System

Abstract

A system is provided.SOLUTION: A system, comprising: fake news detection algorithm means for evaluating post content; means for receiving the post content from terminals; means for performing evaluation of the post content using the algorithm means; means for sending the evaluation results to terminals; and means for displaying the evaluation results on a user interface.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] Recently, fake news and false information have spread rapidly on social media and the internet, causing social unrest and economic impacts in an increasing number of cases. In particular, fake news related to disasters and incidents is likely to cause panic based on incorrect information and increase the number of victims. Furthermore, the current legal system and platform enforcement make it difficult to systematically remove slander and false information, leaving individual victims to deal with the issue themselves. There is a need for a system that can improve this situation and enable users to identify fake news themselves. [Means for solving the problem]

[0005] The present invention provides a system including a fake news detection algorithm for evaluating posted content, a means for receiving the posted content from a terminal, a means for evaluating the posted content using the algorithm, a means for transmitting the evaluation results to the terminal, and a means for displaying the evaluation results on a user interface. This system allows users to easily determine the credibility of posted content and prevent the spread of fake news. Furthermore, the fake news detection algorithm is a means for evaluating the likelihood of fake news based on text input on a five-point scale, allowing for more detailed evaluations. Furthermore, the system includes a means for visually displaying the evaluation results as a fake level and confidence level, allowing users to intuitively determine credibility.

[0006] "Posted Content" refers to text, images, and other information that a user makes public on the Internet or on social media platforms.

[0007] "Fake news detection algorithmic measures" refers to programs and technologies that analyze text and image content and assess its veracity.

[0008] "Means for receiving" refers to the communication means and protocol for receiving posted content from the terminal to the server.

[0009] "Means for performing evaluation" refers to the process and system parts that input received posts into the fake news detection algorithm and generate the evaluation results.

[0010] "Transmission means" refers to the communication means and protocol for sending the evaluation results from the server to the terminal.

[0011] "Means for displaying on a user interface" refers to a display device and associated software for visually presenting the evaluation results to a user.

[0012] "Fake Level" refers to an index rated on a scale of 1 to 5 to indicate the likelihood of fake news.

[0013] "Confidence" refers to a numerical value that indicates the degree of reliability that the fake news detection algorithm has in its evaluation results. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment for preventing the spread of fake news will be described.

[0036] System Overview

[0037] This system has the function of analyzing the content posted by users and evaluating its credibility. The system mainly consists of the following functional blocks.

[0038] 1. Means of receiving posted content (server)

[0039] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[0040] 2. Fake News Detection Algorithm (Server)

[0041] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0042] 3. Evaluation result generation means (server)

[0043] The server takes the evaluation results generated by the algorithm and outputs them as a fake level (1 to 5) and a confidence level (a number between 0 and 1).

[0044] 4. Evaluation result transmission method (server)

[0045] The server then sends the generated evaluation results to the user's device, allowing the user to check in real time how trustworthy the content of their posts are.

[0046] 5. Means of display in the user interface (terminal)

[0047] The evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level and confidence level are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information.

[0048] System processing overview

[0049] An example of the processing of this system is shown below.

[0050] Receiving posted content

[0051] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0052] Analysis and evaluation of posted content

[0053] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (1-5) and a confidence level (0-1).

[0054] Submitting and viewing evaluation results

[0055] The server converts the analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. Specifically, it displays "Fake Level: 4, Confidence: 0.85" next to the post content.

[0056] Specific examples

[0057] Below is a concrete example of the system in action.

[0058] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to be "Fake Level: 4, Confidence: 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[0059] In this way, the system of the present invention prevents the spread of fake news and provides an environment in which users can easily determine the credibility of information.

[0060] The processing flow will be explained below.

[0061] Step 1: Enter post content (user)

[0062] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[0063] Step 2: Send your post (device)

[0064] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[0065] Step 3: Receiving the posted content (server)

[0066] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[0067] Step 4: Analyzing the Post Content (Server)

[0068] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[0069] Step 5: Generating evaluation results (server)

[0070] The server obtains the analysis result of the algorithm. The analysis result includes a fake level (1-5) and a confidence level (0-1). For example, the result generated is "Fake level: 4, confidence level: 0.85".

[0071] Step 6: Formatting the evaluation results (server)

[0072] The server converts the evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[0073] Step 7: Sending evaluation results (server)

[0074] The server then sends the formatted evaluation results to the terminal, again using an HTTP response.

[0075] Step 8: Receiving the evaluation results (terminal)

[0076] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[0077] Step 9: View the evaluation results (on your device)

[0078] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85" next to the entered post content.

[0079] Step 10: Check the evaluation results (user)

[0080] Users can check the fake level and confidence level displayed on their device and use this information to determine the authenticity of the post.

[0081] Step 11: Additional User Actions

[0082] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[0083] Example 1

[0084] 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."

[0085] In recent years, the reliability of information on the Internet has become increasingly important, and the spread of fake news, especially on social media, has become a serious social problem. This fake news not only causes misunderstanding and anxiety, but can also have a negative impact on actual behavior. Therefore, there is a need to quickly evaluate the reliability of content posted by users and prevent the spread of fake news before it happens.

[0086] 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.

[0087] In this invention, the server includes an information evaluation algorithm for evaluating posted content, a means for receiving the posted content from a user device, a means for evaluating the posted content using the algorithm, a means for transmitting the evaluation result to the user device, and a means for displaying the evaluation result on a user interface. This allows users to easily and quickly confirm the reliability of posted content, preventing the spread of fake news and promoting accurate information sharing.

[0088] "Posted content" is a general term for information posted by users through social media or other online platforms, including text and image data.

[0089] "Information evaluation algorithm means" refers to a technical component that executes an algorithm that analyzes the reliability and accuracy of received posts and assesses the likelihood that the content in question is fake news.

[0090] "Devices used" refers to devices that users use to connect to the Internet and send and receive information, and is a general term for smartphones, tablets, PCs, etc.

[0091] The "user interface" refers to components such as a display screen and input devices that users use to operate system functions and visually confirm evaluation results.

[0092] The "trust level" is a number that indicates the evaluation result of whether the content of a post is accurate, and is usually expressed on a scale of 1 to 5.

[0093] "Confidence" is a number that indicates the degree of trust in the reliability assessment result produced by the algorithm, and is expressed in a range from 0 to 1.

[0094] The present invention relates to a system for assessing the reliability of information posted by users, with the aim of preventing the spread of fake news, particularly on social media.

[0095] System Overview

[0096] The system includes an information evaluation algorithm means, a means for receiving posted content from a user device, a means for performing an evaluation of the posted content using the algorithm means, a means for transmitting the evaluation results to the user device, and a means for displaying the evaluation results on a user interface.

[0097] Hardware and Software

[0098] An embodiment of the system uses the following hardware and software:

[0099] 1. Server:

[0100] It provides a high-performance computing environment and is responsible for receiving and analyzing content posted by users.

[0101] The software running on the server includes a web framework using the Flask library.

[0102] 2. Algorithmic means:

[0103] It uses deep learning models and natural language processing techniques to assess the trustworthiness of posts.

[0104] Specifically, it uses a pre-trained model using the Transformers library.

[0105] 3. Equipment used:

[0106] A device used by users to send, receive, and display information, including smartphones, tablets, and PCs.

[0107] Specific details of data processing

[0108] 1. Receiving:

[0109] The server receives posts from users, which may be in various formats such as text or image data.

[0110] 2. Analysis:

[0111] The server then feeds the received posts into an algorithmic process to assess their trustworthiness using deep learning models and natural language processing techniques.

[0112] 3. Generating and sending evaluation results:

[0113] The server obtains the analysis results and generates a confidence level and certainty factor, which are then sent to the user device in JSON format.

[0114] 4.Display:

[0115] The user's terminal receives the evaluation results sent from the server and displays them on the user interface.

[0116] Specific examples

[0117] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "reliability level of 4, certainty factor of 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[0118] Prompt Sentence Examples

[0119] Here are some examples of prompts for generative AI models:

[0120] Please explain the detailed programming process of the fake news detection system. Please explain it in the following steps: 1. Receiving the post content 2. Running the fake news detection algorithm 3. Generating the evaluation results 4. Sending the evaluation results 5. Displaying the evaluation results. Please provide specific operations and techniques for each step.

[0121] This prompt helps the generative AI model provide a detailed description of the system described above.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: Receiving submissions

[0124] Specific description:

[0125] The server receives the content posted by the user from the device used by the user. Specifically, the text and images posted by the user on the social media application are sent to the server.

[0126] Input and Output:

[0127] Input: The post typed by the user (e.g., "A serious incident has occurred").

[0128] Output: The post received by the server.

[0129] Specific behavior:

[0130] The server receives the submission via an HTTP POST request, for example, using Flask's request.get_json() method to retrieve the data.

[0131] Step 2: Analyzing the Post Content

[0132] Specific description:

[0133] The server feeds the received posts into a fake news detection algorithm, which uses pre-trained deep learning models and natural language processing techniques to assess their credibility.

[0134] Input and Output:

[0135] Input: The post content received by the server.

[0136] Output: The result of the fake news detection algorithm (e.g., "Fake Level: 4, Confidence: 0.85").

[0137] Specific behavior:

[0138] The server uses the Transformers library to pass the post to a pre-trained model, which outputs a confidence score and returns it to the server as the analysis result.

[0139] Step 3: Generate evaluation results

[0140] Specific description:

[0141] The server generates a confidence level (1-5) and a confidence level (0-1) based on the results of the algorithm's analysis, which are then formatted for easy display in a user interface.

[0142] Input and Output:

[0143] Input: Analysis results of the fake news detection algorithm.

[0144] Output: Evaluation results (in JSON format) including confidence level and certainty.

[0145] Specific behavior:

[0146] The server maps the score based on the analysis results and generates the evaluation result in JSON format. For example, it maps the fake level and confidence level according to the score value.

[0147] Step 4: Submit your evaluation results

[0148] Specific description:

[0149] The server then sends the generated evaluation results to the device, allowing users to check the reliability of the posted content in real time.

[0150] Input and Output:

[0151] Input: Evaluation results (JSON data including confidence level and certainty).

[0152] Output: Evaluation results sent to the user device.

[0153] Specific behavior:

[0154] The server sends the evaluation result back to the device as an HTTP response, for example, by sending JSON data using Flask's jsonify method.

[0155] Step 5: View the evaluation results

[0156] Specific description:

[0157] The user's device displays the evaluation results received from the server on a user interface, allowing the user to intuitively understand how trustworthy the posted content is.

[0158] Input and Output:

[0159] Input: The evaluation result (confidence level and certainty) received from the server.

[0160] Output: The evaluation results displayed on the user interface.

[0161] Specific behavior:

[0162] The user's device uses JavaScript to embed the evaluation results in HTML elements and display them visually. For example, the document.getElementById().innerHTML method is used to update the displayed content.

[0163] (Application example 1)

[0164] 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."

[0165] In recent years, the increase in fake news on the Internet has become a serious problem, and users are losing trust in news articles in particular. The spread of fake news can encourage decision-making based on erroneous information and have a negative impact on society. Therefore, there is a need for a system that allows users to easily determine the reliability of news articles and prevents the spread of fake news.

[0166] 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.

[0167] In this invention, the server includes a fake news detection algorithm means for evaluating posted content, a means for receiving the posted content from a terminal, a means for evaluating the posted content using the algorithm means, a means for transmitting the evaluation result to the terminal, a means for displaying the evaluation result on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability evaluation, and a means for displaying a warning for articles that are likely to be fake news. This allows users to intuitively judge the reliability of news articles and makes it possible to prevent the spread of fake news.

[0168] "Fake news detection algorithmic means for assessing the content of posts" refers to means that include an algorithm that analyses the content of text, images, etc. posted by users and determines their reliability.

[0169] The "means for receiving posted content from a terminal" refers to a means including an interface and communication means for receiving posted content sent from a user terminal.

[0170] "Means for evaluating posted content using algorithmic means" refers to means that include the function of applying a fake news detection algorithm to received posted content and performing that evaluation.

[0171] The "means for transmitting the evaluation results to the terminal" refers to a means including a communication means for transmitting the evaluation results generated by the algorithm to the user's terminal.

[0172] The "means for displaying the evaluation results on a user interface" refers to a means including an interface and a function for visually displaying the evaluation results sent to the terminal.

[0173] "Means for analyzing the content of news articles in real time and displaying a credibility evaluation" refers to means that includes analysis and display functions for analyzing the content of news articles viewed by users in real time and displaying the results of a credibility evaluation.

[0174] "Means for displaying a warning to articles that are likely to be fake news" refers to means that include a function for displaying a warning to users about articles that are determined to be likely to be fake news as a result of a reliability assessment.

[0175] The present invention provides a system for assessing the reliability of news articles viewed by users in real time and preventing the spread of fake news. The system includes a fake news detection algorithm for assessing the content of posts, a means for receiving the posted content from a terminal, a means for assessing the posted content using the algorithm, a means for transmitting the assessment results to the terminal, a means for displaying the assessment results on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability assessment, and a means for displaying a warning for articles that are likely to be fake news.

[0176] Program processing overview

[0177] The server uses a fake news detection algorithm to analyze news articles posted or viewed by users in real time. The algorithm uses deep learning and natural language processing techniques to evaluate the authenticity of the posted content. The evaluation results are generated as a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[0178] The server sends the evaluation results to the device, which then visually displays them on the user interface. When users view a news article, they can intuitively understand whether the article is fake news or not. Furthermore, articles that are likely to be fake news are displayed with a warning.

[0179] Specific examples

[0180] For example, a user uses a news aggregation application to view a news article titled "A major incident has occurred." The content of this news article is sent to a server and analyzed by a fake news detection algorithm. If the analysis results in the news article being rated "Fake Level: 4, Confidence: 0.85," the server sends this result to the user's device. A warning message stating "This news article is likely to be fake news" is displayed next to the article on the user's device, allowing the user to confirm the reliability of the news article.

[0181] An example of a prompt to be input to the generative AI model is as follows:

[0182] "What program uses a fake news detection algorithm to assess the veracity of today's news posts?"

[0183] "Please explain how a news aggregation app can display fake news warnings to users."

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] A user opens a news aggregation application, selects a news article, and starts viewing it. When the user starts viewing, the device extracts the content (text data) of the news article and sends it to the server.

[0187] Input: News article content (text data)

[0188] Output: Data sent to the server

[0189] Specific behavior: A user operates a news app and clicks to open an article. The app extracts the text data and automatically sends it to the server.

[0190] Step 2:

[0191] The server then inputs the received text data of the news articles into a fake news detection algorithm, which uses natural language processing and deep learning techniques to analyze the text data and evaluate its reliability.

[0192] Input: Text data of news articles sent from the user's device

[0193] Output: Evaluation result of fake news detection (fake level and confidence level)

[0194] How it works: The server receives news text data and inputs it into the fake news detection algorithm, which then analyzes the data and generates a rating.

[0195] Step 3:

[0196] The server sends the generated evaluation result to the terminal. This evaluation result includes a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[0197] Input: Fake news detection evaluation results

[0198] Output: Evaluation result data sent to the user's device

[0199] Specific operation: The server converts the evaluation results into JSON format and sends them to the user's device.

[0200] Step 4:

[0201] The user's device visually displays the received evaluation results in a user interface, displaying a fake level and confidence level next to the news article the user is viewing, and displaying a fake news warning if necessary.

[0202] Input: Evaluation result sent from the server (fake level and confidence level)

[0203] Output: Trust rating and warnings displayed in the user interface

[0204] Specific operation: The user's device analyzes the evaluation result data received and displays a message next to the news article, such as "Fake level: 4, confidence level: 0.85." If a warning is necessary, the message will read, "This news article is likely to be fake news."

[0205] Step 5:

[0206] Users can review the credibility ratings and warnings displayed and decide whether to trust the news article, and if necessary, decide not to share it or conduct additional fact-checking.

[0207] Input: Trust rating and warnings displayed in the user interface

[0208] Output: User decision and action (e.g., not sharing the article, further fact-checking, etc.)

[0209] What happens: Users can view a news article's credibility rating and warnings and make decisions based on that information, such as whether to read the article or refrain from sharing it.

[0210] 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.

[0211] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment will be described that combines an emotion engine that recognizes user emotions.

[0212] System Overview

[0213] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following functional blocks.

[0214] 1. Means of receiving posted content (server)

[0215] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[0216] 2. Fake News Detection Algorithm (Server)

[0217] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0218] 3. Emotion engine means (server)

[0219] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[0220] 4. Evaluation result generation means (server)

[0221] The server combines the fake news evaluation results with the emotion engine analysis results and outputs the overall evaluation result. For example, it generates an evaluation result in the form of "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0222] 5. Evaluation result transmission method (server)

[0223] The server then sends the generated overall evaluation results to the user's device, allowing the user to check the reliability of their own posts as well as their emotional state in real time.

[0224] 6. Means of display in the user interface (terminal)

[0225] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[0226] System processing overview

[0227] An example of the processing of this system is shown below.

[0228] Receiving posted content

[0229] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0230] Analysis and evaluation of posted content

[0231] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[0232] The server then uses an emotion engine to analyze the user's emotional state from their posts, which is then classified into categories such as "joy," "anger," "sadness," and "surprise."

[0233] Submitting and viewing evaluation results

[0234] The server converts the fake news evaluation results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. For example, "Fake level: 4, confidence level: 0.85, sentiment: anger" may be displayed next to the post.

[0235] Specific examples

[0236] Below is a concrete example of the system in action.

[0237] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "Fake Level: 4, Confidence: 0.85." The emotion engine also returns the emotional state of "Anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "Fake Level: 4, Confidence: 0.85, Emotion: Anger," and can take action as necessary.

[0238] In this way, the system of the present invention prevents the spread of fake news and also provides an environment for comprehensively evaluating the credibility of posted content by understanding the user's emotional state.

[0239] The processing flow will be explained below.

[0240] Step 1: Enter post content (user)

[0241] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[0242] Step 2: Send your post (device)

[0243] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[0244] Step 3: Receiving the posted content (server)

[0245] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[0246] Step 4: Analyzing the Post Content (Server)

[0247] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[0248] Step 5: Generate fake levels and confidence (server)

[0249] The server receives the analysis results from the algorithm and outputs them as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1). For example, the result might be "Fake level: 4, confidence level: 0.85."

[0250] Step 6: Performing sentiment analysis (server)

[0251] The server inputs the posted content into an emotion engine and analyzes the user's emotional state, which is classified into categories such as "joy," "anger," "sadness," and "surprise."

[0252] Step 7: Integration of evaluation results (server)

[0253] The server combines the fake news evaluation results with the emotion engine analysis results and compiles them into an overall evaluation result. For example, the results may be summarized as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0254] Step 8: Formatting the evaluation results (server)

[0255] The server converts the integrated evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[0256] Step 9: Sending evaluation results (server)

[0257] The server then sends the formatted evaluation results to the user's device, again using an HTTP response.

[0258] Step 10: Receiving evaluation results (terminal)

[0259] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[0260] Step 11: Viewing the evaluation results (terminal)

[0261] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85, Emotion: Anger" next to the entered post content.

[0262] Step 12: Check the evaluation results (user)

[0263] Users can view the fake level, confidence level, and emotional state displayed on their device, and use this information to determine the authenticity of the post.

[0264] Step 13: Additional User Actions

[0265] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[0266] Example 2

[0267] 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."

[0268] Conventional fake news detection systems are limited to assessing the credibility of posted content and do not take into account the user's emotional state. As a result, when a user's emotions affect the credibility of the posted content, the evaluation of the information may be incomplete. Furthermore, simply assessing whether or not something is fake news does not provide users with enough information to understand the content and take appropriate action.

[0269] 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.

[0270] In this invention, the server includes a false information detection means for evaluating the posted content, a means for analyzing the posted content and classifying the user's emotions, and a means for integrating the evaluation result of the false information detection means and the result of the emotion classification means, thereby enabling a comprehensive evaluation that takes into account not only the credibility of the posted content but also the user's emotional state.

[0271] "Posted content" refers to information such as text, images, and videos that users post on social media or other communication platforms.

[0272] "False information detection methods" refer to algorithms or systems that analyze the veracity of received posts and assess their credibility.

[0273] "Terminal" refers to a computer device used by a user, such as a smartphone, tablet, or PC.

[0274] "Emotion classification means" refers to an algorithm or system that analyzes a user's emotional state from the content of their post and classifies it into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0275] The "integration means" refers to a function for integrating the evaluation results of the false information detection means and the results of the emotion classification means into a single overall evaluation.

[0276] "Evaluation results" is a general term for the analysis results obtained by the false information detection means and emotion classification means, and refers to information including credibility assessments (falsehood level and confidence) and emotion categories.

[0277] "User interface" refers to the screen or operating system that allows the user and the system to exchange information on a terminal.

[0278] The term "system" refers to the collection of all means constituting the entire present invention, and has an integrated function of receiving, analyzing, evaluating, and displaying the results of posted content.

[0279] The present invention relates to a false information detection system for evaluating posted content, and in particular, a specific embodiment will be described in which an emotion classification engine that recognizes user emotions is combined.

[0280] System Overview

[0281] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following components:

[0282] Hardware Configuration

[0283] Server: A computing resource equipped with a display device, a communication module, and a storage device. For example, it is located on a cloud service platform.

[0284] Device: The device used by the user, such as a smartphone, tablet, or computer.

[0285] Software Configuration

[0286] Disinformation detection algorithms: Models using deep learning libraries such as TensorFlow and PyTorch, used to assess the veracity of posts.

[0287] Sentiment classification engine: Uses natural language processing technology such as IBM Watson Natural Language Understanding.

[0288] User interface: Display the evaluation results using front-end technologies such as React Native.

[0289] System processing overview

[0290] An example of the processing of this system is shown below.

[0291] Receiving posted content

[0292] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0293] Analysis and evaluation of posted content

[0294] The server inputs the received post content into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the veracity of the post content. The analysis results are output as a falsehood level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[0295] The server then uses an emotion classification engine to analyze the user's emotional state from their posts, categorizing the emotional state into categories such as "joy," "anger," "sadness," and "surprise."

[0296] Submitting and viewing evaluation results

[0297] The server converts the false information assessment results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it visually in the user interface. For example, "Falsehood level: 4, Confidence: 0.85, Sentiment: Anger" may be displayed next to the post.

[0298] Specific examples

[0299] The following is a concrete example of how the system actually works. For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a false information detection algorithm. As a result of the analysis, the post is determined to have a "falsehood level of 4, confidence level of 0.85." The emotion classification engine also returns the emotional state of "anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "falsehood level of 4, confidence level of 0.85, emotion: anger," and can take action as necessary.

[0300] Example of input prompt for generative AI model

[0301] Please analyze the following posts. We use an algorithm to assess whether they are false and the user's emotional state. As a result, we will output a falsehood level (1-5) and a confidence level (0-1), and tell us your emotional state.

[0302] Example prompts

[0303] A serious incident has occurred

[0304] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0305] Step 1:

[0306] A user creates a post through a social networking application and sends it from the device. Specifically, the user enters the text "A serious incident has occurred" into the social networking application and presses the send button. The input data is sent in text format.

[0307] Step 2:

[0308] The device receives the user's posted content and sends it to the server as an HTTP request. The data sent is in the form of an HTTP request containing text. The content entered by the user is passed to the server as is.

[0309] Step 3:

[0310] The server receives an HTTP request from the device and extracts the post content. The input data is the HTTP request, and the output data is the extracted text ("A serious incident has occurred"). The server passes this extracted text data to the next processing step.

[0311] Step 4:

[0312] The server inputs the extracted text into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the credibility of the text. The input data is the text of the post, and the output data is an evaluation result of the falsehood level (1-5) and confidence level (0-1). For example, for a post saying "A serious incident has occurred," the server returns a rating of "Falsehood level: 4, Confidence level: 0.85."

[0313] Step 5:

[0314] The server inputs the same text into an emotion classification engine, which uses natural language processing techniques to analyze the emotional state of the text. The input data is the text, and the output data is emotion categories such as "joy," "anger," "sadness," and "surprise." For example, for the text "A serious incident has occurred," the server returns an evaluation of "Emotion: Anger."

[0315] Step 6:

[0316] The server integrates the false information evaluation results and the sentiment analysis results. The input data are the falsehood level, confidence level, and sentiment category, and the output data is the integrated result (e.g., "Falsehood level: 4, confidence level: 0.85, sentiment: anger"). The integrated result is converted into JSON format.

[0317] Step 7:

[0318] The server sends the integrated evaluation results to the user's device. The input data is the integrated results in JSON format, and the output data is an HTTP response to the device. For example, the data sent to the device is "falsehood level: 4, confidence level: 0.85, emotion: anger."

[0319] Step 8:

[0320] The device receives the evaluation results sent from the server and displays them on the user interface. The input data is the evaluation results in JSON format, and the output data is the visually displayed evaluation results. Specifically, "Falsehood level: 4, Confidence: 0.85, Emotion: Anger" is displayed next to the user's post.

[0321] (Application example 2)

[0322] 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."

[0323] In recent years, the spread of fake news has become a serious problem in content distribution services. Furthermore, it is not uncommon for users to spread inaccurate information due to their emotional reactions. In this environment, there is a need to provide reliable information and enable users to receive prompt feedback on their posts. Conventional technologies lack a means to simultaneously analyze the user's emotional state in addition to assessing the credibility of the content of posts. As a result, there are problems with delays in assessing the risk of fake news and the inability to take appropriate action that takes the user's emotional state into account.

[0324] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes fake news detection algorithm means for evaluating the posted content, means for receiving the posted content from the terminal, means for evaluating the posted content using the algorithm means, means for transmitting the evaluation result to the terminal, means for displaying the evaluation result on a user interface, emotion engine means for recognizing emotions from the posted content, and means for integrating the evaluation result and the emotion recognition result. This makes it possible to evaluate the risk of fake news in real time and provide rapid feedback that takes into account the user's emotional state.

[0325] "Posted content" refers to information generated by a user and sent to the system via a terminal.

[0326] A "fake news detection algorithm" is a computational method that analyzes input text or image data to determine whether it is false information and evaluates its credibility.

[0327] A "terminal" refers to a communication device that a user uses to input and receive posted content.

[0328] "Evaluation results" refers to the comprehensive data of the analysis results obtained by the fake news detection algorithm and emotion engine.

[0329] The "user interface" refers to a display screen or display portion that visually displays the evaluation results and allows the user to confirm the contents.

[0330] An "emotion engine" is a calculation means for analyzing a user's emotional state from the content of their posts and classifying them into emotion categories such as joy, anger, sadness, and surprise.

[0331] "Integrating" means combining the evaluation results of the fake news detection algorithm and the analysis results of the emotion engine into a single evaluation result.

[0332] This invention relates to a system that simultaneously detects fake news and analyzes user sentiment, and in particular, a specific embodiment in a content distribution service will be described.

[0333] System Overview

[0334] The system mainly consists of a server and a terminal. The server has multiple functions and operates as follows:

[0335] 1. How you will receive your submission:

[0336] The server receives posts from users' devices, which can include a variety of formats, such as text and images.

[0337] 2. Fake news detection algorithmic methods:

[0338] The server then inputs the received content into a fake news detection algorithm to analyze its authenticity. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0339] 3. Emotion engine means:

[0340] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[0341] 4. Means of generating evaluation results:

[0342] The server combines the fake news evaluation results with the emotion engine analysis results to generate a comprehensive evaluation result, such as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0343] 5. Method of sending evaluation results:

[0344] The server transmits the generated overall evaluation result to the user terminal.

[0345] 6. User interface display:

[0346] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[0347] Overview of the technical process

[0348] The server first receives the content of the post and inputs it into the fake news detection algorithm and emotion engine, which utilize deep learning and natural language processing technologies and work as follows:

[0349] Fake News Detection:

[0350] The text input is analyzed using a pre-trained model (e.g., BERT), which then numerically evaluates the likelihood that the post is fake news and outputs a fake level and confidence level.

[0351] Emotion analysis:

[0352] To analyze the emotions from user posts, we use an emotion classification model (e.g., emotion analysis pipeline), which classifies the emotions reflected in the posts and gives results such as "anger."

[0353] Integration and Display:

[0354] The obtained fake news evaluation results and sentiment analysis results are integrated by the server and sent to the user's device in JSON format, where the device displays the received results on a user interface and provides feedback to the user.

[0355] Specific examples

[0356] For example, suppose a user posts, "A serious incident has occurred. It will have serious repercussions!" The content of this post is received by the server and analyzed by the fake news detection algorithm. The result is "Fake Level: 4, Confidence: 0.85," and the emotion engine then determines the emotion as "anger." These evaluation results are combined and sent to the user's device. The user's device displays the message as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0357] Prompt Sentence Examples

[0358] "Create an application that analyzes content posted by users and evaluates the likelihood of it being fake news and the sentiment behind it. For example, if a user posts "A serious incident has occurred," generate a fake news evaluation result of [{"label": "LABEL_1", "score": 0.95}] and a sentiment evaluation result of "POSITIVE." Specifically, the model used should be a pre-trained model from the BERT series, and the evaluation results should be integrated and output in JSON format."

[0359] As a result, the present invention realizes a highly reliable information distribution environment that prevents the spread of fake news and at the same time provides feedback that takes into account the user's emotional state.

[0360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0361] Step 1:

[0362] The user inputs content (text, images, videos, etc.) and generates a post. The post is then sent from the device to the server. The input is the user's post, and the output is the receipt of the post.

[0363] Step 2:

[0364] The server receives the post and inputs it into a fake news detection algorithm. This algorithm analyzes the veracity of the post. The input is the received post, and the output is an evaluation of the veracity of the fake news. Specifically, it performs text analysis using a deep learning model (e.g., BERT).

[0365] Step 3:

[0366] The server obtains the evaluation results of the fake news detection algorithm and then uses an emotion engine to analyze emotions from the post content. In this process, the post content is input into an emotion classification model and classified into emotion categories such as "joy," "anger," "sadness," and "surprise." The input is the post content, and the output is the emotion analysis result. Specific operation utilizes an emotion analysis pipeline.

[0367] Step 4:

[0368] The server integrates the fake news detection results and sentiment analysis results to generate an overall evaluation result. The generated evaluation result is formed as a fake level, confidence level, and emotional state. The inputs are the fake news evaluation results and sentiment analysis results, and the output is an integrated overall evaluation result. Specifically, the evaluation results are converted into JSON format.

[0369] Step 5:

[0370] The server generates an overall evaluation result and sends it to the terminal. In this step, the integrated evaluation result received by the user's terminal is sent as JSON data for processing. The input is the overall evaluation result, and the output is the evaluation result sent to the terminal. The specific operation involves sending data over the network.

[0371] Step 6:

[0372] The terminal displays the overall evaluation results it receives on the user interface. The displayed results allow users to check the authenticity of the posted content and their own emotional state. The input is the overall evaluation results obtained from the server, and the output is a visual display on the user interface. The specific operation is to display the evaluation results on the graphical user interface.

[0373] In this way, the system can efficiently detect fake news and analyze sentiment in posted content, providing intuitive feedback to users.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] [Second embodiment]

[0378] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] 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."

[0390] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment for preventing the spread of fake news will be described.

[0391] System Overview

[0392] This system has the function of analyzing the content posted by users and evaluating its credibility. The system mainly consists of the following functional blocks.

[0393] 1. Means of receiving posted content (server)

[0394] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[0395] 2. Fake News Detection Algorithm (Server)

[0396] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0397] 3. Evaluation result generation means (server)

[0398] The server takes the evaluation results generated by the algorithm and outputs them as a fake level (1 to 5) and a confidence level (a number between 0 and 1).

[0399] 4. Evaluation result transmission method (server)

[0400] The server then sends the generated evaluation results to the user's device, allowing the user to check in real time how trustworthy the content of their posts are.

[0401] 5. Means of display in the user interface (terminal)

[0402] The evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level and confidence level are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information.

[0403] System processing overview

[0404] An example of the processing of this system is shown below.

[0405] Receiving posted content

[0406] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0407] Analysis and evaluation of posted content

[0408] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (1-5) and a confidence level (0-1).

[0409] Submitting and viewing evaluation results

[0410] The server converts the analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. Specifically, it displays "Fake Level: 4, Confidence: 0.85" next to the post content.

[0411] Specific examples

[0412] Below is a concrete example of the system in action.

[0413] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to be "Fake Level: 4, Confidence: 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[0414] In this way, the system of the present invention prevents the spread of fake news and provides an environment in which users can easily determine the credibility of information.

[0415] The processing flow will be explained below.

[0416] Step 1: Enter post content (user)

[0417] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[0418] Step 2: Send your post (device)

[0419] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[0420] Step 3: Receiving the posted content (server)

[0421] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[0422] Step 4: Analyzing the Post Content (Server)

[0423] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[0424] Step 5: Generating evaluation results (server)

[0425] The server obtains the analysis result of the algorithm. The analysis result includes a fake level (1-5) and a confidence level (0-1). For example, the result generated is "Fake level: 4, confidence level: 0.85".

[0426] Step 6: Formatting the evaluation results (server)

[0427] The server converts the evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[0428] Step 7: Sending evaluation results (server)

[0429] The server then sends the formatted evaluation results to the terminal, again using an HTTP response.

[0430] Step 8: Receiving the evaluation results (terminal)

[0431] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[0432] Step 9: View the evaluation results (on your device)

[0433] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85" next to the entered post content.

[0434] Step 10: Check the evaluation results (user)

[0435] Users can check the fake level and confidence level displayed on their device and use this information to determine the authenticity of the post.

[0436] Step 11: Additional User Actions

[0437] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[0438] Example 1

[0439] 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."

[0440] In recent years, the reliability of information on the Internet has become increasingly important, and the spread of fake news, especially on social media, has become a serious social problem. This fake news not only causes misunderstanding and anxiety, but can also have a negative impact on actual behavior. Therefore, there is a need to quickly evaluate the reliability of content posted by users and prevent the spread of fake news before it happens.

[0441] 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.

[0442] In this invention, the server includes an information evaluation algorithm for evaluating posted content, a means for receiving the posted content from a user device, a means for evaluating the posted content using the algorithm, a means for transmitting the evaluation result to the user device, and a means for displaying the evaluation result on a user interface. This allows users to easily and quickly confirm the reliability of posted content, preventing the spread of fake news and promoting accurate information sharing.

[0443] "Posted content" is a general term for information posted by users through social media or other online platforms, including text and image data.

[0444] "Information evaluation algorithm means" refers to a technical component that executes an algorithm that analyzes the reliability and accuracy of received posts and assesses the likelihood that the content in question is fake news.

[0445] "Devices used" refers to devices that users use to connect to the Internet and send and receive information, and is a general term for smartphones, tablets, PCs, etc.

[0446] The "user interface" refers to components such as a display screen and input devices that users use to operate system functions and visually confirm evaluation results.

[0447] The "trust level" is a number that indicates the evaluation result of whether the content of a post is accurate, and is usually expressed on a scale of 1 to 5.

[0448] "Confidence" is a number that indicates the degree of trust in the reliability assessment result produced by the algorithm, and is expressed in a range from 0 to 1.

[0449] The present invention relates to a system for assessing the reliability of information posted by users, with the aim of preventing the spread of fake news, particularly on social media.

[0450] System Overview

[0451] The system includes an information evaluation algorithm means, a means for receiving posted content from a user device, a means for performing an evaluation of the posted content using the algorithm means, a means for transmitting the evaluation results to the user device, and a means for displaying the evaluation results on a user interface.

[0452] Hardware and Software

[0453] An embodiment of the system uses the following hardware and software:

[0454] 1. Server:

[0455] It provides a high-performance computing environment and is responsible for receiving and analyzing content posted by users.

[0456] The software running on the server includes a web framework using the Flask library.

[0457] 2. Algorithmic means:

[0458] It uses deep learning models and natural language processing techniques to assess the trustworthiness of posts.

[0459] Specifically, it uses a pre-trained model using the Transformers library.

[0460] 3. Equipment used:

[0461] A device used by users to send, receive, and display information, including smartphones, tablets, and PCs.

[0462] Specific details of data processing

[0463] 1. Receiving:

[0464] The server receives posts from users, which may be in various formats such as text or image data.

[0465] 2. Analysis:

[0466] The server then feeds the received posts into an algorithmic process to assess their trustworthiness using deep learning models and natural language processing techniques.

[0467] 3. Generating and sending evaluation results:

[0468] The server obtains the analysis results and generates a confidence level and certainty factor, which are then sent to the user device in JSON format.

[0469] 4.Display:

[0470] The user's terminal receives the evaluation results sent from the server and displays them on the user interface.

[0471] Specific examples

[0472] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "reliability level of 4, certainty factor of 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[0473] Prompt Sentence Examples

[0474] Here are some examples of prompts for generative AI models:

[0475] Please explain the detailed programming process of the fake news detection system. Please explain it in the following steps: 1. Receiving the post content 2. Running the fake news detection algorithm 3. Generating the evaluation results 4. Sending the evaluation results 5. Displaying the evaluation results. Please provide specific operations and techniques for each step.

[0476] This prompt helps the generative AI model provide a detailed description of the system described above.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1: Receiving submissions

[0479] Specific description:

[0480] The server receives the content posted by the user from the device used by the user. Specifically, the text and images posted by the user on the social media application are sent to the server.

[0481] Input and Output:

[0482] Input: The post typed by the user (e.g., "A serious incident has occurred").

[0483] Output: The post received by the server.

[0484] Specific behavior:

[0485] The server receives the submission via an HTTP POST request, for example, using Flask's request.get_json() method to retrieve the data.

[0486] Step 2: Analyzing the Post Content

[0487] Specific description:

[0488] The server feeds the received posts into a fake news detection algorithm, which uses pre-trained deep learning models and natural language processing techniques to assess their credibility.

[0489] Input and Output:

[0490] Input: The post content received by the server.

[0491] Output: The result of the fake news detection algorithm (e.g., "Fake Level: 4, Confidence: 0.85").

[0492] Specific behavior:

[0493] The server uses the Transformers library to pass the post to a pre-trained model, which outputs a confidence score and returns it to the server as the analysis result.

[0494] Step 3: Generate evaluation results

[0495] Specific description:

[0496] The server generates a confidence level (1-5) and a confidence level (0-1) based on the results of the algorithm's analysis, which are then formatted for easy display in a user interface.

[0497] Input and Output:

[0498] Input: Analysis results of the fake news detection algorithm.

[0499] Output: Evaluation results (in JSON format) including confidence level and certainty.

[0500] Specific behavior:

[0501] The server maps the score based on the analysis results and generates the evaluation result in JSON format. For example, it maps the fake level and confidence level according to the score value.

[0502] Step 4: Submit your evaluation results

[0503] Specific description:

[0504] The server then sends the generated evaluation results to the device, allowing users to check the reliability of the posted content in real time.

[0505] Input and Output:

[0506] Input: Evaluation results (JSON data including confidence level and certainty).

[0507] Output: Evaluation results sent to the user device.

[0508] Specific behavior:

[0509] The server sends the evaluation result back to the device as an HTTP response, for example, by sending JSON data using Flask's jsonify method.

[0510] Step 5: View the evaluation results

[0511] Specific description:

[0512] The user's device displays the evaluation results received from the server on a user interface, allowing the user to intuitively understand how trustworthy the posted content is.

[0513] Input and Output:

[0514] Input: The evaluation result (confidence level and certainty) received from the server.

[0515] Output: The evaluation results displayed on the user interface.

[0516] Specific behavior:

[0517] The user's device uses JavaScript to embed the evaluation results in HTML elements and display them visually. For example, the document.getElementById().innerHTML method is used to update the displayed content.

[0518] (Application example 1)

[0519] 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."

[0520] In recent years, the increase in fake news on the Internet has become a serious problem, and users are losing trust in news articles in particular. The spread of fake news can encourage decision-making based on erroneous information and have a negative impact on society. Therefore, there is a need for a system that allows users to easily determine the reliability of news articles and prevents the spread of fake news.

[0521] 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.

[0522] In this invention, the server includes a fake news detection algorithm means for evaluating posted content, a means for receiving the posted content from a terminal, a means for evaluating the posted content using the algorithm means, a means for transmitting the evaluation result to the terminal, a means for displaying the evaluation result on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability evaluation, and a means for displaying a warning for articles that are likely to be fake news. This allows users to intuitively judge the reliability of news articles and makes it possible to prevent the spread of fake news.

[0523] "Fake news detection algorithmic means for assessing the content of posts" refers to means that include an algorithm that analyses the content of text, images, etc. posted by users and determines their reliability.

[0524] The "means for receiving posted content from a terminal" refers to a means including an interface and communication means for receiving posted content sent from a user terminal.

[0525] "Means for evaluating posted content using algorithmic means" refers to means that include the function of applying a fake news detection algorithm to received posted content and performing that evaluation.

[0526] The "means for transmitting the evaluation results to the terminal" refers to a means including a communication means for transmitting the evaluation results generated by the algorithm to the user's terminal.

[0527] The "means for displaying the evaluation results on a user interface" refers to a means including an interface and a function for visually displaying the evaluation results sent to the terminal.

[0528] "Means for analyzing the content of news articles in real time and displaying a credibility evaluation" refers to means that includes analysis and display functions for analyzing the content of news articles viewed by users in real time and displaying the results of a credibility evaluation.

[0529] "Means for displaying a warning to articles that are likely to be fake news" refers to means that include a function for displaying a warning to users about articles that are determined to be likely to be fake news as a result of a reliability assessment.

[0530] The present invention provides a system for assessing the reliability of news articles viewed by users in real time and preventing the spread of fake news. The system includes a fake news detection algorithm for assessing the content of posts, a means for receiving the posted content from a terminal, a means for assessing the posted content using the algorithm, a means for transmitting the assessment results to the terminal, a means for displaying the assessment results on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability assessment, and a means for displaying a warning for articles that are likely to be fake news.

[0531] Program processing overview

[0532] The server uses a fake news detection algorithm to analyze news articles posted or viewed by users in real time. The algorithm uses deep learning and natural language processing techniques to evaluate the authenticity of the posted content. The evaluation results are generated as a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[0533] The server sends the evaluation results to the device, which then visually displays them on the user interface. When users view a news article, they can intuitively understand whether the article is fake news or not. Furthermore, articles that are likely to be fake news are displayed with a warning.

[0534] Specific examples

[0535] For example, a user uses a news aggregation application to view a news article titled "A major incident has occurred." The content of this news article is sent to a server and analyzed by a fake news detection algorithm. If the analysis results in the news article being rated "Fake Level: 4, Confidence: 0.85," the server sends this result to the user's device. A warning message stating "This news article is likely to be fake news" is displayed next to the article on the user's device, allowing the user to confirm the reliability of the news article.

[0536] An example of a prompt to be input to the generative AI model is as follows:

[0537] "What program uses a fake news detection algorithm to assess the veracity of today's news posts?"

[0538] "Please explain how a news aggregation app can display fake news warnings to users."

[0539] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0540] Step 1:

[0541] A user opens a news aggregation application, selects a news article, and starts viewing it. When the user starts viewing, the device extracts the content (text data) of the news article and sends it to the server.

[0542] Input: News article content (text data)

[0543] Output: Data sent to the server

[0544] Specific behavior: A user operates a news app and clicks to open an article. The app extracts the text data and automatically sends it to the server.

[0545] Step 2:

[0546] The server then inputs the received text data of the news articles into a fake news detection algorithm, which uses natural language processing and deep learning techniques to analyze the text data and evaluate its reliability.

[0547] Input: Text data of news articles sent from the user's device

[0548] Output: Evaluation result of fake news detection (fake level and confidence level)

[0549] How it works: The server receives news text data and inputs it into the fake news detection algorithm, which then analyzes the data and generates a rating.

[0550] Step 3:

[0551] The server sends the generated evaluation result to the terminal. This evaluation result includes a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[0552] Input: Fake news detection evaluation results

[0553] Output: Evaluation result data sent to the user's device

[0554] Specific operation: The server converts the evaluation results into JSON format and sends them to the user's device.

[0555] Step 4:

[0556] The user's device visually displays the received evaluation results in a user interface, displaying a fake level and confidence level next to the news article the user is viewing, and displaying a fake news warning if necessary.

[0557] Input: Evaluation result sent from the server (fake level and confidence level)

[0558] Output: Trust rating and warnings displayed in the user interface

[0559] Specific operation: The user's device analyzes the evaluation result data received and displays a message next to the news article, such as "Fake level: 4, confidence level: 0.85." If a warning is necessary, the message will read, "This news article is likely to be fake news."

[0560] Step 5:

[0561] Users can review the credibility ratings and warnings displayed and decide whether to trust the news article, and if necessary, decide not to share it or conduct additional fact-checking.

[0562] Input: Trust rating and warnings displayed in the user interface

[0563] Output: User decision and action (e.g., not sharing the article, further fact-checking, etc.)

[0564] What happens: Users can view a news article's credibility rating and warnings and make decisions based on that information, such as whether to read the article or refrain from sharing it.

[0565] 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.

[0566] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment will be described that combines an emotion engine that recognizes user emotions.

[0567] System Overview

[0568] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following functional blocks.

[0569] 1. Means of receiving posted content (server)

[0570] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[0571] 2. Fake News Detection Algorithm (Server)

[0572] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0573] 3. Emotion engine means (server)

[0574] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[0575] 4. Evaluation result generation means (server)

[0576] The server combines the fake news evaluation results with the emotion engine analysis results and outputs the overall evaluation result. For example, it generates an evaluation result in the form of "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0577] 5. Evaluation result transmission method (server)

[0578] The server then sends the generated overall evaluation results to the user's device, allowing the user to check the reliability of their own posts as well as their emotional state in real time.

[0579] 6. Means of display in the user interface (terminal)

[0580] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[0581] System processing overview

[0582] An example of the processing of this system is shown below.

[0583] Receiving posted content

[0584] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0585] Analysis and evaluation of posted content

[0586] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[0587] The server then uses an emotion engine to analyze the user's emotional state from their posts, which is then classified into categories such as "joy," "anger," "sadness," and "surprise."

[0588] Submitting and viewing evaluation results

[0589] The server converts the fake news evaluation results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. For example, "Fake level: 4, confidence level: 0.85, sentiment: anger" may be displayed next to the post.

[0590] Specific examples

[0591] Below is a concrete example of the system in action.

[0592] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "Fake Level: 4, Confidence: 0.85." The emotion engine also returns the emotional state of "Anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "Fake Level: 4, Confidence: 0.85, Emotion: Anger," and can take action as necessary.

[0593] In this way, the system of the present invention prevents the spread of fake news and also provides an environment for comprehensively evaluating the credibility of posted content by understanding the user's emotional state.

[0594] The processing flow will be explained below.

[0595] Step 1: Enter post content (user)

[0596] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[0597] Step 2: Send your post (device)

[0598] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[0599] Step 3: Receiving the posted content (server)

[0600] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[0601] Step 4: Analyzing the Post Content (Server)

[0602] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[0603] Step 5: Generate fake levels and confidence (server)

[0604] The server receives the analysis results from the algorithm and outputs them as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1). For example, the result might be "Fake level: 4, confidence level: 0.85."

[0605] Step 6: Performing sentiment analysis (server)

[0606] The server inputs the posted content into an emotion engine and analyzes the user's emotional state, which is classified into categories such as "joy," "anger," "sadness," and "surprise."

[0607] Step 7: Integration of evaluation results (server)

[0608] The server combines the fake news evaluation results with the emotion engine analysis results and compiles them into an overall evaluation result. For example, the results may be summarized as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0609] Step 8: Formatting the evaluation results (server)

[0610] The server converts the integrated evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[0611] Step 9: Sending evaluation results (server)

[0612] The server then sends the formatted evaluation results to the user's device, again using an HTTP response.

[0613] Step 10: Receiving evaluation results (terminal)

[0614] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[0615] Step 11: Viewing the evaluation results (terminal)

[0616] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85, Emotion: Anger" next to the entered post content.

[0617] Step 12: Check the evaluation results (user)

[0618] Users can view the fake level, confidence level, and emotional state displayed on their device, and use this information to determine the authenticity of the post.

[0619] Step 13: Additional User Actions

[0620] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[0621] Example 2

[0622] 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."

[0623] Conventional fake news detection systems are limited to assessing the credibility of posted content and do not take into account the user's emotional state. As a result, when a user's emotions affect the credibility of the posted content, the evaluation of the information may be incomplete. Furthermore, simply assessing whether or not something is fake news does not provide users with enough information to understand the content and take appropriate action.

[0624] 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.

[0625] In this invention, the server includes a false information detection means for evaluating the posted content, a means for analyzing the posted content and classifying the user's emotions, and a means for integrating the evaluation result of the false information detection means and the result of the emotion classification means, thereby enabling a comprehensive evaluation that takes into account not only the credibility of the posted content but also the user's emotional state.

[0626] "Posted content" refers to information such as text, images, and videos that users post on social media or other communication platforms.

[0627] "False information detection methods" refer to algorithms or systems that analyze the veracity of received posts and assess their credibility.

[0628] "Terminal" refers to a computer device used by a user, such as a smartphone, tablet, or PC.

[0629] "Emotion classification means" refers to an algorithm or system that analyzes a user's emotional state from the content of their post and classifies it into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0630] The "integration means" refers to a function for integrating the evaluation results of the false information detection means and the results of the emotion classification means into a single overall evaluation.

[0631] "Evaluation results" is a general term for the analysis results obtained by the false information detection means and emotion classification means, and refers to information including credibility assessments (falsehood level and confidence) and emotion categories.

[0632] "User interface" refers to the screen or operating system that allows the user and the system to exchange information on a terminal.

[0633] The term "system" refers to the collection of all means constituting the entire present invention, and has an integrated function of receiving, analyzing, evaluating, and displaying the results of posted content.

[0634] The present invention relates to a false information detection system for evaluating posted content, and in particular, a specific embodiment will be described in which an emotion classification engine that recognizes user emotions is combined.

[0635] System Overview

[0636] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following components:

[0637] Hardware Configuration

[0638] Server: A computing resource equipped with a display device, a communication module, and a storage device. For example, it is located on a cloud service platform.

[0639] Device: The device used by the user, such as a smartphone, tablet, or computer.

[0640] Software Configuration

[0641] Disinformation detection algorithms: Models using deep learning libraries such as TensorFlow and PyTorch, used to assess the veracity of posts.

[0642] Sentiment classification engine: Uses natural language processing technology such as IBM Watson Natural Language Understanding.

[0643] User interface: Display the evaluation results using front-end technologies such as React Native.

[0644] System processing overview

[0645] An example of the processing of this system is shown below.

[0646] Receiving posted content

[0647] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0648] Analysis and evaluation of posted content

[0649] The server inputs the received post content into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the veracity of the post content. The analysis results are output as a falsehood level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[0650] The server then uses an emotion classification engine to analyze the user's emotional state from their posts, categorizing the emotional state into categories such as "joy," "anger," "sadness," and "surprise."

[0651] Submitting and viewing evaluation results

[0652] The server converts the false information assessment results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it visually in the user interface. For example, "Falsehood level: 4, Confidence: 0.85, Sentiment: Anger" may be displayed next to the post.

[0653] Specific examples

[0654] The following is a concrete example of how the system actually works. For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a false information detection algorithm. As a result of the analysis, the post is determined to have a "falsehood level of 4, confidence level of 0.85." The emotion classification engine also returns the emotional state of "anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "falsehood level of 4, confidence level of 0.85, emotion: anger," and can take action as necessary.

[0655] Example of input prompt for generative AI model

[0656] Please analyze the following posts. We use an algorithm to assess whether they are false and the user's emotional state. As a result, we will output a falsehood level (1-5) and a confidence level (0-1), and tell us your emotional state.

[0657] Example prompts

[0658] A serious incident has occurred

[0659] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0660] Step 1:

[0661] A user creates a post through a social networking application and sends it from the device. Specifically, the user enters the text "A serious incident has occurred" into the social networking application and presses the send button. The input data is sent in text format.

[0662] Step 2:

[0663] The device receives the user's posted content and sends it to the server as an HTTP request. The data sent is in the form of an HTTP request containing text. The content entered by the user is passed to the server as is.

[0664] Step 3:

[0665] The server receives an HTTP request from the device and extracts the post content. The input data is the HTTP request, and the output data is the extracted text ("A serious incident has occurred"). The server passes this extracted text data to the next processing step.

[0666] Step 4:

[0667] The server inputs the extracted text into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the credibility of the text. The input data is the text of the post, and the output data is an evaluation result of the falsehood level (1-5) and confidence level (0-1). For example, for a post saying "A serious incident has occurred," the server returns a rating of "Falsehood level: 4, Confidence level: 0.85."

[0668] Step 5:

[0669] The server inputs the same text into an emotion classification engine, which uses natural language processing techniques to analyze the emotional state of the text. The input data is the text, and the output data is emotion categories such as "joy," "anger," "sadness," and "surprise." For example, for the text "A serious incident has occurred," the server returns an evaluation of "Emotion: Anger."

[0670] Step 6:

[0671] The server integrates the false information evaluation results and the sentiment analysis results. The input data are the falsehood level, confidence level, and sentiment category, and the output data is the integrated result (e.g., "Falsehood level: 4, confidence level: 0.85, sentiment: anger"). The integrated result is converted into JSON format.

[0672] Step 7:

[0673] The server sends the integrated evaluation results to the user's device. The input data is the integrated results in JSON format, and the output data is an HTTP response to the device. For example, the data sent to the device is "falsehood level: 4, confidence level: 0.85, emotion: anger."

[0674] Step 8:

[0675] The device receives the evaluation results sent from the server and displays them on the user interface. The input data is the evaluation results in JSON format, and the output data is the visually displayed evaluation results. Specifically, "Falsehood level: 4, Confidence: 0.85, Emotion: Anger" is displayed next to the user's post.

[0676] (Application example 2)

[0677] 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."

[0678] In recent years, the spread of fake news has become a serious problem in content distribution services. Furthermore, it is not uncommon for users to spread inaccurate information due to their emotional reactions. In this environment, there is a need to provide reliable information and enable users to receive prompt feedback on their posts. Conventional technologies lack a means to simultaneously analyze the user's emotional state in addition to assessing the credibility of the content of posts. As a result, there are problems with delays in assessing the risk of fake news and the inability to take appropriate action that takes the user's emotional state into account.

[0679] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes fake news detection algorithm means for evaluating the posted content, means for receiving the posted content from the terminal, means for evaluating the posted content using the algorithm means, means for transmitting the evaluation result to the terminal, means for displaying the evaluation result on a user interface, emotion engine means for recognizing emotions from the posted content, and means for integrating the evaluation result and the emotion recognition result. This makes it possible to evaluate the risk of fake news in real time and provide rapid feedback that takes into account the user's emotional state.

[0680] "Posted content" refers to information generated by a user and sent to the system via a terminal.

[0681] A "fake news detection algorithm" is a computational method that analyzes input text or image data to determine whether it is false information and evaluates its credibility.

[0682] A "terminal" refers to a communication device that a user uses to input and receive posted content.

[0683] "Evaluation results" refers to the comprehensive data of the analysis results obtained by the fake news detection algorithm and emotion engine.

[0684] The "user interface" refers to a display screen or display portion that visually displays the evaluation results and allows the user to confirm the contents.

[0685] An "emotion engine" is a calculation means for analyzing a user's emotional state from the content of their posts and classifying them into emotion categories such as joy, anger, sadness, and surprise.

[0686] "Integrating" means combining the evaluation results of the fake news detection algorithm and the analysis results of the emotion engine into a single evaluation result.

[0687] This invention relates to a system that simultaneously detects fake news and analyzes user sentiment, and in particular, a specific embodiment in a content distribution service will be described.

[0688] System Overview

[0689] The system mainly consists of a server and a terminal. The server has multiple functions and operates as follows:

[0690] 1. How you will receive your submission:

[0691] The server receives posts from users' devices, which can include a variety of formats, such as text and images.

[0692] 2. Fake news detection algorithmic methods:

[0693] The server then inputs the received content into a fake news detection algorithm to analyze its authenticity. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0694] 3. Emotion engine means:

[0695] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[0696] 4. Means of generating evaluation results:

[0697] The server combines the fake news evaluation results with the emotion engine analysis results to generate a comprehensive evaluation result, such as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0698] 5. Method of sending evaluation results:

[0699] The server transmits the generated overall evaluation result to the user terminal.

[0700] 6. User interface display:

[0701] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[0702] Overview of the technical process

[0703] The server first receives the content of the post and inputs it into the fake news detection algorithm and emotion engine, which utilize deep learning and natural language processing technologies and work as follows:

[0704] Fake News Detection:

[0705] The text input is analyzed using a pre-trained model (e.g., BERT), which then numerically evaluates the likelihood that the post is fake news and outputs a fake level and confidence level.

[0706] Emotion analysis:

[0707] To analyze the emotions from user posts, we use an emotion classification model (e.g., emotion analysis pipeline), which classifies the emotions reflected in the posts and gives results such as "anger."

[0708] Integration and Display:

[0709] The obtained fake news evaluation results and sentiment analysis results are integrated by the server and sent to the user's device in JSON format, where the device displays the received results on a user interface and provides feedback to the user.

[0710] Specific examples

[0711] For example, suppose a user posts, "A serious incident has occurred. It will have serious repercussions!" The content of this post is received by the server and analyzed by the fake news detection algorithm. The result is "Fake Level: 4, Confidence: 0.85," and the emotion engine then determines the emotion as "anger." These evaluation results are combined and sent to the user's device. The user's device displays the message as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0712] Prompt Sentence Examples

[0713] "Create an application that analyzes content posted by users and evaluates the likelihood of it being fake news and the sentiment behind it. For example, if a user posts "A serious incident has occurred," generate a fake news evaluation result of [{"label": "LABEL_1", "score": 0.95}] and a sentiment evaluation result of "POSITIVE." Specifically, the model used should be a pre-trained model from the BERT series, and the evaluation results should be integrated and output in JSON format."

[0714] As a result, the present invention realizes a highly reliable information distribution environment that prevents the spread of fake news and at the same time provides feedback that takes into account the user's emotional state.

[0715] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0716] Step 1:

[0717] The user inputs content (text, images, videos, etc.) and generates a post. The post is then sent from the device to the server. The input is the user's post, and the output is the receipt of the post.

[0718] Step 2:

[0719] The server receives the post and inputs it into a fake news detection algorithm. This algorithm analyzes the veracity of the post. The input is the received post, and the output is an evaluation of the veracity of the fake news. Specifically, it performs text analysis using a deep learning model (e.g., BERT).

[0720] Step 3:

[0721] The server obtains the evaluation results of the fake news detection algorithm and then uses an emotion engine to analyze emotions from the post content. In this process, the post content is input into an emotion classification model and classified into emotion categories such as "joy," "anger," "sadness," and "surprise." The input is the post content, and the output is the emotion analysis result. Specific operation utilizes an emotion analysis pipeline.

[0722] Step 4:

[0723] The server integrates the fake news detection results and sentiment analysis results to generate an overall evaluation result. The generated evaluation result is formed as a fake level, confidence level, and emotional state. The inputs are the fake news evaluation results and sentiment analysis results, and the output is an integrated overall evaluation result. Specifically, the evaluation results are converted into JSON format.

[0724] Step 5:

[0725] The server generates an overall evaluation result and sends it to the terminal. In this step, the integrated evaluation result received by the user's terminal is sent as JSON data for processing. The input is the overall evaluation result, and the output is the evaluation result sent to the terminal. The specific operation involves sending data over the network.

[0726] Step 6:

[0727] The terminal displays the overall evaluation results it receives on the user interface. The displayed results allow users to check the authenticity of the posted content and their own emotional state. The input is the overall evaluation results obtained from the server, and the output is a visual display on the user interface. The specific operation is to display the evaluation results on the graphical user interface.

[0728] In this way, the system can efficiently detect fake news and analyze sentiment in posted content, providing intuitive feedback to users.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] [Third embodiment]

[0733] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0734] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0735] 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).

[0736] 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.

[0737] 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.

[0738] 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).

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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."

[0745] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment for preventing the spread of fake news will be described.

[0746] System Overview

[0747] This system has the function of analyzing the content posted by users and evaluating its credibility. The system mainly consists of the following functional blocks.

[0748] 1. Means of receiving posted content (server)

[0749] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[0750] 2. Fake News Detection Algorithm (Server)

[0751] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0752] 3. Evaluation result generation means (server)

[0753] The server takes the evaluation results generated by the algorithm and outputs them as a fake level (1 to 5) and a confidence level (a number between 0 and 1).

[0754] 4. Evaluation result transmission method (server)

[0755] The server then sends the generated evaluation results to the user's device, allowing the user to check in real time how trustworthy the content of their posts are.

[0756] 5. Means of display in the user interface (terminal)

[0757] The evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level and confidence level are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information.

[0758] System processing overview

[0759] An example of the processing of this system is shown below.

[0760] Receiving posted content

[0761] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0762] Analysis and evaluation of posted content

[0763] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (1-5) and a confidence level (0-1).

[0764] Submitting and viewing evaluation results

[0765] The server converts the analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. Specifically, it displays "Fake Level: 4, Confidence: 0.85" next to the post content.

[0766] Specific examples

[0767] Below is a concrete example of the system in action.

[0768] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to be "Fake Level: 4, Confidence: 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[0769] In this way, the system of the present invention prevents the spread of fake news and provides an environment in which users can easily determine the credibility of information.

[0770] The processing flow will be explained below.

[0771] Step 1: Enter post content (user)

[0772] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[0773] Step 2: Send your post (device)

[0774] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[0775] Step 3: Receiving the posted content (server)

[0776] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[0777] Step 4: Analyzing the Post Content (Server)

[0778] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[0779] Step 5: Generating evaluation results (server)

[0780] The server obtains the analysis result of the algorithm. The analysis result includes a fake level (1-5) and a confidence level (0-1). For example, the result generated is "Fake level: 4, confidence level: 0.85".

[0781] Step 6: Formatting the evaluation results (server)

[0782] The server converts the evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[0783] Step 7: Sending evaluation results (server)

[0784] The server then sends the formatted evaluation results to the terminal, again using an HTTP response.

[0785] Step 8: Receiving the evaluation results (terminal)

[0786] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[0787] Step 9: View the evaluation results (on your device)

[0788] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85" next to the entered post content.

[0789] Step 10: Check the evaluation results (user)

[0790] Users can check the fake level and confidence level displayed on their device and use this information to determine the authenticity of the post.

[0791] Step 11: Additional User Actions

[0792] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[0793] Example 1

[0794] 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."

[0795] In recent years, the reliability of information on the Internet has become increasingly important, and the spread of fake news, especially on social media, has become a serious social problem. This fake news not only causes misunderstanding and anxiety, but can also have a negative impact on actual behavior. Therefore, there is a need to quickly evaluate the reliability of content posted by users and prevent the spread of fake news before it happens.

[0796] 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.

[0797] In this invention, the server includes an information evaluation algorithm for evaluating posted content, a means for receiving the posted content from a user device, a means for evaluating the posted content using the algorithm, a means for transmitting the evaluation result to the user device, and a means for displaying the evaluation result on a user interface. This allows users to easily and quickly confirm the reliability of posted content, preventing the spread of fake news and promoting accurate information sharing.

[0798] "Posted content" is a general term for information posted by users through social media or other online platforms, including text and image data.

[0799] "Information evaluation algorithm means" refers to a technical component that executes an algorithm that analyzes the reliability and accuracy of received posts and assesses the likelihood that the content in question is fake news.

[0800] "Devices used" refers to devices that users use to connect to the Internet and send and receive information, and is a general term for smartphones, tablets, PCs, etc.

[0801] The "user interface" refers to components such as a display screen and input devices that users use to operate system functions and visually confirm evaluation results.

[0802] The "trust level" is a number that indicates the evaluation result of whether the content of a post is accurate, and is usually expressed on a scale of 1 to 5.

[0803] "Confidence" is a number that indicates the degree of trust in the reliability assessment result produced by the algorithm, and is expressed in a range from 0 to 1.

[0804] The present invention relates to a system for assessing the reliability of information posted by users, with the aim of preventing the spread of fake news, particularly on social media.

[0805] System Overview

[0806] The system includes an information evaluation algorithm means, a means for receiving posted content from a user device, a means for performing an evaluation of the posted content using the algorithm means, a means for transmitting the evaluation results to the user device, and a means for displaying the evaluation results on a user interface.

[0807] Hardware and Software

[0808] An embodiment of the system uses the following hardware and software:

[0809] 1. Server:

[0810] It provides a high-performance computing environment and is responsible for receiving and analyzing content posted by users.

[0811] The software running on the server includes a web framework using the Flask library.

[0812] 2. Algorithmic means:

[0813] It uses deep learning models and natural language processing techniques to assess the trustworthiness of posts.

[0814] Specifically, it uses a pre-trained model using the Transformers library.

[0815] 3. Equipment used:

[0816] A device used by users to send, receive, and display information, including smartphones, tablets, and PCs.

[0817] Specific details of data processing

[0818] 1. Receiving:

[0819] The server receives posts from users, which may be in various formats such as text or image data.

[0820] 2. Analysis:

[0821] The server then feeds the received posts into an algorithmic process to assess their trustworthiness using deep learning models and natural language processing techniques.

[0822] 3. Generating and sending evaluation results:

[0823] The server obtains the analysis results and generates a confidence level and certainty factor, which are then sent to the user device in JSON format.

[0824] 4.Display:

[0825] The user's terminal receives the evaluation results sent from the server and displays them on the user interface.

[0826] Specific examples

[0827] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "reliability level of 4, certainty factor of 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[0828] Prompt Sentence Examples

[0829] Here are some examples of prompts for generative AI models:

[0830] Please explain the detailed programming process of the fake news detection system. Please explain it in the following steps: 1. Receiving the post content 2. Running the fake news detection algorithm 3. Generating the evaluation results 4. Sending the evaluation results 5. Displaying the evaluation results. Please provide specific operations and techniques for each step.

[0831] This prompt helps the generative AI model provide a detailed description of the system described above.

[0832] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0833] Step 1: Receiving submissions

[0834] Specific description:

[0835] The server receives the content posted by the user from the device used by the user. Specifically, the text and images posted by the user on the social media application are sent to the server.

[0836] Input and Output:

[0837] Input: The post typed by the user (e.g., "A serious incident has occurred").

[0838] Output: The post received by the server.

[0839] Specific behavior:

[0840] The server receives the submission via an HTTP POST request, for example, using Flask's request.get_json() method to retrieve the data.

[0841] Step 2: Analyzing the Post Content

[0842] Specific description:

[0843] The server feeds the received posts into a fake news detection algorithm, which uses pre-trained deep learning models and natural language processing techniques to assess their credibility.

[0844] Input and Output:

[0845] Input: The post content received by the server.

[0846] Output: The result of the fake news detection algorithm (e.g., "Fake Level: 4, Confidence: 0.85").

[0847] Specific behavior:

[0848] The server uses the Transformers library to pass the post to a pre-trained model, which outputs a confidence score and returns it to the server as the analysis result.

[0849] Step 3: Generate evaluation results

[0850] Specific description:

[0851] The server generates a confidence level (1-5) and a confidence level (0-1) based on the results of the algorithm's analysis, which are then formatted for easy display in a user interface.

[0852] Input and Output:

[0853] Input: Analysis results of the fake news detection algorithm.

[0854] Output: Evaluation results (in JSON format) including confidence level and certainty.

[0855] Specific behavior:

[0856] The server maps the score based on the analysis results and generates the evaluation result in JSON format. For example, it maps the fake level and confidence level according to the score value.

[0857] Step 4: Submit your evaluation results

[0858] Specific description:

[0859] The server then sends the generated evaluation results to the device, allowing users to check the reliability of the posted content in real time.

[0860] Input and Output:

[0861] Input: Evaluation results (JSON data including confidence level and certainty).

[0862] Output: Evaluation results sent to the user device.

[0863] Specific behavior:

[0864] The server sends the evaluation result back to the device as an HTTP response, for example, by sending JSON data using Flask's jsonify method.

[0865] Step 5: View the evaluation results

[0866] Specific description:

[0867] The user's device displays the evaluation results received from the server on a user interface, allowing the user to intuitively understand how trustworthy the posted content is.

[0868] Input and Output:

[0869] Input: The evaluation result (confidence level and certainty) received from the server.

[0870] Output: The evaluation results displayed on the user interface.

[0871] Specific behavior:

[0872] The user's device uses JavaScript to embed the evaluation results in HTML elements and display them visually. For example, the document.getElementById().innerHTML method is used to update the displayed content.

[0873] (Application example 1)

[0874] 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."

[0875] In recent years, the increase in fake news on the Internet has become a serious problem, and users are losing trust in news articles in particular. The spread of fake news can encourage decision-making based on erroneous information and have a negative impact on society. Therefore, there is a need for a system that allows users to easily determine the reliability of news articles and prevents the spread of fake news.

[0876] 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.

[0877] In this invention, the server includes a fake news detection algorithm means for evaluating posted content, a means for receiving the posted content from a terminal, a means for evaluating the posted content using the algorithm means, a means for transmitting the evaluation result to the terminal, a means for displaying the evaluation result on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability evaluation, and a means for displaying a warning for articles that are likely to be fake news. This allows users to intuitively judge the reliability of news articles and makes it possible to prevent the spread of fake news.

[0878] "Fake news detection algorithmic means for assessing the content of posts" refers to means that include an algorithm that analyses the content of text, images, etc. posted by users and determines their reliability.

[0879] The "means for receiving posted content from a terminal" refers to a means including an interface and communication means for receiving posted content sent from a user terminal.

[0880] "Means for evaluating posted content using algorithmic means" refers to means that include the function of applying a fake news detection algorithm to received posted content and performing that evaluation.

[0881] The "means for transmitting the evaluation results to the terminal" refers to a means including a communication means for transmitting the evaluation results generated by the algorithm to the user's terminal.

[0882] The "means for displaying the evaluation results on a user interface" refers to a means including an interface and a function for visually displaying the evaluation results sent to the terminal.

[0883] "Means for analyzing the content of news articles in real time and displaying a credibility evaluation" refers to means that includes analysis and display functions for analyzing the content of news articles viewed by users in real time and displaying the results of a credibility evaluation.

[0884] "Means for displaying a warning to articles that are likely to be fake news" refers to means that include a function for displaying a warning to users about articles that are determined to be likely to be fake news as a result of a reliability assessment.

[0885] The present invention provides a system for assessing the reliability of news articles viewed by users in real time and preventing the spread of fake news. The system includes a fake news detection algorithm for assessing the content of posts, a means for receiving the posted content from a terminal, a means for assessing the posted content using the algorithm, a means for transmitting the assessment results to the terminal, a means for displaying the assessment results on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability assessment, and a means for displaying a warning for articles that are likely to be fake news.

[0886] Program processing overview

[0887] The server uses a fake news detection algorithm to analyze news articles posted or viewed by users in real time. The algorithm uses deep learning and natural language processing techniques to evaluate the authenticity of the posted content. The evaluation results are generated as a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[0888] The server sends the evaluation results to the device, which then visually displays them on the user interface. When users view a news article, they can intuitively understand whether the article is fake news or not. Furthermore, articles that are likely to be fake news are displayed with a warning.

[0889] Specific examples

[0890] For example, a user uses a news aggregation application to view a news article titled "A major incident has occurred." The content of this news article is sent to a server and analyzed by a fake news detection algorithm. If the analysis results in the news article being rated "Fake Level: 4, Confidence: 0.85," the server sends this result to the user's device. A warning message stating "This news article is likely to be fake news" is displayed next to the article on the user's device, allowing the user to confirm the reliability of the news article.

[0891] An example of a prompt to be input to the generative AI model is as follows:

[0892] "What program uses a fake news detection algorithm to assess the veracity of today's news posts?"

[0893] "Please explain how a news aggregation app can display fake news warnings to users."

[0894] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0895] Step 1:

[0896] A user opens a news aggregation application, selects a news article, and starts viewing it. When the user starts viewing, the device extracts the content (text data) of the news article and sends it to the server.

[0897] Input: News article content (text data)

[0898] Output: Data sent to the server

[0899] Specific behavior: A user operates a news app and clicks to open an article. The app extracts the text data and automatically sends it to the server.

[0900] Step 2:

[0901] The server then inputs the received text data of the news articles into a fake news detection algorithm, which uses natural language processing and deep learning techniques to analyze the text data and evaluate its reliability.

[0902] Input: Text data of news articles sent from the user's device

[0903] Output: Evaluation result of fake news detection (fake level and confidence level)

[0904] How it works: The server receives news text data and inputs it into the fake news detection algorithm, which then analyzes the data and generates a rating.

[0905] Step 3:

[0906] The server sends the generated evaluation result to the terminal. This evaluation result includes a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[0907] Input: Fake news detection evaluation results

[0908] Output: Evaluation result data sent to the user's device

[0909] Specific operation: The server converts the evaluation results into JSON format and sends them to the user's device.

[0910] Step 4:

[0911] The user's device visually displays the received evaluation results in a user interface, displaying a fake level and confidence level next to the news article the user is viewing, and displaying a fake news warning if necessary.

[0912] Input: Evaluation result sent from the server (fake level and confidence level)

[0913] Output: Trust rating and warnings displayed in the user interface

[0914] Specific operation: The user's device analyzes the evaluation result data received and displays a message next to the news article, such as "Fake level: 4, confidence level: 0.85." If a warning is necessary, the message will read, "This news article is likely to be fake news."

[0915] Step 5:

[0916] Users can review the credibility ratings and warnings displayed and decide whether to trust the news article, and if necessary, decide not to share it or conduct additional fact-checking.

[0917] Input: Trust rating and warnings displayed in the user interface

[0918] Output: User decision and action (e.g., not sharing the article, further fact-checking, etc.)

[0919] What happens: Users can view a news article's credibility rating and warnings and make decisions based on that information, such as whether to read the article or refrain from sharing it.

[0920] 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.

[0921] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment will be described that combines an emotion engine that recognizes user emotions.

[0922] System Overview

[0923] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following functional blocks.

[0924] 1. Means of receiving posted content (server)

[0925] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[0926] 2. Fake News Detection Algorithm (Server)

[0927] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[0928] 3. Emotion engine means (server)

[0929] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[0930] 4. Evaluation result generation means (server)

[0931] The server combines the fake news evaluation results with the emotion engine analysis results and outputs the overall evaluation result. For example, it generates an evaluation result in the form of "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0932] 5. Evaluation result transmission method (server)

[0933] The server then sends the generated overall evaluation results to the user's device, allowing the user to check the reliability of their own posts as well as their emotional state in real time.

[0934] 6. Means of display in the user interface (terminal)

[0935] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[0936] System processing overview

[0937] An example of the processing of this system is shown below.

[0938] Receiving posted content

[0939] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[0940] Analysis and evaluation of posted content

[0941] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[0942] The server then uses an emotion engine to analyze the user's emotional state from their posts, which is then classified into categories such as "joy," "anger," "sadness," and "surprise."

[0943] Submitting and viewing evaluation results

[0944] The server converts the fake news evaluation results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. For example, "Fake level: 4, confidence level: 0.85, sentiment: anger" may be displayed next to the post.

[0945] Specific examples

[0946] Below is a concrete example of the system in action.

[0947] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "Fake Level: 4, Confidence: 0.85." The emotion engine also returns the emotional state of "Anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "Fake Level: 4, Confidence: 0.85, Emotion: Anger," and can take action as necessary.

[0948] In this way, the system of the present invention prevents the spread of fake news and also provides an environment for comprehensively evaluating the credibility of posted content by understanding the user's emotional state.

[0949] The processing flow will be explained below.

[0950] Step 1: Enter post content (user)

[0951] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[0952] Step 2: Send your post (device)

[0953] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[0954] Step 3: Receiving the posted content (server)

[0955] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[0956] Step 4: Analyzing the Post Content (Server)

[0957] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[0958] Step 5: Generate fake levels and confidence (server)

[0959] The server receives the analysis results from the algorithm and outputs them as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1). For example, the result might be "Fake level: 4, confidence level: 0.85."

[0960] Step 6: Performing sentiment analysis (server)

[0961] The server inputs the posted content into an emotion engine and analyzes the user's emotional state, which is classified into categories such as "joy," "anger," "sadness," and "surprise."

[0962] Step 7: Integration of evaluation results (server)

[0963] The server combines the fake news evaluation results with the emotion engine analysis results and compiles them into an overall evaluation result. For example, the results may be summarized as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[0964] Step 8: Formatting the evaluation results (server)

[0965] The server converts the integrated evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[0966] Step 9: Sending evaluation results (server)

[0967] The server then sends the formatted evaluation results to the user's device, again using an HTTP response.

[0968] Step 10: Receiving evaluation results (terminal)

[0969] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[0970] Step 11: Viewing the evaluation results (terminal)

[0971] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85, Emotion: Anger" next to the entered post content.

[0972] Step 12: Check the evaluation results (user)

[0973] Users can view the fake level, confidence level, and emotional state displayed on their device, and use this information to determine the authenticity of the post.

[0974] Step 13: Additional User Actions

[0975] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[0976] Example 2

[0977] 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."

[0978] Conventional fake news detection systems are limited to assessing the credibility of posted content and do not take into account the user's emotional state. As a result, when a user's emotions affect the credibility of the posted content, the evaluation of the information may be incomplete. Furthermore, simply assessing whether or not something is fake news does not provide users with enough information to understand the content and take appropriate action.

[0979] 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.

[0980] In this invention, the server includes a false information detection means for evaluating the posted content, a means for analyzing the posted content and classifying the user's emotions, and a means for integrating the evaluation result of the false information detection means and the result of the emotion classification means, thereby enabling a comprehensive evaluation that takes into account not only the credibility of the posted content but also the user's emotional state.

[0981] "Posted content" refers to information such as text, images, and videos that users post on social media or other communication platforms.

[0982] "False information detection methods" refer to algorithms or systems that analyze the veracity of received posts and assess their credibility.

[0983] "Terminal" refers to a computer device used by a user, such as a smartphone, tablet, or PC.

[0984] "Emotion classification means" refers to an algorithm or system that analyzes a user's emotional state from the content of their post and classifies it into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0985] The "integration means" refers to a function for integrating the evaluation results of the false information detection means and the results of the emotion classification means into a single overall evaluation.

[0986] "Evaluation results" is a general term for the analysis results obtained by the false information detection means and emotion classification means, and refers to information including credibility assessments (falsehood level and confidence) and emotion categories.

[0987] "User interface" refers to the screen or operating system that allows the user and the system to exchange information on a terminal.

[0988] The term "system" refers to the collection of all means constituting the entire present invention, and has an integrated function of receiving, analyzing, evaluating, and displaying the results of posted content.

[0989] The present invention relates to a false information detection system for evaluating posted content, and in particular, a specific embodiment will be described in which an emotion classification engine that recognizes user emotions is combined.

[0990] System Overview

[0991] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following components:

[0992] Hardware Configuration

[0993] Server: A computing resource equipped with a display device, a communication module, and a storage device. For example, it is located on a cloud service platform.

[0994] Device: The device used by the user, such as a smartphone, tablet, or computer.

[0995] Software Configuration

[0996] Disinformation detection algorithms: Models using deep learning libraries such as TensorFlow and PyTorch, used to assess the veracity of posts.

[0997] Sentiment classification engine: Uses natural language processing technology such as IBM Watson Natural Language Understanding.

[0998] User interface: Display the evaluation results using front-end technologies such as React Native.

[0999] System processing overview

[1000] An example of the processing of this system is shown below.

[1001] Receiving posted content

[1002] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[1003] Analysis and evaluation of posted content

[1004] The server inputs the received post content into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the veracity of the post content. The analysis results are output as a falsehood level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[1005] The server then uses an emotion classification engine to analyze the user's emotional state from their posts, categorizing the emotional state into categories such as "joy," "anger," "sadness," and "surprise."

[1006] Submitting and viewing evaluation results

[1007] The server converts the false information assessment results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it visually in the user interface. For example, "Falsehood level: 4, Confidence: 0.85, Sentiment: Anger" may be displayed next to the post.

[1008] Specific examples

[1009] The following is a concrete example of how the system actually works. For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a false information detection algorithm. As a result of the analysis, the post is determined to have a "falsehood level of 4, confidence level of 0.85." The emotion classification engine also returns the emotional state of "anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "falsehood level of 4, confidence level of 0.85, emotion: anger," and can take action as necessary.

[1010] Example of input prompt for generative AI model

[1011] Please analyze the following posts. We use an algorithm to assess whether they are false and the user's emotional state. As a result, we will output a falsehood level (1-5) and a confidence level (0-1), and tell us your emotional state.

[1012] Example prompts

[1013] A serious incident has occurred

[1014] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1015] Step 1:

[1016] A user creates a post through a social networking application and sends it from the device. Specifically, the user enters the text "A serious incident has occurred" into the social networking application and presses the send button. The input data is sent in text format.

[1017] Step 2:

[1018] The device receives the user's posted content and sends it to the server as an HTTP request. The data sent is in the form of an HTTP request containing text. The content entered by the user is passed to the server as is.

[1019] Step 3:

[1020] The server receives an HTTP request from the device and extracts the post content. The input data is the HTTP request, and the output data is the extracted text ("A serious incident has occurred"). The server passes this extracted text data to the next processing step.

[1021] Step 4:

[1022] The server inputs the extracted text into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the credibility of the text. The input data is the text of the post, and the output data is an evaluation result of the falsehood level (1-5) and confidence level (0-1). For example, for a post saying "A serious incident has occurred," the server returns a rating of "Falsehood level: 4, Confidence level: 0.85."

[1023] Step 5:

[1024] The server inputs the same text into an emotion classification engine, which uses natural language processing techniques to analyze the emotional state of the text. The input data is the text, and the output data is emotion categories such as "joy," "anger," "sadness," and "surprise." For example, for the text "A serious incident has occurred," the server returns an evaluation of "Emotion: Anger."

[1025] Step 6:

[1026] The server integrates the false information evaluation results and the sentiment analysis results. The input data are the falsehood level, confidence level, and sentiment category, and the output data is the integrated result (e.g., "Falsehood level: 4, confidence level: 0.85, sentiment: anger"). The integrated result is converted into JSON format.

[1027] Step 7:

[1028] The server sends the integrated evaluation results to the user's device. The input data is the integrated results in JSON format, and the output data is an HTTP response to the device. For example, the data sent to the device is "falsehood level: 4, confidence level: 0.85, emotion: anger."

[1029] Step 8:

[1030] The device receives the evaluation results sent from the server and displays them on the user interface. The input data is the evaluation results in JSON format, and the output data is the visually displayed evaluation results. Specifically, "Falsehood level: 4, Confidence: 0.85, Emotion: Anger" is displayed next to the user's post.

[1031] (Application example 2)

[1032] 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."

[1033] In recent years, the spread of fake news has become a serious problem in content distribution services. Furthermore, it is not uncommon for users to spread inaccurate information due to their emotional reactions. In this environment, there is a need to provide reliable information and enable users to receive prompt feedback on their posts. Conventional technologies lack a means to simultaneously analyze the user's emotional state in addition to assessing the credibility of the content of posts. As a result, there are problems with delays in assessing the risk of fake news and the inability to take appropriate action that takes the user's emotional state into account.

[1034] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes fake news detection algorithm means for evaluating the posted content, means for receiving the posted content from the terminal, means for evaluating the posted content using the algorithm means, means for transmitting the evaluation result to the terminal, means for displaying the evaluation result on a user interface, emotion engine means for recognizing emotions from the posted content, and means for integrating the evaluation result and the emotion recognition result. This makes it possible to evaluate the risk of fake news in real time and provide rapid feedback that takes into account the user's emotional state.

[1035] "Posted content" refers to information generated by a user and sent to the system via a terminal.

[1036] A "fake news detection algorithm" is a computational method that analyzes input text or image data to determine whether it is false information and evaluates its credibility.

[1037] A "terminal" refers to a communication device that a user uses to input and receive posted content.

[1038] "Evaluation results" refers to the comprehensive data of the analysis results obtained by the fake news detection algorithm and emotion engine.

[1039] The "user interface" refers to a display screen or display portion that visually displays the evaluation results and allows the user to confirm the contents.

[1040] An "emotion engine" is a calculation means for analyzing a user's emotional state from the content of their posts and classifying them into emotion categories such as joy, anger, sadness, and surprise.

[1041] "Integrating" means combining the evaluation results of the fake news detection algorithm and the analysis results of the emotion engine into a single evaluation result.

[1042] This invention relates to a system that simultaneously detects fake news and analyzes user sentiment, and in particular, a specific embodiment in a content distribution service will be described.

[1043] System Overview

[1044] The system mainly consists of a server and a terminal. The server has multiple functions and operates as follows:

[1045] 1. How you will receive your submission:

[1046] The server receives posts from users' devices, which can include a variety of formats, such as text and images.

[1047] 2. Fake news detection algorithmic methods:

[1048] The server then inputs the received content into a fake news detection algorithm to analyze its authenticity. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[1049] 3. Emotion engine means:

[1050] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[1051] 4. Means of generating evaluation results:

[1052] The server combines the fake news evaluation results with the emotion engine analysis results to generate a comprehensive evaluation result, such as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[1053] 5. Method of sending evaluation results:

[1054] The server transmits the generated overall evaluation result to the user terminal.

[1055] 6. User interface display:

[1056] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[1057] Overview of the technical process

[1058] The server first receives the content of the post and inputs it into the fake news detection algorithm and emotion engine, which utilize deep learning and natural language processing technologies and work as follows:

[1059] Fake News Detection:

[1060] The text input is analyzed using a pre-trained model (e.g., BERT), which then numerically evaluates the likelihood that the post is fake news and outputs a fake level and confidence level.

[1061] Emotion analysis:

[1062] To analyze the emotions from user posts, we use an emotion classification model (e.g., emotion analysis pipeline), which classifies the emotions reflected in the posts and gives results such as "anger."

[1063] Integration and Display:

[1064] The obtained fake news evaluation results and sentiment analysis results are integrated by the server and sent to the user's device in JSON format, where the device displays the received results on a user interface and provides feedback to the user.

[1065] Specific examples

[1066] For example, suppose a user posts, "A serious incident has occurred. It will have serious repercussions!" The content of this post is received by the server and analyzed by the fake news detection algorithm. The result is "Fake Level: 4, Confidence: 0.85," and the emotion engine then determines the emotion as "anger." These evaluation results are combined and sent to the user's device. The user's device displays the message as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[1067] Prompt Sentence Examples

[1068] "Create an application that analyzes content posted by users and evaluates the likelihood of it being fake news and the sentiment behind it. For example, if a user posts "A serious incident has occurred," generate a fake news evaluation result of [{"label": "LABEL_1", "score": 0.95}] and a sentiment evaluation result of "POSITIVE." Specifically, the model used should be a pre-trained model from the BERT series, and the evaluation results should be integrated and output in JSON format."

[1069] As a result, the present invention realizes a highly reliable information distribution environment that prevents the spread of fake news and at the same time provides feedback that takes into account the user's emotional state.

[1070] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1071] Step 1:

[1072] The user inputs content (text, images, videos, etc.) and generates a post. The post is then sent from the device to the server. The input is the user's post, and the output is the receipt of the post.

[1073] Step 2:

[1074] The server receives the post and inputs it into a fake news detection algorithm. This algorithm analyzes the veracity of the post. The input is the received post, and the output is an evaluation of the veracity of the fake news. Specifically, it performs text analysis using a deep learning model (e.g., BERT).

[1075] Step 3:

[1076] The server obtains the evaluation results of the fake news detection algorithm and then uses an emotion engine to analyze emotions from the post content. In this process, the post content is input into an emotion classification model and classified into emotion categories such as "joy," "anger," "sadness," and "surprise." The input is the post content, and the output is the emotion analysis result. Specific operation utilizes an emotion analysis pipeline.

[1077] Step 4:

[1078] The server integrates the fake news detection results and sentiment analysis results to generate an overall evaluation result. The generated evaluation result is formed as a fake level, confidence level, and emotional state. The inputs are the fake news evaluation results and sentiment analysis results, and the output is an integrated overall evaluation result. Specifically, the evaluation results are converted into JSON format.

[1079] Step 5:

[1080] The server generates an overall evaluation result and sends it to the terminal. In this step, the integrated evaluation result received by the user's terminal is sent as JSON data for processing. The input is the overall evaluation result, and the output is the evaluation result sent to the terminal. The specific operation involves sending data over the network.

[1081] Step 6:

[1082] The terminal displays the overall evaluation results it receives on the user interface. The displayed results allow users to check the authenticity of the posted content and their own emotional state. The input is the overall evaluation results obtained from the server, and the output is a visual display on the user interface. The specific operation is to display the evaluation results on the graphical user interface.

[1083] In this way, the system can efficiently detect fake news and analyze sentiment in posted content, providing intuitive feedback to users.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] [Fourth embodiment]

[1088] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1089] 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.

[1090] 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).

[1091] 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.

[1092] 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.

[1093] 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).

[1094] 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.

[1095] 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.

[1096] 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.

[1097] 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.

[1098] 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.

[1099] 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.

[1100] 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."

[1101] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment for preventing the spread of fake news will be described.

[1102] System Overview

[1103] This system has the function of analyzing the content posted by users and evaluating its credibility. The system mainly consists of the following functional blocks.

[1104] 1. Means of receiving posted content (server)

[1105] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[1106] 2. Fake News Detection Algorithm (Server)

[1107] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[1108] 3. Evaluation result generation means (server)

[1109] The server takes the evaluation results generated by the algorithm and outputs them as a fake level (1 to 5) and a confidence level (a number between 0 and 1).

[1110] 4. Evaluation result transmission method (server)

[1111] The server then sends the generated evaluation results to the user's device, allowing the user to check in real time how trustworthy the content of their posts are.

[1112] 5. Means of display in the user interface (terminal)

[1113] The evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level and confidence level are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information.

[1114] System processing overview

[1115] An example of the processing of this system is shown below.

[1116] Receiving posted content

[1117] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[1118] Analysis and evaluation of posted content

[1119] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (1-5) and a confidence level (0-1).

[1120] Submitting and viewing evaluation results

[1121] The server converts the analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. Specifically, it displays "Fake Level: 4, Confidence: 0.85" next to the post content.

[1122] Specific examples

[1123] Below is a concrete example of the system in action.

[1124] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to be "Fake Level: 4, Confidence: 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[1125] In this way, the system of the present invention prevents the spread of fake news and provides an environment in which users can easily determine the credibility of information.

[1126] The processing flow will be explained below.

[1127] Step 1: Enter post content (user)

[1128] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[1129] Step 2: Send your post (device)

[1130] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[1131] Step 3: Receiving the posted content (server)

[1132] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[1133] Step 4: Analyzing the Post Content (Server)

[1134] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[1135] Step 5: Generating evaluation results (server)

[1136] The server obtains the analysis result of the algorithm. The analysis result includes a fake level (1-5) and a confidence level (0-1). For example, the result generated is "Fake level: 4, confidence level: 0.85".

[1137] Step 6: Formatting the evaluation results (server)

[1138] The server converts the evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[1139] Step 7: Sending evaluation results (server)

[1140] The server then sends the formatted evaluation results to the terminal, again using an HTTP response.

[1141] Step 8: Receiving the evaluation results (terminal)

[1142] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[1143] Step 9: View the evaluation results (on your device)

[1144] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85" next to the entered post content.

[1145] Step 10: Check the evaluation results (user)

[1146] Users can check the fake level and confidence level displayed on their device and use this information to determine the authenticity of the post.

[1147] Step 11: Additional User Actions

[1148] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[1149] Example 1

[1150] 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."

[1151] In recent years, the reliability of information on the Internet has become increasingly important, and the spread of fake news, especially on social media, has become a serious social problem. This fake news not only causes misunderstanding and anxiety, but can also have a negative impact on actual behavior. Therefore, there is a need to quickly evaluate the reliability of content posted by users and prevent the spread of fake news before it happens.

[1152] 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.

[1153] In this invention, the server includes an information evaluation algorithm for evaluating posted content, a means for receiving the posted content from a user device, a means for evaluating the posted content using the algorithm, a means for transmitting the evaluation result to the user device, and a means for displaying the evaluation result on a user interface. This allows users to easily and quickly confirm the reliability of posted content, preventing the spread of fake news and promoting accurate information sharing.

[1154] "Posted content" is a general term for information posted by users through social media or other online platforms, including text and image data.

[1155] "Information evaluation algorithm means" refers to a technical component that executes an algorithm that analyzes the reliability and accuracy of received posts and assesses the likelihood that the content in question is fake news.

[1156] "Devices used" refers to devices that users use to connect to the Internet and send and receive information, and is a general term for smartphones, tablets, PCs, etc.

[1157] The "user interface" refers to components such as a display screen and input devices that users use to operate system functions and visually confirm evaluation results.

[1158] The "trust level" is a number that indicates the evaluation result of whether the content of a post is accurate, and is usually expressed on a scale of 1 to 5.

[1159] "Confidence" is a number that indicates the degree of trust in the reliability assessment result produced by the algorithm, and is expressed in a range from 0 to 1.

[1160] The present invention relates to a system for assessing the reliability of information posted by users, with the aim of preventing the spread of fake news, particularly on social media.

[1161] System Overview

[1162] The system includes an information evaluation algorithm means, a means for receiving posted content from a user device, a means for performing an evaluation of the posted content using the algorithm means, a means for transmitting the evaluation results to the user device, and a means for displaying the evaluation results on a user interface.

[1163] Hardware and Software

[1164] An embodiment of the system uses the following hardware and software:

[1165] 1. Server:

[1166] It provides a high-performance computing environment and is responsible for receiving and analyzing content posted by users.

[1167] The software running on the server includes a web framework using the Flask library.

[1168] 2. Algorithmic means:

[1169] It uses deep learning models and natural language processing techniques to assess the trustworthiness of posts.

[1170] Specifically, it uses a pre-trained model using the Transformers library.

[1171] 3. Equipment used:

[1172] A device used by users to send, receive, and display information, including smartphones, tablets, and PCs.

[1173] Specific details of data processing

[1174] 1. Receiving:

[1175] The server receives posts from users, which may be in various formats such as text or image data.

[1176] 2. Analysis:

[1177] The server then feeds the received posts into an algorithmic process to assess their trustworthiness using deep learning models and natural language processing techniques.

[1178] 3. Generating and sending evaluation results:

[1179] The server obtains the analysis results and generates a confidence level and certainty factor, which are then sent to the user device in JSON format.

[1180] 4.Display:

[1181] The user's terminal receives the evaluation results sent from the server and displays them on the user interface.

[1182] Specific examples

[1183] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "reliability level of 4, certainty factor of 0.85," and this result is sent to the user's device. The user then recognizes that there is a high probability that the content of their post is fake news, and can either delete the post or check the facts.

[1184] Prompt Sentence Examples

[1185] Here are some examples of prompts for generative AI models:

[1186] Please explain the detailed programming process of the fake news detection system. Please explain it in the following steps: 1. Receiving the post content 2. Running the fake news detection algorithm 3. Generating the evaluation results 4. Sending the evaluation results 5. Displaying the evaluation results. Please provide specific operations and techniques for each step.

[1187] This prompt helps the generative AI model provide a detailed description of the system described above.

[1188] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1189] Step 1: Receiving submissions

[1190] Specific description:

[1191] The server receives the content posted by the user from the device used by the user. Specifically, the text and images posted by the user on the social media application are sent to the server.

[1192] Input and Output:

[1193] Input: The post typed by the user (e.g., "A serious incident has occurred").

[1194] Output: The post received by the server.

[1195] Specific behavior:

[1196] The server receives the submission via an HTTP POST request, for example, using Flask's request.get_json() method to retrieve the data.

[1197] Step 2: Analyzing the Post Content

[1198] Specific description:

[1199] The server feeds the received posts into a fake news detection algorithm, which uses pre-trained deep learning models and natural language processing techniques to assess their credibility.

[1200] Input and Output:

[1201] Input: The post content received by the server.

[1202] Output: The result of the fake news detection algorithm (e.g., "Fake Level: 4, Confidence: 0.85").

[1203] Specific behavior:

[1204] The server uses the Transformers library to pass the post to a pre-trained model, which outputs a confidence score and returns it to the server as the analysis result.

[1205] Step 3: Generate evaluation results

[1206] Specific description:

[1207] The server generates a confidence level (1-5) and a confidence level (0-1) based on the results of the algorithm's analysis, which are then formatted for easy display in a user interface.

[1208] Input and Output:

[1209] Input: Analysis results of the fake news detection algorithm.

[1210] Output: Evaluation results (in JSON format) including confidence level and certainty.

[1211] Specific behavior:

[1212] The server maps the score based on the analysis results and generates the evaluation result in JSON format. For example, it maps the fake level and confidence level according to the score value.

[1213] Step 4: Submit your evaluation results

[1214] Specific description:

[1215] The server then sends the generated evaluation results to the device, allowing users to check the reliability of the posted content in real time.

[1216] Input and Output:

[1217] Input: Evaluation results (JSON data including confidence level and certainty).

[1218] Output: Evaluation results sent to the user device.

[1219] Specific behavior:

[1220] The server sends the evaluation result back to the device as an HTTP response, for example, by sending JSON data using Flask's jsonify method.

[1221] Step 5: View the evaluation results

[1222] Specific description:

[1223] The user's device displays the evaluation results received from the server on a user interface, allowing the user to intuitively understand how trustworthy the posted content is.

[1224] Input and Output:

[1225] Input: The evaluation result (confidence level and certainty) received from the server.

[1226] Output: The evaluation results displayed on the user interface.

[1227] Specific behavior:

[1228] The user's device uses JavaScript to embed the evaluation results in HTML elements and display them visually. For example, the document.getElementById().innerHTML method is used to update the displayed content.

[1229] (Application example 1)

[1230] 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."

[1231] In recent years, the increase in fake news on the Internet has become a serious problem, and users are losing trust in news articles in particular. The spread of fake news can encourage decision-making based on erroneous information and have a negative impact on society. Therefore, there is a need for a system that allows users to easily determine the reliability of news articles and prevents the spread of fake news.

[1232] 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.

[1233] In this invention, the server includes a fake news detection algorithm means for evaluating posted content, a means for receiving the posted content from a terminal, a means for evaluating the posted content using the algorithm means, a means for transmitting the evaluation result to the terminal, a means for displaying the evaluation result on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability evaluation, and a means for displaying a warning for articles that are likely to be fake news. This allows users to intuitively judge the reliability of news articles and makes it possible to prevent the spread of fake news.

[1234] "Fake news detection algorithmic means for assessing the content of posts" refers to means that include an algorithm that analyses the content of text, images, etc. posted by users and determines their reliability.

[1235] The "means for receiving posted content from a terminal" refers to a means including an interface and communication means for receiving posted content sent from a user terminal.

[1236] "Means for evaluating posted content using algorithmic means" refers to means that include the function of applying a fake news detection algorithm to received posted content and performing that evaluation.

[1237] The "means for transmitting the evaluation results to the terminal" refers to a means including a communication means for transmitting the evaluation results generated by the algorithm to the user's terminal.

[1238] The "means for displaying the evaluation results on a user interface" refers to a means including an interface and a function for visually displaying the evaluation results sent to the terminal.

[1239] "Means for analyzing the content of news articles in real time and displaying a credibility evaluation" refers to means that includes analysis and display functions for analyzing the content of news articles viewed by users in real time and displaying the results of a credibility evaluation.

[1240] "Means for displaying a warning to articles that are likely to be fake news" refers to means that include a function for displaying a warning to users about articles that are determined to be likely to be fake news as a result of a reliability assessment.

[1241] The present invention provides a system for assessing the reliability of news articles viewed by users in real time and preventing the spread of fake news. The system includes a fake news detection algorithm for assessing the content of posts, a means for receiving the posted content from a terminal, a means for assessing the posted content using the algorithm, a means for transmitting the assessment results to the terminal, a means for displaying the assessment results on a user interface, a means for analyzing the content of news articles in real time and displaying a reliability assessment, and a means for displaying a warning for articles that are likely to be fake news.

[1242] Program processing overview

[1243] The server uses a fake news detection algorithm to analyze news articles posted or viewed by users in real time. The algorithm uses deep learning and natural language processing techniques to evaluate the authenticity of the posted content. The evaluation results are generated as a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[1244] The server sends the evaluation results to the device, which then visually displays them on the user interface. When users view a news article, they can intuitively understand whether the article is fake news or not. Furthermore, articles that are likely to be fake news are displayed with a warning.

[1245] Specific examples

[1246] For example, a user uses a news aggregation application to view a news article titled "A major incident has occurred." The content of this news article is sent to a server and analyzed by a fake news detection algorithm. If the analysis results in the news article being rated "Fake Level: 4, Confidence: 0.85," the server sends this result to the user's device. A warning message stating "This news article is likely to be fake news" is displayed next to the article on the user's device, allowing the user to confirm the reliability of the news article.

[1247] An example of a prompt to be input to the generative AI model is as follows:

[1248] "What program uses a fake news detection algorithm to assess the veracity of today's news posts?"

[1249] "Please explain how a news aggregation app can display fake news warnings to users."

[1250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1251] Step 1:

[1252] A user opens a news aggregation application, selects a news article, and starts viewing it. When the user starts viewing, the device extracts the content (text data) of the news article and sends it to the server.

[1253] Input: News article content (text data)

[1254] Output: Data sent to the server

[1255] Specific behavior: A user operates a news app and clicks to open an article. The app extracts the text data and automatically sends it to the server.

[1256] Step 2:

[1257] The server then inputs the received text data of the news articles into a fake news detection algorithm, which uses natural language processing and deep learning techniques to analyze the text data and evaluate its reliability.

[1258] Input: Text data of news articles sent from the user's device

[1259] Output: Evaluation result of fake news detection (fake level and confidence level)

[1260] How it works: The server receives news text data and inputs it into the fake news detection algorithm, which then analyzes the data and generates a rating.

[1261] Step 3:

[1262] The server sends the generated evaluation result to the terminal. This evaluation result includes a fake level (1 to 5) and a confidence level (a number from 0 to 1).

[1263] Input: Fake news detection evaluation results

[1264] Output: Evaluation result data sent to the user's device

[1265] Specific operation: The server converts the evaluation results into JSON format and sends them to the user's device.

[1266] Step 4:

[1267] The user's device visually displays the received evaluation results in a user interface, displaying a fake level and confidence level next to the news article the user is viewing, and displaying a fake news warning if necessary.

[1268] Input: Evaluation result sent from the server (fake level and confidence level)

[1269] Output: Trust rating and warnings displayed in the user interface

[1270] Specific operation: The user's device analyzes the evaluation result data received and displays a message next to the news article, such as "Fake level: 4, confidence level: 0.85." If a warning is necessary, the message will read, "This news article is likely to be fake news."

[1271] Step 5:

[1272] Users can review the credibility ratings and warnings displayed and decide whether to trust the news article, and if necessary, decide not to share it or conduct additional fact-checking.

[1273] Input: Trust rating and warnings displayed in the user interface

[1274] Output: User decision and action (e.g., not sharing the article, further fact-checking, etc.)

[1275] What happens: Users can view a news article's credibility rating and warnings and make decisions based on that information, such as whether to read the article or refrain from sharing it.

[1276] 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.

[1277] The present invention relates to a fake news detection system for evaluating posted content, and in particular, a specific embodiment will be described that combines an emotion engine that recognizes user emotions.

[1278] System Overview

[1279] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following functional blocks.

[1280] 1. Means of receiving posted content (server)

[1281] The server receives posts from the terminals used by the users, which may include various formats such as text and images.

[1282] 2. Fake News Detection Algorithm (Server)

[1283] The server inputs the received post content into a fake news detection algorithm to analyze its credibility. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[1284] 3. Emotion engine means (server)

[1285] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[1286] 4. Evaluation result generation means (server)

[1287] The server combines the fake news evaluation results with the emotion engine analysis results and outputs the overall evaluation result. For example, it generates an evaluation result in the form of "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[1288] 5. Evaluation result transmission method (server)

[1289] The server then sends the generated overall evaluation results to the user's device, allowing the user to check the reliability of their own posts as well as their emotional state in real time.

[1290] 6. Means of display in the user interface (terminal)

[1291] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[1292] System processing overview

[1293] An example of the processing of this system is shown below.

[1294] Receiving posted content

[1295] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[1296] Analysis and evaluation of posted content

[1297] The server inputs the received post content into a fake news detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the authenticity of the post content. The analysis results are output as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[1298] The server then uses an emotion engine to analyze the user's emotional state from their posts, which is then classified into categories such as "joy," "anger," "sadness," and "surprise."

[1299] Submitting and viewing evaluation results

[1300] The server converts the fake news evaluation results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it in the user interface. For example, "Fake level: 4, confidence level: 0.85, sentiment: anger" may be displayed next to the post.

[1301] Specific examples

[1302] Below is a concrete example of the system in action.

[1303] For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a fake news detection algorithm. As a result of the analysis, the post is determined to have a "Fake Level: 4, Confidence: 0.85." The emotion engine also returns the emotional state of "Anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "Fake Level: 4, Confidence: 0.85, Emotion: Anger," and can take action as necessary.

[1304] In this way, the system of the present invention prevents the spread of fake news and also provides an environment for comprehensively evaluating the credibility of posted content by understanding the user's emotional state.

[1305] The processing flow will be explained below.

[1306] Step 1: Enter post content (user)

[1307] A user opens a social networking application and enters a post, for example, "A serious incident has occurred" into a text box.

[1308] Step 2: Send your post (device)

[1309] The device sends the entered post content to the server using an HTTP request, sending a data packet containing the post content to the server.

[1310] Step 3: Receiving the posted content (server)

[1311] The server receives the content posted by the device and prepares it for analysis. Specifically, it parses the data sent in JSON format.

[1312] Step 4: Analyzing the Post Content (Server)

[1313] The server then inputs the received content into a fake news detection algorithm, which analyzes the content using deep learning and natural language processing techniques.

[1314] Step 5: Generate fake levels and confidence (server)

[1315] The server receives the analysis results from the algorithm and outputs them as a fake level (a number from 1 to 5) and a confidence level (a number from 0 to 1). For example, the result might be "Fake level: 4, confidence level: 0.85."

[1316] Step 6: Performing sentiment analysis (server)

[1317] The server inputs the posted content into an emotion engine and analyzes the user's emotional state, which is classified into categories such as "joy," "anger," "sadness," and "surprise."

[1318] Step 7: Integration of evaluation results (server)

[1319] The server combines the fake news evaluation results with the emotion engine analysis results and compiles them into an overall evaluation result. For example, the results may be summarized as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[1320] Step 8: Formatting the evaluation results (server)

[1321] The server converts the integrated evaluation results into JSON format, which makes it easier to send the evaluation results to the terminal.

[1322] Step 9: Sending evaluation results (server)

[1323] The server then sends the formatted evaluation results to the user's device, again using an HTTP response.

[1324] Step 10: Receiving evaluation results (terminal)

[1325] The terminal receives the evaluation results sent from the server and prepares the received data for display on the user interface.

[1326] Step 11: Viewing the evaluation results (terminal)

[1327] The device displays the evaluation results in the user interface, specifically displaying "Fake Level: 4, Confidence: 0.85, Emotion: Anger" next to the entered post content.

[1328] Step 12: Check the evaluation results (user)

[1329] Users can view the fake level, confidence level, and emotional state displayed on their device, and use this information to determine the authenticity of the post.

[1330] Step 13: Additional User Actions

[1331] If necessary, users can delete the post, check the facts with a reliable source, or report the post to the administrators using the reporting function of the social networking site.

[1332] Example 2

[1333] 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."

[1334] Conventional fake news detection systems are limited to assessing the credibility of posted content and do not take into account the user's emotional state. As a result, when a user's emotions affect the credibility of the posted content, the evaluation of the information may be incomplete. Furthermore, simply assessing whether or not something is fake news does not provide users with enough information to understand the content and take appropriate action.

[1335] 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.

[1336] In this invention, the server includes a false information detection means for evaluating the posted content, a means for analyzing the posted content and classifying the user's emotions, and a means for integrating the evaluation result of the false information detection means and the result of the emotion classification means, thereby enabling a comprehensive evaluation that takes into account not only the credibility of the posted content but also the user's emotional state.

[1337] "Posted content" refers to information such as text, images, and videos that users post on social media or other communication platforms.

[1338] "False information detection methods" refer to algorithms or systems that analyze the veracity of received posts and assess their credibility.

[1339] "Terminal" refers to a computer device used by a user, such as a smartphone, tablet, or PC.

[1340] "Emotion classification means" refers to an algorithm or system that analyzes a user's emotional state from the content of their post and classifies it into emotional categories such as "joy," "anger," "sadness," and "surprise."

[1341] The "integration means" refers to a function for integrating the evaluation results of the false information detection means and the results of the emotion classification means into a single overall evaluation.

[1342] "Evaluation results" is a general term for the analysis results obtained by the false information detection means and emotion classification means, and refers to information including credibility assessments (falsehood level and confidence) and emotion categories.

[1343] "User interface" refers to the screen or operating system that allows the user and the system to exchange information on a terminal.

[1344] The term "system" refers to the collection of all means constituting the entire present invention, and has an integrated function of receiving, analyzing, evaluating, and displaying the results of posted content.

[1345] The present invention relates to a false information detection system for evaluating posted content, and in particular, a specific embodiment will be described in which an emotion classification engine that recognizes user emotions is combined.

[1346] System Overview

[1347] This system analyzes the content posted by users and simultaneously evaluates its credibility and the user's emotions. The system mainly consists of the following components:

[1348] Hardware Configuration

[1349] Server: A computing resource equipped with a display device, a communication module, and a storage device. For example, it is located on a cloud service platform.

[1350] Device: The device used by the user, such as a smartphone, tablet, or computer.

[1351] Software Configuration

[1352] Disinformation detection algorithms: Models using deep learning libraries such as TensorFlow and PyTorch, used to assess the veracity of posts.

[1353] Sentiment classification engine: Uses natural language processing technology such as IBM Watson Natural Language Understanding.

[1354] User interface: Display the evaluation results using front-end technologies such as React Native.

[1355] System processing overview

[1356] An example of the processing of this system is shown below.

[1357] Receiving posted content

[1358] A user inputs content to post using an SNS application and sends it to the server, which receives the content and starts the analysis process.

[1359] Analysis and evaluation of posted content

[1360] The server inputs the received post content into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the veracity of the post content. The analysis results are output as a falsehood level (a number from 1 to 5) and a confidence level (a number from 0 to 1).

[1361] The server then uses an emotion classification engine to analyze the user's emotional state from their posts, categorizing the emotional state into categories such as "joy," "anger," "sadness," and "surprise."

[1362] Submitting and viewing evaluation results

[1363] The server converts the false information assessment results and sentiment analysis results into JSON format and sends them to the user's device. The user's device receives this data and displays it visually in the user interface. For example, "Falsehood level: 4, Confidence: 0.85, Sentiment: Anger" may be displayed next to the post.

[1364] Specific examples

[1365] The following is a concrete example of how the system actually works. For example, suppose a user posts, "A serious incident has occurred." When this post is sent to the server, the server analyzes it using a false information detection algorithm. As a result of the analysis, the post is determined to have a "falsehood level of 4, confidence level of 0.85." The emotion classification engine also returns the emotional state of "anger" as the analysis result. The server combines these evaluation results and sends them to the user's device. The user can confirm that the evaluation result for their own post is "falsehood level of 4, confidence level of 0.85, emotion: anger," and can take action as necessary.

[1366] Example of input prompt for generative AI model

[1367] Please analyze the following posts. We use an algorithm to assess whether they are false and the user's emotional state. As a result, we will output a falsehood level (1-5) and a confidence level (0-1), and tell us your emotional state.

[1368] Example prompts

[1369] A serious incident has occurred

[1370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1371] Step 1:

[1372] A user creates a post through a social networking application and sends it from the device. Specifically, the user enters the text "A serious incident has occurred" into the social networking application and presses the send button. The input data is sent in text format.

[1373] Step 2:

[1374] The device receives the user's posted content and sends it to the server as an HTTP request. The data sent is in the form of an HTTP request containing text. The content entered by the user is passed to the server as is.

[1375] Step 3:

[1376] The server receives an HTTP request from the device and extracts the post content. The input data is the HTTP request, and the output data is the extracted text ("A serious incident has occurred"). The server passes this extracted text data to the next processing step.

[1377] Step 4:

[1378] The server inputs the extracted text into a false information detection algorithm. The algorithm uses deep learning and natural language processing techniques to analyze the credibility of the text. The input data is the text of the post, and the output data is an evaluation result of the falsehood level (1-5) and confidence level (0-1). For example, for a post saying "A serious incident has occurred," the server returns a rating of "Falsehood level: 4, Confidence level: 0.85."

[1379] Step 5:

[1380] The server inputs the same text into an emotion classification engine, which uses natural language processing techniques to analyze the emotional state of the text. The input data is the text, and the output data is emotion categories such as "joy," "anger," "sadness," and "surprise." For example, for the text "A serious incident has occurred," the server returns an evaluation of "Emotion: Anger."

[1381] Step 6:

[1382] The server integrates the false information evaluation results and the sentiment analysis results. The input data are the falsehood level, confidence level, and sentiment category, and the output data is the integrated result (e.g., "Falsehood level: 4, confidence level: 0.85, sentiment: anger"). The integrated result is converted into JSON format.

[1383] Step 7:

[1384] The server sends the integrated evaluation results to the user's device. The input data is the integrated results in JSON format, and the output data is an HTTP response to the device. For example, the data sent to the device is "falsehood level: 4, confidence level: 0.85, emotion: anger."

[1385] Step 8:

[1386] The device receives the evaluation results sent from the server and displays them on the user interface. The input data is the evaluation results in JSON format, and the output data is the visually displayed evaluation results. Specifically, "Falsehood level: 4, Confidence: 0.85, Emotion: Anger" is displayed next to the user's post.

[1387] (Application example 2)

[1388] 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."

[1389] In recent years, the spread of fake news has become a serious problem in content distribution services. Furthermore, it is not uncommon for users to spread inaccurate information due to their emotional reactions. In this environment, there is a need to provide reliable information and enable users to receive prompt feedback on their posts. Conventional technologies lack a means to simultaneously analyze the user's emotional state in addition to assessing the credibility of the content of posts. As a result, there are problems with delays in assessing the risk of fake news and the inability to take appropriate action that takes the user's emotional state into account.

[1390] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes fake news detection algorithm means for evaluating the posted content, means for receiving the posted content from the terminal, means for evaluating the posted content using the algorithm means, means for transmitting the evaluation result to the terminal, means for displaying the evaluation result on a user interface, emotion engine means for recognizing emotions from the posted content, and means for integrating the evaluation result and the emotion recognition result. This makes it possible to evaluate the risk of fake news in real time and provide rapid feedback that takes into account the user's emotional state.

[1391] "Posted content" refers to information generated by a user and sent to the system via a terminal.

[1392] A "fake news detection algorithm" is a computational method that analyzes input text or image data to determine whether it is false information and evaluates its credibility.

[1393] A "terminal" refers to a communication device that a user uses to input and receive posted content.

[1394] "Evaluation results" refers to the comprehensive data of the analysis results obtained by the fake news detection algorithm and emotion engine.

[1395] The "user interface" refers to a display screen or display portion that visually displays the evaluation results and allows the user to confirm the contents.

[1396] An "emotion engine" is a calculation means for analyzing a user's emotional state from the content of their posts and classifying them into emotion categories such as joy, anger, sadness, and surprise.

[1397] "Integrating" means combining the evaluation results of the fake news detection algorithm and the analysis results of the emotion engine into a single evaluation result.

[1398] This invention relates to a system that simultaneously detects fake news and analyzes user sentiment, and in particular, a specific embodiment in a content distribution service will be described.

[1399] System Overview

[1400] The system mainly consists of a server and a terminal. The server has multiple functions and operates as follows:

[1401] 1. How you will receive your submission:

[1402] The server receives posts from users' devices, which can include a variety of formats, such as text and images.

[1403] 2. Fake news detection algorithmic methods:

[1404] The server then inputs the received content into a fake news detection algorithm to analyze its authenticity. The algorithm analyzes the text data and rates the likelihood of it being fake news on a five-point scale.

[1405] 3. Emotion engine means:

[1406] The server uses an emotion engine to analyze emotions from users' posts and determine their emotional state, which is classified into multiple categories such as "joy," "anger," "sadness," and "surprise."

[1407] 4. Means of generating evaluation results:

[1408] The server combines the fake news evaluation results with the emotion engine analysis results to generate a comprehensive evaluation result, such as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[1409] 5. Method of sending evaluation results:

[1410] The server transmits the generated overall evaluation result to the user terminal.

[1411] 6. User interface display:

[1412] The overall evaluation results received from the server are visually displayed on the user's device. Specifically, the fake level, confidence level, and emotional state are displayed next to the posted content, allowing the user to intuitively understand the credibility of the information and their own emotional state.

[1413] Overview of the technical process

[1414] The server first receives the content of the post and inputs it into the fake news detection algorithm and emotion engine, which utilize deep learning and natural language processing technologies and work as follows:

[1415] Fake News Detection:

[1416] The text input is analyzed using a pre-trained model (e.g., BERT), which then numerically evaluates the likelihood that the post is fake news and outputs a fake level and confidence level.

[1417] Emotion analysis:

[1418] To analyze the emotions from user posts, we use an emotion classification model (e.g., emotion analysis pipeline), which classifies the emotions reflected in the posts and gives results such as "anger."

[1419] Integration and Display:

[1420] The obtained fake news evaluation results and sentiment analysis results are integrated by the server and sent to the user's device in JSON format, where the device displays the received results on a user interface and provides feedback to the user.

[1421] Specific examples

[1422] For example, suppose a user posts, "A serious incident has occurred. It will have serious repercussions!" The content of this post is received by the server and analyzed by the fake news detection algorithm. The result is "Fake Level: 4, Confidence: 0.85," and the emotion engine then determines the emotion as "anger." These evaluation results are combined and sent to the user's device. The user's device displays the message as "Fake Level: 4, Confidence: 0.85, Emotion: Anger."

[1423] Prompt Sentence Examples

[1424] "Create an application that analyzes content posted by users and evaluates the likelihood of it being fake news and the sentiment behind it. For example, if a user posts "A serious incident has occurred," generate a fake news evaluation result of [{"label": "LABEL_1", "score": 0.95}] and a sentiment evaluation result of "POSITIVE." Specifically, the model used should be a pre-trained model from the BERT series, and the evaluation results should be integrated and output in JSON format."

[1425] As a result, the present invention realizes a highly reliable information distribution environment that prevents the spread of fake news and at the same time provides feedback that takes into account the user's emotional state.

[1426] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1427] Step 1:

[1428] The user inputs content (text, images, videos, etc.) and generates a post. The post is then sent from the device to the server. The input is the user's post, and the output is the receipt of the post.

[1429] Step 2:

[1430] The server receives the post and inputs it into a fake news detection algorithm. This algorithm analyzes the veracity of the post. The input is the received post, and the output is an evaluation of the veracity of the fake news. Specifically, it performs text analysis using a deep learning model (e.g., BERT).

[1431] Step 3:

[1432] The server obtains the evaluation results of the fake news detection algorithm and then uses an emotion engine to analyze emotions from the post content. In this process, the post content is input into an emotion classification model and classified into emotion categories such as "joy," "anger," "sadness," and "surprise." The input is the post content, and the output is the emotion analysis result. Specific operation utilizes an emotion analysis pipeline.

[1433] Step 4:

[1434] The server integrates the fake news detection results and sentiment analysis results to generate an overall evaluation result. The generated evaluation result is formed as a fake level, confidence level, and emotional state. The inputs are the fake news evaluation results and sentiment analysis results, and the output is an integrated overall evaluation result. Specifically, the evaluation results are converted into JSON format.

[1435] Step 5:

[1436] The server generates an overall evaluation result and sends it to the terminal. In this step, the integrated evaluation result received by the user's terminal is sent as JSON data for processing. The input is the overall evaluation result, and the output is the evaluation result sent to the terminal. The specific operation involves sending data over the network.

[1437] Step 6:

[1438] The terminal displays the overall evaluation results it receives on the user interface. The displayed results allow users to check the authenticity of the posted content and their own emotional state. The input is the overall evaluation results obtained from the server, and the output is a visual display on the user interface. The specific operation is to display the evaluation results on the graphical user interface.

[1439] In this way, the system can efficiently detect fake news and analyze sentiment in posted content, providing intuitive feedback to users.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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).

[1447] 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.

[1448] 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."

[1449] 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.

[1450] 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).

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] The following is further disclosed regarding the above embodiment.

[1462] (Claim 1)

[1463] a fake news detection algorithmic means for evaluating the content of posts;

[1464] means for receiving the posted content from a terminal;

[1465] means for performing an evaluation of the posted content using the algorithm means;

[1466] means for transmitting the evaluation result to a terminal;

[1467] means for displaying the evaluation results on a user interface;

[1468] A system including:

[1469] (Claim 2)

[1470] The system of claim 1, wherein the fake news detection algorithm means is a means for evaluating the likelihood of fake news based on text input on a five-point scale.

[1471] (Claim 3)

[1472] The system of claim 1, further comprising means for visually displaying the evaluation results as a fake level and a confidence level.

[1473] "Example 1"

[1474] (Claim 1)

[1475] an information evaluation algorithm means for evaluating the content of the posts;

[1476] means for receiving the posted content from the device;

[1477] means for performing an evaluation of the posted content using the algorithm means;

[1478] means for transmitting the evaluation result to a utilization device;

[1479] means for displaying the evaluation results on a user interface;

[1480] A system including:

[1481] (Claim 2)

[1482] 2. The system according to claim 1, wherein the information evaluation algorithm means is a means for evaluating the likelihood of reliability on a five-point scale based on character data input.

[1483] (Claim 3)

[1484] 10. The system of claim 1, further comprising means for visually displaying the evaluation results as a confidence level and a confidence factor.

[1485] "Application Example 1"

[1486] (Claim 1)

[1487] a fake news detection algorithmic means for evaluating the content of posts;

[1488] means for receiving the posted content from a terminal;

[1489] means for performing an evaluation of the posted content using the algorithm means;

[1490] means for transmitting the evaluation result to a terminal;

[1491] means for displaying the evaluation results on a user interface;

[1492] A means for analyzing the content of news articles in real time and displaying a credibility rating;

[1493] A means to display warnings for articles that are likely to be fake news, and

[1494] A system including:

[1495] (Claim 2)

[1496] The system of claim 1, wherein the fake news detection algorithm means is a means for evaluating the likelihood of fake news based on text input on a five-point scale.

[1497] (Claim 3)

[1498] The system of claim 1, further comprising means for visually displaying the evaluation results as a fake level and a confidence level.

[1499] "Example 2: Combining Emotion Engines"

[1500] (Claim 1)

[1501] a false information detection means for evaluating the content of posts;

[1502] means for receiving the posted content from a terminal;

[1503] a means for evaluating the posted content using the false information detection means;

[1504] means for analyzing the posted content and classifying the user's emotions;

[1505] means for integrating the evaluation result of the false information detection means and the result of the emotion classification means;

[1506] means for transmitting the integration result to a terminal;

[1507] means for displaying the integration result on a user interface;

[1508] A system including:

[1509] (Claim 2)

[1510] 2. The system according to claim 1, wherein the false information detection means is a means for evaluating the likelihood of false information based on a text input on a five-point scale.

[1511] (Claim 3)

[1512] The system according to claim 1, further comprising means for visually displaying the integration results as a falsehood level, a confidence level, and an emotion category.

[1513] "Application example 2 when combining emotion engines"

[1514] (Claim 1)

[1515] a fake news detection algorithmic means for evaluating the content of posts;

[1516] means for receiving the posted content from a terminal;

[1517] means for performing an evaluation of the posted content using the algorithm means;

[1518] means for transmitting the evaluation result to a terminal;

[1519] means for displaying the evaluation results on a user interface;

[1520] an emotion engine means for recognizing emotions from the posted content;

[1521] means for integrating the evaluation result and the emotion recognition result;

[1522] A system including:

[1523] (Claim 2)

[1524] The system of claim 1, wherein the fake news detection algorithm means is a means for evaluating the likelihood of fake news based on text input on a five-point scale.

[1525] (Claim 3)

[1526] The system of claim 1, further comprising means for visually displaying the evaluation results as a fake level and a confidence level. [Explanation of symbols]

[1527] 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 fake news detection algorithmic means for evaluating the content of posts; means for receiving the posted content from a terminal; means for performing an evaluation of the posted content using the algorithm means; means for transmitting the evaluation result to a terminal; means for displaying the evaluation results on a user interface; A system including:

2. The system of claim 1, wherein the fake news detection algorithm means is a means for evaluating the likelihood of fake news based on text input on a five-point scale.

3. The system according to claim 1 , further comprising means for visually displaying the evaluation results as a fake level and a confidence level.

Images