system

Abstract

A system is provided.SOLUTION: A system comprising: means for monitoring posts of an SNS platform in real-time; means for detecting a post including a particular keyword; means for deleting the detected post; and means for displaying a warning about the deleted post to a user.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] When a disaster occurs, hoax posts containing specific keywords such as "address," "name," and "please spread the word" frequently appear on social media platforms. These hoax posts are likely to disrupt and hinder rescue efforts. The present invention aims to provide a system that prevents the spread of hoax posts during disasters and supports rapid rescue efforts. Specifically, the objective is to reduce the disruption of rescue efforts by monitoring and detecting hoax posts on social media in real time during a disaster and deleting or displaying a warning. [Means for solving the problem]

[0005] The present invention is a system that monitors posts on social media platforms in real time, detecting posts containing specific keywords, deleting detected posts, and displaying warnings to users about deleted posts. Specific keywords, such as "address," "name," and "please spread the word," are set, and an algorithm is used to automatically detect these. Furthermore, posts determined to be hoax posts are deleted or marked as fake to alert users. This allows for responses before hoax posts are spread, effectively reducing interference with rescue operations.

[0006] An "SNS platform" is an online service that allows users to share information and communicate over the Internet.

[0007] "Monitoring" is the act of continuously observing specific activities or data to detect changes or anomalies.

[0008] "Keywords" are important words or phrases used to search for and categorize specific information or content.

[0009] A "Post" is any content, message, or comment created and published by a User on a Social Media Platform.

[0010] "Discovery" is the act of identifying data or information that matches certain conditions or patterns.

[0011] "Deletion" is the act of completely removing data or information from a system.

[0012] A "warning" is a message or indication that notifies or alerts the user to a particular risk or problem.

[0013] "User" means an individual or organization that sends or receives information using the SNS platform.

[0014] A "fake mark" is a visual indicator or label used to indicate that a particular post may be false. [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 automatically monitors posts of false information on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake. Specific embodiments for carrying out the present invention will be described below.

[0037] System Overview

[0038] This system consists of a server, a terminal, and a user component. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please spread"), and takes appropriate action accordingly. The terminal is an interface that displays fake marks and notifies users with warning messages. Users send and receive information on a daily basis.

[0039] Server Operation

[0040] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[0041] If a post containing a specific keyword is detected, the server will either: First, delete the post via the social media platform's API. The deletion process involves obtaining the ID associated with the post and using this to permanently remove it from the database. Second, it will log the completion of the deletion and notify an administrator if necessary.

[0042] Alternatively, the server can mark detected posts as fake and warn users when they view the posts. This method is effective when it is deemed unnecessary to remove the posts or when immediate removal is technically difficult.

[0043] Device behavior

[0044] The device receives a notification from the server and marks the post as fake. Specifically, a warning icon or message is placed next to the post to inform the user that the post may be a hoax. The warning message includes a statement such as "⚠️ This post may be a hoax."

[0045] User Actions

[0046] Users use social media platforms on a daily basis to send and receive information. When users access posts marked with a fake symbol or warning message, they can recognize that the post is likely a hoax and respond appropriately. This can prevent the spread of false information and minimize confusion during disasters.

[0047] Specific examples

[0048] For example, if user A posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[0049] This invention makes it possible to quickly respond to false information posted during a disaster before it spreads and minimize disruption to rescue operations, which is a system that improves the efficiency of disaster response and helps save many lives.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[0053] Step 2:

[0054] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[0055] Step 3:

[0056] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[0057] Step 4:

[0058] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[0059] Step 5:

[0060] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[0061] Step 6:

[0062] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[0063] Step 7:

[0064] The device receives the fake mark information sent from the server and displays it appropriately on the user interface, specifically by placing a warning icon or message next to the relevant post.

[0065] Step 8:

[0066] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[0067] Step 9:

[0068] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[0069] Example 1

[0070] 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."

[0071] When a disaster occurs, the rapid spread of false information on social media can cause serious disruptions to rescue efforts and information gathering. For example, the spread of posts containing false addresses, names, or urgent requests for dissemination can lead to inappropriate use of resources by relevant agencies, which can delay truly necessary rescue efforts. A system that can prevent such situations and effectively suppress the spread of false information is needed.

[0072] 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.

[0073] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for analyzing and detecting posts containing specific keywords using natural language processing technology, means for deleting the detected posts, and means for displaying a warning to users about the deleted posts. This allows false information to be quickly detected and deleted, and a warning to be displayed to users, thereby preventing the spread of false information.

[0074] An "SNS platform" is a virtual space that provides services that allow users to share information and communicate online.

[0075] "Real-time" refers to the time characteristic in which data or information is processed immediately without delay.

[0076] "Monitoring" refers to the act of continuously observing specific events or data to detect anomalies or significant changes.

[0077] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes text analysis and language generation.

[0078] A "keyword" is an important word that symbolizes specific information and is used to represent the content or category of that information.

[0079] "Analysis and detection" is the process of examining and analyzing collected data in detail to identify specific patterns and information.

[0080] "Post" refers to any type of content such as text, images, or videos that a user publishes on a social media platform.

[0081] "Deletion" refers to the act of completely removing data or information from a system or database.

[0082] "Warning" refers to a message or signal that alerts the user to risks or caution.

[0083] "User" refers to an individual or organization that sends and receives information using the SNS platform.

[0084] A "fake mark" is a visual symbol or icon that indicates that certain information is likely not true.

[0085] MODE FOR CARRYING OUT THE INVENTION

[0086] The present invention is a system that automatically detects and removes false information spread on social media in the event of a disaster, and displays a warning to users. Specific embodiments for carrying out the present invention will be described below.

[0087] System Components

[0088] This system consists of three main components: a server, a terminal, and a user. The server retrieves and analyzes posted data from the SNS platform in real time. The terminal is an interface that notifies users of warning messages about false information and marks fakes. Users are individuals or organizations that use the SNS platform on a daily basis.

[0089] Server Operation

[0090] The server first starts streaming real-time post data through the social media platform's API. Specifically, it uses a programming language such as Python and a machine learning framework such as TENSORFLOW (registered trademark) or PyTorch. The server is typically run using a hosting service or cloud infrastructure. The server analyzes the acquired post data and uses natural language processing (NLP) techniques to detect whether specific keywords are included. NLP libraries such as spaCy and NLTK are used for this analysis.

[0091] For example, if the server detects a post containing keywords such as "address," "name," or "please spread the word," it will flag the post. This flagged post will then be either deleted or marked as fake based on a set algorithm, as explained below.

[0092] Device behavior

[0093] The device receives the notification from the server and displays a fake mark or a warning message on the relevant post. This is typically done using the UI components of the social networking application. For example, a warning icon or a message such as "⚠️ This post may be a hoax" can be displayed next to a specific post to warn the user.

[0094] User Actions

[0095] Users will see posts marked with a fake symbol or warning message on the social media platforms they use daily. This will make users aware that the post is likely to be a hoax and encourage them to handle the information with caution. This will prevent the spread of false information and reduce confusion during disasters.

[0096] Specific examples

[0097] For example, if user A posts "Address: XX, Name: △△, please help. Please spread the word" during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[0098] Prompt Sentence Examples

[0099] "Please describe a system that automatically monitors posts about disaster-related misinformation, detects posts containing specific keywords, and removes or issues a warning. Please provide details about how this system works, including specific examples of the techniques and tools used."

[0100] In this way, the present invention allows for the rapid detection and response to false information, ensuring that users receive accurate information, thereby preventing confusion during disasters and enabling effective rescue operations.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] The flow of this system's program processing

[0103] Step 1:

[0104] The server retrieves post data in real time using the API of the social media platform. A specific API call initiates the reception of streaming data. The input is the social media post data, and the output is the streamed post data. This streaming data includes detailed information about each post (text, posting time, poster information, etc.).

[0105] Step 2:

[0106] The server analyzes the posted data it acquires using natural language processing (NLP) technology. NLP libraries used include spaCy and NLTK. The input is the streamed posted data, and the output is the results of keyword analysis (whether or not a specific keyword is included). Specifically, text analysis is performed to check for the presence of keywords such as "address," "name," and "please share."

[0107] Step 3:

[0108] The server detects posts containing specific keywords. Based on the analysis results, it flags posts that may be hoaxes. The input is the keyword analysis results, and the output is the flagged posts. Specifically, the flagged posts are sent to the next processing step.

[0109] Step 4:

[0110] The server selects whether to delete or flag a flagged post. First, if a post is to be deleted based on specific conditions, the SNS API is called to send a deletion request for each post ID. The input is the flagged post data, and the output is the deletion success / failure status. In another case, the metadata is updated to mark the post as fake. Specifically, the server updates the settings to add a hoax warning icon and message.

[0111] Step 5:

[0112] The server logs the process and notifies the administrator. After the deletion or flagging is complete, the result is recorded in a log file or database, and the administrator is notified as needed. The input is the result data of the deletion or flagging, and the output is the recorded log information and the status of the notified administrator. Specifically, the log records details such as the post ID, processing content, and execution time.

[0113] Step 6:

[0114] The device receives the notification from the server and displays a warning to the user. Specifically, it applies updated data containing a fake mark and a warning message to the SNS application and displays it on the user's screen. The input is the warning message and fake mark instructions from the server, and the output is the warning information displayed on the user's interface.

[0115] Step 7:

[0116] Users check the warning message and correct their behavior. When users see a warning message or a post marked as fake, they recognize that it may be a hoax. The input is the warning message displayed on the device, and the output is for users to be more cautious in their actions. Specifically, users should refrain from sharing hoax information and strive to gather accurate information.

[0117] Through the above processing steps, this system can effectively detect and delete false information and display warnings, thereby increasing the reliability of information during disasters.

[0118] (Application example 1)

[0119] 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."

[0120] The spread of misinformation and rumours is a serious problem on modern social media platforms. Particularly during disasters and crises, misinformation can spread quickly, causing significant confusion and panic. This can hinder rescue efforts and lead to actions based on false information. Advertisers also face the risk of damaging their brand's credibility. A system is needed to resolve these issues and ensure accurate information is shared.

[0121] 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.

[0122] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for deleting the detected posts, means for displaying warnings about the deleted posts, and means for detecting false information related to advertisers in real time and issuing alerts. This allows accurate information to be disseminated quickly even during disasters or crisis situations, preventing the spread of false information and protecting the brand credibility of advertisers.

[0123] "SNS platform" refers to software or websites that allow users to share information and communicate online.

[0124] "Real time" refers to the ability to process events and data almost simultaneously.

[0125] "Monitoring" refers to the act of watching for events or data on a particular system or network.

[0126] "Specific keywords" refer to the specific words or phrases the system is configured to detect.

[0127] "Post" refers to a message or content that a user publishes on a social media platform.

[0128] "Detection" refers to the act of a system finding data or events that meet set conditions.

[0129] "Deletion" refers to the act of completely removing specific data or information from a system.

[0130] "Warning" refers to a notification that alerts the user to a risk or problem.

[0131] "Advertiser" refers to a company or individual that places advertisements to promote products or services.

[0132] "Misinformation" refers to information that is not based on facts or is false.

[0133] "Alert" refers to a warning message that notifies you of important information or an emergency.

[0134] MODE FOR CARRYING OUT THE INVENTION

[0135] This invention is a system for preventing the spread of misinformation and rumours, and for protecting the reliability of information, particularly that related to advertisers. The system consists of components: a server, a terminal, and a user. The server retrieves post data from social media platforms in real time, detects posts containing specific keywords, and takes action as necessary. The terminal is an interface that notifies the user of alerts regarding detected misinformation. The user can then take prompt action based on this information.

[0136] Server Operation

[0137] The server first starts streaming real-time post data through the social media platform's API. It authenticates using the social media platform's API key and token to retrieve the post data. It then analyzes the retrieved post data to detect whether it contains specific keywords. Keywords used include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." The analysis process uses the Python tweepy library.

[0138] If a post is detected, the server takes the following actions. First, it deletes the detected post. During the deletion process, it uses the API of the social media platform to obtain the ID of the post in question and uses it to delete the post from the database. Once the deletion is complete, the server logs the completion and notifies the administrator.

[0139] Instead of removing the post, the system will mark it as inauthentic and warn users when they view it. The warning message will include a statement such as "⚠️ This post may be misinformation." Additionally, if misinformation relevant to an advertiser is detected, the system will identify high-risk posts and send an alert to the advertiser. The alert will include the content of the post and a risk assessment.

[0140] Device behavior

[0141] The device receives notifications from the server and displays fake marks and warning messages on posts. It runs on the user's device as a social networking client application and can issue warnings directly to posts on the social networking platforms the user uses. The device also provides an interface to alert advertisers about misinformation, allowing them to take swift action and maintain the credibility of their brand.

[0142] User Actions

[0143] Users use social media platforms on a daily basis to send and receive information. When users access a post marked with a misinformation symbol or a warning message, they can recognize that the post is likely to be a hoax or misinformation and respond appropriately. For example, they can report the problematic post or take measures to spread accurate information.

[0144] Specific examples

[0145] A specific scenario for using the system is when an advertiser posts false information on social media during a disaster, such as "The relief supplies provided by Company X are fake." The server detects this post and sends an alert to the advertiser as risk information related to the post. It also displays a warning mark to general users, informing them that the information is likely to be incorrect.

[0146] Prompt Sentence Examples

[0147] Set up a misinformation monitoring system for advertisers. Monitor social media posts containing specified keywords in real time and display a warning icon for relevant posts. Specific keywords include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." Build a system that sends alerts to advertisers for detected posts.

[0148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0149] Step 1:

[0150] The server authenticates using the social media platform's API, using the API key and token as input and getting an authentication token as output. Using this authentication token, the server prepares to retrieve real-time posting data.

[0151] Step 2:

[0152] The server streams post data in real time from the social media platform through its API. It takes an authentication token as input and gets a stream of post data as output. This stream contains all posts published on the social media platform.

[0153] Step 3:

[0154] The server parses the streamed post data. It takes the stream data as input and uses a regular expression library to analyze it for specific keywords. It generates a list of posts that contain the specific keywords as output.

[0155] Step 4:

[0156] The server determines how to deal with each detected post. As input, it uses a list of posts containing specific keywords. To process the data, it performs a risk assessment on the post and decides whether to delete it or mark it with a warning. As output, it generates a list of posts to be deleted and a list of posts to be marked with a warning.

[0157] Step 5:

[0158] The server uses the SNS platform's API to process the posts to be deleted. It uses the list of posts to be deleted as input and sends an API request to delete the relevant posts from the database. As output, it logs a deletion completion notification and notifies the administrator.

[0159] Step 6:

[0160] The server marks posts that are eligible for warning marking. It uses the list of posts that are eligible for warning marking as input and adds warning marks to the corresponding posts in the database. As output, it logs a notification that the warning mark has been added and generates data to notify the user.

[0161] Step 7:

[0162] The device receives the notification about the warning mark sent from the server. As input, it uses the warning mark notification data sent from the server and processes the display of a warning icon in the SNS client application. As output, the warning icon is displayed to the user in response to the SNS post.

[0163] Step 8:

[0164] If misinformation related to an advertiser is detected, the server sends an alert to the advertiser. The input is the posted data of misinformation related to the advertiser. The data is processed by performing a risk assessment and generating an alert message. The output is an alert notification sent to the advertiser.

[0165] Step 9:

[0166] The user receives a warning icon or alert notification. As input, the user recognizes the warning icon or alert notification displayed on the device and checks the warning content regarding the misinformation. As output, the user can take appropriate action.

[0167] Step 10:

[0168] The server records all processing results in a log. The inputs used are deletion completion notification, warning mark attachment notification, and alert sending notification. Data processing involves adding a timestamp to all actions and saving them in a log database. The output is a log that the system administrator can check.

[0169] In this way, a system is built in which the server, terminals, and users work together to prevent the spread of misinformation and hoaxes and protect the brand credibility of advertisers.

[0170] 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.

[0171] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[0172] System Overview

[0173] This system consists of a server, a terminal, and a user. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please share"), and recognizes the user's emotions using an emotion engine. The terminal provides the user with an interface for displaying appropriate warning messages and fake marks. Users use the SNS platform on a daily basis to send and receive information.

[0174] Server Operation

[0175] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[0176] If a post containing a specific keyword is detected, the server then initiates a sentiment analysis of the post using a sentiment engine, which uses machine learning algorithms to identify the user's emotions from the post's text data, categorizing them into basic emotional categories such as joy, anger, sadness, and fear.

[0177] Processing Posts

[0178] For posts whose emotions have been identified by the emotion engine, the server takes the following actions. First, if the post is determined to be a hoax, it is deleted. In the deletion process, the database is accessed using the post's ID as a key to completely remove the post. When the deletion is complete, the information is recorded in a log.

[0179] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[0180] Device behavior

[0181] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to inform the user that the post may be a hoax.

[0182] User Actions

[0183] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post's content. This allows users to take appropriate action and prevent the spread of false information.

[0184] Specific examples

[0185] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[0186] The present invention makes it possible to effectively prevent the spread of false information during disasters and to provide appropriate warning messages according to the emotional state of users, thereby facilitating rescue operations and saving many lives.

[0187] The processing flow will be explained below.

[0188] Step 1:

[0189] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[0190] Step 2:

[0191] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[0192] Step 3:

[0193] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[0194] Step 4:

[0195] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[0196] Step 5:

[0197] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[0198] Step 6:

[0199] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[0200] Step 7:

[0201] The server uses an emotion engine to analyze the sentiment of posts containing specific keywords. The emotion engine identifies the user's emotions (e.g., "joy," "anger," "sadness," "fear," etc.) from the content of the post. The emotion engine uses machine learning algorithms to classify the text data.

[0202] Step 8:

[0203] The server generates a warning message appropriate for the user based on the emotion identified by the emotion engine. For example, if the emotion is identified as "fear," the server creates a warning message such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0204] Step 9:

[0205] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post.

[0206] Step 10:

[0207] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[0208] Step 11:

[0209] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[0210] Example 2

[0211] 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."

[0212] Social media platforms have become an important means of information transmission in modern times, but in times of disaster, false information can easily spread, resulting in confusion and panic. Furthermore, depending on the content of the false information, it may have an emotional impact on users, causing anxiety and fear. To solve these problems, real-time detection and appropriate processing of false posts is necessary, and a warning system that takes user emotions into account is also required.

[0213] 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.

[0214] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for analyzing the sentiment of the detected posts, means for determining whether the posts are hoaxes based on the sentiment analysis results, means for deleting posts determined to be hoaxes, means for displaying a fake mark when deletion is difficult, means for generating a warning message based on the sentiment, and means for displaying the generated warning message on the user's device. This enables the rapid detection and deletion of hoaxes or appropriate warnings to users, thereby preventing the spread of hoaxes while minimizing the emotional impact on users.

[0215] An "SNS platform" is an online service that allows users to share information and communicate with others.

[0216] "Real-time" means that information and data are processed immediately and provided without delay.

[0217] "Monitoring" is the act of continuously observing a specific object and supervising its situation.

[0218] "Keywords" are key words or phrases used to locate specific information.

[0219] "Analyzing sentiment" is the process of determining the emotional state of a writer from text data.

[0220] A "hoax" is false information that is spread intentionally or accidentally.

[0221] "Hoax assessment" is the process of assessing whether information is true or false.

[0222] A "fake mark" is an identifying icon that indicates that certain information is likely to be false.

[0223] A "warning message" is a notification message that warns users of risks and cautions them.

[0224] A "terminal" is an electronic device that a user uses to send and receive information.

[0225] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[0226] Hardware and software used

[0227] server

[0228] Hardware: High-performance data center servers (e.g., general-purpose high-performance servers)

[0229] Software: API of social media platform, Python, Pandas, syntax analysis library (e.g., natural language processing library), machine learning library (e.g., machine learning framework)

[0230] Terminal

[0231] Hardware: Regular PCs and mobile devices (e.g., laptops and smartphones)

[0232] Software: Web browsers (e.g., internet browsers), dedicated applications (e.g., apps developed using cross-platform frameworks)

[0233] User

[0234] Hardware: Same as above (regular PC or mobile device)

[0235] Software: Same as above

[0236] Explanation of the system processing flow

[0237] 1. Collecting social media posting data

[0238] The server starts streaming real-time post data through the social media platform's API, and uses a Python library to retrieve the data and convert it into the format required for analysis.

[0239] 2. Keyword detection

[0240] The server stores the retrieved post data in a data frame and uses a syntax analysis library to detect specific keywords (e.g., "address," "name," "please share") This analysis involves text tokenization and keyword matching.

[0241] 3. Sentiment analysis

[0242] The server runs an emotion engine based on the keyword detection results to perform sentiment analysis of the posts, classifying them into emotion categories (e.g., joy, anger, sadness, fear) using a machine learning library.

[0243] 4. Post Judgment and Processing

[0244] The server judges the post based on the analysis results of the emotion engine. If it is judged to be a hoax, the server accesses the database and deletes the post. If deletion is difficult, the server marks the post as fake and records a log of the deletion process.

[0245] 5. Warning message generation and display

[0246] The server generates a warning message based on the emotion analysis results. For example, if "fear" is identified, the server generates a message saying "⚠️ This post may be a hoax. Please be careful as the content may be disturbing" and sends it to the device. The device then displays this message on the user interface.

[0247] Specific examples

[0248] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[0249] Prompt Sentence Examples

[0250] Recognize the sentiment of the post "Address: XX, Name: △△, Please help. Please spread the word.", determine whether it is a hoax, and delete it. Please describe the steps required to build a system that uses an emotion engine to identify sentiment and generate and display a warning message as necessary.

[0251] This detailed description clarifies the specific operations of each processing step of the system. Understanding what happens at each step makes it easier to grasp the overall function of the system.

[0252] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0253] The flow of this system's program processing

[0254] Step 1: Collect social media post data

[0255] Step 2: Keyword detection

[0256] Step 3: Sentiment analysis

[0257] Step 4: Identifying and Processing Posts

[0258] Step 5: Generate and display warning messages

[0259] Detailed explanation of the processing steps

[0260] Step 1: Collect social media post data

[0261] Input: The server receives post data through the API of the social networking platform.

[0262] How it works: The server collects real-time posting data via the API of the social media platform, starts data streaming using a Python library (e.g., Tweepy), and converts the collected data into a data frame.

[0263] Output: Streaming data is stored on the server as a data frame.

[0264] Step 2: Keyword detection

[0265] Input: Streaming data exists on the server as a DataFrame.

[0266] How it works: The server uses a syntax analysis library (e.g., SpaCy) to detect specific keywords (e.g., "address," "name," "please share") in the post data. This analysis involves tokenizing the text and keyword matching.

[0267] Output: Posts in which the keyword was found are identified and the appropriate rows are flagged.

[0268] Step 3: Sentiment analysis

[0269] Input: Post data with keyword detection completed.

[0270] How it works: The server uses a sentiment engine (e.g., a BERT-based machine learning model) to analyze the sentiment of the detected posts, classify them into sentiment categories (e.g., joy, anger, sadness, fear), and add the results to a data frame.

[0271] Output: Generates sentiment-identified post data and adds sentiment categories to each post.

[0272] Step 4: Identifying and Processing Posts

[0273] Input: Post data that has undergone keyword detection and sentiment analysis.

[0274] Operation: The server judges the post based on the analysis results of the emotion engine. If it is judged to be a hoax, it accesses a database (e.g., MySQL (registered trademark)) and deletes the post. If it is difficult to delete or there is no need to delete it immediately, it marks the post as fake. At this time, it records logs of the deletion process and the marking of the post as fake.

[0275] Output: Data on posts that were deleted or marked as fake is generated and logged.

[0276] Step 5: Generate and display warning messages

[0277] Input: Post data that has been identified as a hoax or marked as fake.

[0278] Operation: The server generates a warning message based on the results of the sentiment analysis. For example, if "fear" is identified, the server generates a message stating "This post may be a hoax. Please be careful as the content may be disturbing," and sends it to the user's device via the user interface. The device then displays this warning message on its screen.

[0279] Output: A warning message is generated and displayed on the user's terminal.

[0280] The above is a detailed explanation of the system's specific processing steps and their operation. It details what data is input at each step, what processing is performed, and what output is obtained.

[0281] (Application example 2)

[0282] 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."

[0283] During disasters and emergencies, false information spreads rapidly on social media, causing anxiety and confusion among many users. This can also cause confusion and hinder rescue efforts, so there is a need for a method to quickly and effectively prevent the spread of false information. Furthermore, measures are also needed to ensure that users can obtain accurate information without being emotionally affected.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0285] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for performing emotion recognition on the detected posts using an emotion engine, means for deleting the detected posts, means for marking the detected posts as fake if deletion is difficult or not necessary immediately, and means for generating a warning message based on the identified emotion, and means for displaying the generated warning message on a user interface. This allows users to receive appropriate warnings while preventing the spread of false information.

[0286] An "SNS platform" is a software service that allows users to disseminate information and interact with others online.

[0287] "Real-time monitoring means" refers to technology that allows for instant monitoring and analysis of posts on social media platforms.

[0288] "Specific keywords" are words used to identify specific content, such as "address," "name," or "please share."

[0289] The "means for detecting posts" refers to technology for finding posts containing specific keywords from posts on social media platforms that are monitored in real time.

[0290] An "emotion engine" is an algorithm or system that analyzes text data contained in posts and identifies user emotions.

[0291] "Means for emotion recognition" refers to technology that uses an emotion engine to identify a user's emotional state from the text of a post.

[0292] "Methods for removing posts" refers to techniques used to physically remove posts determined to be false from social media platforms.

[0293] "Means of assigning fake marks" refers to a technology that adds a mark to problematic posts to visually warn users.

[0294] A "warning message" is a message that informs users that a post may be a hoax and urges them to be careful.

[0295] The "means for generating" is a technology for creating a warning message or a counterfeit mark based on specific conditions.

[0296] A "user interface" is the screen and operating environment through which a user interacts with a system.

[0297] The "display means" refers to a technique for visually displaying the generated warning message or fake mark on the user interface.

[0298] A "generative AI model" is an artificial intelligence model used to determine the output generated from input data.

[0299] A "prompt" is a sentence used as input to a generative AI model, and is an instruction to produce a specific output based on its content.

[0300] An embodiment of the present invention will be described below.

[0301] System Overview

[0302] This system monitors posts on social media platforms in real time, detects posts containing specific keywords, and uses an emotion engine to recognize the emotions in the posts. If detected posts are determined to be hoaxes, they are deleted, or if deletion is difficult, they are marked as fake. A warning message based on the emotion is displayed on the user interface.

[0303] Server Operation

[0304] The server streams post data in real time through the API of the social media platform. The server analyzes the received post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). If a post containing specific keywords is detected, it performs a sentiment analysis of the post content using an emotion engine. The emotion engine uses a machine learning algorithm (e.g., TextBlob) to identify the user's emotions from the text data of the post. These emotions are classified into basic emotional categories such as joy, anger, sadness, and fear.

[0305] Processing Posts

[0306] For posts whose emotions have been identified by the emotion engine, the server responds as follows: First, if the post is determined to be a hoax, it is deleted. The deletion process involves accessing the database using the post's ID as a key and completely removing the post. Once the deletion is complete, the information is recorded in a log.

[0307] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[0308] Device behavior

[0309] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to notify the user that the post may be a hoax.

[0310] User Actions

[0311] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post. This allows users to take appropriate action and prevent the spread of hoax information.

[0312] Specific examples

[0313] For example, if a user posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "Address," "Name," and "Please spread the word." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes the post and logs the completion of the deletion. In another scenario, the server marks the post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on its user interface to alert the user.

[0314] Example prompt sentence:

[0315] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0317] Step 1:

[0318] The server starts streaming post data through the SNS platform's API. As input, it receives the SNS platform's API key and the real-time stream of post data. This allows the server to continuously obtain new post data. The output is the obtained SNS post data.

[0319] Step 2:

[0320] The server analyzes the acquired post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). The input is the acquired post data, and the output is a list of posts in which specific keywords are detected. The server parses the text in the post data and checks whether the specific keywords are present.

[0321] Step 3:

[0322] The server uses an emotion engine to perform emotion recognition on posts containing specific keywords. The input is post data containing specific keywords, and the emotion is identified using a machine learning algorithm (e.g., TextBlob). The output is the emotion category (e.g., joy, anger, sadness, fear) corresponding to each post.

[0323] Step 4:

[0324] The server determines whether posts with identified emotions are hoaxes. The input is post data with emotional categories, and the server uses a hoax detection algorithm to determine whether a post is a hoax. The output is a list of posts that are determined to be hoaxes.

[0325] Step 5:

[0326] The server deletes posts that are determined to be hoaxes. The input is the post data that was determined to be hoax, and the post ID is used to delete it from the database. The output is a log of the completion of the deletion process. If deletion is difficult or there is no need to delete it immediately, proceed to the next step.

[0327] Step 6:

[0328] The server marks posts that are difficult to delete as fake and generates a warning message based on emotion using a generative AI model. The input is the post data that cannot be deleted and its emotion category, and the output is the post data marked as fake and the generated warning message. The server sends a prompt sentence as input to the generative AI model and receives an appropriate warning message. Example:

[0329] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0330] Step 7:

[0331] The terminal receives the fake mark and warning message sent from the server and displays them on the user interface. The input is the fake mark and warning message sent from the server, and the output is a visual display on the user interface. Based on this, the user can judge the content of the post and take appropriate action.

[0332] 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.

[0333] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0334] 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.

[0335] [Second embodiment]

[0336] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0337] 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.

[0338] 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).

[0339] 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.

[0340] 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.

[0341] 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).

[0342] 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.

[0343] 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.

[0344] 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.

[0345] 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.

[0346] 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.

[0347] 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."

[0348] The present invention relates to a system that automatically monitors posts of false information on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake. Specific embodiments for carrying out the present invention will be described below.

[0349] System Overview

[0350] This system consists of a server, a terminal, and a user component. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please spread"), and takes appropriate action accordingly. The terminal is an interface that displays fake marks and notifies users with warning messages. Users send and receive information on a daily basis.

[0351] Server Operation

[0352] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[0353] If a post containing a specific keyword is detected, the server will either: First, delete the post via the social media platform's API. The deletion process involves obtaining the ID associated with the post and using this to permanently remove it from the database. Second, it will log the completion of the deletion and notify an administrator if necessary.

[0354] Alternatively, the server can mark detected posts as fake and warn users when they view the posts. This method is effective when it is deemed unnecessary to remove the posts or when immediate removal is technically difficult.

[0355] Device behavior

[0356] The device receives a notification from the server and marks the post as fake. Specifically, a warning icon or message is placed next to the post to inform the user that the post may be a hoax. The warning message includes a statement such as "⚠️ This post may be a hoax."

[0357] User Actions

[0358] Users use social media platforms on a daily basis to send and receive information. When users access posts marked with a fake symbol or warning message, they can recognize that the post is likely a hoax and respond appropriately. This can prevent the spread of false information and minimize confusion during disasters.

[0359] Specific examples

[0360] For example, if user A posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[0361] This invention makes it possible to quickly respond to false information posted during a disaster before it spreads and minimize disruption to rescue operations, which is a system that improves the efficiency of disaster response and helps save many lives.

[0362] The processing flow will be explained below.

[0363] Step 1:

[0364] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[0365] Step 2:

[0366] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[0367] Step 3:

[0368] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[0369] Step 4:

[0370] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[0371] Step 5:

[0372] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[0373] Step 6:

[0374] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[0375] Step 7:

[0376] The device receives the fake mark information sent from the server and displays it appropriately on the user interface, specifically by placing a warning icon or message next to the relevant post.

[0377] Step 8:

[0378] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[0379] Step 9:

[0380] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[0381] Example 1

[0382] 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."

[0383] When a disaster occurs, the rapid spread of false information on social media can cause serious disruptions to rescue efforts and information gathering. For example, the spread of posts containing false addresses, names, or urgent requests for dissemination can lead to inappropriate use of resources by relevant agencies, which can delay truly necessary rescue efforts. A system that can prevent such situations and effectively suppress the spread of false information is needed.

[0384] 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.

[0385] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for analyzing and detecting posts containing specific keywords using natural language processing technology, means for deleting the detected posts, and means for displaying a warning to users about the deleted posts. This allows false information to be quickly detected and deleted, and a warning to be displayed to users, thereby preventing the spread of false information.

[0386] An "SNS platform" is a virtual space that provides services that allow users to share information and communicate online.

[0387] "Real-time" refers to the time characteristic in which data or information is processed immediately without delay.

[0388] "Monitoring" refers to the act of continuously observing specific events or data to detect anomalies or significant changes.

[0389] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes text analysis and language generation.

[0390] A "keyword" is an important word that symbolizes specific information and is used to represent the content or category of that information.

[0391] "Analysis and detection" is the process of examining and analyzing collected data in detail to identify specific patterns and information.

[0392] "Post" refers to any type of content such as text, images, or videos that a user publishes on a social media platform.

[0393] "Deletion" refers to the act of completely removing data or information from a system or database.

[0394] "Warning" refers to a message or signal that alerts the user to risks or caution.

[0395] "User" refers to an individual or organization that sends and receives information using the SNS platform.

[0396] A "fake mark" is a visual symbol or icon that indicates that certain information is likely not true.

[0397] MODE FOR CARRYING OUT THE INVENTION

[0398] The present invention is a system that automatically detects and removes false information spread on social media in the event of a disaster, and displays a warning to users. Specific embodiments for carrying out the present invention will be described below.

[0399] System Components

[0400] This system consists of three main components: a server, a terminal, and a user. The server retrieves and analyzes posted data from the SNS platform in real time. The terminal is an interface that notifies users of warning messages about false information and marks fakes. Users are individuals or organizations that use the SNS platform on a daily basis.

[0401] Server Operation

[0402] The server first starts streaming real-time post data through the social media platform's API. Specifically, it uses a programming language such as Python and a machine learning framework such as TensorFlow or PyTorch. The server is typically run using a hosting service or cloud infrastructure. The server then analyzes the acquired post data and uses natural language processing (NLP) techniques to detect whether specific keywords are included. NLP libraries such as spaCy and NLTK are used for this analysis.

[0403] For example, if the server detects a post containing keywords such as "address," "name," or "please spread the word," it will flag the post. This flagged post will then be either deleted or marked as fake based on a set algorithm, as explained below.

[0404] Device behavior

[0405] The device receives the notification from the server and displays a fake mark or a warning message on the relevant post. This is typically done using the UI components of the social networking application. For example, a warning icon or a message such as "⚠️ This post may be a hoax" can be displayed next to a specific post to warn the user.

[0406] User Actions

[0407] Users will see posts marked with a fake symbol or warning message on the social media platforms they use daily. This will make users aware that the post is likely to be a hoax and encourage them to handle the information with caution. This will prevent the spread of false information and reduce confusion during disasters.

[0408] Specific examples

[0409] For example, if user A posts "Address: XX, Name: △△, please help. Please spread the word" during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[0410] Prompt Sentence Examples

[0411] "Please describe a system that automatically monitors posts about disaster-related misinformation, detects posts containing specific keywords, and removes or issues a warning. Please provide details about how this system works, including specific examples of the techniques and tools used."

[0412] In this way, the present invention allows for the rapid detection and response to false information, ensuring that users receive accurate information, thereby preventing confusion during disasters and enabling effective rescue operations.

[0413] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0414] The flow of this system's program processing

[0415] Step 1:

[0416] The server retrieves post data in real time using the API of the social media platform. A specific API call initiates the reception of streaming data. The input is the social media post data, and the output is the streamed post data. This streaming data includes detailed information about each post (text, posting time, poster information, etc.).

[0417] Step 2:

[0418] The server analyzes the posted data it acquires using natural language processing (NLP) technology. NLP libraries used include spaCy and NLTK. The input is the streamed posted data, and the output is the results of keyword analysis (whether or not a specific keyword is included). Specifically, text analysis is performed to check for the presence of keywords such as "address," "name," and "please share."

[0419] Step 3:

[0420] The server detects posts containing specific keywords. Based on the analysis results, it flags posts that may be hoaxes. The input is the keyword analysis results, and the output is the flagged posts. Specifically, the flagged posts are sent to the next processing step.

[0421] Step 4:

[0422] The server selects whether to delete or flag a flagged post. First, if a post is to be deleted based on specific conditions, the SNS API is called to send a deletion request for each post ID. The input is the flagged post data, and the output is the deletion success / failure status. In another case, the metadata is updated to mark the post as fake. Specifically, the server updates the settings to add a hoax warning icon and message.

[0423] Step 5:

[0424] The server logs the process and notifies the administrator. After the deletion or flagging is complete, the result is recorded in a log file or database, and the administrator is notified as needed. The input is the result data of the deletion or flagging, and the output is the recorded log information and the status of the notified administrator. Specifically, the log records details such as the post ID, processing content, and execution time.

[0425] Step 6:

[0426] The device receives the notification from the server and displays a warning to the user. Specifically, it applies updated data containing a fake mark and a warning message to the SNS application and displays it on the user's screen. The input is the warning message and fake mark instructions from the server, and the output is the warning information displayed on the user's interface.

[0427] Step 7:

[0428] Users check the warning message and correct their behavior. When users see a warning message or a post marked as fake, they recognize that it may be a hoax. The input is the warning message displayed on the device, and the output is for users to be more cautious in their actions. Specifically, users should refrain from sharing hoax information and strive to gather accurate information.

[0429] Through the above processing steps, this system can effectively detect and delete false information and display warnings, thereby increasing the reliability of information during disasters.

[0430] (Application example 1)

[0431] 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."

[0432] The spread of misinformation and rumours is a serious problem on modern social media platforms. Particularly during disasters and crises, misinformation can spread quickly, causing significant confusion and panic. This can hinder rescue efforts and lead to actions based on false information. Advertisers also face the risk of damaging their brand's credibility. A system is needed to resolve these issues and ensure accurate information is shared.

[0433] 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.

[0434] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for deleting the detected posts, means for displaying warnings about the deleted posts, and means for detecting false information related to advertisers in real time and issuing alerts. This allows accurate information to be disseminated quickly even during disasters or crisis situations, preventing the spread of false information and protecting the brand credibility of advertisers.

[0435] "SNS platform" refers to software or websites that allow users to share information and communicate online.

[0436] "Real time" refers to the ability to process events and data almost simultaneously.

[0437] "Monitoring" refers to the act of watching for events or data on a particular system or network.

[0438] "Specific keywords" refer to the specific words or phrases the system is configured to detect.

[0439] "Post" refers to a message or content that a user publishes on a social media platform.

[0440] "Detection" refers to the act of a system finding data or events that meet set conditions.

[0441] "Deletion" refers to the act of completely removing specific data or information from a system.

[0442] "Warning" refers to a notification that alerts the user to a risk or problem.

[0443] "Advertiser" refers to a company or individual that places advertisements to promote products or services.

[0444] "Misinformation" refers to information that is not based on facts or is false.

[0445] "Alert" refers to a warning message that notifies you of important information or an emergency.

[0446] MODE FOR CARRYING OUT THE INVENTION

[0447] This invention is a system for preventing the spread of misinformation and rumours, and for protecting the reliability of information, particularly that related to advertisers. The system consists of components: a server, a terminal, and a user. The server retrieves post data from social media platforms in real time, detects posts containing specific keywords, and takes action as necessary. The terminal is an interface that notifies the user of alerts regarding detected misinformation. The user can then take prompt action based on this information.

[0448] Server Operation

[0449] The server first starts streaming real-time post data through the social media platform's API. It authenticates using the social media platform's API key and token to retrieve the post data. It then analyzes the retrieved post data to detect whether it contains specific keywords. Keywords used include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." The analysis process uses the Python tweepy library.

[0450] If a post is detected, the server takes the following actions. First, it deletes the detected post. During the deletion process, it uses the API of the social media platform to obtain the ID of the post in question and uses it to delete the post from the database. Once the deletion is complete, the server logs the completion and notifies the administrator.

[0451] Instead of removing the post, the system will mark it as inauthentic and warn users when they view it. The warning message will include a statement such as "⚠️ This post may be misinformation." Additionally, if misinformation relevant to an advertiser is detected, the system will identify high-risk posts and send an alert to the advertiser. The alert will include the content of the post and a risk assessment.

[0452] Device behavior

[0453] The device receives notifications from the server and displays fake marks and warning messages on posts. It runs on the user's device as a social networking client application and can issue warnings directly to posts on the social networking platforms the user uses. The device also provides an interface to alert advertisers about misinformation, allowing them to take swift action and maintain the credibility of their brand.

[0454] User Actions

[0455] Users use social media platforms on a daily basis to send and receive information. When users access a post marked with a misinformation symbol or a warning message, they can recognize that the post is likely to be a hoax or misinformation and respond appropriately. For example, they can report the problematic post or take measures to spread accurate information.

[0456] Specific examples

[0457] A specific scenario for using the system is when an advertiser posts false information on social media during a disaster, such as "The relief supplies provided by Company X are fake." The server detects this post and sends an alert to the advertiser as risk information related to the post. It also displays a warning mark to general users, informing them that the information is likely to be incorrect.

[0458] Prompt Sentence Examples

[0459] Set up a misinformation monitoring system for advertisers. Monitor social media posts containing specified keywords in real time and display a warning icon for relevant posts. Specific keywords include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." Build a system that sends alerts to advertisers for detected posts.

[0460] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0461] Step 1:

[0462] The server authenticates using the social media platform's API, using the API key and token as input and getting an authentication token as output. Using this authentication token, the server prepares to retrieve real-time posting data.

[0463] Step 2:

[0464] The server streams post data in real time from the social media platform through its API. It takes an authentication token as input and gets a stream of post data as output. This stream contains all posts published on the social media platform.

[0465] Step 3:

[0466] The server parses the streamed post data. It takes the stream data as input and uses a regular expression library to analyze it for specific keywords. It generates a list of posts that contain the specific keywords as output.

[0467] Step 4:

[0468] The server determines how to deal with each detected post. As input, it uses a list of posts containing specific keywords. To process the data, it performs a risk assessment on the post and decides whether to delete it or mark it with a warning. As output, it generates a list of posts to be deleted and a list of posts to be marked with a warning.

[0469] Step 5:

[0470] The server uses the SNS platform's API to process the posts to be deleted. It uses the list of posts to be deleted as input and sends an API request to delete the relevant posts from the database. As output, it logs a deletion completion notification and notifies the administrator.

[0471] Step 6:

[0472] The server marks posts that are eligible for warning marking. It uses the list of posts that are eligible for warning marking as input and adds warning marks to the corresponding posts in the database. As output, it logs a notification that the warning mark has been added and generates data to notify the user.

[0473] Step 7:

[0474] The device receives the notification about the warning mark sent from the server. As input, it uses the warning mark notification data sent from the server and processes the display of a warning icon in the SNS client application. As output, the warning icon is displayed to the user in response to the SNS post.

[0475] Step 8:

[0476] If misinformation related to an advertiser is detected, the server sends an alert to the advertiser. The input is the posted data of misinformation related to the advertiser. The data is processed by performing a risk assessment and generating an alert message. The output is an alert notification sent to the advertiser.

[0477] Step 9:

[0478] The user receives a warning icon or alert notification. As input, the user recognizes the warning icon or alert notification displayed on the device and checks the warning content regarding the misinformation. As output, the user can take appropriate action.

[0479] Step 10:

[0480] The server records all processing results in a log. The inputs used are deletion completion notification, warning mark attachment notification, and alert sending notification. Data processing involves adding a timestamp to all actions and saving them in a log database. The output is a log that the system administrator can check.

[0481] In this way, a system is built in which the server, terminals, and users work together to prevent the spread of misinformation and hoaxes and protect the brand credibility of advertisers.

[0482] 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.

[0483] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[0484] System Overview

[0485] This system consists of a server, a terminal, and a user. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please share"), and recognizes the user's emotions using an emotion engine. The terminal provides the user with an interface for displaying appropriate warning messages and fake marks. Users use the SNS platform on a daily basis to send and receive information.

[0486] Server Operation

[0487] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[0488] If a post containing a specific keyword is detected, the server then initiates a sentiment analysis of the post using a sentiment engine, which uses machine learning algorithms to identify the user's emotions from the post's text data, categorizing them into basic emotional categories such as joy, anger, sadness, and fear.

[0489] Processing Posts

[0490] For posts whose emotions have been identified by the emotion engine, the server takes the following actions. First, if the post is determined to be a hoax, it is deleted. In the deletion process, the database is accessed using the post's ID as a key to completely remove the post. When the deletion is complete, the information is recorded in a log.

[0491] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[0492] Device behavior

[0493] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to inform the user that the post may be a hoax.

[0494] User Actions

[0495] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post's content. This allows users to take appropriate action and prevent the spread of false information.

[0496] Specific examples

[0497] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[0498] The present invention makes it possible to effectively prevent the spread of false information during disasters and to provide appropriate warning messages according to the emotional state of users, thereby facilitating rescue operations and saving many lives.

[0499] The processing flow will be explained below.

[0500] Step 1:

[0501] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[0502] Step 2:

[0503] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[0504] Step 3:

[0505] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[0506] Step 4:

[0507] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[0508] Step 5:

[0509] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[0510] Step 6:

[0511] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[0512] Step 7:

[0513] The server uses an emotion engine to analyze the sentiment of posts containing specific keywords. The emotion engine identifies the user's emotions (e.g., "joy," "anger," "sadness," "fear," etc.) from the content of the post. The emotion engine uses machine learning algorithms to classify the text data.

[0514] Step 8:

[0515] The server generates a warning message appropriate for the user based on the emotion identified by the emotion engine. For example, if the emotion is identified as "fear," the server creates a warning message such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0516] Step 9:

[0517] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post.

[0518] Step 10:

[0519] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[0520] Step 11:

[0521] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[0522] Example 2

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

[0524] Social media platforms have become an important means of information transmission in modern times, but in times of disaster, false information can easily spread, resulting in confusion and panic. Furthermore, depending on the content of the false information, it may have an emotional impact on users, causing anxiety and fear. To solve these problems, real-time detection and appropriate processing of false posts is necessary, and a warning system that takes user emotions into account is also required.

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

[0526] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for analyzing the sentiment of the detected posts, means for determining whether the posts are hoaxes based on the sentiment analysis results, means for deleting posts determined to be hoaxes, means for displaying a fake mark when deletion is difficult, means for generating a warning message based on the sentiment, and means for displaying the generated warning message on the user's device. This enables the rapid detection and deletion of hoaxes or appropriate warnings to users, thereby preventing the spread of hoaxes while minimizing the emotional impact on users.

[0527] An "SNS platform" is an online service that allows users to share information and communicate with others.

[0528] "Real-time" means that information and data are processed immediately and provided without delay.

[0529] "Monitoring" is the act of continuously observing a specific object and supervising its situation.

[0530] "Keywords" are key words or phrases used to locate specific information.

[0531] "Analyzing sentiment" is the process of determining the emotional state of a writer from text data.

[0532] A "hoax" is false information that is spread intentionally or accidentally.

[0533] "Hoax assessment" is the process of assessing whether information is true or false.

[0534] A "fake mark" is an identifying icon that indicates that certain information is likely to be false.

[0535] A "warning message" is a notification message that warns users of risks and cautions them.

[0536] A "terminal" is an electronic device that a user uses to send and receive information.

[0537] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[0538] Hardware and software used

[0539] server

[0540] Hardware: High-performance data center servers (e.g., general-purpose high-performance servers)

[0541] Software: API of social media platform, Python, Pandas, syntax analysis library (e.g., natural language processing library), machine learning library (e.g., machine learning framework)

[0542] Terminal

[0543] Hardware: Regular PCs and mobile devices (e.g., laptops and smartphones)

[0544] Software: Web browsers (e.g., internet browsers), dedicated applications (e.g., apps developed using cross-platform frameworks)

[0545] User

[0546] Hardware: Same as above (regular PC or mobile device)

[0547] Software: Same as above

[0548] Explanation of the system processing flow

[0549] 1. Collecting social media posting data

[0550] The server starts streaming real-time post data through the social media platform's API, and uses a Python library to retrieve the data and convert it into the format required for analysis.

[0551] 2. Keyword detection

[0552] The server stores the retrieved post data in a data frame and uses a syntax analysis library to detect specific keywords (e.g., "address," "name," "please share") This analysis involves text tokenization and keyword matching.

[0553] 3. Sentiment analysis

[0554] The server runs an emotion engine based on the keyword detection results to perform sentiment analysis of the posts, classifying them into emotion categories (e.g., joy, anger, sadness, fear) using a machine learning library.

[0555] 4. Post Judgment and Processing

[0556] The server judges the post based on the analysis results of the emotion engine. If it is judged to be a hoax, the server accesses the database and deletes the post. If deletion is difficult, the server marks the post as fake and records a log of the deletion process.

[0557] 5. Warning message generation and display

[0558] The server generates a warning message based on the emotion analysis results. For example, if "fear" is identified, the server generates a message saying "⚠️ This post may be a hoax. Please be careful as the content may be disturbing" and sends it to the device. The device then displays this message on the user interface.

[0559] Specific examples

[0560] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[0561] Prompt Sentence Examples

[0562] Recognize the sentiment of the post "Address: XX, Name: △△, Please help. Please spread the word.", determine whether it is a hoax, and delete it. Please describe the steps required to build a system that uses an emotion engine to identify sentiment and generate and display a warning message as necessary.

[0563] This detailed description clarifies the specific operations of each processing step of the system. Understanding what happens at each step makes it easier to grasp the overall function of the system.

[0564] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0565] The flow of this system's program processing

[0566] Step 1: Collect social media post data

[0567] Step 2: Keyword detection

[0568] Step 3: Sentiment analysis

[0569] Step 4: Identifying and Processing Posts

[0570] Step 5: Generate and display warning messages

[0571] Detailed explanation of the processing steps

[0572] Step 1: Collect social media post data

[0573] Input: The server receives post data through the API of the social networking platform.

[0574] How it works: The server collects real-time posting data via the API of the social media platform, starts data streaming using a Python library (e.g., Tweepy), and converts the collected data into a data frame.

[0575] Output: Streaming data is stored on the server as a data frame.

[0576] Step 2: Keyword detection

[0577] Input: Streaming data exists on the server as a DataFrame.

[0578] How it works: The server uses a syntax analysis library (e.g., SpaCy) to detect specific keywords (e.g., "address," "name," "please share") in the post data. This analysis involves tokenizing the text and keyword matching.

[0579] Output: Posts in which the keyword was found are identified and the appropriate rows are flagged.

[0580] Step 3: Sentiment analysis

[0581] Input: Post data with keyword detection completed.

[0582] How it works: The server uses a sentiment engine (e.g., a BERT-based machine learning model) to analyze the sentiment of the detected posts, classify them into sentiment categories (e.g., joy, anger, sadness, fear), and add the results to a data frame.

[0583] Output: Generates sentiment-identified post data and adds sentiment categories to each post.

[0584] Step 4: Identifying and Processing Posts

[0585] Input: Post data that has undergone keyword detection and sentiment analysis.

[0586] How it works: The server judges posts based on the analysis results of the emotion engine. If it judges a post to be a hoax, it accesses a database (e.g., MySQL) to delete the post. If it is difficult to delete the post or if immediate deletion is not necessary, it marks the post as fake. At this time, it records logs of the deletion process and the marking of the post as fake.

[0587] Output: Data on posts that were deleted or marked as fake is generated and logged.

[0588] Step 5: Generate and display warning messages

[0589] Input: Post data that has been identified as a hoax or marked as fake.

[0590] Operation: The server generates a warning message based on the results of the sentiment analysis. For example, if "fear" is identified, the server generates a message stating "This post may be a hoax. Please be careful as the content may be disturbing," and sends it to the user's device via the user interface. The device then displays this warning message on its screen.

[0591] Output: A warning message is generated and displayed on the user's terminal.

[0592] The above is a detailed explanation of the system's specific processing steps and their operation. It details what data is input at each step, what processing is performed, and what output is obtained.

[0593] (Application example 2)

[0594] 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."

[0595] During disasters and emergencies, false information spreads rapidly on social media, causing anxiety and confusion among many users. This can also cause confusion and hinder rescue efforts, so there is a need for a method to quickly and effectively prevent the spread of false information. Furthermore, measures are also needed to ensure that users can obtain accurate information without being emotionally affected.

[0596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0597] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for performing emotion recognition on the detected posts using an emotion engine, means for deleting the detected posts, means for marking the detected posts as fake if deletion is difficult or not necessary immediately, and means for generating a warning message based on the identified emotion, and means for displaying the generated warning message on a user interface. This allows users to receive appropriate warnings while preventing the spread of false information.

[0598] An "SNS platform" is a software service that allows users to disseminate information and interact with others online.

[0599] "Real-time monitoring means" refers to technology that allows for instant monitoring and analysis of posts on social media platforms.

[0600] "Specific keywords" are words used to identify specific content, such as "address," "name," or "please share."

[0601] The "means for detecting posts" refers to technology for finding posts containing specific keywords from posts on social media platforms that are monitored in real time.

[0602] An "emotion engine" is an algorithm or system that analyzes text data contained in posts and identifies user emotions.

[0603] "Means for emotion recognition" refers to technology that uses an emotion engine to identify a user's emotional state from the text of a post.

[0604] "Methods for removing posts" refers to techniques used to physically remove posts determined to be false from social media platforms.

[0605] "Means of assigning fake marks" refers to a technology that adds a mark to problematic posts to visually warn users.

[0606] A "warning message" is a message that informs users that a post may be a hoax and urges them to be careful.

[0607] The "means for generating" is a technology for creating a warning message or a counterfeit mark based on specific conditions.

[0608] A "user interface" is the screen and operating environment through which a user interacts with a system.

[0609] The "display means" refers to a technique for visually displaying the generated warning message or fake mark on the user interface.

[0610] A "generative AI model" is an artificial intelligence model used to determine the output generated from input data.

[0611] A "prompt" is a sentence used as input to a generative AI model, and is an instruction to produce a specific output based on its content.

[0612] An embodiment of the present invention will be described below.

[0613] System Overview

[0614] This system monitors posts on social media platforms in real time, detects posts containing specific keywords, and uses an emotion engine to recognize the emotions in the posts. If detected posts are determined to be hoaxes, they are deleted, or if deletion is difficult, they are marked as fake. A warning message based on the emotion is displayed on the user interface.

[0615] Server Operation

[0616] The server streams post data in real time through the API of the social media platform. The server analyzes the received post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). If a post containing specific keywords is detected, it performs a sentiment analysis of the post content using an emotion engine. The emotion engine uses a machine learning algorithm (e.g., TextBlob) to identify the user's emotions from the text data of the post. These emotions are classified into basic emotional categories such as joy, anger, sadness, and fear.

[0617] Processing Posts

[0618] For posts whose emotions have been identified by the emotion engine, the server responds as follows: First, if the post is determined to be a hoax, it is deleted. The deletion process involves accessing the database using the post's ID as a key and completely removing the post. Once the deletion is complete, the information is recorded in a log.

[0619] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[0620] Device behavior

[0621] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to notify the user that the post may be a hoax.

[0622] User Actions

[0623] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post. This allows users to take appropriate action and prevent the spread of hoax information.

[0624] Specific examples

[0625] For example, if a user posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "Address," "Name," and "Please spread the word." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes the post and logs the completion of the deletion. In another scenario, the server marks the post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on its user interface to alert the user.

[0626] Example prompt sentence:

[0627] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0629] Step 1:

[0630] The server starts streaming post data through the SNS platform's API. As input, it receives the SNS platform's API key and the real-time stream of post data. This allows the server to continuously obtain new post data. The output is the obtained SNS post data.

[0631] Step 2:

[0632] The server analyzes the acquired post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). The input is the acquired post data, and the output is a list of posts in which specific keywords are detected. The server parses the text in the post data and checks whether the specific keywords are present.

[0633] Step 3:

[0634] The server uses an emotion engine to perform emotion recognition on posts containing specific keywords. The input is post data containing specific keywords, and the emotion is identified using a machine learning algorithm (e.g., TextBlob). The output is the emotion category (e.g., joy, anger, sadness, fear) corresponding to each post.

[0635] Step 4:

[0636] The server determines whether posts with identified emotions are hoaxes. The input is post data with emotional categories, and the server uses a hoax detection algorithm to determine whether a post is a hoax. The output is a list of posts that are determined to be hoaxes.

[0637] Step 5:

[0638] The server deletes posts that are determined to be hoaxes. The input is the post data that was determined to be hoax, and the post ID is used to delete it from the database. The output is a log of the completion of the deletion process. If deletion is difficult or there is no need to delete it immediately, proceed to the next step.

[0639] Step 6:

[0640] The server marks posts that are difficult to delete as fake and generates a warning message based on emotion using a generative AI model. The input is the post data that cannot be deleted and its emotion category, and the output is the post data marked as fake and the generated warning message. The server sends a prompt sentence as input to the generative AI model and receives an appropriate warning message. Example:

[0641] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0642] Step 7:

[0643] The terminal receives the fake mark and warning message sent from the server and displays them on the user interface. The input is the fake mark and warning message sent from the server, and the output is a visual display on the user interface. Based on this, the user can judge the content of the post and take appropriate action.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] [Third embodiment]

[0648] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0649] 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.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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).

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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."

[0660] The present invention relates to a system that automatically monitors posts of false information on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake. Specific embodiments for carrying out the present invention will be described below.

[0661] System Overview

[0662] This system consists of a server, a terminal, and a user component. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please spread"), and takes appropriate action accordingly. The terminal is an interface that displays fake marks and notifies users with warning messages. Users send and receive information on a daily basis.

[0663] Server Operation

[0664] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[0665] If a post containing a specific keyword is detected, the server will either: First, delete the post via the social media platform's API. The deletion process involves obtaining the ID associated with the post and using this to permanently remove it from the database. Second, it will log the completion of the deletion and notify an administrator if necessary.

[0666] Alternatively, the server can mark detected posts as fake and warn users when they view the posts. This method is effective when it is deemed unnecessary to remove the posts or when immediate removal is technically difficult.

[0667] Device behavior

[0668] The device receives a notification from the server and marks the post as fake. Specifically, a warning icon or message is placed next to the post to inform the user that the post may be a hoax. The warning message includes a statement such as "⚠️ This post may be a hoax."

[0669] User Actions

[0670] Users use social media platforms on a daily basis to send and receive information. When users access posts marked with a fake symbol or warning message, they can recognize that the post is likely a hoax and respond appropriately. This can prevent the spread of false information and minimize confusion during disasters.

[0671] Specific examples

[0672] For example, if user A posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[0673] This invention makes it possible to quickly respond to false information posted during a disaster before it spreads and minimize disruption to rescue operations, which is a system that improves the efficiency of disaster response and helps save many lives.

[0674] The processing flow will be explained below.

[0675] Step 1:

[0676] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[0677] Step 2:

[0678] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[0679] Step 3:

[0680] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[0681] Step 4:

[0682] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[0683] Step 5:

[0684] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[0685] Step 6:

[0686] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[0687] Step 7:

[0688] The device receives the fake mark information sent from the server and displays it appropriately on the user interface, specifically by placing a warning icon or message next to the relevant post.

[0689] Step 8:

[0690] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[0691] Step 9:

[0692] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[0693] Example 1

[0694] 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."

[0695] When a disaster occurs, the rapid spread of false information on social media can cause serious disruptions to rescue efforts and information gathering. For example, the spread of posts containing false addresses, names, or urgent requests for dissemination can lead to inappropriate use of resources by relevant agencies, which can delay truly necessary rescue efforts. A system that can prevent such situations and effectively suppress the spread of false information is needed.

[0696] 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.

[0697] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for analyzing and detecting posts containing specific keywords using natural language processing technology, means for deleting the detected posts, and means for displaying a warning to users about the deleted posts. This allows false information to be quickly detected and deleted, and a warning to be displayed to users, thereby preventing the spread of false information.

[0698] An "SNS platform" is a virtual space that provides services that allow users to share information and communicate online.

[0699] "Real-time" refers to the time characteristic in which data or information is processed immediately without delay.

[0700] "Monitoring" refers to the act of continuously observing specific events or data to detect anomalies or significant changes.

[0701] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes text analysis and language generation.

[0702] A "keyword" is an important word that symbolizes specific information and is used to represent the content or category of that information.

[0703] "Analysis and detection" is the process of examining and analyzing collected data in detail to identify specific patterns and information.

[0704] "Post" refers to any type of content such as text, images, or videos that a user publishes on a social media platform.

[0705] "Deletion" refers to the act of completely removing data or information from a system or database.

[0706] "Warning" refers to a message or signal that alerts the user to risks or caution.

[0707] "User" refers to an individual or organization that sends and receives information using the SNS platform.

[0708] A "fake mark" is a visual symbol or icon that indicates that certain information is likely not true.

[0709] MODE FOR CARRYING OUT THE INVENTION

[0710] The present invention is a system that automatically detects and removes false information spread on social media in the event of a disaster, and displays a warning to users. Specific embodiments for carrying out the present invention will be described below.

[0711] System Components

[0712] This system consists of three main components: a server, a terminal, and a user. The server retrieves and analyzes posted data from the SNS platform in real time. The terminal is an interface that notifies users of warning messages about false information and marks fakes. Users are individuals or organizations that use the SNS platform on a daily basis.

[0713] Server Operation

[0714] The server first starts streaming real-time post data through the social media platform's API. Specifically, it uses a programming language such as Python and a machine learning framework such as TensorFlow or PyTorch. The server is typically run using a hosting service or cloud infrastructure. The server then analyzes the acquired post data and uses natural language processing (NLP) techniques to detect whether specific keywords are included. NLP libraries such as spaCy and NLTK are used for this analysis.

[0715] For example, if the server detects a post containing keywords such as "address," "name," or "please spread the word," it will flag the post. This flagged post will then be either deleted or marked as fake based on a set algorithm, as explained below.

[0716] Device behavior

[0717] The device receives the notification from the server and displays a fake mark or a warning message on the relevant post. This is typically done using the UI components of the social networking application. For example, a warning icon or a message such as "⚠️ This post may be a hoax" can be displayed next to a specific post to warn the user.

[0718] User Actions

[0719] Users will see posts marked with a fake symbol or warning message on the social media platforms they use daily. This will make users aware that the post is likely to be a hoax and encourage them to handle the information with caution. This will prevent the spread of false information and reduce confusion during disasters.

[0720] Specific examples

[0721] For example, if user A posts "Address: XX, Name: △△, please help. Please spread the word" during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[0722] Prompt Sentence Examples

[0723] "Please describe a system that automatically monitors posts about disaster-related misinformation, detects posts containing specific keywords, and removes or issues a warning. Please provide details about how this system works, including specific examples of the techniques and tools used."

[0724] In this way, the present invention allows for the rapid detection and response to false information, ensuring that users receive accurate information, thereby preventing confusion during disasters and enabling effective rescue operations.

[0725] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0726] The flow of this system's program processing

[0727] Step 1:

[0728] The server retrieves post data in real time using the API of the social media platform. A specific API call initiates the reception of streaming data. The input is the social media post data, and the output is the streamed post data. This streaming data includes detailed information about each post (text, posting time, poster information, etc.).

[0729] Step 2:

[0730] The server analyzes the posted data it acquires using natural language processing (NLP) technology. NLP libraries used include spaCy and NLTK. The input is the streamed posted data, and the output is the results of keyword analysis (whether or not a specific keyword is included). Specifically, text analysis is performed to check for the presence of keywords such as "address," "name," and "please share."

[0731] Step 3:

[0732] The server detects posts containing specific keywords. Based on the analysis results, it flags posts that may be hoaxes. The input is the keyword analysis results, and the output is the flagged posts. Specifically, the flagged posts are sent to the next processing step.

[0733] Step 4:

[0734] The server selects whether to delete or flag a flagged post. First, if a post is to be deleted based on specific conditions, the SNS API is called to send a deletion request for each post ID. The input is the flagged post data, and the output is the deletion success / failure status. In another case, the metadata is updated to mark the post as fake. Specifically, the server updates the settings to add a hoax warning icon and message.

[0735] Step 5:

[0736] The server logs the process and notifies the administrator. After the deletion or flagging is complete, the result is recorded in a log file or database, and the administrator is notified as needed. The input is the result data of the deletion or flagging, and the output is the recorded log information and the status of the notified administrator. Specifically, the log records details such as the post ID, processing content, and execution time.

[0737] Step 6:

[0738] The device receives the notification from the server and displays a warning to the user. Specifically, it applies updated data containing a fake mark and a warning message to the SNS application and displays it on the user's screen. The input is the warning message and fake mark instructions from the server, and the output is the warning information displayed on the user's interface.

[0739] Step 7:

[0740] Users check the warning message and correct their behavior. When users see a warning message or a post marked as fake, they recognize that it may be a hoax. The input is the warning message displayed on the device, and the output is for users to be more cautious in their actions. Specifically, users should refrain from sharing hoax information and strive to gather accurate information.

[0741] Through the above processing steps, this system can effectively detect and delete false information and display warnings, thereby increasing the reliability of information during disasters.

[0742] (Application example 1)

[0743] 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."

[0744] The spread of misinformation and rumours is a serious problem on modern social media platforms. Particularly during disasters and crises, misinformation can spread quickly, causing significant confusion and panic. This can hinder rescue efforts and lead to actions based on false information. Advertisers also face the risk of damaging their brand's credibility. A system is needed to resolve these issues and ensure accurate information is shared.

[0745] 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.

[0746] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for deleting the detected posts, means for displaying warnings about the deleted posts, and means for detecting false information related to advertisers in real time and issuing alerts. This allows accurate information to be disseminated quickly even during disasters or crisis situations, preventing the spread of false information and protecting the brand credibility of advertisers.

[0747] "SNS platform" refers to software or websites that allow users to share information and communicate online.

[0748] "Real time" refers to the ability to process events and data almost simultaneously.

[0749] "Monitoring" refers to the act of watching for events or data on a particular system or network.

[0750] "Specific keywords" refer to the specific words or phrases the system is configured to detect.

[0751] "Post" refers to a message or content that a user publishes on a social media platform.

[0752] "Detection" refers to the act of a system finding data or events that meet set conditions.

[0753] "Deletion" refers to the act of completely removing specific data or information from a system.

[0754] "Warning" refers to a notification that alerts the user to a risk or problem.

[0755] "Advertiser" refers to a company or individual that places advertisements to promote products or services.

[0756] "Misinformation" refers to information that is not based on facts or is false.

[0757] "Alert" refers to a warning message that notifies you of important information or an emergency.

[0758] MODE FOR CARRYING OUT THE INVENTION

[0759] This invention is a system for preventing the spread of misinformation and rumours, and for protecting the reliability of information, particularly that related to advertisers. The system consists of components: a server, a terminal, and a user. The server retrieves post data from social media platforms in real time, detects posts containing specific keywords, and takes action as necessary. The terminal is an interface that notifies the user of alerts regarding detected misinformation. The user can then take prompt action based on this information.

[0760] Server Operation

[0761] The server first starts streaming real-time post data through the social media platform's API. It authenticates using the social media platform's API key and token to retrieve the post data. It then analyzes the retrieved post data to detect whether it contains specific keywords. Keywords used include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." The analysis process uses the Python tweepy library.

[0762] If a post is detected, the server takes the following actions. First, it deletes the detected post. During the deletion process, it uses the API of the social media platform to obtain the ID of the post in question and uses it to delete the post from the database. Once the deletion is complete, the server logs the completion and notifies the administrator.

[0763] Instead of removing the post, the system will mark it as inauthentic and warn users when they view it. The warning message will include a statement such as "⚠️ This post may be misinformation." Additionally, if misinformation relevant to an advertiser is detected, the system will identify high-risk posts and send an alert to the advertiser. The alert will include the content of the post and a risk assessment.

[0764] Device behavior

[0765] The device receives notifications from the server and displays fake marks and warning messages on posts. It runs on the user's device as a social networking client application and can issue warnings directly to posts on the social networking platforms the user uses. The device also provides an interface to alert advertisers about misinformation, allowing them to take swift action and maintain the credibility of their brand.

[0766] User Actions

[0767] Users use social media platforms on a daily basis to send and receive information. When users access a post marked with a misinformation symbol or a warning message, they can recognize that the post is likely to be a hoax or misinformation and respond appropriately. For example, they can report the problematic post or take measures to spread accurate information.

[0768] Specific examples

[0769] A specific scenario for using the system is when an advertiser posts false information on social media during a disaster, such as "The relief supplies provided by Company X are fake." The server detects this post and sends an alert to the advertiser as risk information related to the post. It also displays a warning mark to general users, informing them that the information is likely to be incorrect.

[0770] Prompt Sentence Examples

[0771] Set up a misinformation monitoring system for advertisers. Monitor social media posts containing specified keywords in real time and display a warning icon for relevant posts. Specific keywords include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." Build a system that sends alerts to advertisers for detected posts.

[0772] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0773] Step 1:

[0774] The server authenticates using the social media platform's API, using the API key and token as input and getting an authentication token as output. Using this authentication token, the server prepares to retrieve real-time posting data.

[0775] Step 2:

[0776] The server streams post data in real time from the social media platform through its API. It takes an authentication token as input and gets a stream of post data as output. This stream contains all posts published on the social media platform.

[0777] Step 3:

[0778] The server parses the streamed post data. It takes the stream data as input and uses a regular expression library to analyze it for specific keywords. It generates a list of posts that contain the specific keywords as output.

[0779] Step 4:

[0780] The server determines how to deal with each detected post. As input, it uses a list of posts containing specific keywords. To process the data, it performs a risk assessment on the post and decides whether to delete it or mark it with a warning. As output, it generates a list of posts to be deleted and a list of posts to be marked with a warning.

[0781] Step 5:

[0782] The server uses the SNS platform's API to process the posts to be deleted. It uses the list of posts to be deleted as input and sends an API request to delete the relevant posts from the database. As output, it logs a deletion completion notification and notifies the administrator.

[0783] Step 6:

[0784] The server marks posts that are eligible for warning marking. It uses the list of posts that are eligible for warning marking as input and adds warning marks to the corresponding posts in the database. As output, it logs a notification that the warning mark has been added and generates data to notify the user.

[0785] Step 7:

[0786] The device receives the notification about the warning mark sent from the server. As input, it uses the warning mark notification data sent from the server and processes the display of a warning icon in the SNS client application. As output, the warning icon is displayed to the user in response to the SNS post.

[0787] Step 8:

[0788] If misinformation related to an advertiser is detected, the server sends an alert to the advertiser. The input is the posted data of misinformation related to the advertiser. The data is processed by performing a risk assessment and generating an alert message. The output is an alert notification sent to the advertiser.

[0789] Step 9:

[0790] The user receives a warning icon or alert notification. As input, the user recognizes the warning icon or alert notification displayed on the device and checks the warning content regarding the misinformation. As output, the user can take appropriate action.

[0791] Step 10:

[0792] The server records all processing results in a log. The inputs used are deletion completion notification, warning mark attachment notification, and alert sending notification. Data processing involves adding a timestamp to all actions and saving them in a log database. The output is a log that the system administrator can check.

[0793] In this way, a system is built in which the server, terminals, and users work together to prevent the spread of misinformation and hoaxes and protect the brand credibility of advertisers.

[0794] 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.

[0795] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[0796] System Overview

[0797] This system consists of a server, a terminal, and a user. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please share"), and recognizes the user's emotions using an emotion engine. The terminal provides the user with an interface for displaying appropriate warning messages and fake marks. Users use the SNS platform on a daily basis to send and receive information.

[0798] Server Operation

[0799] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[0800] If a post containing a specific keyword is detected, the server then initiates a sentiment analysis of the post using a sentiment engine, which uses machine learning algorithms to identify the user's emotions from the post's text data, categorizing them into basic emotional categories such as joy, anger, sadness, and fear.

[0801] Processing Posts

[0802] For posts whose emotions have been identified by the emotion engine, the server takes the following actions. First, if the post is determined to be a hoax, it is deleted. In the deletion process, the database is accessed using the post's ID as a key to completely remove the post. When the deletion is complete, the information is recorded in a log.

[0803] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[0804] Device behavior

[0805] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to inform the user that the post may be a hoax.

[0806] User Actions

[0807] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post's content. This allows users to take appropriate action and prevent the spread of false information.

[0808] Specific examples

[0809] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[0810] The present invention makes it possible to effectively prevent the spread of false information during disasters and to provide appropriate warning messages according to the emotional state of users, thereby facilitating rescue operations and saving many lives.

[0811] The processing flow will be explained below.

[0812] Step 1:

[0813] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[0814] Step 2:

[0815] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[0816] Step 3:

[0817] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[0818] Step 4:

[0819] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[0820] Step 5:

[0821] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[0822] Step 6:

[0823] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[0824] Step 7:

[0825] The server uses an emotion engine to analyze the sentiment of posts containing specific keywords. The emotion engine identifies the user's emotions (e.g., "joy," "anger," "sadness," "fear," etc.) from the content of the post. The emotion engine uses machine learning algorithms to classify the text data.

[0826] Step 8:

[0827] The server generates a warning message appropriate for the user based on the emotion identified by the emotion engine. For example, if the emotion is identified as "fear," the server creates a warning message such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0828] Step 9:

[0829] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post.

[0830] Step 10:

[0831] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[0832] Step 11:

[0833] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[0834] Example 2

[0835] 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."

[0836] Social media platforms have become an important means of information transmission in modern times, but in times of disaster, false information can easily spread, resulting in confusion and panic. Furthermore, depending on the content of the false information, it may have an emotional impact on users, causing anxiety and fear. To solve these problems, real-time detection and appropriate processing of false posts is necessary, and a warning system that takes user emotions into account is also required.

[0837] 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.

[0838] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for analyzing the sentiment of the detected posts, means for determining whether the posts are hoaxes based on the sentiment analysis results, means for deleting posts determined to be hoaxes, means for displaying a fake mark when deletion is difficult, means for generating a warning message based on the sentiment, and means for displaying the generated warning message on the user's device. This enables the rapid detection and deletion of hoaxes or appropriate warnings to users, thereby preventing the spread of hoaxes while minimizing the emotional impact on users.

[0839] An "SNS platform" is an online service that allows users to share information and communicate with others.

[0840] "Real-time" means that information and data are processed immediately and provided without delay.

[0841] "Monitoring" is the act of continuously observing a specific object and supervising its situation.

[0842] "Keywords" are key words or phrases used to locate specific information.

[0843] "Analyzing sentiment" is the process of determining the emotional state of a writer from text data.

[0844] A "hoax" is false information that is spread intentionally or accidentally.

[0845] "Hoax assessment" is the process of assessing whether information is true or false.

[0846] A "fake mark" is an identifying icon that indicates that certain information is likely to be false.

[0847] A "warning message" is a notification message that warns users of risks and cautions them.

[0848] A "terminal" is an electronic device that a user uses to send and receive information.

[0849] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[0850] Hardware and software used

[0851] server

[0852] Hardware: High-performance data center servers (e.g., general-purpose high-performance servers)

[0853] Software: API of social media platform, Python, Pandas, syntax analysis library (e.g., natural language processing library), machine learning library (e.g., machine learning framework)

[0854] Terminal

[0855] Hardware: Regular PCs and mobile devices (e.g., laptops and smartphones)

[0856] Software: Web browsers (e.g., internet browsers), dedicated applications (e.g., apps developed using cross-platform frameworks)

[0857] User

[0858] Hardware: Same as above (regular PC or mobile device)

[0859] Software: Same as above

[0860] Explanation of the system processing flow

[0861] 1. Collecting social media posting data

[0862] The server starts streaming real-time post data through the social media platform's API, and uses a Python library to retrieve the data and convert it into the format required for analysis.

[0863] 2. Keyword detection

[0864] The server stores the retrieved post data in a data frame and uses a syntax analysis library to detect specific keywords (e.g., "address," "name," "please share") This analysis involves text tokenization and keyword matching.

[0865] 3. Sentiment analysis

[0866] The server runs an emotion engine based on the keyword detection results to perform sentiment analysis of the posts, classifying them into emotion categories (e.g., joy, anger, sadness, fear) using a machine learning library.

[0867] 4. Post Judgment and Processing

[0868] The server judges the post based on the analysis results of the emotion engine. If it is judged to be a hoax, the server accesses the database and deletes the post. If deletion is difficult, the server marks the post as fake and records a log of the deletion process.

[0869] 5. Warning message generation and display

[0870] The server generates a warning message based on the emotion analysis results. For example, if "fear" is identified, the server generates a message saying "⚠️ This post may be a hoax. Please be careful as the content may be disturbing" and sends it to the device. The device then displays this message on the user interface.

[0871] Specific examples

[0872] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[0873] Prompt Sentence Examples

[0874] Recognize the sentiment of the post "Address: XX, Name: △△, Please help. Please spread the word.", determine whether it is a hoax, and delete it. Please describe the steps required to build a system that uses an emotion engine to identify sentiment and generate and display a warning message as necessary.

[0875] This detailed description clarifies the specific operations of each processing step of the system. Understanding what happens at each step makes it easier to grasp the overall function of the system.

[0876] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0877] The flow of this system's program processing

[0878] Step 1: Collect social media post data

[0879] Step 2: Keyword detection

[0880] Step 3: Sentiment analysis

[0881] Step 4: Identifying and Processing Posts

[0882] Step 5: Generate and display warning messages

[0883] Detailed explanation of the processing steps

[0884] Step 1: Collect social media post data

[0885] Input: The server receives post data through the API of the social networking platform.

[0886] How it works: The server collects real-time posting data via the API of the social media platform, starts data streaming using a Python library (e.g., Tweepy), and converts the collected data into a data frame.

[0887] Output: Streaming data is stored on the server as a data frame.

[0888] Step 2: Keyword detection

[0889] Input: Streaming data exists on the server as a DataFrame.

[0890] How it works: The server uses a syntax analysis library (e.g., SpaCy) to detect specific keywords (e.g., "address," "name," "please share") in the post data. This analysis involves tokenizing the text and keyword matching.

[0891] Output: Posts in which the keyword was found are identified and the appropriate rows are flagged.

[0892] Step 3: Sentiment analysis

[0893] Input: Post data with keyword detection completed.

[0894] How it works: The server uses a sentiment engine (e.g., a BERT-based machine learning model) to analyze the sentiment of the detected posts, classify them into sentiment categories (e.g., joy, anger, sadness, fear), and add the results to a data frame.

[0895] Output: Generates sentiment-identified post data and adds sentiment categories to each post.

[0896] Step 4: Identifying and Processing Posts

[0897] Input: Post data that has undergone keyword detection and sentiment analysis.

[0898] How it works: The server judges posts based on the analysis results of the emotion engine. If it judges a post to be a hoax, it accesses a database (e.g., MySQL) to delete the post. If it is difficult to delete the post or if immediate deletion is not necessary, it marks the post as fake. At this time, it records logs of the deletion process and the marking of the post as fake.

[0899] Output: Data on posts that were deleted or marked as fake is generated and logged.

[0900] Step 5: Generate and display warning messages

[0901] Input: Post data that has been identified as a hoax or marked as fake.

[0902] Operation: The server generates a warning message based on the results of the sentiment analysis. For example, if "fear" is identified, the server generates a message stating "This post may be a hoax. Please be careful as the content may be disturbing," and sends it to the user's device via the user interface. The device then displays this warning message on its screen.

[0903] Output: A warning message is generated and displayed on the user's terminal.

[0904] The above is a detailed explanation of the system's specific processing steps and their operation. It details what data is input at each step, what processing is performed, and what output is obtained.

[0905] (Application example 2)

[0906] 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."

[0907] During disasters and emergencies, false information spreads rapidly on social media, causing anxiety and confusion among many users. This can also cause confusion and hinder rescue efforts, so there is a need for a method to quickly and effectively prevent the spread of false information. Furthermore, measures are also needed to ensure that users can obtain accurate information without being emotionally affected.

[0908] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0909] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for performing emotion recognition on the detected posts using an emotion engine, means for deleting the detected posts, means for marking the detected posts as fake if deletion is difficult or not necessary immediately, and means for generating a warning message based on the identified emotion, and means for displaying the generated warning message on a user interface. This allows users to receive appropriate warnings while preventing the spread of false information.

[0910] An "SNS platform" is a software service that allows users to disseminate information and interact with others online.

[0911] "Real-time monitoring means" refers to technology that allows for instant monitoring and analysis of posts on social media platforms.

[0912] "Specific keywords" are words used to identify specific content, such as "address," "name," or "please share."

[0913] The "means for detecting posts" refers to technology for finding posts containing specific keywords from posts on social media platforms that are monitored in real time.

[0914] An "emotion engine" is an algorithm or system that analyzes text data contained in posts and identifies user emotions.

[0915] "Means for emotion recognition" refers to technology that uses an emotion engine to identify a user's emotional state from the text of a post.

[0916] "Methods for removing posts" refers to techniques used to physically remove posts determined to be false from social media platforms.

[0917] "Means of assigning fake marks" refers to a technology that adds a mark to problematic posts to visually warn users.

[0918] A "warning message" is a message that informs users that a post may be a hoax and urges them to be careful.

[0919] The "means for generating" is a technology for creating a warning message or a counterfeit mark based on specific conditions.

[0920] A "user interface" is the screen and operating environment through which a user interacts with a system.

[0921] The "display means" refers to a technique for visually displaying the generated warning message or fake mark on the user interface.

[0922] A "generative AI model" is an artificial intelligence model used to determine the output generated from input data.

[0923] A "prompt" is a sentence used as input to a generative AI model, and is an instruction to produce a specific output based on its content.

[0924] An embodiment of the present invention will be described below.

[0925] System Overview

[0926] This system monitors posts on social media platforms in real time, detects posts containing specific keywords, and uses an emotion engine to recognize the emotions in the posts. If detected posts are determined to be hoaxes, they are deleted, or if deletion is difficult, they are marked as fake. A warning message based on the emotion is displayed on the user interface.

[0927] Server Operation

[0928] The server streams post data in real time through the API of the social media platform. The server analyzes the received post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). If a post containing specific keywords is detected, it performs a sentiment analysis of the post content using an emotion engine. The emotion engine uses a machine learning algorithm (e.g., TextBlob) to identify the user's emotions from the text data of the post. These emotions are classified into basic emotional categories such as joy, anger, sadness, and fear.

[0929] Processing Posts

[0930] For posts whose emotions have been identified by the emotion engine, the server responds as follows: First, if the post is determined to be a hoax, it is deleted. The deletion process involves accessing the database using the post's ID as a key and completely removing the post. Once the deletion is complete, the information is recorded in a log.

[0931] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[0932] Device behavior

[0933] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to notify the user that the post may be a hoax.

[0934] User Actions

[0935] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post. This allows users to take appropriate action and prevent the spread of hoax information.

[0936] Specific examples

[0937] For example, if a user posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "Address," "Name," and "Please spread the word." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes the post and logs the completion of the deletion. In another scenario, the server marks the post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on its user interface to alert the user.

[0938] Example prompt sentence:

[0939] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0940] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0941] Step 1:

[0942] The server starts streaming post data through the SNS platform's API. As input, it receives the SNS platform's API key and the real-time stream of post data. This allows the server to continuously obtain new post data. The output is the obtained SNS post data.

[0943] Step 2:

[0944] The server analyzes the acquired post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). The input is the acquired post data, and the output is a list of posts in which specific keywords are detected. The server parses the text in the post data and checks whether the specific keywords are present.

[0945] Step 3:

[0946] The server uses an emotion engine to perform emotion recognition on posts containing specific keywords. The input is post data containing specific keywords, and the emotion is identified using a machine learning algorithm (e.g., TextBlob). The output is the emotion category (e.g., joy, anger, sadness, fear) corresponding to each post.

[0947] Step 4:

[0948] The server determines whether posts with identified emotions are hoaxes. The input is post data with emotional categories, and the server uses a hoax detection algorithm to determine whether a post is a hoax. The output is a list of posts that are determined to be hoaxes.

[0949] Step 5:

[0950] The server deletes posts that are determined to be hoaxes. The input is the post data that was determined to be hoax, and the post ID is used to delete it from the database. The output is a log of the completion of the deletion process. If deletion is difficult or there is no need to delete it immediately, proceed to the next step.

[0951] Step 6:

[0952] The server marks posts that are difficult to delete as fake and generates a warning message based on emotion using a generative AI model. The input is the post data that cannot be deleted and its emotion category, and the output is the post data marked as fake and the generated warning message. The server sends a prompt sentence as input to the generative AI model and receives an appropriate warning message. Example:

[0953] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[0954] Step 7:

[0955] The terminal receives the fake mark and warning message sent from the server and displays them on the user interface. The input is the fake mark and warning message sent from the server, and the output is a visual display on the user interface. Based on this, the user can judge the content of the post and take appropriate action.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] [Fourth embodiment]

[0960] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0961] 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.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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).

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] 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."

[0973] The present invention relates to a system that automatically monitors posts of false information on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake. Specific embodiments for carrying out the present invention will be described below.

[0974] System Overview

[0975] This system consists of a server, a terminal, and a user component. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please spread"), and takes appropriate action accordingly. The terminal is an interface that displays fake marks and notifies users with warning messages. Users send and receive information on a daily basis.

[0976] Server Operation

[0977] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[0978] If a post containing a specific keyword is detected, the server will either: First, delete the post via the social media platform's API. The deletion process involves obtaining the ID associated with the post and using this to permanently remove it from the database. Second, it will log the completion of the deletion and notify an administrator if necessary.

[0979] Alternatively, the server can mark detected posts as fake and warn users when they view the posts. This method is effective when it is deemed unnecessary to remove the posts or when immediate removal is technically difficult.

[0980] Device behavior

[0981] The device receives a notification from the server and marks the post as fake. Specifically, a warning icon or message is placed next to the post to inform the user that the post may be a hoax. The warning message includes a statement such as "⚠️ This post may be a hoax."

[0982] User Actions

[0983] Users use social media platforms on a daily basis to send and receive information. When users access posts marked with a fake symbol or warning message, they can recognize that the post is likely a hoax and respond appropriately. This can prevent the spread of false information and minimize confusion during disasters.

[0984] Specific examples

[0985] For example, if user A posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[0986] This invention makes it possible to quickly respond to false information posted during a disaster before it spreads and minimize disruption to rescue operations, which is a system that improves the efficiency of disaster response and helps save many lives.

[0987] The processing flow will be explained below.

[0988] Step 1:

[0989] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[0990] Step 2:

[0991] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[0992] Step 3:

[0993] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[0994] Step 4:

[0995] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[0996] Step 5:

[0997] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[0998] Step 6:

[0999] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[1000] Step 7:

[1001] The device receives the fake mark information sent from the server and displays it appropriately on the user interface, specifically by placing a warning icon or message next to the relevant post.

[1002] Step 8:

[1003] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[1004] Step 9:

[1005] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[1006] Example 1

[1007] 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."

[1008] When a disaster occurs, the rapid spread of false information on social media can cause serious disruptions to rescue efforts and information gathering. For example, the spread of posts containing false addresses, names, or urgent requests for dissemination can lead to inappropriate use of resources by relevant agencies, which can delay truly necessary rescue efforts. A system that can prevent such situations and effectively suppress the spread of false information is needed.

[1009] 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.

[1010] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for analyzing and detecting posts containing specific keywords using natural language processing technology, means for deleting the detected posts, and means for displaying a warning to users about the deleted posts. This allows false information to be quickly detected and deleted, and a warning to be displayed to users, thereby preventing the spread of false information.

[1011] An "SNS platform" is a virtual space that provides services that allow users to share information and communicate online.

[1012] "Real-time" refers to the time characteristic in which data or information is processed immediately without delay.

[1013] "Monitoring" refers to the act of continuously observing specific events or data to detect anomalies or significant changes.

[1014] "Natural language processing technology" refers to technology that enables computers to understand, interpret, and generate human language, and includes text analysis and language generation.

[1015] A "keyword" is an important word that symbolizes specific information and is used to represent the content or category of that information.

[1016] "Analysis and detection" is the process of examining and analyzing collected data in detail to identify specific patterns and information.

[1017] "Post" refers to any type of content such as text, images, or videos that a user publishes on a social media platform.

[1018] "Deletion" refers to the act of completely removing data or information from a system or database.

[1019] "Warning" refers to a message or signal that alerts the user to risks or caution.

[1020] "User" refers to an individual or organization that sends and receives information using the SNS platform.

[1021] A "fake mark" is a visual symbol or icon that indicates that certain information is likely not true.

[1022] MODE FOR CARRYING OUT THE INVENTION

[1023] The present invention is a system that automatically detects and removes false information spread on social media in the event of a disaster, and displays a warning to users. Specific embodiments for carrying out the present invention will be described below.

[1024] System Components

[1025] This system consists of three main components: a server, a terminal, and a user. The server retrieves and analyzes posted data from the SNS platform in real time. The terminal is an interface that notifies users of warning messages about false information and marks fakes. Users are individuals or organizations that use the SNS platform on a daily basis.

[1026] Server Operation

[1027] The server first starts streaming real-time post data through the social media platform's API. Specifically, it uses a programming language such as Python and a machine learning framework such as TensorFlow or PyTorch. The server is typically run using a hosting service or cloud infrastructure. The server then analyzes the acquired post data and uses natural language processing (NLP) techniques to detect whether specific keywords are included. NLP libraries such as spaCy and NLTK are used for this analysis.

[1028] For example, if the server detects a post containing keywords such as "address," "name," or "please spread the word," it will flag the post. This flagged post will then be either deleted or marked as fake based on a set algorithm, as explained below.

[1029] Device behavior

[1030] The device receives the notification from the server and displays a fake mark or a warning message on the relevant post. This is typically done using the UI components of the social networking application. For example, a warning icon or a message such as "⚠️ This post may be a hoax" can be displayed next to a specific post to warn the user.

[1031] User Actions

[1032] Users will see posts marked with a fake symbol or warning message on the social media platforms they use daily. This will make users aware that the post is likely to be a hoax and encourage them to handle the information with caution. This will prevent the spread of false information and reduce confusion during disasters.

[1033] Specific examples

[1034] For example, if user A posts "Address: XX, Name: △△, please help. Please spread the word" during a disaster, the server will detect this post in real time. The server will analyze the content of the post and confirm that it contains specific keywords: "address," "name," and "please spread the word." The server will then automatically delete the post and record the completion of the deletion in a log. In another scenario, the server will mark the post as fake and display a warning message to user B via their device.

[1035] Prompt Sentence Examples

[1036] "Please describe a system that automatically monitors posts about disaster-related misinformation, detects posts containing specific keywords, and removes or issues a warning. Please provide details about how this system works, including specific examples of the techniques and tools used."

[1037] In this way, the present invention allows for the rapid detection and response to false information, ensuring that users receive accurate information, thereby preventing confusion during disasters and enabling effective rescue operations.

[1038] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1039] The flow of this system's program processing

[1040] Step 1:

[1041] The server retrieves post data in real time using the API of the social media platform. A specific API call initiates the reception of streaming data. The input is the social media post data, and the output is the streamed post data. This streaming data includes detailed information about each post (text, posting time, poster information, etc.).

[1042] Step 2:

[1043] The server analyzes the posted data it acquires using natural language processing (NLP) technology. NLP libraries used include spaCy and NLTK. The input is the streamed posted data, and the output is the results of keyword analysis (whether or not a specific keyword is included). Specifically, text analysis is performed to check for the presence of keywords such as "address," "name," and "please share."

[1044] Step 3:

[1045] The server detects posts containing specific keywords. Based on the analysis results, it flags posts that may be hoaxes. The input is the keyword analysis results, and the output is the flagged posts. Specifically, the flagged posts are sent to the next processing step.

[1046] Step 4:

[1047] The server selects whether to delete or flag a flagged post. First, if a post is to be deleted based on specific conditions, the SNS API is called to send a deletion request for each post ID. The input is the flagged post data, and the output is the deletion success / failure status. In another case, the metadata is updated to mark the post as fake. Specifically, the server updates the settings to add a hoax warning icon and message.

[1048] Step 5:

[1049] The server logs the process and notifies the administrator. After the deletion or flagging is complete, the result is recorded in a log file or database, and the administrator is notified as needed. The input is the result data of the deletion or flagging, and the output is the recorded log information and the status of the notified administrator. Specifically, the log records details such as the post ID, processing content, and execution time.

[1050] Step 6:

[1051] The device receives the notification from the server and displays a warning to the user. Specifically, it applies updated data containing a fake mark and a warning message to the SNS application and displays it on the user's screen. The input is the warning message and fake mark instructions from the server, and the output is the warning information displayed on the user's interface.

[1052] Step 7:

[1053] Users check the warning message and correct their behavior. When users see a warning message or a post marked as fake, they recognize that it may be a hoax. The input is the warning message displayed on the device, and the output is for users to be more cautious in their actions. Specifically, users should refrain from sharing hoax information and strive to gather accurate information.

[1054] Through the above processing steps, this system can effectively detect and delete false information and display warnings, thereby increasing the reliability of information during disasters.

[1055] (Application example 1)

[1056] 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."

[1057] The spread of misinformation and rumours is a serious problem on modern social media platforms. Particularly during disasters and crises, misinformation can spread quickly, causing significant confusion and panic. This can hinder rescue efforts and lead to actions based on false information. Advertisers also face the risk of damaging their brand's credibility. A system is needed to resolve these issues and ensure accurate information is shared.

[1058] 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.

[1059] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for deleting the detected posts, means for displaying warnings about the deleted posts, and means for detecting false information related to advertisers in real time and issuing alerts. This allows accurate information to be disseminated quickly even during disasters or crisis situations, preventing the spread of false information and protecting the brand credibility of advertisers.

[1060] "SNS platform" refers to software or websites that allow users to share information and communicate online.

[1061] "Real time" refers to the ability to process events and data almost simultaneously.

[1062] "Monitoring" refers to the act of watching for events or data on a particular system or network.

[1063] "Specific keywords" refer to the specific words or phrases the system is configured to detect.

[1064] "Post" refers to a message or content that a user publishes on a social media platform.

[1065] "Detection" refers to the act of a system finding data or events that meet set conditions.

[1066] "Deletion" refers to the act of completely removing specific data or information from a system.

[1067] "Warning" refers to a notification that alerts the user to a risk or problem.

[1068] "Advertiser" refers to a company or individual that places advertisements to promote products or services.

[1069] "Misinformation" refers to information that is not based on facts or is false.

[1070] "Alert" refers to a warning message that notifies you of important information or an emergency.

[1071] MODE FOR CARRYING OUT THE INVENTION

[1072] This invention is a system for preventing the spread of misinformation and rumours, and for protecting the reliability of information, particularly that related to advertisers. The system consists of components: a server, a terminal, and a user. The server retrieves post data from social media platforms in real time, detects posts containing specific keywords, and takes action as necessary. The terminal is an interface that notifies the user of alerts regarding detected misinformation. The user can then take prompt action based on this information.

[1073] Server Operation

[1074] The server first starts streaming real-time post data through the social media platform's API. It authenticates using the social media platform's API key and token to retrieve the post data. It then analyzes the retrieved post data to detect whether it contains specific keywords. Keywords used include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." The analysis process uses the Python tweepy library.

[1075] If a post is detected, the server takes the following actions. First, it deletes the detected post. During the deletion process, it uses the API of the social media platform to obtain the ID of the post in question and uses it to delete the post from the database. Once the deletion is complete, the server logs the completion and notifies the administrator.

[1076] Instead of removing the post, the system will mark it as inauthentic and warn users when they view it. The warning message will include a statement such as "⚠️ This post may be misinformation." Additionally, if misinformation relevant to an advertiser is detected, the system will identify high-risk posts and send an alert to the advertiser. The alert will include the content of the post and a risk assessment.

[1077] Device behavior

[1078] The device receives notifications from the server and displays fake marks and warning messages on posts. It runs on the user's device as a social networking client application and can issue warnings directly to posts on the social networking platforms the user uses. The device also provides an interface to alert advertisers about misinformation, allowing them to take swift action and maintain the credibility of their brand.

[1079] User Actions

[1080] Users use social media platforms on a daily basis to send and receive information. When users access a post marked with a misinformation symbol or a warning message, they can recognize that the post is likely to be a hoax or misinformation and respond appropriately. For example, they can report the problematic post or take measures to spread accurate information.

[1081] Specific examples

[1082] A specific scenario for using the system is when an advertiser posts false information on social media during a disaster, such as "The relief supplies provided by Company X are fake." The server detects this post and sends an alert to the advertiser as risk information related to the post. It also displays a warning mark to general users, informing them that the information is likely to be incorrect.

[1083] Prompt Sentence Examples

[1084] Set up a misinformation monitoring system for advertisers. Monitor social media posts containing specified keywords in real time and display a warning icon for relevant posts. Specific keywords include "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation." Build a system that sends alerts to advertisers for detected posts.

[1085] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1086] Step 1:

[1087] The server authenticates using the social media platform's API, using the API key and token as input and getting an authentication token as output. Using this authentication token, the server prepares to retrieve real-time posting data.

[1088] Step 2:

[1089] The server streams post data in real time from the social media platform through its API. It takes an authentication token as input and gets a stream of post data as output. This stream contains all posts published on the social media platform.

[1090] Step 3:

[1091] The server parses the streamed post data. It takes the stream data as input and uses a regular expression library to analyze it for specific keywords. It generates a list of posts that contain the specific keywords as output.

[1092] Step 4:

[1093] The server determines how to deal with each detected post. As input, it uses a list of posts containing specific keywords. To process the data, it performs a risk assessment on the post and decides whether to delete it or mark it with a warning. As output, it generates a list of posts to be deleted and a list of posts to be marked with a warning.

[1094] Step 5:

[1095] The server uses the SNS platform's API to process the posts to be deleted. It uses the list of posts to be deleted as input and sends an API request to delete the relevant posts from the database. As output, it logs a deletion completion notification and notifies the administrator.

[1096] Step 6:

[1097] The server marks posts that are eligible for warning marking. It uses the list of posts that are eligible for warning marking as input and adds warning marks to the corresponding posts in the database. As output, it logs a notification that the warning mark has been added and generates data to notify the user.

[1098] Step 7:

[1099] The device receives the notification about the warning mark sent from the server. As input, it uses the warning mark notification data sent from the server and processes the display of a warning icon in the SNS client application. As output, the warning icon is displayed to the user in response to the SNS post.

[1100] Step 8:

[1101] If misinformation related to an advertiser is detected, the server sends an alert to the advertiser. The input is the posted data of misinformation related to the advertiser. The data is processed by performing a risk assessment and generating an alert message. The output is an alert notification sent to the advertiser.

[1102] Step 9:

[1103] The user receives a warning icon or alert notification. As input, the user recognizes the warning icon or alert notification displayed on the device and checks the warning content regarding the misinformation. As output, the user can take appropriate action.

[1104] Step 10:

[1105] The server records all processing results in a log. The inputs used are deletion completion notification, warning mark attachment notification, and alert sending notification. Data processing involves adding a timestamp to all actions and saving them in a log database. The output is a log that the system administrator can check.

[1106] In this way, a system is built in which the server, terminals, and users work together to prevent the spread of misinformation and hoaxes and protect the brand credibility of advertisers.

[1107] 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.

[1108] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[1109] System Overview

[1110] This system consists of a server, a terminal, and a user. The server retrieves post data from the SNS platform in real time, detects posts containing specific keywords (e.g., "address," "name," "please share"), and recognizes the user's emotions using an emotion engine. The terminal provides the user with an interface for displaying appropriate warning messages and fake marks. Users use the SNS platform on a daily basis to send and receive information.

[1111] Server Operation

[1112] The server first starts streaming real-time post data through the social media platform's API, and then analyzes the data as it arrives to determine whether it contains specific keywords.

[1113] If a post containing a specific keyword is detected, the server then initiates a sentiment analysis of the post using a sentiment engine, which uses machine learning algorithms to identify the user's emotions from the post's text data, categorizing them into basic emotional categories such as joy, anger, sadness, and fear.

[1114] Processing Posts

[1115] For posts whose emotions have been identified by the emotion engine, the server takes the following actions. First, if the post is determined to be a hoax, it is deleted. In the deletion process, the database is accessed using the post's ID as a key to completely remove the post. When the deletion is complete, the information is recorded in a log.

[1116] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[1117] Device behavior

[1118] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to inform the user that the post may be a hoax.

[1119] User Actions

[1120] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post's content. This allows users to take appropriate action and prevent the spread of false information.

[1121] Specific examples

[1122] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[1123] The present invention makes it possible to effectively prevent the spread of false information during disasters and to provide appropriate warning messages according to the emotional state of users, thereby facilitating rescue operations and saving many lives.

[1124] The processing flow will be explained below.

[1125] Step 1:

[1126] The server establishes a connection by initializing the social media platform's API and entering authentication information, and is then ready to retrieve post data in real time.

[1127] Step 2:

[1128] The server sets up a listener that monitors specific keywords ("address," "name," "please share") and uses this listener to stream new posts on the social media platform in real time.

[1129] Step 3:

[1130] The server analyzes the streamed posting data and checks whether the content contains specific keywords. If the keyword is detected, the post is recognized as a "hoax posting."

[1131] Step 4:

[1132] The server obtains the ID of the post that it has identified as a hoax and deletes it via API. This deletion process is achieved by accessing the database using the post ID as a key and completely removing the relevant post.

[1133] Step 5:

[1134] If the deletion is successful, the server will log the information and notify an administrator if necessary. If the deletion fails, it will log an error message and begin the process of retrying.

[1135] Step 6:

[1136] If the server chooses to display a warning instead of deleting the post, it marks the post as fake and sends data including this fake marking information to the terminal.

[1137] Step 7:

[1138] The server uses an emotion engine to analyze the sentiment of posts containing specific keywords. The emotion engine identifies the user's emotions (e.g., "joy," "anger," "sadness," "fear," etc.) from the content of the post. The emotion engine uses machine learning algorithms to classify the text data.

[1139] Step 8:

[1140] The server generates a warning message appropriate for the user based on the emotion identified by the emotion engine. For example, if the emotion is identified as "fear," the server creates a warning message such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[1141] Step 9:

[1142] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post.

[1143] Step 10:

[1144] When users browse social media platforms through their devices, they can check for posts that display fake marks or warning messages, allowing them to recognize that a post may be a hoax and take appropriate action.

[1145] Step 11:

[1146] While users respond to the false information posts, the server continues to monitor the posted data in real time and continues to detect and process new false information posts, which effectively prevents the spread of false information during disasters.

[1147] Example 2

[1148] 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."

[1149] Social media platforms have become an important means of information transmission in modern times, but in times of disaster, false information can easily spread, resulting in confusion and panic. Furthermore, depending on the content of the false information, it may have an emotional impact on users, causing anxiety and fear. To solve these problems, real-time detection and appropriate processing of false posts is necessary, and a warning system that takes user emotions into account is also required.

[1150] 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.

[1151] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for analyzing the sentiment of the detected posts, means for determining whether the posts are hoaxes based on the sentiment analysis results, means for deleting posts determined to be hoaxes, means for displaying a fake mark when deletion is difficult, means for generating a warning message based on the sentiment, and means for displaying the generated warning message on the user's device. This enables the rapid detection and deletion of hoaxes or appropriate warnings to users, thereby preventing the spread of hoaxes while minimizing the emotional impact on users.

[1152] An "SNS platform" is an online service that allows users to share information and communicate with others.

[1153] "Real-time" means that information and data are processed immediately and provided without delay.

[1154] "Monitoring" is the act of continuously observing a specific object and supervising its situation.

[1155] "Keywords" are key words or phrases used to locate specific information.

[1156] "Analyzing sentiment" is the process of determining the emotional state of a writer from text data.

[1157] A "hoax" is false information that is spread intentionally or accidentally.

[1158] "Hoax assessment" is the process of assessing whether information is true or false.

[1159] A "fake mark" is an identifying icon that indicates that certain information is likely to be false.

[1160] A "warning message" is a notification message that warns users of risks and cautions them.

[1161] A "terminal" is an electronic device that a user uses to send and receive information.

[1162] The present invention relates to a system that automatically monitors hoax posts on social media in the event of a disaster, detects posts containing specific keywords, and deletes them or marks them as fake, in addition to a system that combines an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described below.

[1163] Hardware and software used

[1164] server

[1165] Hardware: High-performance data center servers (e.g., general-purpose high-performance servers)

[1166] Software: API of social media platform, Python, Pandas, syntax analysis library (e.g., natural language processing library), machine learning library (e.g., machine learning framework)

[1167] Terminal

[1168] Hardware: Regular PCs and mobile devices (e.g., laptops and smartphones)

[1169] Software: Web browsers (e.g., internet browsers), dedicated applications (e.g., apps developed using cross-platform frameworks)

[1170] User

[1171] Hardware: Same as above (regular PC or mobile device)

[1172] Software: Same as above

[1173] Explanation of the system processing flow

[1174] 1. Collecting social media posting data

[1175] The server starts streaming real-time post data through the social media platform's API, and uses a Python library to retrieve the data and convert it into the format required for analysis.

[1176] 2. Keyword detection

[1177] The server stores the retrieved post data in a data frame and uses a syntax analysis library to detect specific keywords (e.g., "address," "name," "please share") This analysis involves text tokenization and keyword matching.

[1178] 3. Sentiment analysis

[1179] The server runs an emotion engine based on the keyword detection results to perform sentiment analysis of the posts, classifying them into emotion categories (e.g., joy, anger, sadness, fear) using a machine learning library.

[1180] 4. Post Judgment and Processing

[1181] The server judges the post based on the analysis results of the emotion engine. If it is judged to be a hoax, the server accesses the database and deletes the post. If deletion is difficult, the server marks the post as fake and records a log of the deletion process.

[1182] 5. Warning message generation and display

[1183] The server generates a warning message based on the emotion analysis results. For example, if "fear" is identified, the server generates a message saying "⚠️ This post may be a hoax. Please be careful as the content may be disturbing" and sends it to the device. The device then displays this message on the user interface.

[1184] Specific examples

[1185] For example, if user A posts "Address: XX, Name: △△, Please help. Please share this information" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "address," "name," and "please share this information." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes this post and logs the completion of the deletion. In another scenario, the server marks this post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on the user interface to warn user B.

[1186] Prompt Sentence Examples

[1187] Recognize the sentiment of the post "Address: XX, Name: △△, Please help. Please spread the word.", determine whether it is a hoax, and delete it. Please describe the steps required to build a system that uses an emotion engine to identify sentiment and generate and display a warning message as necessary.

[1188] This detailed description clarifies the specific operations of each processing step of the system. Understanding what happens at each step makes it easier to grasp the overall function of the system.

[1189] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1190] The flow of this system's program processing

[1191] Step 1: Collect social media post data

[1192] Step 2: Keyword detection

[1193] Step 3: Sentiment analysis

[1194] Step 4: Identifying and Processing Posts

[1195] Step 5: Generate and display warning messages

[1196] Detailed explanation of the processing steps

[1197] Step 1: Collect social media post data

[1198] Input: The server receives post data through the API of the social networking platform.

[1199] How it works: The server collects real-time posting data via the API of the social media platform, starts data streaming using a Python library (e.g., Tweepy), and converts the collected data into a data frame.

[1200] Output: Streaming data is stored on the server as a data frame.

[1201] Step 2: Keyword detection

[1202] Input: Streaming data exists on the server as a DataFrame.

[1203] How it works: The server uses a syntax analysis library (e.g., SpaCy) to detect specific keywords (e.g., "address," "name," "please share") in the post data. This analysis involves tokenizing the text and keyword matching.

[1204] Output: Posts in which the keyword was found are identified and the appropriate rows are flagged.

[1205] Step 3: Sentiment analysis

[1206] Input: Post data with keyword detection completed.

[1207] How it works: The server uses a sentiment engine (e.g., a BERT-based machine learning model) to analyze the sentiment of the detected posts, classify them into sentiment categories (e.g., joy, anger, sadness, fear), and add the results to a data frame.

[1208] Output: Generates sentiment-identified post data and adds sentiment categories to each post.

[1209] Step 4: Identifying and Processing Posts

[1210] Input: Post data that has undergone keyword detection and sentiment analysis.

[1211] How it works: The server judges posts based on the analysis results of the emotion engine. If it judges a post to be a hoax, it accesses a database (e.g., MySQL) to delete the post. If it is difficult to delete the post or if immediate deletion is not necessary, it marks the post as fake. At this time, it records logs of the deletion process and the marking of the post as fake.

[1212] Output: Data on posts that were deleted or marked as fake is generated and logged.

[1213] Step 5: Generate and display warning messages

[1214] Input: Post data that has been identified as a hoax or marked as fake.

[1215] Operation: The server generates a warning message based on the results of the sentiment analysis. For example, if "fear" is identified, the server generates a message stating "This post may be a hoax. Please be careful as the content may be disturbing," and sends it to the user's device via the user interface. The device then displays this warning message on its screen.

[1216] Output: A warning message is generated and displayed on the user's terminal.

[1217] The above is a detailed explanation of the system's specific processing steps and their operation. It details what data is input at each step, what processing is performed, and what output is obtained.

[1218] (Application example 2)

[1219] 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."

[1220] During disasters and emergencies, false information spreads rapidly on social media, causing anxiety and confusion among many users. This can also cause confusion and hinder rescue efforts, so there is a need for a method to quickly and effectively prevent the spread of false information. Furthermore, measures are also needed to ensure that users can obtain accurate information without being emotionally affected.

[1221] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1222] In this invention, the server includes means for monitoring posts on the SNS platform in real time, means for detecting posts containing specific keywords, means for performing emotion recognition on the detected posts using an emotion engine, means for deleting the detected posts, means for marking the detected posts as fake if deletion is difficult or not necessary immediately, and means for generating a warning message based on the identified emotion, and means for displaying the generated warning message on a user interface. This allows users to receive appropriate warnings while preventing the spread of false information.

[1223] An "SNS platform" is a software service that allows users to disseminate information and interact with others online.

[1224] "Real-time monitoring means" refers to technology that allows for instant monitoring and analysis of posts on social media platforms.

[1225] "Specific keywords" are words used to identify specific content, such as "address," "name," or "please share."

[1226] The "means for detecting posts" refers to technology for finding posts containing specific keywords from posts on social media platforms that are monitored in real time.

[1227] An "emotion engine" is an algorithm or system that analyzes text data contained in posts and identifies user emotions.

[1228] "Means for emotion recognition" refers to technology that uses an emotion engine to identify a user's emotional state from the text of a post.

[1229] "Methods for removing posts" refers to techniques used to physically remove posts determined to be false from social media platforms.

[1230] "Means of assigning fake marks" refers to a technology that adds a mark to problematic posts to visually warn users.

[1231] A "warning message" is a message that informs users that a post may be a hoax and urges them to be careful.

[1232] The "means for generating" is a technology for creating a warning message or a counterfeit mark based on specific conditions.

[1233] A "user interface" is the screen and operating environment through which a user interacts with a system.

[1234] The "display means" refers to a technique for visually displaying the generated warning message or fake mark on the user interface.

[1235] A "generative AI model" is an artificial intelligence model used to determine the output generated from input data.

[1236] A "prompt" is a sentence used as input to a generative AI model, and is an instruction to produce a specific output based on its content.

[1237] An embodiment of the present invention will be described below.

[1238] System Overview

[1239] This system monitors posts on social media platforms in real time, detects posts containing specific keywords, and uses an emotion engine to recognize the emotions in the posts. If detected posts are determined to be hoaxes, they are deleted, or if deletion is difficult, they are marked as fake. A warning message based on the emotion is displayed on the user interface.

[1240] Server Operation

[1241] The server streams post data in real time through the API of the social media platform. The server analyzes the received post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). If a post containing specific keywords is detected, it performs a sentiment analysis of the post content using an emotion engine. The emotion engine uses a machine learning algorithm (e.g., TextBlob) to identify the user's emotions from the text data of the post. These emotions are classified into basic emotional categories such as joy, anger, sadness, and fear.

[1242] Processing Posts

[1243] For posts whose emotions have been identified by the emotion engine, the server responds as follows: First, if the post is determined to be a hoax, it is deleted. The deletion process involves accessing the database using the post's ID as a key and completely removing the post. Once the deletion is complete, the information is recorded in a log.

[1244] If deletion is difficult or does not require immediate deletion, the server will mark the post as fake and generate a warning message based on the identified emotion. For example, if the emotion engine identifies "fear," it will generate a warning message such as "⚠️ This post may be a hoax. Please be careful as it contains disturbing content."

[1245] Device behavior

[1246] The device receives the fake mark and warning message based on the emotion sent from the server and displays it appropriately on the user interface. Specifically, it places a warning icon or message next to the relevant post to notify the user that the post may be a hoax.

[1247] User Actions

[1248] Users send and receive information through social media platforms. By checking posts marked as fake or with warning messages, they can recognize the possibility that the post is a hoax and the emotional impact of the post. This allows users to take appropriate action and prevent the spread of hoax information.

[1249] Specific examples

[1250] For example, if a user posts "Address: XX, Name: △△, Please help. Please spread the word" on a social media platform during a disaster, the server detects this post in real time. The server analyzes the content of the post and confirms that it contains specific keywords: "Address," "Name," and "Please spread the word." The emotion engine then identifies the emotion contained in this post as "anxiety." The server automatically deletes the post and logs the completion of the deletion. In another scenario, the server marks the post as fake and generates and sends a warning message to the device stating, "⚠️ This post may be a hoax. Please be careful as the content may be disturbing." The device then displays this warning message on its user interface to alert the user.

[1251] Example prompt sentence:

[1252] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[1253] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1254] Step 1:

[1255] The server starts streaming post data through the SNS platform's API. As input, it receives the SNS platform's API key and the real-time stream of post data. This allows the server to continuously obtain new post data. The output is the obtained SNS post data.

[1256] Step 2:

[1257] The server analyzes the acquired post data and detects whether it contains specific keywords (e.g., "address," "name," "please share"). The input is the acquired post data, and the output is a list of posts in which specific keywords are detected. The server parses the text in the post data and checks whether the specific keywords are present.

[1258] Step 3:

[1259] The server uses an emotion engine to perform emotion recognition on posts containing specific keywords. The input is post data containing specific keywords, and the emotion is identified using a machine learning algorithm (e.g., TextBlob). The output is the emotion category (e.g., joy, anger, sadness, fear) corresponding to each post.

[1260] Step 4:

[1261] The server determines whether posts with identified emotions are hoaxes. The input is post data with emotional categories, and the server uses a hoax detection algorithm to determine whether a post is a hoax. The output is a list of posts that are determined to be hoaxes.

[1262] Step 5:

[1263] The server deletes posts that are determined to be hoaxes. The input is the post data that was determined to be hoax, and the post ID is used to delete it from the database. The output is a log of the completion of the deletion process. If deletion is difficult or there is no need to delete it immediately, proceed to the next step.

[1264] Step 6:

[1265] The server marks posts that are difficult to delete as fake and generates a warning message based on emotion using a generative AI model. The input is the post data that cannot be deleted and its emotion category, and the output is the post data marked as fake and the generated warning message. The server sends a prompt sentence as input to the generative AI model and receives an appropriate warning message. Example:

[1266] Analyze posts such as "Help is needed in town X during a disaster. Name is △△, please spread the word" to determine whether they are likely to be hoaxes. If so, remove the post and generate a sentiment-based warning message, such as "⚠️ This post may be a hoax. Please be careful as the content may be disturbing."

[1267] Step 7:

[1268] The terminal receives the fake mark and warning message sent from the server and displays them on the user interface. The input is the fake mark and warning message sent from the server, and the output is a visual display on the user interface. Based on this, the user can judge the content of the post and take appropriate action.

[1269] 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.

[1270] 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.

[1271] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1272] 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.

[1273] 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.

[1274] 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.

[1275] 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).

[1276] 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.

[1277] 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."

[1278] 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.

[1279] 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).

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] 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.

[1290] The following is further disclosed regarding the above embodiment.

[1291] (Claim 1)

[1292] A means of monitoring posts on social media platforms in real time,

[1293] A means of detecting posts containing specific keywords;

[1294] A means to remove detected posts; and

[1295] a means for displaying a warning to users about the deleted post;

[1296] A system including:

[1297] (Claim 2)

[1298] The system of claim 1, wherein the specific keywords include "address," "name," and "please spread the word."

[1299] (Claim 3)

[1300] The system of claim 1, further comprising means for marking a detected post as fake instead of deleting it.

[1301] "Example 1"

[1302] (Claim 1)

[1303] A means of monitoring posts on social media platforms in real time,

[1304] A method for analyzing and detecting posts containing specific keywords using natural language processing technology;

[1305] A means to remove detected posts; and

[1306] a means for displaying a warning to users about the deleted post;

[1307] A system including:

[1308] (Claim 2)

[1309] The system of claim 1, wherein the specific keywords include "location," "person's name," and "request for dissemination."

[1310] (Claim 3)

[1311] The system of claim 1, further comprising means for marking a detected post as fake instead of deleting it.

[1312] "Application Example 1"

[1313] (Claim 1)

[1314] A means of monitoring posts on social media platforms in real time,

[1315] A means of detecting posts containing specific keywords;

[1316] A means to remove detected posts; and

[1317] a means to display warnings about deleted posts;

[1318] A means to detect and alert advertisers to misinformation in real time; and

[1319] A system including:

[1320] (Claim 2)

[1321] 2. The system of claim 1, wherein the specific keywords are "address," "name," "please spread," "fake news," "rumor," "scam," and "misinformation."

[1322] (Claim 3)

[1323] The system of claim 1, further comprising means for displaying a fake mark and means for notifying the advertiser instead of deleting the detected post.

[1324] "Example 2: Combining Emotion Engines"

[1325] (Claim 1)

[1326] A means of monitoring posts on social media platforms in real time,

[1327] A means of detecting posts containing specific keywords;

[1328] a means for analyzing the sentiment of the detected posts;

[1329] A means for determining whether a post is a hoax based on the result of sentiment analysis;

[1330] A means to remove posts determined to be hoaxes;

[1331] A method to display a fake mark when removal is difficult, and

[1332] means for generating an emotion-based warning message;

[1333] means for displaying the generated warning message on a user's terminal;

[1334] A system including:

[1335] (Claim 2)

[1336] The system of claim 1, wherein the specific keywords include "address," "name," and "please spread the word."

[1337] (Claim 3)

[1338] The system of claim 1, further comprising means for marking a detected post as fake instead of deleting it.

[1339] "Application example 2 when combining emotion engines"

[1340] (Claim 1)

[1341] A means of monitoring posts on social media platforms in real time,

[1342] A means of detecting posts containing specific keywords;

[1343] A means for performing emotion recognition on the detected posts using an emotion engine;

[1344] A means to remove detected posts; and

[1345] If removal is difficult or does not require immediate removal, a means of marking the detected post as fake and generating a warning message based on the identified sentiment; and

[1346] means for displaying the generated warning message on a user interface;

[1347] ...

[1348] A system including:

[1349] (Claim 2)

[1350] The system of claim 1, wherein the specific keywords include "address," "name," and "please spread the word."

[1351] (Claim 3)

[1352] 10. The system of claim 1, further comprising means for generating a warning message using a generative AI model. [Explanation of symbols]

[1353] 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 monitoring posts on social media platforms in real time, A means of detecting posts containing specific keywords; A means to remove the detected posts; and a means for displaying a warning to users about the deleted post; A system including:

2. The system of claim 1 , wherein the specific keywords include "address," "name," and "please spread the word."

3. The system of claim 1 further comprising means for marking a detected post as fake instead of deleting it.

Images