in XX city.

[0625] Step 5: Generate prediction data

[0626] Server: Generates future traffic fluctuation data based on a predictive model. This data specifically indicates increases or decreases in traffic in specific areas.

[0627] Step 6: Provide traffic forecast data

[0628] Server: Provides predictive data to telecommunications carriers and disaster response organizations via dashboards and API endpoints. The dashboard also displays the results of the emotion engine's recognition, helping personnel understand the detailed situation.

[0629] Step 7: Area Tuning

[0630] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. Specifically, it allocates additional network resources to specific areas to avoid overload.

[0631] Step 8: Receive and respond to notifications

[0632] Users: General users receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and instructions to refrain from using communications.

[0633] Examples:

[0634] Disaster response agencies can use data with high emotion scores, such as anxiety and anger, to quickly send emergency notifications and encourage users to take prompt action.

[0635] Step 9: Building a feedback loop

[0636] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[0637] The above are the specific processing steps for implementing the present invention. This system enables real-time communication traffic prediction and rapid response by utilizing social media data and an emotion engine.

[0638] Example 2

[0639] 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."

[0640] In recent years, the amount of information disseminated on social media has increased, and during disasters and large-scale events, a large number of posts are often made in real time. This has resulted in a sudden increase in communication traffic, increasing the risk of communication networks becoming overloaded. However, conventional communication traffic management systems have had difficulty making real-time predictions and responding quickly. In particular, they were unable to predict traffic taking into account user emotions and the importance of information, and only inaccurate countermeasures could be implemented. For this reason, communication carriers and disaster response organizations are required to respond quickly and appropriately to prevent communication traffic overload.

[0641] 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.

[0642] In this invention, the server includes means for scraping social media data, means for preprocessing the collected social media data, means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing communication traffic prediction data to telecommunications carriers and disaster response organizations, and means for performing area tuning based on the provided communication traffic prediction data. This makes it possible to predict communication traffic in real time based on the analysis results of the social media data and provide highly accurate prediction data that takes into account importance scores and sentiment scores. This allows telecommunications carriers and disaster response organizations to respond quickly and appropriately and prevent communication network overload.

[0643] "Social media data" refers to content such as text, images, videos, and links posted by users on social networking services (SNS) and online platforms.

[0644] "Scraping" refers to the automated capture and extraction of website data, including using the APIs of social media platforms to gather data.

[0645] "Preprocessing" refers to the process of removing spam and duplicate data from collected data and converting it into a format suitable for analysis, including text normalization.

[0646] "Generative artificial intelligence (AI)" refers to machine learning algorithms that are trained to perform specific tasks, including analyzing social media data using natural language processing (NLP) techniques.

[0647] "Real-time" refers to processing and analysis occurring close to the moment data is generated, with extremely little delay.

[0648] "Communication traffic forecasting" refers to predicting future fluctuations in data transfer volume within a communication network based on collected and analyzed data.

[0649] "Telecommunications carrier" refers to a company or organization that provides and operates a telecommunications network, including fixed-line and mobile communications.

[0650] "Disaster response agencies" refer to public institutions and organizations that take response measures in response to natural disasters such as earthquakes and typhoons, as well as man-made disasters.

[0651] "Area Tuning" refers to the process of adjusting communication settings in a particular geographic area, including increasing or limiting communication capacity.

[0652] The "importance score" is a number that indicates how important a particular post is in the collected social media data. For example, posts in the "disaster" category are given a high score.

[0653] "Emotion score" refers to the numerical value of the intensity of emotions (e.g., joy, sadness, anger) extracted from social media posts. It is assigned by the emotion engine.

[0654] "User interface" refers to the screens and methods of operation that allow users to interact with a system, including dashboards.

[0655] A "dashboard" is an interface that visually displays multiple data points and analysis results, allowing managers to understand the situation in real time.

[0656] This invention is a system that collects social media data, predicts communication traffic in real time, and provides the results to telecommunications carriers and disaster response organizations. How to implement this system in concrete terms is explained below.

[0657] Social Media Data Collection

[0658] server:

[0659] The server collects relevant data using the APIs of social media platforms (e.g., Twitter and Facebook) in the following manner:

[0660] 1. Authentication to the API: The server uses the API key or access token of each social media to authenticate access to the API.

[0661] 2. Setting up keyword filters: The server sets up specific keywords such as "power outage," "live," and "earthquake."

[0662] 3. Performing data collection: The server collects relevant posts based on the set keywords and stores the acquired data in an internal database.

[0663] Data Preprocessing

[0664] server:

[0665] The server pre-processes the collected social media data. The specific details of the pre-processing are as follows:

[0666] 1. Spam filtering: The server detects and removes spam posts, for example, filtering out posts with repetitive content and advertisements.

[0667] 2. Removing duplicate data: Removing duplicates to make data collected in multiple places unique.

[0668] 3. Text normalization: The server corrects variations and typos in the text data and formats it consistently.

[0669] Data analysis

[0670] server:

[0671] The server analyzes the pre-processed data using generative artificial intelligence (AI) and an emotion engine. The specific analysis is as follows:

[0672] 1. Natural Language Processing (NLP): Generative AI uses natural language processing techniques to analyze posts and classify them into categories (e.g., disasters, events, etc.).

[0673] 2. Assigning importance scores: Each post is assigned an importance score. For example, "Power outage in XX city" is assigned a high importance score.

[0674] 3. Sentiment Analysis: The emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from collected posts and assigns an emotion score to each post.

[0675] Example: A generative AI classifies a post such as "There was a power outage in XX city" into the "disaster" category, and the emotion engine recognizes "anxiety" or "anger" from the post and assigns it an emotion score.

[0676] Communications traffic forecast

[0677] server:

[0678] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[0679] 1. Data integration: Integrate the analysis results of generative AI and emotion engines.

[0680] 2. Applying machine learning algorithms: Using the integrated data, we build a predictive model for communication traffic. We combine historical traffic data with real-time data and perform analysis.

[0681] 3. Bias verification and correction: Balance the predictive model as necessary to ensure it is not biased towards specific data.

[0682] Example: The server combines past traffic data for XX city with currently collected post data with high importance and high sentiment scores, such as "There was a power outage in XX city," to predict a sudden increase in traffic.

[0683] Providing forecast data

[0684] server:

[0685] The server provides the forecast data to telecommunications carriers and disaster response organizations. The specific procedure is as follows:

[0686] 1. Build a dashboard: Build a dashboard that can visualize the forecast data and set it up so that the data is updated in real time.

[0687] 2. API disclosure: We will publish an API endpoint to provide forecast data to telecommunications carriers and disaster response organizations.

[0688] 3. Alert function: Receives an alert when certain conditions are met (e.g., high sentiment score, traffic forecast exceeds a critical value).

[0689] Device:

[0690] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[0691] 1. Receiving data: Obtaining prediction data via API.

[0692] 2. Area Tuning: Adjust communication settings in specific areas based on predictive data.

[0693] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are expected.

[0694] User:

[0695] General users receive notifications from disaster response organizations and telecommunications carriers. The specific procedure is as follows:

[0696] 1. Receive emergency notifications: Receive emergency notifications on your smartphone or email.

[0697] 2. Promoting action: Based on the notification, take necessary actions such as evacuation and refraining from communication.

[0698] Example: Disaster management organizations send emergency notifications and instruct users to evacuate based on "power outage" data with a high emotional score and traffic forecast data. Telecommunications carriers also limit communication speeds in specific areas to reduce traffic loads.

[0699] Prompt Sentence Examples

[0700] Below are some example prompts to input to a generative AI model:

[0701] "Please collect data about outages from Twitter, assign a sentiment score to it, and predict traffic and display the results on a dashboard."

[0702] By using this prompt statement, you can check how the system processes and what data it will ultimately output.

[0703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0704] Step 1:

[0705] Social Media Data Collection

[0706] server:

[0707] The server collects data using the APIs of social media platforms (e.g., Twitter, Facebook). The specific steps are as follows:

[0708] 1. Authentication to the API: The server authenticates using an API key and an access token. The input is the API key and the access token, and the output is an authentication token.

[0709] 2. Keyword filter setting: The server sets keywords such as "power outage," "live," "earthquake," etc. The input is a list of keywords, and the output is the filter conditions.

[0710] 3. Execution of Data Collection: The server retrieves social media posts based on the set keywords. The input is the filtering condition, and the output is the collected post data. As a specific operation, it uses the Twitter API to collect tweets containing the keyword "power outage" in real time and saves them in the database.

[0711] Step 2:

[0712] Preprocessing of Data

[0713] Server:

[0714] The server preprocesses the collected social media data. The specific content of the preprocessing is as follows.

[0715] 1. Spam Filtering: The server detects and deletes spam posts. The input is the collected post data, and the output is the data with spam removed.

[0716] 2. Duplicate Data Removal: The server removes duplicate data. The input is the data after spam filtering, and the output is the data made unique.

[0717] 3. Text Normalization: The server converts the text data into a consistent format. The input is the data made unique, and the output is the normalized data. As a specific operation, it arranges so that "power outage" can be correctly recognized even in different forms such as "ていでん" or "停電。".

[0718] Step 3:

[0719] Data Analysis

[0720] Server:

[0721] The server analyzes the data using generative artificial intelligence (AI) and an emotion engine. The specific content of the analysis is as follows.

[0722] 1. Natural Language Processing (NLP): Generative AI uses natural language processing techniques to analyze posts and classify them into categories (e.g., disasters, events, etc.). The input is normalized data, and the output is categorized data.

[0723] 2. Importance Score Assignment: The server assigns an importance score to each post. The input is the categorized data, and the output is the data with the importance score assigned.

[0724] 3. Sentiment analysis: The emotion engine recognizes the user's emotions from each post and assigns an emotion score. The input is data with an importance score assigned, and the output is data with an emotion score assigned. For example, a post saying "There was a power outage in XX city" is assigned a high importance and a high emotion score such as "anxiety" or "anger."

[0725] Step 4:

[0726] Communications traffic forecast

[0727] server:

[0728] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[0729] 1. Data integration: Integrate the analysis results of the generative AI and the emotion engine. The input is data with importance and emotion scores, and the output is the integrated data.

[0730] 2. Applying machine learning algorithms: The server uses the integrated data to create a communication traffic prediction model. The input is the integrated data, and the output is the communication traffic prediction model.

[0731] 3. Bias verification and correction: The server adjusts the balance so that the prediction model is not biased towards specific data. The input is the prediction model, and the output is the balanced prediction model. As a specific example, the server uses past traffic data for XX city and real-time collected data such as "A power outage has occurred in XX city" to predict a sudden increase in traffic.

[0732] Step 5:

[0733] Providing forecast data

[0734] server:

[0735] The server provides the forecast data to telecommunications carriers and disaster response organizations. The procedure is as follows:

[0736] 1. Building a dashboard: We build a dashboard that can visualize the forecast data. The input is the communication traffic forecast model, and the output is a dashboard that is updated in real time.

[0737] 2. Exposing API: The server exposes an API endpoint for providing prediction data. The input is the traffic prediction model, and the output is the API endpoint.

[0738] 3. Alert function: The server sends an alert notification when a specific condition occurs (e.g., the sentiment score is high, or the traffic prediction exceeds a critical value). The input is the prediction data, and the output is the alert notification.

[0739] Device:

[0740] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[0741] 1. Receiving data: Receive prediction data through the API. The input is the API endpoint and the output is the prediction data.

[0742] 2. Area Tuning: Adjusting communication settings in a specific area based on predicted data. The input is the predicted data, and the output is the adjusted communication settings.

[0743] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are predicted. The input is forecast data, and the output is an enhanced monitoring system.

[0744] User:

[0745] General users will receive notifications from disaster response organizations and telecommunications carriers and take the following actions:

[0746] 1. Receiving emergency notifications: Receive emergency notifications via smartphone or email. The input is the alert notification, and the output is the notification content.

[0747] 2. Promoting action: Based on the content of the notification, actions such as evacuation or limiting communication are taken. The input is the notification content, and the output is the user's action. As a specific example, a disaster response organization sends out an emergency notification based on "power outage" data with a high emotional score and traffic prediction data, instructing users to evacuate quickly or limit communication.

[0748] (Application example 2)

[0749] 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."

[0750] In recent years, there has been an increasing number of cases of sudden increases in communication traffic due to disasters and large-scale events, and there is a need for an appropriate prediction system to respond quickly to these situations. A notification mechanism is also needed to prompt general users to take appropriate action in real time. Conventional systems have inadequate means for predicting communication traffic by combining social media data and users' emotional responses, making it difficult to respond appropriately to sudden increases in traffic.

[0751] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting social media data, generative artificial intelligence means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results and an emotion score by an emotion engine, means for providing communication traffic prediction data to a telecommunications carrier or a disaster response organization, means for performing area tuning based on the provided communication traffic prediction data and the real-time importance score, and means for sending a real-time notification to a user. This enables a quick and appropriate response to a sudden increase in communication traffic, improving the safety of users and the communication network.

[0752] "Social Media Data" refers to information such as user posts and comments obtained from social media platforms such as Twitter and Facebook.

[0753] "Generative AI means" refers to AI that uses natural language processing techniques to analyze data, particularly for text classification and sentiment analysis.

[0754] An "emotion engine" is an algorithm or software that recognizes a user's emotions (happiness, sadness, anger, etc.) from collected data and assigns an emotion score.

[0755] "Communication traffic forecasting" is the process of combining historical communication data with real-time posting data and using machine learning algorithms to predict future fluctuations in communication traffic.

[0756] A "communications carrier" is a company or organization that provides communications services such as telephone and internet.

[0757] "Disaster response agencies" are public institutions and organizations that take measures in the event of disasters such as earthquakes, floods, and typhoons.

[0758] "Area tuning" refers to dynamically changing and optimizing the settings and configuration of a communication network in a specific area.

[0759] The "importance score" is an index that quantitatively evaluates the urgency and importance of collected data.

[0760] "Real-time notification" is a function that provides users with information immediately when a specific event or situation occurs.

[0761] The present invention relates to a system that uses social media data, generative artificial intelligence (AI), and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[0762] Social Media Data Collection

[0763] Server: The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter and Facebook to retrieve posts based on specific keywords (e.g., "power outage," "live," "earthquake") and stores the retrieved data in an internal database.

[0764] Data Preprocessing

[0765] Server: Removes unnecessary information from collected social media data. Specifically, it filters out spam posts and duplicate data and converts it into a format suitable for analysis. This process includes text normalization.

[0766] Data analysis

[0767] Server: The server analyzes the preprocessed data using generative artificial intelligence (AI) and an emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters or events) and assigns an importance score to each post. Furthermore, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[0768] Communications traffic forecast

[0769] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[0770] Providing forecast data

[0771] Server: The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via dashboards and APIs, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[0772] Performing area tuning

[0773] Telecommunications carrier's terminal: The telecommunications carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communications environment.

[0774] Sending real-time notifications

[0775] Server and user device: The server sends real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[0776] Hardware and software used

[0777] Hardware: Cloud server, smartphone (iOS or Android)

[0778] Software: Python, Flask, Tweepy (server side), React Native, Axios (client side)

[0779] Specific examples

[0780] For example, if there are many posts saying "There is a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[0781] Prompt Sentence Examples

[0782] "Analyze data collected from social media based on keywords such as 'power outage,' 'earthquake,' and 'event,' and calculate a sentiment score and importance."

[0783] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0784] Step 1:

[0785] Social Media Data Collection

[0786] The server collects relevant data using APIs of social media platforms, such as Twitter and Facebook, to retrieve posts based on specific keywords (e.g., "power outage," "live," and "earthquake") and store them in an internal database.

[0787] Input: Social media platform API, specific keywords

[0788] Output: Collected social media data

[0789] What it does: The program uses the API key to retrieve social media data and saves it in JSON format.

[0790] Step 2:

[0791] Data Preprocessing

[0792] The server removes unnecessary information from the collected social media data, for example filtering out spam posts and duplicate data, and converts it into a format suitable for analysis. Text normalization also takes place at this stage.

[0793] Input: Collected social media data

[0794] Output: Preprocessed social media data

[0795] What you will do: Clean data using regular expressions and filtering algorithms to build a valid dataset.

[0796] Step 3:

[0797] Data analysis

[0798] The server analyzes the pre-processed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses NLP techniques to classify posts into categories (e.g., disasters or events) and assign importance scores. At the same time, the emotion engine recognizes users' emotions (e.g., joy, sadness, anger, etc.) and assigns emotion scores.

[0799] Input: Preprocessed social media data

[0800] Output: Analysis results (category classification, importance score, sentiment score)

[0801] What it does: Analyzes text using an NLP model to calculate categories and scores.

[0802] Step 4:

[0803] Communications traffic forecast

[0804] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. Past traffic data and real-time posting data are input into a machine learning algorithm to predict future traffic fluctuations.

[0805] Input: Analysis results, past traffic data

[0806] Output: Communication traffic forecast data

[0807] What it does: It uses machine learning algorithms to learn from data and generate predictive models.

[0808] Step 5:

[0809] Providing forecast data

[0810] The server provides telecommunications carriers and disaster response organizations with traffic forecast data, which is displayed in real time via a dashboard and API.

[0811] Input: Communication traffic forecast data

[0812] Output: Dashboard display data, API communication data

[0813] What it does: Formats the data, displays it in a dashboard, and serves it to an API endpoint.

[0814] Step 6:

[0815] Performing area tuning

[0816] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[0817] Input: Communication traffic forecast data

[0818] Output: Optimized communication network

[0819] Specific operation: Dynamically adjusts communication network settings based on predictive data to maintain optimal conditions.

[0820] Step 7:

[0821] Sending real-time notifications

[0822] The server and user device send real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[0823] Input: Importance score, sentiment score

[0824] Output: Real-time notification

[0825] Specific Actions: Use notifications to alert the user and provide specific instructions.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] [Third embodiment]

[0830] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0831] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0832] 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).

[0833] 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.

[0834] 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.

[0835] 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).

[0836] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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."

[0842] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[0843] Social Media Data Collection

[0844] server:

[0845] The server uses the APIs of social media platforms to collect relevant data. For example, the server uses the APIs of Twitter and Facebook to retrieve posts matching keywords such as "power outage," "live," and "earthquake." The retrieved data is stored in an internal database and prepared for analysis.

[0846] Data analysis

[0847] server:

[0848] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The generative AI uses natural language processing (NLP) technology to analyze the posts and classify them into categories (disasters, events, etc.).

[0849] Examples:

[0850] A post such as "Power outage in XX city" is classified as a "disaster" category, and the generative AI will rate its importance highly. In contrast, a post such as "Live concert at YY venue" is classified as an "event" category, and is considered a factor in increasing communication traffic.

[0851] Communications traffic forecast

[0852] server:

[0853] The server applies a traffic prediction model based on the results of the generative AI analysis. This predictive model combines historical traffic data with real-time posting data. It uses machine learning algorithms to predict future traffic fluctuations.

[0854] Examples:

[0855] If there are many posts such as "There was a power outage in XX City," the server will refer to similar cases in past data, predict a sudden increase in communication traffic in XX City, and propose load reduction measures for this area.

[0856] Providing forecast data

[0857] server:

[0858] The server provides forecast data to telecommunications carriers and disaster response organizations, which then display the data in real time via dashboards and APIs, allowing personnel to take immediate action.

[0859] Device:

[0860] The carrier's terminals receive the forecast data provided by the server and perform area tuning and strengthen equipment monitoring, thereby maintaining an optimal communication environment.

[0861] User:

[0862] General users can receive notifications from disaster response organizations and telecommunications carriers and take necessary actions. For example, information is provided that encourages appropriate actions depending on the situation, such as evacuation orders and refraining from using telecommunications.

[0863] Examples:

[0864] Based on the collected data and predicted communication traffic, disaster response organizations will issue emergency notifications and request users to take prompt action. Users will also be notified of measures such as limiting communication speeds to reduce communication load in specific areas.

[0865] As described above, the present invention is a system that analyzes social media data in real time to predict communication traffic and respond appropriately, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[0866] The processing flow will be explained below.

[0867] Step 1: Collect social media data

[0868] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[0869] Step 2: Preprocessing the data

[0870] Server: Removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process includes text normalization.

[0871] Step 3: Analyze the data

[0872] Server: Analyzes pre-processed data using generative artificial intelligence (AI). Specifically, it uses natural language processing (NLP) technology to classify posts into categories (disasters, events, etc.) and assigns an importance score to each post.

[0873] Step 4: Generate a predictive model for communication traffic

[0874] Server: Integrates historical communication traffic data with real-time social media data and uses machine learning algorithms to build a communication traffic prediction model. The server trains the prediction model using a training dataset and verifies the accuracy of the model.

[0875] Step 5: Generate prediction data

[0876] Server: Using the constructed prediction model, it predicts communication traffic based on collected and analyzed real-time data. The prediction results show specific increases or decreases in traffic for specific areas.

[0877] Step 6: Provide traffic forecast data

[0878] Server: Provides forecast data to telecommunications carriers and disaster response organizations. The server updates a dashboard that displays the forecast data in a user interface and provides data through an API endpoint.

[0879] Step 7: Area Tuning

[0880] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. For example, it allocates additional network resources to specific areas to reduce communication load.

[0881] Step 8: Receive and respond to notifications

[0882] Users: General users receive notifications from disaster response organizations and telecommunications carriers. For example, they can take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[0883] Step 9: Building a feedback loop

[0884] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[0885] These are the specific processing steps of this system. This system analyzes social media data in real time and predicts increases in communication traffic, enabling quick and effective responses.

[0886] Example 1

[0887] 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."

[0888] There is a need to effectively utilize real-time information on social media to quickly and accurately predict communication traffic and encourage appropriate responses from telecommunications carriers and disaster response organizations. However, conventional technologies have not fully automated the collection and analysis of social media data, making it difficult to predict communication traffic in real time and implement appropriate responses.

[0889] 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.

[0890] In this invention, the server includes means for acquiring social media data, means using a generative artificial intelligence module to analyze the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing the predicted communication traffic data to a telecommunications carrier or a disaster response organization, and means for performing area tuning based on the provided communication traffic prediction data, thereby enabling real-time analysis of the collected data and rapid prediction and response to communication traffic.

[0891] "Social media data" refers to digital content, such as text, images, and videos, that users post or share on online platforms, such as social networking services.

[0892] "Means of collection" refers to devices or software programs used to collect data from social media platforms using APIs or scraping techniques based on specific keywords or hashtags.

[0893] "Generative AI Module" refers to software or systems that implement artificial intelligence techniques used to process and analyze collected data and make classifications and predictions.

[0894] "Natural language processing" refers to the technology of analyzing human language and understanding and extracting its meaning, and is used to analyze and classify text data.

[0895] "Communications traffic" refers to the amount of data passing through a particular network or communication line, usually measured in units of time.

[0896] "Prediction means" refers to a device or program that uses machine learning or statistical models to estimate future fluctuations in communication traffic based on collected and analyzed data.

[0897] "Means of providing" refers to the equipment or system that presents and transmits collected, analyzed, and predicted data to telecommunications carriers and disaster response organizations.

[0898] "Area tuning" refers to adjustments to optimize the communications infrastructure in a specific area based on predictive data, such as base station placement and bandwidth allocation.

[0899] A "dashboard" refers to a user interface that visualizes collected and analyzed data and displays it to relevant parties in real time.

[0900] "API" stands for Application Program Interface, which provides a way for software applications to communicate with other software services.

[0901] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[0902] Social Media Data Collection

[0903] server:

[0904] The server collects relevant data using APIs of social media platforms, specifically, posts based on keywords such as "power outage," "live," and "earthquake" via Twitter and other social media APIs, and stores the data in an internal database for subsequent analysis.

[0905] Data analysis

[0906] server:

[0907] The server sends the collected social media data to a generative artificial intelligence (AI) module, which analyzes the content of posts using natural language processing (NLP) technology. This generative AI module classifies the retrieved posts into categories such as "disaster" and "event," and then scores the importance of each post. For example, a post about "power outage in XX city" would be classified in the disaster category and assigned a high importance rating.

[0908] Communications traffic forecast

[0909] server:

[0910] Based on the analyzed data, the server applies a predictive model that combines past communication traffic data with real-time posted data. A machine learning algorithm is used to predict future fluctuations in communication traffic. This prediction allows communication carriers and disaster response organizations to take measures in advance. For example, if there are many posts saying "There was a power outage in XX city," the server will predict a sudden increase in communication traffic in XX city based on similar cases in the past and propose load reduction measures for this area.

[0911] Providing forecast data

[0912] server:

[0913] The server provides predicted communication traffic data to telecommunications carriers and disaster response organizations. The data is displayed and shared in real time via a dashboard and API. Alerts are also sent to encourage specific countermeasures.

[0914] Device:

[0915] The carrier's terminals acquire the forecast data provided by the server and perform area tuning and enhanced monitoring of the communications infrastructure to maintain an optimal communications environment. Based on the acquired forecast data, the terminals perform specific resource management such as base station placement and bandwidth adjustment.

[0916] User:

[0917] Ordinary users receive notifications from disaster response organizations and telecommunications carriers. These notifications include evacuation orders and recommended actions such as refraining from using communications. This allows users to take prompt and appropriate action. As a specific example, disaster response organizations issue emergency notifications based on collected data and predicted communications traffic, requesting users to respond promptly. In addition, users are notified of measures such as limiting communication speeds to reduce communications load in specific areas.

[0918] Example prompt sentence:

[0919] "There have been reports of a power outage in XX city. Please tell me the expected communication traffic and countermeasures."

[0920] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0921] Step 1:

[0922] server:

[0923] Collects social media data. The server queries the API of a social media platform using specific keywords (e.g., "power outage," "live," "earthquake"). A list of keywords and a timestamp are used as input. The post data returned from the API is received and stored in a database. The output is the stored social media data. Specifically, the query is run every minute to collect new posts.

[0924] Step 2:

[0925] server:

[0926] The collected data is analyzed. The server retrieves the collected social media data from its internal database and sends it to the generative AI module. The input is the collected social media data. The generative AI module uses natural language processing (NLP) technology to analyze the content of posts, classifying them into categories such as "disaster" and "event," and assigning an importance score to each post. The output is the categorized and importance-assigned analysis result data. Specifically, the generative AI module classifies the post "Power outage in XX city" into the disaster category and assigns a high importance score.

[0927] Step 3:

[0928] server:

[0929] Predicts communication traffic. The server applies a predictive model based on the analysis results of the generative AI module. The input is categorized social media data and past communication traffic data. A machine learning algorithm (e.g., random forest, LSTM) is used to predict future fluctuations in communication traffic. The output is predicted communication traffic data. Specifically, it analyzes a large number of posted data items saying "A power outage has occurred in XX city" and predicts a sudden increase in communication traffic in that area.

[0930] Step 4:

[0931] server:

[0932] Provides predicted communication traffic data. The server prepares a dashboard and API to provide predicted data to telecommunications carriers and disaster response organizations. The input is predicted communication traffic data. The output is real-time data displayed through the dashboard and API. Specifically, the predicted communication traffic data is displayed on the dashboard and updated in real time.

[0933] Step 5:

[0934] Device:

[0935] The carrier's terminal obtains the forecast data provided by the server and performs area tuning. The input is the forecast data provided by the server. The output is an optimized communications infrastructure. Specifically, the system readjusts the placement of communications base stations and bandwidth based on the forecast data to maintain communications quality in real time.

[0936] Step 6:

[0937] User:

[0938] Ordinary users receive notifications from telecommunications carriers and disaster response organizations and take the necessary action. The input is the received notification. The output is the specific action the user takes (e.g., evacuation, refraining from using communications). Specifically, if a disaster response organization notifies the user that "There is a power outage in XX city, so please evacuate to a safe location," the user will evacuate promptly.

[0939] (Application example 1)

[0940] 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."

[0941] In modern society, with the spread of social media, a huge amount of information is being circulated in real time. It is extremely important to utilize this information to predict communication traffic and local security situations and take appropriate measures. However, with conventional methods, it has been difficult to efficiently collect and analyze this data and realize real-time predictions and responses. Furthermore, there has been no established method for quickly notifying and responding to sudden increases in communication traffic or sudden changes in security situations.

[0942] 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.

[0943] In this invention, the server includes a means for scraping social media data, a generative artificial intelligence means for analyzing the collected social media data, a means for predicting communication traffic in real time based on the analysis results, and a means for sending notifications to users based on the predicted local security situation, thereby enabling real-time communication traffic prediction and local security situation prediction and appropriate responses based on the predictions.

[0944] "Social media data" refers to digital information such as text, images, and videos posted by users on social media platforms such as Twitter, Facebook, and Instagram.

[0945] "Scraping" is a technique for automatically extracting and collecting specific data from a website.

[0946] "Generative AI means" refers to algorithms or models that use AI technology to analyze input data and generate new information from the results.

[0947] "Analysis" is the process of classifying and organizing collected data according to a specific purpose and discovering meanings and trends.

[0948] "Communication traffic" refers to the amount of data sent and received over a communication network within a given period of time.

[0949] "Forecasting" is the act of estimating possible future events or situations based on current and past data.

[0950] "Telecommunications carrier" refers to a company or organization that provides communications services such as internet and telephone.

[0951] A "disaster management organization" is a public or private organization that works to mitigate damage and ensure rapid recovery when natural or man-made disasters occur.

[0952] "Area tuning" is the process of optimizing communication network settings in a specific area.

[0953] "Regional security situation" refers to information about safety in a particular area, such as the crime rate and frequency of accidents.

[0954] "Notification" is the act of sending a message to inform a target person of specific information.

[0955] "User" refers to an individual or organization that uses this system.

[0956] A "user interface" is the means and display screen through which a computer system and its users interact with information.

[0957] "Dashboard" refers to a display screen that visually displays data in real time to facilitate monitoring and management.

[0958] This invention relates to a system that utilizes social media data to predict communication traffic and local security situations in real time and take appropriate measures. This system is realized by using the following multiple means.

[0959] First, the server uses scraping technology to collect data from social media platforms such as Twitter and Facebook. For example, it uses the Twitter API or Facebook Graph API to collect posts that match specific keywords (e.g., "power outage," "crime," "accident"), and stores the collected data in an internal database, ready for subsequent analysis.

[0960] The collected social media data is then analyzed by a generative artificial intelligence (AI) tool. This invention includes an analysis system that uses natural language processing (NLP) techniques, such as NLP libraries like spacy or NLTK. The AI ​​classifies these posts into categories ("Disaster," "Security," "Other") and assigns an importance score to each category.

[0961] Based on the analysis results, the server makes a prediction of communication traffic. This prediction is made using a machine learning algorithm that combines past traffic data with real-time posting data. For example, machine learning libraries such as Scikit-Learn and TensorFlow are used. The machine learning model analyzes past traffic patterns related to specific keywords and predicts future fluctuations in communication traffic.

[0962] Furthermore, local security situation predictions are also performed using the same method. The server analyzes the collected data and predicts the likelihood of crimes or accidents occurring in a specific area. Based on the results, appropriate notifications are sent to users. Notifications can be provided in the form of push notifications, email notifications, etc.

[0963] For example, if a large number of posts are collected stating "There is a power outage in XX city," the server can compare them with past data and predict a sudden increase in communication traffic in XX city. Also, if there are many posts about "crimes" or "accidents" in a particular area, a warning notification will be sent to users staying in that area.

[0964] Examples of prompts to use include:

[0965] "The latest information on power outages, crimes, and accidents is collected and analyzed using natural language processing. Each tweet is classified into a category (disaster, security, etc.) and the importance of each category is evaluated. Communication traffic is predicted based on past and real-time data, and countermeasures are proposed."

[0966] This allows users to understand the situation in real time and take appropriate action.By combining the server, generative AI, scraping technology, and natural language processing technology, an efficient and effective real-time prediction system is realized.

[0967] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0968] Step 1:

[0969] Social Media Data Collection

[0970] The server uses the API of a social media platform (e.g., Twitter or Facebook) to collect relevant data. Specifically, it retrieves posts based on specific keywords (e.g., "power outage," "crime," or "accident"). The input to this process is the parameters of the API request, and the output is the retrieved post data. The server stores this data in an internal database.

[0971] Step 2:

[0972] Data analysis

[0973] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The input for this process is the post data obtained in step 1, and the output is the analysis results. Specifically, the generative AI uses natural language processing (NLP) technology to analyze the content of the posts, classifying each post into a category ("Disaster," "Security," "Other"), and assigning an importance score to each. This process uses an NLP library (e.g., spacy or NLTK).

[0974] Step 3:

[0975] Communications traffic forecast

[0976] The server applies a communication traffic prediction model based on the analysis results of the generative AI. The inputs to this process are the analysis results from step 2 and past traffic data, and the output is predicted communication traffic data. Specifically, a machine learning algorithm (e.g., Scikit-Learn or TensorFlow) is used to predict how communication traffic will fluctuate in the future.

[0977] Step 4:

[0978] Predicting the security situation

[0979] The server analyzes the collected data and predicts the frequency of crimes and accidents in a specific area. The input to this process is the social media data from step 1 and the analysis results from step 2, and the output is the predicted security situation in the area. The server analyzes the content of posts about "crimes" and "accidents" in a specific area to identify occurrence frequencies and trends.

[0980] Step 5:

[0981] Providing forecast data

[0982] The server provides the forecast data to telecommunications carriers and disaster response organizations. The input to this process is the forecast data from Steps 3 and 4, and the output is the provided forecast data. The server displays this data in real time via a dashboard or API, allowing personnel to take immediate action.

[0983] Step 6:

[0984] User Notification

[0985] The server sends a notification to the user based on the predicted local security situation. The input to this process is the security prediction data from step 4, and the output is a notification message to the user. The server provides users with risk information using push notifications and email notifications, encouraging them to take prompt action.

[0986] 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.

[0987] The present invention relates to a system that combines social media data, generative artificial intelligence, and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[0988] The following describes how to implement this system specifically.

[0989] Social Media Data Collection

[0990] server:

[0991] The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter, Facebook, etc. to obtain posts based on keywords (e.g., "power outage," "live," "earthquake"), and stores the obtained data in an internal database.

[0992] Data Preprocessing

[0993] server:

[0994] Remove unnecessary information from collected social media data, such as filtering out spam posts and duplicate data, and converting it into a format suitable for analysis. This process involves text normalization.

[0995] Data analysis

[0996] server:

[0997] The server analyzes the preprocessed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters, events, etc.) and assign an importance score to each post. In addition, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[0998] Examples:

[0999] A post such as "There is a power outage in XX city" is classified as a "disaster" category, and the generative AI gives it a high importance. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns it an emotion score.

[1000] Communications traffic forecast

[1001] server:

[1002] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[1003] Examples:

[1004] If there are many posts saying "There was a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[1005] Providing forecast data

[1006] server:

[1007] The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via a dashboard and API, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[1008] Device:

[1009] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[1010] User:

[1011] General users will receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and information to encourage appropriate actions depending on the situation, such as refraining from using telecommunications.

[1012] Examples:

[1013] Based on the collected data with high emotion scores and traffic forecast data, disaster response organizations can issue emergency notifications, requesting users to take prompt action, and notify users of measures such as limiting communication speeds to reduce communication load in specific areas.

[1014] As described above, the present invention is a system that uses social media data and an emotion engine to predict communication traffic and respond quickly, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[1015] The processing flow will be explained below.

[1016] Step 1: Collect social media data

[1017] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[1018] Step 2: Preprocessing the data

[1019] Server: This removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process involves techniques such as text normalization.

[1020] Step 3: Analyze the data

[1021] Server: The server uses a generative artificial intelligence (AI) and emotion engine to analyze the preprocessed data. The generative AI uses natural language processing (NLP) to classify posts into categories (disasters, events, etc.) and assign an importance score to each post. Meanwhile, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from posts and assigns an emotion score.

[1022] Examples:

[1023] A post saying "There is a power outage in XX city" is classified as a "disaster" and the generative AI rates it as important. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns a high emotion score.

[1024] Step 4: Traffic forecast

[1025] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model integrates historical traffic data with real-time posting data and uses machine learning algorithms to predict traffic fluctuations. Emotion scores are also incorporated into this model to improve prediction accuracy.

[1026] Examples:

[1027] If there are many posts saying "There is a power outage in XX city," the system will refer to past data and sentiment scores to predict a sudden increase in communication traffic in XX city.

[1028] Step 5: Generate prediction data

[1029] Server: Generates future traffic fluctuation data based on a predictive model. This data specifically indicates increases or decreases in traffic in specific areas.

[1030] Step 6: Provide traffic forecast data

[1031] Server: Provides predictive data to telecommunications carriers and disaster response organizations via dashboards and API endpoints. The dashboard also displays the results of the emotion engine's recognition, helping personnel understand the detailed situation.

[1032] Step 7: Area Tuning

[1033] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. Specifically, it allocates additional network resources to specific areas to avoid overload.

[1034] Step 8: Receive and respond to notifications

[1035] Users: General users receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and instructions to refrain from using communications.

[1036] Examples:

[1037] Disaster response agencies can use data with high emotion scores, such as anxiety and anger, to quickly send emergency notifications and encourage users to take prompt action.

[1038] Step 9: Building a feedback loop

[1039] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[1040] The above are the specific processing steps for implementing the present invention. This system enables real-time communication traffic prediction and rapid response by utilizing social media data and an emotion engine.

[1041] Example 2

[1042] 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."

[1043] In recent years, the amount of information disseminated on social media has increased, and during disasters and large-scale events, a large number of posts are often made in real time. This has resulted in a sudden increase in communication traffic, increasing the risk of communication networks becoming overloaded. However, conventional communication traffic management systems have had difficulty making real-time predictions and responding quickly. In particular, they were unable to predict traffic taking into account user emotions and the importance of information, and only inaccurate countermeasures could be implemented. For this reason, communication carriers and disaster response organizations are required to respond quickly and appropriately to prevent communication traffic overload.

[1044] 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.

[1045] In this invention, the server includes means for scraping social media data, means for preprocessing the collected social media data, means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing communication traffic prediction data to telecommunications carriers and disaster response organizations, and means for performing area tuning based on the provided communication traffic prediction data. This makes it possible to predict communication traffic in real time based on the analysis results of the social media data and provide highly accurate prediction data that takes into account importance scores and sentiment scores. This allows telecommunications carriers and disaster response organizations to respond quickly and appropriately and prevent communication network overload.

[1046] "Social media data" refers to content such as text, images, videos, and links posted by users on social networking services (SNS) and online platforms.

[1047] "Scraping" refers to the automated capture and extraction of website data, including using the APIs of social media platforms to gather data.

[1048] "Preprocessing" refers to the process of removing spam and duplicate data from collected data and converting it into a format suitable for analysis, including text normalization.

[1049] "Generative artificial intelligence (AI)" refers to machine learning algorithms that are trained to perform specific tasks, including analyzing social media data using natural language processing (NLP) techniques.

[1050] "Real-time" refers to processing and analysis occurring close to the moment data is generated, with extremely little delay.

[1051] "Communication traffic forecasting" refers to predicting future fluctuations in data transfer volume within a communication network based on collected and analyzed data.

[1052] "Telecommunications carrier" refers to a company or organization that provides and operates a telecommunications network, including fixed-line and mobile communications.

[1053] "Disaster response agencies" refer to public institutions and organizations that take response measures in response to natural disasters such as earthquakes and typhoons, as well as man-made disasters.

[1054] "Area Tuning" refers to the process of adjusting communication settings in a particular geographic area, including increasing or limiting communication capacity.

[1055] The "importance score" is a number that indicates how important a particular post is in the collected social media data. For example, posts in the "disaster" category are given a high score.

[1056] "Emotion score" refers to the numerical value of the intensity of emotions (e.g., joy, sadness, anger) extracted from social media posts. It is assigned by the emotion engine.

[1057] "User interface" refers to the screens and methods of operation that allow users to interact with a system, including dashboards.

[1058] A "dashboard" is an interface that visually displays multiple data points and analysis results, allowing managers to understand the situation in real time.

[1059] This invention is a system that collects social media data, predicts communication traffic in real time, and provides the results to telecommunications carriers and disaster response organizations. How to implement this system in concrete terms is explained below.

[1060] Social Media Data Collection

[1061] server:

[1062] The server collects relevant data using the APIs of social media platforms (e.g., Twitter and Facebook) in the following manner:

[1063] 1. Authentication to the API: The server uses the API key or access token of each social media to authenticate access to the API.

[1064] 2. Setting up keyword filters: The server sets up specific keywords such as "power outage," "live," and "earthquake."

[1065] 3. Performing data collection: The server collects relevant posts based on the set keywords and stores the acquired data in an internal database.

[1066] Data Preprocessing

[1067] server:

[1068] The server pre-processes the collected social media data. The specific details of the pre-processing are as follows:

[1069] 1. Spam filtering: The server detects and removes spam posts, for example, filtering out posts with repetitive content and advertisements.

[1070] 2. Removing duplicate data: Removing duplicates to make data collected in multiple places unique.

[1071] 3. Text normalization: The server corrects variations and typos in the text data and formats it consistently.

[1072] Data analysis

[1073] server:

[1074] The server analyzes the pre-processed data using generative artificial intelligence (AI) and an emotion engine. The specific analysis is as follows:

[1075] 1. Natural Language Processing (NLP): Generative AI uses natural language processing techniques to analyze posts and classify them into categories (e.g., disasters, events, etc.).

[1076] 2. Assigning importance scores: Each post is assigned an importance score. For example, "Power outage in XX city" is assigned a high importance score.

[1077] 3. Sentiment Analysis: The emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from collected posts and assigns an emotion score to each post.

[1078] Example: A generative AI classifies a post such as "There was a power outage in XX city" into the "disaster" category, and the emotion engine recognizes "anxiety" or "anger" from the post and assigns it an emotion score.

[1079] Communications traffic forecast

[1080] server:

[1081] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[1082] 1. Data integration: Integrate the analysis results of generative AI and emotion engines.

[1083] 2. Applying machine learning algorithms: Using the integrated data, we build a predictive model for communication traffic. We combine historical traffic data with real-time data and perform analysis.

[1084] 3. Bias verification and correction: Balance the predictive model as necessary to ensure it is not biased towards specific data.

[1085] Example: The server combines past traffic data for XX city with currently collected post data with high importance and high sentiment scores, such as "There was a power outage in XX city," to predict a sudden increase in traffic.

[1086] Providing forecast data

[1087] server:

[1088] The server provides the forecast data to telecommunications carriers and disaster response organizations. The specific procedure is as follows:

[1089] 1. Build a dashboard: Build a dashboard that can visualize the forecast data and set it up so that the data is updated in real time.

[1090] 2. API disclosure: We will publish an API endpoint to provide forecast data to telecommunications carriers and disaster response organizations.

[1091] 3. Alert function: Receives an alert when certain conditions are met (e.g., high sentiment score, traffic forecast exceeds a critical value).

[1092] Device:

[1093] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[1094] 1. Receiving data: Obtaining prediction data via API.

[1095] 2. Area Tuning: Adjust communication settings in specific areas based on predictive data.

[1096] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are expected.

[1097] User:

[1098] General users receive notifications from disaster response organizations and telecommunications carriers. The specific procedure is as follows:

[1099] 1. Receive emergency notifications: Receive emergency notifications on your smartphone or email.

[1100] 2. Promoting action: Based on the notification, take necessary actions such as evacuation and refraining from communication.

[1101] Example: Disaster management organizations send emergency notifications and instruct users to evacuate based on "power outage" data with a high emotional score and traffic forecast data. Telecommunications carriers also limit communication speeds in specific areas to reduce traffic loads.

[1102] Prompt Sentence Examples

[1103] Below are some example prompts to input to a generative AI model:

[1104] "Please collect data about outages from Twitter, assign a sentiment score to it, and predict traffic and display the results on a dashboard."

[1105] By using this prompt statement, you can check how the system processes and what data it will ultimately output.

[1106] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1107] Step 1:

[1108] Social Media Data Collection

[1109] server:

[1110] The server collects data using the APIs of social media platforms (e.g., Twitter, Facebook). The specific steps are as follows:

[1111] 1. Authentication to the API: The server authenticates using an API key and an access token. The input is the API key and the access token, and the output is an authentication token.

[1112] 2. Keyword filter setting: The server sets keywords such as "power outage," "live," "earthquake," etc. The input is a list of keywords, and the output is the filter conditions.

[1113] 3. Execution of Data Collection: The server retrieves social media posts based on the set keywords. The input is the filtering condition, and the output is the collected post data. As a specific operation, it uses the Twitter API to collect tweets containing the keyword "power outage" in real time and saves them in the database.

[1114] Step 2:

[1115] Preprocessing of Data

[1116] Server:

[1117] The server preprocesses the collected social media data. The specific content of the preprocessing is as follows.

[1118] 1. Spam Filtering: The server detects and deletes spam posts. The input is the collected post data, and the output is the data with spam removed.

[1119] 2. Duplicate Data Removal: The server removes duplicate data. The input is the data after spam filtering, and the output is the data made unique.

[1120] 3. Text Normalization: The server converts text data into a consistent format. The input is the data made unique, and the output is the normalized data. As a specific operation, it arranges so that "power outage" can be correctly recognized even in different forms such as "ていでん" or "停電。".

[1121] Step 3:

[1122] Data Analysis

[1123] Server:

[1124] The server analyzes the data using generative artificial intelligence (AI) and an emotion engine. The specific content of the analysis is as follows.

[1125] 1. Natural Language Processing (NLP): Generative AI uses natural language processing techniques to analyze posts and classify them into categories (e.g., disasters, events, etc.). The input is normalized data, and the output is categorized data.

[1126] 2. Importance Score Assignment: The server assigns an importance score to each post. The input is the categorized data, and the output is the data with the importance score assigned.

[1127] 3. Sentiment analysis: The emotion engine recognizes the user's emotions from each post and assigns an emotion score. The input is data with an importance score assigned, and the output is data with an emotion score assigned. For example, a post saying "There was a power outage in XX city" is assigned a high importance and a high emotion score such as "anxiety" or "anger."

[1128] Step 4:

[1129] Communications traffic forecast

[1130] server:

[1131] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[1132] 1. Data integration: Integrate the analysis results of the generative AI and the emotion engine. The input is data with importance and emotion scores, and the output is the integrated data.

[1133] 2. Applying machine learning algorithms: The server uses the integrated data to create a communication traffic prediction model. The input is the integrated data, and the output is the communication traffic prediction model.

[1134] 3. Bias verification and correction: The server adjusts the balance so that the prediction model is not biased towards specific data. The input is the prediction model, and the output is the balanced prediction model. As a specific example, the server uses past traffic data for XX city and real-time collected data such as "A power outage has occurred in XX city" to predict a sudden increase in traffic.

[1135] Step 5:

[1136] Providing forecast data

[1137] server:

[1138] The server provides the forecast data to telecommunications carriers and disaster response organizations. The procedure is as follows:

[1139] 1. Building a dashboard: We build a dashboard that can visualize the forecast data. The input is the communication traffic forecast model, and the output is a dashboard that is updated in real time.

[1140] 2. Exposing API: The server exposes an API endpoint for providing prediction data. The input is the traffic prediction model, and the output is the API endpoint.

[1141] 3. Alert function: The server sends an alert notification when a specific condition occurs (e.g., the sentiment score is high, or the traffic prediction exceeds a critical value). The input is the prediction data, and the output is the alert notification.

[1142] Device:

[1143] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[1144] 1. Receiving data: Receive prediction data through the API. The input is the API endpoint and the output is the prediction data.

[1145] 2. Area Tuning: Adjusting communication settings in a specific area based on predicted data. The input is the predicted data, and the output is the adjusted communication settings.

[1146] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are predicted. The input is forecast data, and the output is an enhanced monitoring system.

[1147] User:

[1148] General users will receive notifications from disaster response organizations and telecommunications carriers and take the following actions:

[1149] 1. Receiving emergency notifications: Receive emergency notifications via smartphone or email. The input is the alert notification, and the output is the notification content.

[1150] 2. Promoting action: Based on the content of the notification, actions such as evacuation or limiting communication are taken. The input is the notification content, and the output is the user's action. As a specific example, a disaster response organization sends out an emergency notification based on "power outage" data with a high emotional score and traffic prediction data, instructing users to evacuate quickly or limit communication.

[1151] (Application example 2)

[1152] 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."

[1153] In recent years, there has been an increasing number of cases of sudden increases in communication traffic due to disasters and large-scale events, and there is a need for an appropriate prediction system to respond quickly to these situations. A notification mechanism is also needed to prompt general users to take appropriate action in real time. Conventional systems have inadequate means for predicting communication traffic by combining social media data and users' emotional responses, making it difficult to respond appropriately to sudden increases in traffic.

[1154] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting social media data, generative artificial intelligence means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results and an emotion score by an emotion engine, means for providing communication traffic prediction data to a telecommunications carrier or a disaster response organization, means for performing area tuning based on the provided communication traffic prediction data and the real-time importance score, and means for sending a real-time notification to a user. This enables a quick and appropriate response to a sudden increase in communication traffic, improving the safety of users and the communication network.

[1155] "Social Media Data" refers to information such as user posts and comments obtained from social media platforms such as Twitter and Facebook.

[1156] "Generative AI means" refers to AI that uses natural language processing techniques to analyze data, particularly for text classification and sentiment analysis.

[1157] An "emotion engine" is an algorithm or software that recognizes a user's emotions (happiness, sadness, anger, etc.) from collected data and assigns an emotion score.

[1158] "Communication traffic forecasting" is the process of combining historical communication data with real-time posting data and using machine learning algorithms to predict future fluctuations in communication traffic.

[1159] A "communications carrier" is a company or organization that provides communications services such as telephone and internet.

[1160] "Disaster response agencies" are public institutions and organizations that take measures in the event of disasters such as earthquakes, floods, and typhoons.

[1161] "Area tuning" refers to dynamically changing and optimizing the settings and configuration of a communication network in a specific area.

[1162] The "importance score" is an index that quantitatively evaluates the urgency and importance of collected data.

[1163] "Real-time notification" is a function that provides users with information immediately when a specific event or situation occurs.

[1164] The present invention relates to a system that uses social media data, generative artificial intelligence (AI), and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[1165] Social Media Data Collection

[1166] Server: The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter and Facebook to retrieve posts based on specific keywords (e.g., "power outage," "live," "earthquake") and stores the retrieved data in an internal database.

[1167] Data Preprocessing

[1168] Server: Removes unnecessary information from collected social media data. Specifically, it filters out spam posts and duplicate data and converts it into a format suitable for analysis. This process includes text normalization.

[1169] Data analysis

[1170] Server: The server analyzes the preprocessed data using generative artificial intelligence (AI) and an emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters or events) and assigns an importance score to each post. Furthermore, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[1171] Communications traffic forecast

[1172] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[1173] Providing forecast data

[1174] Server: The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via dashboards and APIs, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[1175] Performing area tuning

[1176] Telecommunications carrier's terminal: The telecommunications carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communications environment.

[1177] Sending real-time notifications

[1178] Server and user device: The server sends real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[1179] Hardware and software used

[1180] Hardware: Cloud server, smartphone (iOS or Android)

[1181] Software: Python, Flask, Tweepy (server side), React Native, Axios (client side)

[1182] Specific examples

[1183] For example, if there are many posts saying "There is a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[1184] Prompt Sentence Examples

[1185] "Analyze data collected from social media based on keywords such as 'power outage,' 'earthquake,' and 'event,' and calculate a sentiment score and importance."

[1186] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1187] Step 1:

[1188] Social Media Data Collection

[1189] The server collects relevant data using APIs of social media platforms, such as Twitter and Facebook, to retrieve posts based on specific keywords (e.g., "power outage," "live," and "earthquake") and store them in an internal database.

[1190] Input: Social media platform API, specific keywords

[1191] Output: Collected social media data

[1192] What it does: The program uses the API key to retrieve social media data and saves it in JSON format.

[1193] Step 2:

[1194] Data Preprocessing

[1195] The server removes unnecessary information from the collected social media data, for example filtering out spam posts and duplicate data, and converts it into a format suitable for analysis. Text normalization also takes place at this stage.

[1196] Input: Collected social media data

[1197] Output: Preprocessed social media data

[1198] What you will do: Clean data using regular expressions and filtering algorithms to build a valid dataset.

[1199] Step 3:

[1200] Data analysis

[1201] The server analyzes the pre-processed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses NLP techniques to classify posts into categories (e.g., disasters or events) and assign importance scores. At the same time, the emotion engine recognizes users' emotions (e.g., joy, sadness, anger, etc.) and assigns emotion scores.

[1202] Input: Preprocessed social media data

[1203] Output: Analysis results (category classification, importance score, sentiment score)

[1204] What it does: Analyzes text using an NLP model to calculate categories and scores.

[1205] Step 4:

[1206] Communications traffic forecast

[1207] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. Past traffic data and real-time posting data are input into a machine learning algorithm to predict future traffic fluctuations.

[1208] Input: Analysis results, past traffic data

[1209] Output: Communication traffic forecast data

[1210] What it does: It uses machine learning algorithms to learn from data and generate predictive models.

[1211] Step 5:

[1212] Providing forecast data

[1213] The server provides telecommunications carriers and disaster response organizations with traffic forecast data, which is displayed in real time via a dashboard and API.

[1214] Input: Communication traffic forecast data

[1215] Output: Dashboard display data, API communication data

[1216] What it does: Formats the data, displays it in a dashboard, and serves it to an API endpoint.

[1217] Step 6:

[1218] Performing area tuning

[1219] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[1220] Input: Communication traffic forecast data

[1221] Output: Optimized communication network

[1222] Specific operation: Dynamically adjusts communication network settings based on predictive data to maintain optimal conditions.

[1223] Step 7:

[1224] Sending real-time notifications

[1225] The server and user device send real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[1226] Input: Importance score, sentiment score

[1227] Output: Real-time notification

[1228] Specific Actions: Use notifications to alert the user and provide specific instructions.

[1229] 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.

[1230] 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.

[1231] 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.

[1232] [Fourth embodiment]

[1233] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1234] 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.

[1235] 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).

[1236] 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.

[1237] 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.

[1238] 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).

[1239] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1240] 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.

[1241] 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.

[1242] 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.

[1243] 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.

[1244] 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.

[1245] 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."

[1246] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[1247] Social Media Data Collection

[1248] server:

[1249] The server uses the APIs of social media platforms to collect relevant data. For example, the server uses the APIs of Twitter and Facebook to retrieve posts matching keywords such as "power outage," "live," and "earthquake." The retrieved data is stored in an internal database and prepared for analysis.

[1250] Data analysis

[1251] server:

[1252] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The generative AI uses natural language processing (NLP) technology to analyze the posts and classify them into categories (disasters, events, etc.).

[1253] Examples:

[1254] A post such as "Power outage in XX city" is classified as a "disaster" category, and the generative AI will rate its importance highly. In contrast, a post such as "Live concert at YY venue" is classified as an "event" category, and is considered a factor in increasing communication traffic.

[1255] Communications traffic forecast

[1256] server:

[1257] The server applies a traffic prediction model based on the results of the generative AI analysis. This predictive model combines historical traffic data with real-time posting data. It uses machine learning algorithms to predict future traffic fluctuations.

[1258] Examples:

[1259] If there are many posts such as "There was a power outage in XX City," the server will refer to similar cases in past data, predict a sudden increase in communication traffic in XX City, and propose load reduction measures for this area.

[1260] Providing forecast data

[1261] server:

[1262] The server provides forecast data to telecommunications carriers and disaster response organizations, which then display the data in real time via dashboards and APIs, allowing personnel to take immediate action.

[1263] Device:

[1264] The carrier's terminals receive the forecast data provided by the server and perform area tuning and strengthen equipment monitoring, thereby maintaining an optimal communication environment.

[1265] User:

[1266] General users can receive notifications from disaster response organizations and telecommunications carriers and take necessary actions. For example, information is provided that encourages appropriate actions depending on the situation, such as evacuation orders and refraining from using telecommunications.

[1267] Examples:

[1268] Based on the collected data and predicted communication traffic, disaster response organizations will issue emergency notifications and request users to take prompt action. Users will also be notified of measures such as limiting communication speeds to reduce communication load in specific areas.

[1269] As described above, the present invention is a system that analyzes social media data in real time to predict communication traffic and respond appropriately, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[1270] The processing flow will be explained below.

[1271] Step 1: Collect social media data

[1272] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[1273] Step 2: Preprocessing the data

[1274] Server: Removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process includes text normalization.

[1275] Step 3: Analyze the data

[1276] Server: Analyzes pre-processed data using generative artificial intelligence (AI). Specifically, it uses natural language processing (NLP) technology to classify posts into categories (disasters, events, etc.) and assigns an importance score to each post.

[1277] Step 4: Generate a predictive model for communication traffic

[1278] Server: Integrates historical communication traffic data with real-time social media data and uses machine learning algorithms to build a communication traffic prediction model. The server trains the prediction model using a training dataset and verifies the accuracy of the model.

[1279] Step 5: Generate prediction data

[1280] Server: Using the constructed prediction model, it predicts communication traffic based on collected and analyzed real-time data. The prediction results show specific increases or decreases in traffic for specific areas.

[1281] Step 6: Provide traffic forecast data

[1282] Server: Provides forecast data to telecommunications carriers and disaster response organizations. The server updates a dashboard that displays the forecast data in a user interface and provides data through an API endpoint.

[1283] Step 7: Area Tuning

[1284] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. For example, it allocates additional network resources to specific areas to reduce communication load.

[1285] Step 8: Receive and respond to notifications

[1286] Users: General users receive notifications from disaster response organizations and telecommunications carriers. For example, they can take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[1287] Step 9: Building a feedback loop

[1288] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[1289] These are the specific processing steps of this system. This system analyzes social media data in real time and predicts increases in communication traffic, enabling quick and effective responses.

[1290] Example 1

[1291] 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."

[1292] There is a need to effectively utilize real-time information on social media to quickly and accurately predict communication traffic and encourage appropriate responses from telecommunications carriers and disaster response organizations. However, conventional technologies have not fully automated the collection and analysis of social media data, making it difficult to predict communication traffic in real time and implement appropriate responses.

[1293] 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.

[1294] In this invention, the server includes means for acquiring social media data, means using a generative artificial intelligence module to analyze the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing the predicted communication traffic data to a telecommunications carrier or a disaster response organization, and means for performing area tuning based on the provided communication traffic prediction data, thereby enabling real-time analysis of the collected data and rapid prediction and response to communication traffic.

[1295] "Social media data" refers to digital content, such as text, images, and videos, that users post or share on online platforms, such as social networking services.

[1296] "Means of collection" refers to devices or software programs used to collect data from social media platforms using APIs or scraping techniques based on specific keywords or hashtags.

[1297] "Generative AI Module" refers to software or systems that implement artificial intelligence techniques used to process and analyze collected data and make classifications and predictions.

[1298] "Natural language processing" refers to the technology of analyzing human language and understanding and extracting its meaning, and is used to analyze and classify text data.

[1299] "Communications traffic" refers to the amount of data passing through a particular network or communication line, usually measured in units of time.

[1300] "Prediction means" refers to a device or program that uses machine learning or statistical models to estimate future fluctuations in communication traffic based on collected and analyzed data.

[1301] "Means of providing" refers to the equipment or system that presents and transmits collected, analyzed, and predicted data to telecommunications carriers and disaster response organizations.

[1302] "Area tuning" refers to adjustments to optimize the communications infrastructure in a specific area based on predictive data, such as base station placement and bandwidth allocation.

[1303] A "dashboard" refers to a user interface that visualizes collected and analyzed data and displays it to relevant parties in real time.

[1304] "API" stands for Application Program Interface, which provides a way for software applications to communicate with other software services.

[1305] The present invention relates to a system that uses social media data to predict communication traffic in real time and encourages communication carriers and disaster response organizations to take appropriate measures. The following describes how to specifically implement this system.

[1306] Social Media Data Collection

[1307] server:

[1308] The server collects relevant data using APIs of social media platforms, specifically, posts based on keywords such as "power outage," "live," and "earthquake" via Twitter and other social media APIs, and stores the data in an internal database for subsequent analysis.

[1309] Data analysis

[1310] server:

[1311] The server sends the collected social media data to a generative artificial intelligence (AI) module, which analyzes the content of posts using natural language processing (NLP) technology. This generative AI module classifies the retrieved posts into categories such as "disaster" and "event," and then scores the importance of each post. For example, a post about "power outage in XX city" would be classified in the disaster category and assigned a high importance rating.

[1312] Communications traffic forecast

[1313] server:

[1314] Based on the analyzed data, the server applies a predictive model that combines past communication traffic data with real-time posted data. A machine learning algorithm is used to predict future fluctuations in communication traffic. This prediction allows communication carriers and disaster response organizations to take measures in advance. For example, if there are many posts saying "There was a power outage in XX city," the server will predict a sudden increase in communication traffic in XX city based on similar cases in the past and propose load reduction measures for this area.

[1315] Providing forecast data

[1316] server:

[1317] The server provides predicted communication traffic data to telecommunications carriers and disaster response organizations. The data is displayed and shared in real time via a dashboard and API. Alerts are also sent to encourage specific countermeasures.

[1318] Device:

[1319] The carrier's terminals acquire the forecast data provided by the server and perform area tuning and enhanced monitoring of the communications infrastructure to maintain an optimal communications environment. Based on the acquired forecast data, the terminals perform specific resource management such as base station placement and bandwidth adjustment.

[1320] User:

[1321] Ordinary users receive notifications from disaster response organizations and telecommunications carriers. These notifications include evacuation orders and recommended actions such as refraining from using communications. This allows users to take prompt and appropriate action. As a specific example, disaster response organizations issue emergency notifications based on collected data and predicted communications traffic, requesting users to respond promptly. In addition, users are notified of measures such as limiting communication speeds to reduce communications load in specific areas.

[1322] Example prompt sentence:

[1323] "There have been reports of a power outage in XX city. Please tell me the expected communication traffic and countermeasures."

[1324] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1325] Step 1:

[1326] server:

[1327] Collects social media data. The server queries the API of a social media platform using specific keywords (e.g., "power outage," "live," "earthquake"). A list of keywords and a timestamp are used as input. The post data returned from the API is received and stored in a database. The output is the stored social media data. Specifically, the query is run every minute to collect new posts.

[1328] Step 2:

[1329] server:

[1330] The collected data is analyzed. The server retrieves the collected social media data from its internal database and sends it to the generative AI module. The input is the collected social media data. The generative AI module uses natural language processing (NLP) technology to analyze the content of posts, classifying them into categories such as "disaster" and "event," and assigning an importance score to each post. The output is the categorized and importance-assigned analysis result data. Specifically, the generative AI module classifies the post "Power outage in XX city" into the disaster category and assigns a high importance score.

[1331] Step 3:

[1332] server:

[1333] Predicts communication traffic. The server applies a predictive model based on the analysis results of the generative AI module. The input is categorized social media data and past communication traffic data. A machine learning algorithm (e.g., random forest, LSTM) is used to predict future fluctuations in communication traffic. The output is predicted communication traffic data. Specifically, it analyzes a large number of posted data items saying "A power outage has occurred in XX city" and predicts a sudden increase in communication traffic in that area.

[1334] Step 4:

[1335] server:

[1336] Provides predicted communication traffic data. The server prepares a dashboard and API to provide predicted data to telecommunications carriers and disaster response organizations. The input is predicted communication traffic data. The output is real-time data displayed through the dashboard and API. Specifically, the predicted communication traffic data is displayed on the dashboard and updated in real time.

[1337] Step 5:

[1338] Device:

[1339] The carrier's terminal obtains the forecast data provided by the server and performs area tuning. The input is the forecast data provided by the server. The output is an optimized communications infrastructure. Specifically, the system readjusts the placement of communications base stations and bandwidth based on the forecast data to maintain communications quality in real time.

[1340] Step 6:

[1341] User:

[1342] Ordinary users receive notifications from telecommunications carriers and disaster response organizations and take the necessary action. The input is the received notification. The output is the specific action the user takes (e.g., evacuation, refraining from using communications). Specifically, if a disaster response organization notifies the user that "There is a power outage in XX city, so please evacuate to a safe location," the user will evacuate promptly.

[1343] (Application example 1)

[1344] 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."

[1345] In modern society, with the spread of social media, a huge amount of information is being circulated in real time. It is extremely important to utilize this information to predict communication traffic and local security situations and take appropriate measures. However, with conventional methods, it has been difficult to efficiently collect and analyze this data and realize real-time predictions and responses. Furthermore, there has been no established method for quickly notifying and responding to sudden increases in communication traffic or sudden changes in security situations.

[1346] 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.

[1347] In this invention, the server includes a means for scraping social media data, a generative artificial intelligence means for analyzing the collected social media data, a means for predicting communication traffic in real time based on the analysis results, and a means for sending notifications to users based on the predicted local security situation, thereby enabling real-time communication traffic prediction and local security situation prediction and appropriate responses based on the predictions.

[1348] "Social media data" refers to digital information such as text, images, and videos posted by users on social media platforms such as Twitter, Facebook, and Instagram.

[1349] "Scraping" is a technique for automatically extracting and collecting specific data from a website.

[1350] "Generative AI means" refers to algorithms or models that use AI technology to analyze input data and generate new information from the results.

[1351] "Analysis" is the process of classifying and organizing collected data according to a specific purpose and discovering meanings and trends.

[1352] "Communication traffic" refers to the amount of data sent and received over a communication network within a given period of time.

[1353] "Forecasting" is the act of estimating possible future events or situations based on current and past data.

[1354] "Telecommunications carrier" refers to a company or organization that provides communications services such as internet and telephone.

[1355] A "disaster management organization" is a public or private organization that works to mitigate damage and ensure rapid recovery when natural or man-made disasters occur.

[1356] "Area tuning" is the process of optimizing communication network settings in a specific area.

[1357] "Regional security situation" refers to information about safety in a particular area, such as the crime rate and frequency of accidents.

[1358] "Notification" is the act of sending a message to inform a target person of specific information.

[1359] "User" refers to an individual or organization that uses this system.

[1360] A "user interface" is the means and display screen through which a computer system and its users interact with information.

[1361] "Dashboard" refers to a display screen that visually displays data in real time to facilitate monitoring and management.

[1362] This invention relates to a system that utilizes social media data to predict communication traffic and local security situations in real time and take appropriate measures. This system is realized by using the following multiple means.

[1363] First, the server uses scraping technology to collect data from social media platforms such as Twitter and Facebook. For example, it uses the Twitter API or Facebook Graph API to collect posts that match specific keywords (e.g., "power outage," "crime," "accident"), and stores the collected data in an internal database, ready for subsequent analysis.

[1364] The collected social media data is then analyzed by a generative artificial intelligence (AI) tool. This invention includes an analysis system that uses natural language processing (NLP) techniques, such as NLP libraries like spacy or NLTK. The AI ​​classifies these posts into categories ("Disaster," "Security," "Other") and assigns an importance score to each category.

[1365] Based on the analysis results, the server makes a prediction of communication traffic. This prediction is made using a machine learning algorithm that combines past traffic data with real-time posting data. For example, machine learning libraries such as Scikit-Learn and TensorFlow are used. The machine learning model analyzes past traffic patterns related to specific keywords and predicts future fluctuations in communication traffic.

[1366] Furthermore, local security situation predictions are also performed using the same method. The server analyzes the collected data and predicts the likelihood of crimes or accidents occurring in a specific area. Based on the results, appropriate notifications are sent to users. Notifications can be provided in the form of push notifications, email notifications, etc.

[1367] For example, if a large number of posts are collected stating "There is a power outage in XX city," the server can compare them with past data and predict a sudden increase in communication traffic in XX city. Also, if there are many posts about "crimes" or "accidents" in a particular area, a warning notification will be sent to users staying in that area.

[1368] Examples of prompts to use include:

[1369] "The latest information on power outages, crimes, and accidents is collected and analyzed using natural language processing. Each tweet is classified into a category (disaster, security, etc.) and the importance of each category is evaluated. Communication traffic is predicted based on past and real-time data, and countermeasures are proposed."

[1370] This allows users to understand the situation in real time and take appropriate action.By combining the server, generative AI, scraping technology, and natural language processing technology, an efficient and effective real-time prediction system is realized.

[1371] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1372] Step 1:

[1373] Social Media Data Collection

[1374] The server uses the API of a social media platform (e.g., Twitter or Facebook) to collect relevant data. Specifically, it retrieves posts based on specific keywords (e.g., "power outage," "crime," or "accident"). The input to this process is the parameters of the API request, and the output is the retrieved post data. The server stores this data in an internal database.

[1375] Step 2:

[1376] Data analysis

[1377] The server sends the collected social media data to a generative artificial intelligence (AI) module for data analysis. The input for this process is the post data obtained in step 1, and the output is the analysis results. Specifically, the generative AI uses natural language processing (NLP) technology to analyze the content of the posts, classifying each post into a category ("Disaster," "Security," "Other"), and assigning an importance score to each. This process uses an NLP library (e.g., spacy or NLTK).

[1378] Step 3:

[1379] Communications traffic forecast

[1380] The server applies a communication traffic prediction model based on the analysis results of the generative AI. The inputs to this process are the analysis results from step 2 and past traffic data, and the output is predicted communication traffic data. Specifically, a machine learning algorithm (e.g., Scikit-Learn or TensorFlow) is used to predict how communication traffic will fluctuate in the future.

[1381] Step 4:

[1382] Predicting the security situation

[1383] The server analyzes the collected data and predicts the frequency of crimes and accidents in a specific area. The input to this process is the social media data from step 1 and the analysis results from step 2, and the output is the predicted security situation in the area. The server analyzes the content of posts about "crimes" and "accidents" in a specific area to identify occurrence frequencies and trends.

[1384] Step 5:

[1385] Providing forecast data

[1386] The server provides the forecast data to telecommunications carriers and disaster response organizations. The input to this process is the forecast data from Steps 3 and 4, and the output is the provided forecast data. The server displays this data in real time via a dashboard or API, allowing personnel to take immediate action.

[1387] Step 6:

[1388] User Notification

[1389] The server sends a notification to the user based on the predicted local security situation. The input to this process is the security prediction data from step 4, and the output is a notification message to the user. The server provides users with risk information using push notifications and email notifications, encouraging them to take prompt action.

[1390] 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.

[1391] The present invention relates to a system that combines social media data, generative artificial intelligence, and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[1392] The following describes how to implement this system specifically.

[1393] Social Media Data Collection

[1394] server:

[1395] The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter, Facebook, etc. to obtain posts based on keywords (e.g., "power outage," "live," "earthquake"), and stores the obtained data in an internal database.

[1396] Data Preprocessing

[1397] server:

[1398] Remove unnecessary information from collected social media data, such as filtering out spam posts and duplicate data, and converting it into a format suitable for analysis. This process involves text normalization.

[1399] Data analysis

[1400] server:

[1401] The server analyzes the preprocessed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters, events, etc.) and assign an importance score to each post. In addition, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[1402] Examples:

[1403] A post such as "There is a power outage in XX city" is classified as a "disaster" category, and the generative AI gives it a high importance. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns it an emotion score.

[1404] Communications traffic forecast

[1405] server:

[1406] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[1407] Examples:

[1408] If there are many posts saying "There was a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[1409] Providing forecast data

[1410] server:

[1411] The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via a dashboard and API, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[1412] Device:

[1413] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[1414] User:

[1415] General users will receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and information to encourage appropriate actions depending on the situation, such as refraining from using telecommunications.

[1416] Examples:

[1417] Based on the collected data with high emotion scores and traffic forecast data, disaster response organizations can issue emergency notifications, requesting users to take prompt action, and notify users of measures such as limiting communication speeds to reduce communication load in specific areas.

[1418] As described above, the present invention is a system that uses social media data and an emotion engine to predict communication traffic and respond quickly, thereby preventing communication network overload and reducing risks during disasters and large-scale events.

[1419] The processing flow will be explained below.

[1420] Step 1: Collect social media data

[1421] Server: Accesses the API of the social media platform and collects post data based on specified keywords (e.g., "power outage," "live," "earthquake") The server sends an API request using an authentication token and stores the data obtained as a response in an internal database.

[1422] Step 2: Preprocessing the data

[1423] Server: This removes unnecessary information from the collected social media data. For example, it filters out spam posts and duplicate data, and converts it into a format suitable for analysis. This process involves techniques such as text normalization.

[1424] Step 3: Analyze the data

[1425] Server: The server uses a generative artificial intelligence (AI) and emotion engine to analyze the preprocessed data. The generative AI uses natural language processing (NLP) to classify posts into categories (disasters, events, etc.) and assign an importance score to each post. Meanwhile, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from posts and assigns an emotion score.

[1426] Examples:

[1427] A post saying "There is a power outage in XX city" is classified as a "disaster" and the generative AI rates it as important. At the same time, the emotion engine recognizes emotions such as "anxiety" and "anger" from the post and assigns a high emotion score.

[1428] Step 4: Traffic forecast

[1429] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model integrates historical traffic data with real-time posting data and uses machine learning algorithms to predict traffic fluctuations. Emotion scores are also incorporated into this model to improve prediction accuracy.

[1430] Examples:

[1431] If there are many posts saying "There is a power outage in XX city," the system will refer to past data and sentiment scores to predict a sudden increase in communication traffic in XX city.

[1432] Step 5: Generate prediction data

[1433] Server: Generates future traffic fluctuation data based on a predictive model. This data specifically indicates increases or decreases in traffic in specific areas.

[1434] Step 6: Provide traffic forecast data

[1435] Server: Provides predictive data to telecommunications carriers and disaster response organizations via dashboards and API endpoints. The dashboard also displays the results of the emotion engine's recognition, helping personnel understand the detailed situation.

[1436] Step 7: Area Tuning

[1437] Terminal: The carrier's terminal performs area tuning based on the forecast data provided by the server. Specifically, it allocates additional network resources to specific areas to avoid overload.

[1438] Step 8: Receive and respond to notifications

[1439] Users: General users receive notifications from disaster response agencies and telecommunications carriers, including evacuation orders and instructions to refrain from using communications.

[1440] Examples:

[1441] Disaster response agencies can use data with high emotion scores, such as anxiety and anger, to quickly send emergency notifications and encourage users to take prompt action.

[1442] Step 9: Building a feedback loop

[1443] Server: Compares actual traffic data with predicted data, creating a feedback loop to improve the accuracy of the prediction model, thereby improving future prediction accuracy.

[1444] The above are the specific processing steps for implementing the present invention. This system enables real-time communication traffic prediction and rapid response by utilizing social media data and an emotion engine.

[1445] Example 2

[1446] 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."

[1447] In recent years, the amount of information disseminated on social media has increased, and during disasters and large-scale events, a large number of posts are often made in real time. This has resulted in a sudden increase in communication traffic, increasing the risk of communication networks becoming overloaded. However, conventional communication traffic management systems have had difficulty making real-time predictions and responding quickly. In particular, they were unable to predict traffic taking into account user emotions and the importance of information, and only inaccurate countermeasures could be implemented. For this reason, communication carriers and disaster response organizations are required to respond quickly and appropriately to prevent communication traffic overload.

[1448] 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.

[1449] In this invention, the server includes means for scraping social media data, means for preprocessing the collected social media data, means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results, means for providing communication traffic prediction data to telecommunications carriers and disaster response organizations, and means for performing area tuning based on the provided communication traffic prediction data. This makes it possible to predict communication traffic in real time based on the analysis results of the social media data and provide highly accurate prediction data that takes into account importance scores and sentiment scores. This allows telecommunications carriers and disaster response organizations to respond quickly and appropriately and prevent communication network overload.

[1450] "Social media data" refers to content such as text, images, videos, and links posted by users on social networking services (SNS) and online platforms.

[1451] "Scraping" refers to the automated capture and extraction of website data, including using the APIs of social media platforms to gather data.

[1452] "Preprocessing" refers to the process of removing spam and duplicate data from collected data and converting it into a format suitable for analysis, including text normalization.

[1453] "Generative artificial intelligence (AI)" refers to machine learning algorithms that are trained to perform specific tasks, including analyzing social media data using natural language processing (NLP) techniques.

[1454] "Real-time" refers to processing and analysis occurring close to the moment data is generated, with extremely little delay.

[1455] "Communication traffic forecasting" refers to predicting future fluctuations in data transfer volume within a communication network based on collected and analyzed data.

[1456] "Telecommunications carrier" refers to a company or organization that provides and operates a telecommunications network, including fixed-line and mobile communications.

[1457] "Disaster response agencies" refer to public institutions and organizations that take response measures in response to natural disasters such as earthquakes and typhoons, as well as man-made disasters.

[1458] "Area Tuning" refers to the process of adjusting communication settings in a particular geographic area, including increasing or limiting communication capacity.

[1459] The "importance score" is a number that indicates how important a particular post is in the collected social media data. For example, posts in the "disaster" category are given a high score.

[1460] "Emotion score" refers to the numerical value of the intensity of emotions (e.g., joy, sadness, anger) extracted from social media posts. It is assigned by the emotion engine.

[1461] "User interface" refers to the screens and methods of operation that allow users to interact with a system, including dashboards.

[1462] A "dashboard" is an interface that visually displays multiple data points and analysis results, allowing managers to understand the situation in real time.

[1463] This invention is a system that collects social media data, predicts communication traffic in real time, and provides the results to telecommunications carriers and disaster response organizations. How to implement this system in concrete terms is explained below.

[1464] Social Media Data Collection

[1465] server:

[1466] The server collects relevant data using the APIs of social media platforms (e.g., Twitter and Facebook) in the following manner:

[1467] 1. Authentication to the API: The server uses the API key or access token of each social media to authenticate access to the API.

[1468] 2. Setting up keyword filters: The server sets up specific keywords such as "power outage," "live," and "earthquake."

[1469] 3. Performing data collection: The server collects relevant posts based on the set keywords and stores the acquired data in an internal database.

[1470] Data Preprocessing

[1471] server:

[1472] The server pre-processes the collected social media data. The specific details of the pre-processing are as follows:

[1473] 1. Spam filtering: The server detects and removes spam posts, for example, filtering out posts with repetitive content and advertisements.

[1474] 2. Removing duplicate data: Removing duplicates to make data collected in multiple places unique.

[1475] 3. Text normalization: The server corrects variations and typos in the text data and formats it consistently.

[1476] Data analysis

[1477] server:

[1478] The server analyzes the pre-processed data using generative artificial intelligence (AI) and an emotion engine. The specific analysis is as follows:

[1479] 1. Natural Language Processing (NLP): Generative AI uses natural language processing techniques to analyze posts and classify them into categories (e.g., disasters, events, etc.).

[1480] 2. Assigning importance scores: Each post is assigned an importance score. For example, "Power outage in XX city" is assigned a high importance score.

[1481] 3. Sentiment Analysis: The emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from collected posts and assigns an emotion score to each post.

[1482] Example: A generative AI classifies a post such as "There was a power outage in XX city" into the "disaster" category, and the emotion engine recognizes "anxiety" or "anger" from the post and assigns it an emotion score.

[1483] Communications traffic forecast

[1484] server:

[1485] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[1486] 1. Data integration: Integrate the analysis results of generative AI and emotion engines.

[1487] 2. Applying machine learning algorithms: Using the integrated data, we build a predictive model for communication traffic. We combine historical traffic data with real-time data and perform analysis.

[1488] 3. Bias verification and correction: Balance the predictive model as necessary to ensure it is not biased towards specific data.

[1489] Example: The server combines past traffic data for XX city with currently collected post data with high importance and high sentiment scores, such as "There was a power outage in XX city," to predict a sudden increase in traffic.

[1490] Providing forecast data

[1491] server:

[1492] The server provides the forecast data to telecommunications carriers and disaster response organizations. The specific procedure is as follows:

[1493] 1. Build a dashboard: Build a dashboard that can visualize the forecast data and set it up so that the data is updated in real time.

[1494] 2. API disclosure: We will publish an API endpoint to provide forecast data to telecommunications carriers and disaster response organizations.

[1495] 3. Alert function: Receives an alert when certain conditions are met (e.g., high sentiment score, traffic forecast exceeds a critical value).

[1496] Device:

[1497] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[1498] 1. Receiving data: Obtaining prediction data via API.

[1499] 2. Area Tuning: Adjust communication settings in specific areas based on predictive data.

[1500] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are expected.

[1501] User:

[1502] General users receive notifications from disaster response organizations and telecommunications carriers. The specific procedure is as follows:

[1503] 1. Receive emergency notifications: Receive emergency notifications on your smartphone or email.

[1504] 2. Promoting action: Based on the notification, take necessary actions such as evacuation and refraining from communication.

[1505] Example: Disaster management organizations send emergency notifications and instruct users to evacuate based on "power outage" data with a high emotional score and traffic forecast data. Telecommunications carriers also limit communication speeds in specific areas to reduce traffic loads.

[1506] Prompt Sentence Examples

[1507] Below are some example prompts to input to a generative AI model:

[1508] "Please collect data about outages from Twitter, assign a sentiment score to it, and predict traffic and display the results on a dashboard."

[1509] By using this prompt statement, you can check how the system processes and what data it will ultimately output.

[1510] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1511] Step 1:

[1512] Social Media Data Collection

[1513] server:

[1514] The server collects data using the APIs of social media platforms (e.g., Twitter, Facebook). The specific steps are as follows:

[1515] 1. Authentication to the API: The server authenticates using an API key and an access token. The input is the API key and the access token, and the output is an authentication token.

[1516] 2. Keyword Filter Settings: The server sets keywords such as "power outage", "live", "earthquake", etc. The input is a list of keywords, and the output is the filter condition.

[1517] 3. Execution of Data Collection: The server retrieves social media posts based on the set keywords. The input is the filter condition, and the output is the collected post data. Specifically, it uses the Twitter API to collect tweets containing the keyword "power outage" in real time and saves them in the database.

[1518] Step 2:

[1519] Data Preprocessing

[1520] Server:

[1521] The server preprocesses the collected social media data. The specific content of the preprocessing is as follows.

[1522] 1. Spam Filtering: The server detects and deletes spam posts. The input is the collected post data, and the output is the data with spam removed.

[1523] 2. Duplicate Data Removal: The server removes duplicate data. The input is the data after spam filtering, and the output is the unique data.

[1524] 3. Text Normalization: The server converts text data into a consistent format. The input is the unique data, and the output is the normalized data. Specifically, it arranges the data so that "power outage" can be correctly recognized even in different formats such as "ていでん" or "停電。".

[1525] Step 3:

[1526] Data Analysis

[1527] Server:

[1528] The server analyzes the data using generative artificial intelligence (AI) and an emotion engine. The specific analysis results are as follows:

[1529] 1. Natural Language Processing (NLP): Generative AI uses natural language processing techniques to analyze posts and classify them into categories (e.g., disasters, events, etc.). The input is normalized data, and the output is categorized data.

[1530] 2. Importance Score Assignment: The server assigns an importance score to each post. The input is the categorized data, and the output is the data with the importance score assigned.

[1531] 3. Sentiment analysis: The emotion engine recognizes the user's emotions from each post and assigns an emotion score. The input is data with an importance score assigned, and the output is data with an emotion score assigned. For example, a post saying "There was a power outage in XX city" is assigned a high importance and a high emotion score such as "anxiety" or "anger."

[1532] Step 4:

[1533] Communications traffic forecast

[1534] server:

[1535] The server generates a communication traffic prediction model based on the analysis results. The specific steps are as follows:

[1536] 1. Data integration: Integrate the analysis results of the generative AI and the emotion engine. The input is data with importance and emotion scores, and the output is the integrated data.

[1537] 2. Applying machine learning algorithms: The server uses the integrated data to create a communication traffic prediction model. The input is the integrated data, and the output is the communication traffic prediction model.

[1538] 3. Bias verification and correction: The server adjusts the balance so that the prediction model is not biased towards specific data. The input is the prediction model, and the output is the balanced prediction model. As a specific example, the server uses past traffic data for XX city and real-time collected data such as "A power outage has occurred in XX city" to predict a sudden increase in traffic.

[1539] Step 5:

[1540] Providing forecast data

[1541] server:

[1542] The server provides the forecast data to telecommunications carriers and disaster response organizations. The procedure is as follows:

[1543] 1. Building a dashboard: We build a dashboard that can visualize the forecast data. The input is the communication traffic forecast model, and the output is a dashboard that is updated in real time.

[1544] 2. Exposing API: The server exposes an API endpoint for providing prediction data. The input is the traffic prediction model, and the output is the API endpoint.

[1545] 3. Alert function: The server sends an alert notification when a specific condition occurs (e.g., the sentiment score is high, or the traffic prediction exceeds a critical value). The input is the prediction data, and the output is the alert notification.

[1546] Device:

[1547] The carrier's terminal receives the forecast data provided by the server and takes the following actions:

[1548] 1. Receiving data: Receive prediction data through the API. The input is the API endpoint and the output is the prediction data.

[1549] 2. Area Tuning: Adjusting communication settings in a specific area based on predicted data. The input is the predicted data, and the output is the adjusted communication settings.

[1550] 3. Strengthening facility monitoring: Strengthening facility monitoring in areas where traffic increases are predicted. The input is forecast data, and the output is an enhanced monitoring system.

[1551] User:

[1552] General users will receive notifications from disaster response organizations and telecommunications carriers and take the following actions:

[1553] 1. Receiving emergency notifications: Receive emergency notifications via smartphone or email. The input is the alert notification, and the output is the notification content.

[1554] 2. Promoting action: Based on the content of the notification, actions such as evacuation or limiting communication are taken. The input is the notification content, and the output is the user's action. As a specific example, a disaster response organization sends out an emergency notification based on "power outage" data with a high emotional score and traffic prediction data, instructing users to evacuate quickly or limit communication.

[1555] (Application example 2)

[1556] 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."

[1557] In recent years, there has been an increasing number of cases of sudden increases in communication traffic due to disasters and large-scale events, and there is a need for an appropriate prediction system to respond quickly to these situations. A notification mechanism is also needed to prompt general users to take appropriate action in real time. Conventional systems have inadequate means for predicting communication traffic by combining social media data and users' emotional responses, making it difficult to respond appropriately to sudden increases in traffic.

[1558] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting social media data, generative artificial intelligence means for analyzing the collected social media data, means for predicting communication traffic in real time based on the analysis results and an emotion score by an emotion engine, means for providing communication traffic prediction data to a telecommunications carrier or a disaster response organization, means for performing area tuning based on the provided communication traffic prediction data and the real-time importance score, and means for sending a real-time notification to a user. This enables a quick and appropriate response to a sudden increase in communication traffic, improving the safety of users and the communication network.

[1559] "Social Media Data" refers to information such as user posts and comments obtained from social media platforms such as Twitter and Facebook.

[1560] "Generative AI means" refers to AI that uses natural language processing techniques to analyze data, particularly for text classification and sentiment analysis.

[1561] An "emotion engine" is an algorithm or software that recognizes a user's emotions (happiness, sadness, anger, etc.) from collected data and assigns an emotion score.

[1562] "Communication traffic forecasting" is the process of combining historical communication data with real-time posting data and using machine learning algorithms to predict future fluctuations in communication traffic.

[1563] A "communications carrier" is a company or organization that provides communications services such as telephone and internet.

[1564] "Disaster response agencies" are public institutions and organizations that take measures in the event of disasters such as earthquakes, floods, and typhoons.

[1565] "Area tuning" refers to dynamically changing and optimizing the settings and configuration of a communication network in a specific area.

[1566] The "importance score" is an index that quantitatively evaluates the urgency and importance of collected data.

[1567] "Real-time notification" is a function that provides users with information immediately when a specific event or situation occurs.

[1568] The present invention relates to a system that uses social media data, generative artificial intelligence (AI), and an emotion engine to predict communication traffic in real time and encourages telecommunications carriers and disaster response organizations to take appropriate measures.

[1569] Social Media Data Collection

[1570] Server: The server uses the APIs of social media platforms to collect relevant data. Specifically, it uses the APIs of Twitter and Facebook to retrieve posts based on specific keywords (e.g., "power outage," "live," "earthquake") and stores the retrieved data in an internal database.

[1571] Data Preprocessing

[1572] Server: Removes unnecessary information from collected social media data. Specifically, it filters out spam posts and duplicate data and converts it into a format suitable for analysis. This process includes text normalization.

[1573] Data analysis

[1574] Server: The server analyzes the preprocessed data using generative artificial intelligence (AI) and an emotion engine. The generative AI uses natural language processing (NLP) techniques to classify posts into categories (e.g., disasters or events) and assigns an importance score to each post. Furthermore, the emotion engine recognizes user emotions (e.g., joy, sadness, anger, etc.) from the collected posts and assigns an emotion score to each post.

[1575] Communications traffic forecast

[1576] Server: The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. This predictive model combines historical traffic data with real-time posting data and uses machine learning algorithms to predict future traffic fluctuations.

[1577] Providing forecast data

[1578] Server: The server provides predictive data to telecommunications carriers and disaster response organizations. This data is displayed in real time via dashboards and APIs, allowing personnel to take immediate action. The results of the emotion engine's recognition are also displayed on the dashboard, making it even easier to understand the situation.

[1579] Performing area tuning

[1580] Telecommunications carrier's terminal: The telecommunications carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communications environment.

[1581] Sending real-time notifications

[1582] Server and user device: The server sends real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[1583] Hardware and software used

[1584] Hardware: Cloud server, smartphone (iOS or Android)

[1585] Software: Python, Flask, Tweepy (server side), React Native, Axios (client side)

[1586] Specific examples

[1587] For example, if there are many posts saying "There is a power outage in XX city," the server will refer to past data and predict a sudden increase in communication traffic in XX city. In this case, if the emotion engine sets high emotion scores for "anxiety" and "anger," the accuracy of traffic increase predictions will improve.

[1588] Prompt Sentence Examples

[1589] "Analyze data collected from social media based on keywords such as 'power outage,' 'earthquake,' and 'event,' and calculate a sentiment score and importance."

[1590] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1591] Step 1:

[1592] Social Media Data Collection

[1593] The server collects relevant data using APIs of social media platforms, such as Twitter and Facebook, to retrieve posts based on specific keywords (e.g., "power outage," "live," and "earthquake") and store them in an internal database.

[1594] Input: Social media platform API, specific keywords

[1595] Output: Collected social media data

[1596] What it does: The program uses the API key to retrieve social media data and saves it in JSON format.

[1597] Step 2:

[1598] Data Preprocessing

[1599] The server removes unnecessary information from the collected social media data, for example filtering out spam posts and duplicate data, and converts it into a format suitable for analysis. Text normalization also takes place at this stage.

[1600] Input: Collected social media data

[1601] Output: Preprocessed social media data

[1602] What you will do: Clean data using regular expressions and filtering algorithms to build a valid dataset.

[1603] Step 3:

[1604] Data analysis

[1605] The server analyzes the pre-processed data using a generative artificial intelligence (AI) and emotion engine. The generative AI uses NLP techniques to classify posts into categories (e.g., disasters or events) and assign importance scores. At the same time, the emotion engine recognizes users' emotions (e.g., joy, sadness, anger, etc.) and assigns emotion scores.

[1606] Input: Preprocessed social media data

[1607] Output: Analysis results (category classification, importance score, sentiment score)

[1608] What it does: Analyzes text using an NLP model to calculate categories and scores.

[1609] Step 4:

[1610] Communications traffic forecast

[1611] The server generates a traffic prediction model based on the analysis results of the generative AI and emotion engine. Past traffic data and real-time posting data are input into a machine learning algorithm to predict future traffic fluctuations.

[1612] Input: Analysis results, past traffic data

[1613] Output: Communication traffic forecast data

[1614] What it does: It uses machine learning algorithms to learn from data and generate predictive models.

[1615] Step 5:

[1616] Providing forecast data

[1617] The server provides telecommunications carriers and disaster response organizations with traffic forecast data, which is displayed in real time via a dashboard and API.

[1618] Input: Communication traffic forecast data

[1619] Output: Dashboard display data, API communication data

[1620] What it does: Formats the data, displays it in a dashboard, and serves it to an API endpoint.

[1621] Step 6:

[1622] Performing area tuning

[1623] The carrier's terminal receives the forecast data provided by the server and performs area tuning and strengthens equipment monitoring, thereby maintaining an optimal communication environment.

[1624] Input: Communication traffic forecast data

[1625] Output: Optimized communication network

[1626] Specific operation: Dynamically adjusts communication network settings based on predictive data to maintain optimal conditions.

[1627] Step 7:

[1628] Sending real-time notifications

[1629] The server and user device send real-time notifications to users based on the importance score and emotion score. Users can receive these notifications via their smartphones or other devices and take appropriate action depending on the situation, such as issuing evacuation orders or refraining from using communications.

[1630] Input: Importance score, sentiment score

[1631] Output: Real-time notification

[1632] Specific Actions: Use notifications to alert the user and provide specific instructions.

[1633] 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.

[1634] 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.

[1635] 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 robot 414.

[1636] 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.

[1637] 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.

[1638] 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.

[1639] 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).

[1640] 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.

[1641] 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."

[1642] 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.

[1643] 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).

[1644] 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.

[1645] 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.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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.

[1652] 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.

[1653] 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.

[1654] The following is further disclosed regarding the above embodiment.

[1655] (Claim 1)

[1656] A means of scraping social media data;

[1657] a generative artificial intelligence means for analyzing the collected social media data;

[1658] A means for predicting communication traffic in real time based on the analysis results;

[1659] A means of providing communication traffic forecast data to telecommunications carriers and disaster response organizations;

[1660] A system including means for performing area tuning based on provided communication traffic prediction data.

[1661] (Claim 2)

[1662] 10. The system of claim 1, further comprising means for categorizing and assigning importance scores to the collected social media data.

[1663] (Claim 3)

[1664] 10. The system of claim 1, further comprising a dashboard that displays the provided communication traffic forecast data in a user interface.

[1665] "Example 1"

[1666] (Claim 1)

[1667] a means for obtaining social media data;

[1668] a means using a generative artificial intelligence module to analyze the collected social media data;

[1669] A means for predicting communication traffic in real time based on the analysis results;

[1670] A means of providing predicted communication traffic data to telecommunications carriers and disaster response organizations;

[1671] A system including means for performing area tuning based on provided communication traffic prediction data.

[1672] (Claim 2)

[1673] 10. The system of claim 1, further comprising means for categorizing and assigning importance scores to the collected social media data.

[1674] (Claim 3)

[1675] 10. The system of claim 1, further comprising a dashboard that displays the provided communication traffic forecast data in a user interface.

[1676] "Application Example 1"

[1677] (Claim 1)

[1678] A means of scraping social media data;

[1679] a generative artificial intelligence means for analyzing the collected social media data;

[1680] A means for predicting communication traffic in real time based on the analysis results;

[1681] A means of providing communication traffic forecast data to telecommunications carriers and disaster response organizations;

[1682] means for performing area tuning based on the provided communication traffic prediction data;

[1683] A means of analyzing collected social media data to predict local security situations;

[1684] The system includes a means for sending notifications to users based on predicted local security conditions.

[1685] (Claim 2)

[1686] A means of categorizing and assigning importance scores to collected social media data;

[1687] a user interface for displaying regional security forecast data;

[1688] 10. The system of claim 1.

[1689] (Claim 3)

[1690] A dashboard that displays security forecast data and communication traffic forecast data for the area provided in a user interface.

[1691] 10. The system of claim 1.

[1692] "Example 2: Combining Emotion Engines"

[1693] (Claim 1)

[1694] A means of scraping social media data;

[1695] a means for preprocessing the collected social media data;

[1696] a generative artificial intelligence means for analyzing the collected social media data;

[1697] A means for predicting communication traffic in real time based on the analysis results;

[1698] A means of providing communication traffic forecast data to telecommunications carriers and disaster response organizations;

[1699] A system including means for performing area tuning based on provided communication traffic prediction data.

[1700] (Claim 2)

[1701] 10. The system of claim 1, further comprising means for categorizing the collected social media data and assigning importance and sentiment scores.

[1702] (Claim 3)

[1703] The system according to claim 1, further comprising a dashboard that displays the provided communication traffic forecast data and sentiment analysis results in a user interface.

[1704] "Application example 2 when combining emotion engines"

[1705] (Claim 1)

[1706] a means of collecting social media data;

[1707] a generative artificial intelligence means for analyzing the collected social media data;

[1708] A means for predicting communication traffic in real time based on the analysis results and the emotion score generated by the emotion engine;

[1709] A means of providing communication traffic forecast data to telecommunications carriers and disaster response organizations;

[1710] means for performing area tuning based on the provided communication traffic prediction data and real-time importance scores;

[1711] A system including means for sending real-time notifications to a user.

[1712] (Claim 2)

[1713] 10. The system of claim 1, further comprising means for categorizing the collected social media data and assigning importance and sentiment scores.

[1714] (Claim 3)

[1715] 10. The system of claim 1, further comprising a dashboard that displays the provided communication traffic forecast data and importance scores in a user interface. [Explanation of symbols]

[1716] 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 scraping social media data; a generative artificial intelligence means for analyzing the collected social media data; A means for predicting communication traffic in real time based on the analysis results; A means of providing communication traffic forecast data to telecommunications carriers and disaster response organizations; A system including means for performing area tuning based on provided communication traffic prediction data.

2. The system of claim 1 , further comprising means for categorizing and assigning importance scores to the collected social media data.

3. The system according to claim 1 , further comprising a dashboard that displays the provided communication traffic forecast data in a user interface.

Images