System

Abstract

A system is provided.SOLUTION: A system, comprising: means for inputting a news article by a user; means for transmitting the input news article to a server; means for analyzing the news article and extracting a main keyword by the server; means for generating an Internet search query based on the extracted keyword and collecting related information; means for determining authenticity of the news based on the collected data and calculating a certainty factor; means for transmitting the determination result, the certainty factor, and ground information to a terminal; and means for displaying a result received by the terminal to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Fake news abounds on the Internet, causing problems for society. The lack of a system for efficiently and automatically determining the reliability of information users receive leads to decisions and actions based on erroneous information, which can lead to the spread of untrue information. In such a situation, it is difficult for society to act based on accurate information, so there is a need for a system that can quickly and reliably determine the authenticity of news. [Means for solving the problem]

[0005] This invention provides a system including: a means for a user to input a news text; a means for transmitting the input news text to a server; a means for the server to analyze the news text and extract key keywords; a means for generating an internet search query based on the extracted keywords and collecting related information; a means for determining the veracity of the news based on the collected data and calculating a confidence level; a means for transmitting the determination result, the confidence level, and supporting information to a terminal; and a means for displaying the results received by the terminal to the user. A generative AI model determines the veracity of the news and compares the collected data with a database of past truth determinations, enabling a highly reliable truth determination. Furthermore, providing the confidence level and supporting information makes it easier for users to understand the determination result and make decisions based on reliable information.

[0006] "News text" refers to text data that includes news reports and information published in newspaper articles, online media, etc.

[0007] A "server" is a computer system that provides data and resources to other computers via a network.

[0008] A "terminal" is a device such as a computer or smartphone that is operated by a user.

[0009] "Users" refer to individuals or groups who manipulate the system and attempt to verify the authenticity of news.

[0010] "Analysis" is the process of converting input news text into a format that a computer can understand and extracting meaning and important keywords.

[0011] A "keyword" is an important word or phrase in a news article, and is an element that plays a key role in the search and judgment process.

[0012] An "Internet search query" is a query to a search engine used to locate information on the Internet.

[0013] "Related information" refers to data and articles related to the news content obtained through an Internet search.

[0014] A "generative AI model" is an algorithm or program that is trained to use artificial intelligence to determine whether news is true or false.

[0015] "Truth-checking" is the process of determining whether news is true or false.

[0016] "Confidence" is an indicator that shows how confident the generative AI model is in the veracity of the news.

[0017] "Evidence" refers to the sources of information and evidential data used to determine the veracity of news. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The system of the present invention includes a means for determining the authenticity of news texts entered by users and displaying the results. This system performs processing in cooperation with users, terminals, and a server.

[0040] overview

[0041] The user inputs a news text through their device and sends a request to verify its authenticity. The device analyzes the input news text and sends it to the server. The server analyzes the received news text to extract key keywords and collects related information from internet search engines. It then uses a generative AI model to determine the authenticity of the news and calculates the confidence level and evidence information. Finally, the determination result is sent to the device and displayed to the user.

[0042] Embodiment

[0043] Entering and sending news

[0044] User: Enter the news text into the input field on the device and click the "Confirm" button.

[0045] Terminal: Converts the input news text into a JSON format request and sends it to the server.

[0046] Receiving and analyzing news data

[0047] Server: Receives requests sent from the device and analyzes the news text. First, it extracts key keywords, such as "football player," "club," and "transfer."

[0048] Internet information search

[0049] Server: Generates search queries based on the extracted keywords and uses search engine APIs to collect relevant information from the Internet. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[0050] Information collection and analysis

[0051] Server: The collected relevant information is compared with past truth-determining data stored in a database. The generative AI model analyzes this data and executes a process to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[0052] Calculation of judgment results and confidence

[0053] Server: Calculates the confidence level based on the truthfulness judgment results. For example, if there are multiple highly reliable sources, the confidence level is calculated as 85%. It also compiles the links and content of each source used as evidence.

[0054] Generation and notification of judgment results

[0055] Server: Generates a response to send the judgment result, confidence level, and evidence information to the terminal.

[0056] Terminal: Analyzes the response received from the server and displays the result to the user in a human-readable format, for example, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0057] User: Check the displayed judgment result, confidence level, and supporting information, and use it as reliable information.

[0058] Specific examples

[0059] For example, if a user inputs the news that "a famous soccer player has transferred to a new club," the process proceeds as follows:

[0060] 1. The user enters the news text into the terminal and presses the "Confirm" button.

[0061] 2. The terminal sends the entered news text to the server.

[0062] 3. The server analyzes the news text and extracts the main keywords: "football player," "club," and "transfer."

[0063] 4. The server generates internet search queries based on these keywords and uses internet search engines to gather relevant information.

[0064] 5. The server determines the authenticity of the news based on the collected information and calculates the confidence level. For example, if the transfer is announced on the player's official website, it is determined to be true with a high probability, with a confidence level of 85%.

[0065] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[0066] 7. The device displays the received information to the user, for example, "This news is highly likely to be true. Confidence level is 85%. Basis: The player's official website has announced the transfer."

[0067] 8. The user acts based on the displayed judgment result, confidence level, and supporting information.

[0068] In this way, the system achieves efficient and reliable news authenticity determination.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. The news sentence may include, for example, "A famous soccer player has transferred to a new club."

[0072] Step 2:

[0073] The device receives the news text entered by the user, converts it into an appropriate data format (e.g., JSON), and then sends a request containing the news text to the server.

[0074] Step 3:

[0075] The server receives a request from the device. It performs initial processing to analyze the news text and extracts key keywords from the text. For example, keywords such as "football player," "club," and "transfer" are extracted.

[0076] Step 4:

[0077] The server generates an internet search query based on the extracted keywords, and then combines the keywords appropriately to create a query to search for related information on the internet using a search engine API.

[0078] Step 5:

[0079] The server uses a search engine API to perform an internet search, collects relevant information, and retrieves data from sports news sites, players' official social media accounts, club official announcements, etc.

[0080] Step 6:

[0081] The server compares the collected information with past truth-determination data stored in a database, and uses a generative AI model to analyze the collected information and past cases to determine the truth of the news.

[0082] Step 7:

[0083] The server calculates the confidence level of the news based on the results of the truth judgment. For example, if there are many matches with highly reliable sources (such as official websites), the confidence level will be high. Specifically, the confidence level may be calculated as 85%.

[0084] Step 8:

[0085] The server compiles the news verdict, confidence level, and evidence and generates a response that includes a detailed explanation of the verdict and links to the sources used.

[0086] Step 9:

[0087] The server generates a response and sends it to the terminal, which receives it and analyzes it.

[0088] Step 10:

[0089] The device displays the received judgment result, confidence level, and evidence information to the user. For example, it displays, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0090] Step 11:

[0091] The user can check the displayed judgment result, confidence level, and supporting information, and use it as reliable information. The user can make a decision based on this information and decide on their next action.

[0092] Example 1

[0093] 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."

[0094] In recent years, the amount of false news and information on the Internet has been increasing, creating a need for a system that can quickly and accurately determine whether the news is true or false. However, conventional methods require time to collect and analyze information, making it difficult for users to make decisions based on reliable information. Therefore, there is a need to develop a system that can quickly and accurately determine the truth of news and provide the results to users.

[0095] 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.

[0096] In this invention, the server includes means for converting news texts into JSON format requests, means for using a natural language processing library to extract key keywords from the news texts, means for using a search engine API to collect related information from online sources using the extracted keywords, means for generating and inputting prompts into a generative AI model to determine the authenticity of the news, and means for converting the determination result into a JSON format response. This makes it possible to quickly and accurately determine the authenticity of news texts entered by users and provide the results to the users.

[0097] "News text" is text data that is provided in the form of user input and is intended to report news or provide information.

[0098] The "server" is a centralized computer system that performs multiple data processing operations, such as analyzing news text, extracting keywords, collecting internet information, determining authenticity using generative AI models, and providing the results.

[0099] A "terminal" is a device, such as a computer, smartphone, or tablet, that allows a user to input news text and receive and display responses from the server.

[0100] A "natural language processing library" is a software tool for analyzing news texts and extracting key keywords. Examples include NLTK and SpaCy.

[0101] A "search engine API" is a program interface for automatically collecting information related to specific keywords from the Internet. Examples include the Google Search API and the Bing Search API.

[0102] A "generative AI model" is an artificial intelligence model that determines the veracity of news based on collected data. A specific example is OpenAI's GPT series.

[0103] A "prompt" is text data that is input into a generative AI model and includes news text and related information.

[0104] "JSON" is a lightweight data interchange format for storing and transmitting data. It stands for JavaScript Object Notation.

[0105] An "HTTP POST request" is an Internet protocol for sending data from a client (terminal) to a server.

[0106] The system of the present invention provides a means for users to quickly and accurately determine the authenticity of news articles. The system is composed of a user, a terminal, and a server.

[0107] First, a user inputs a news sentence into the device, which then converts the input news sentence into a JSON-formatted request and sends it to the server as an HTTP POST request. JSON is a lightweight data exchange format used for data storage and transmission.

[0108] The server receives the request in JSON format and uses a natural language processing library (e.g., NLTK or SpaCy) to parse the news text, allowing it to extract key keywords (e.g., "football player," "club," "transfer," etc.) from the news text.

[0109] The server then generates an internet search query based on the extracted keywords and uses a search engine API (e.g., Google Search API or Bing Search API) to collect related information, which is set to come from reliable sources (e.g., news sites, official social media, official announcements, etc.).

[0110] The collected related information is stored on a server and compared with a database of past truth judgments. In this process, a generative AI model (such as OpenAI's GPT series) is used to judge the truth of the news. The prompts input to the generative AI model include the news text and related information, and the model outputs a result based on this.

[0111] For example, a concrete example of a prompt would be:

[0112] "Please determine whether this news statement is true or false: A famous soccer player has moved to a new club."

[0113] The generative AI model determines the veracity of news based on collected information and past data, calculates the confidence level, and generates a response in JSON format that is sent from the server to the device.

[0114] The device analyzes the JSON response and displays the results to the user. The results include the news's veracity, confidence level, and evidence, and may be displayed in a format such as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0115] As described above, the user, terminal, and server components work together to process and calculate data, enabling the truth or falsity of news to be determined quickly and accurately.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The user inputs a news sentence.

[0119] Specific operation: The user enters a news sentence (e.g., "A famous soccer player has transferred to a new club") into the input field of the terminal and clicks the "Confirm" button.

[0120] Input: News article

[0121] Output: Triggered when the user presses the Enter button

[0122] Step 2:

[0123] The device converts the news text into a JSON format request and sends it to the server.

[0124] Specific operation: The device converts the news text into JSON format and sends it to the server as an HTTP POST request, including metadata such as the user ID and timestamp.

[0125] Input: news article, user ID, timestamp

[0126] Output: The request sent to the server in JSON format.

[0127] Step 3:

[0128] The server parses the JSON data and extracts the news text.

[0129] Specific operation: The server parses the received JSON data and extracts the news text.

[0130] Input: JSON formatted request

[0131] Output: News article

[0132] Step 4:

[0133] The server uses natural language processing libraries to extract key keywords from news texts.

[0134] What it does: The server uses a natural language processing library (e.g., NLTK or SpaCy) to analyze the news text and extract key keywords (e.g., "football player," "club," "transfer").

[0135] Input: News article

[0136] Output: Extracted keywords

[0137] Step 5:

[0138] The server generates a search query based on the extracted keywords and collects related information using a search engine API.

[0139] Specific operation: The server sends a search query to the Google Search API or Bing Search API to collect related information. The information obtained is obtained from reliable sources (news sites, official social media, official announcements, etc.).

[0140] Input: Extracted keywords

[0141] Output: Relevant information collected

[0142] Step 6:

[0143] The server compares the collected information with a database of past authenticity determinations.

[0144] Specific operation: The server stores the collected information in an internal database and compares it with a database of past authenticity judgments. In this process, it identifies highly reliable information.

[0145] Input: Relevant information collected

[0146] Output: Matching result

[0147] Step 7:

[0148] The server inputs prompts into the generative AI model to determine whether the news is true or false.

[0149] Specific operation: The server generates and inputs a prompt to a generative AI model (e.g., OpenAI's GPT-series). For example, the prompt might be in the form of "Please determine the truth or falsity of this news sentence: A famous soccer player has transferred to a new club." The generative AI model performs analysis based on this prompt.

[0150] Input: News article, collected related information

[0151] Output: True / false result, confidence level

[0152] Step 8:

[0153] The server converts the result of the judgment into a JSON format response and sends it to the terminal.

[0154] Specific operation: The server receives the output of the generative AI model, converts the judgment result, confidence level, and evidence information into a JSON-formatted response, and sends this to the terminal as an HTTP response.

[0155] Input: True / false judgment result, confidence level, evidence information

[0156] Output: JSON response

[0157] Step 9:

[0158] The terminal analyzes the received information and displays the results to the user.

[0159] Specific operation: The device analyzes the JSON response and displays the results in a format that is easy for the user to understand. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0160] Input: JSON format response

[0161] Output: Displayed judgment result, confidence level, and evidence information

[0162] Step 10:

[0163] The user checks the displayed information and makes a decision.

[0164] Specific operation: The user checks the displayed judgment result, confidence level, and supporting information to determine whether the news is true or false. This will help them decide their next action.

[0165] Input: Displayed judgment result, confidence level, and evidence information

[0166] Output: User decisions and actions

[0167] (Application example 1)

[0168] 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."

[0169] In today's information society, false information and misinformation circulating online have become a serious problem. Dealing with this problem is extremely difficult, especially because information spreads rapidly through news articles and social media. Existing methods struggle to quickly and accurately determine the authenticity of information, putting many people at risk of being misled by false information. To solve this problem, an efficient and reliable system for determining whether information is true or false is needed.

[0170] 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.

[0171] In this invention, the server includes a means for analyzing information text and extracting key words and phrases, a means for determining the authenticity of information based on collected data and calculating the degree of certainty, a means for determining the authenticity of information using a generative AI model, and a means for comparing the results with a database of past authenticity determinations, thereby enabling the authenticity of information to be determined quickly and accurately over the Internet.

[0172] "Information text" refers to textual data that users input into the system, including news articles and social media posts that are subject to evaluation.

[0173] "Communication equipment" refers to network equipment such as servers and devices that send and receive information and perform analysis and judgment.

[0174] "Key words" refer to important keywords and phrases extracted from the input information text to determine its authenticity.

[0175] An "information search query" is a set of search terms generated based on a key phrase to gather related information from the Internet.

[0176] "Related information" refers to data collected from the Internet through information search queries and used as the basis for determining authenticity.

[0177] "Confidence" is a percentage or score that indicates how certain you can determine whether a piece of information is true or false, based on the relevant information collected.

[0178] The "judgment result" is a final evaluation indicating whether the information text is true or not, and includes the degree of certainty and evidence information.

[0179] A "terminal" is a device used by a user for input and display, and includes a smartphone, a computer, and the like.

[0180] This invention is a system that judges the authenticity of information text input by a user. This system is mainly composed of three elements: a user, a terminal, and a server.

[0181] User operations

[0182] A user can use a device such as a smartphone or computer to input information text, such as the text of a news article or a social media post. After inputting, the user taps or clicks a "Confirm" button.

[0183] Device Features

[0184] The terminal receives information text entered by the user, converts it into JSON format, and sends it to the server. The terminal functions as an interface for sending and receiving information.

[0185] Server Processing

[0186] The server analyzes the received information text and extracts key words and phrases using natural language processing technology. Next, it generates an information search query based on the extracted key words and phrases and uses a search engine API to collect related information from the Internet. Data is collected from reliable sources (e.g., official websites, news sites, etc.).

[0187] Based on the collected data, the server uses a generative AI model to determine the truth of the information text and calculates its confidence level. This generative AI model also compares it with a database of past truth-based judgments. For example, if similar information has been judged to be true in the past, the confidence level will increase.

[0188] The server finally transmits the judgment result, the confidence level, and the basis information thereof to the terminal.

[0189] Display of judgment results

[0190] The device displays the judgment result received from the server to the user. Specifically, the result is provided in the form of "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer." This allows the user to quickly confirm the authenticity of the information.

[0191] Hardware and software used

[0192] Hardware: smartphones, computers, servers

[0193] Software: Python, Flask (server side), requests library (client side), generative AI model, search engine API

[0194] Specific examples

[0195] For example, if a user enters the news "A famous soccer player has transferred to a new club," the server analyzes the sentence and extracts key words such as "soccer player," "club," and "transfer." It then uses an information search query generated based on these words to gather related information from the internet. Based on the collected information, the generative AI model determines whether the information is true or false, and calculates the confidence level and supporting information. Finally, these results are sent to the device and displayed to the user.

[0196] Example prompt sentence:

[0197] "Based on structured data, determine whether the news item 'A famous soccer player has transferred to a new club' is true."

[0198] Thus, the present invention is a system that quickly and accurately determines the authenticity of information and provides the user with the results, thereby effectively resolving the issue of reliability in the information society.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The user enters the information text into the input field of the terminal and clicks the "Confirm" button.

[0202] Input: Informational text entered by the user (e.g., "A famous soccer player has moved to a new club.")

[0203] Output: The information text is sent to the next processing step.

[0204] Step 2:

[0205] The terminal receives the information text entered by the user, converts it into JSON format, and sends it to the server.

[0206] Input: Informational text

[0207] Data processing: Convert information text into JSON format

[0208] Output: Request data in JSON format

[0209] Step 3:

[0210] The server analyzes the information text received from the terminal and extracts key words and phrases using natural language processing technology.

[0211] Input: JSON formatted information text

[0212] Data analysis: Extraction of key terms (e.g. "football player", "club", "transfer")

[0213] Output: Key phrase list

[0214] Step 4:

[0215] The server generates an information search query based on the extracted key words and phrases and collects related information from the Internet using a search engine API.

[0216] Input: Key phrase list

[0217] Data Computing: Information Retrieval Query Generation and Internet Searching

[0218] Output: A list of collected relevant information

[0219] Step 5:

[0220] The server uses a generative AI model based on the collected related information to determine the authenticity of the information text and calculates its confidence level. It also compares it with a database of past authenticity determinations.

[0221] Input: List of collected related information, generative AI model, past truth judgment data

[0222] Data analysis: True / false determination and confidence calculation (e.g., confidence level 85%)

[0223] Output: Verification result, confidence level, and evidence

[0224] Step 6:

[0225] The server transmits the determination result, the confidence level, and the basis information to the terminal.

[0226] Input: Verification result, confidence level, and evidence

[0227] Output: Data sent as the judgment result

[0228] Step 7:

[0229] The terminal analyzes the judgment result received from the server and displays it to the user.

[0230] Input: Verification result, confidence level, and evidence received from the server

[0231] Data processing: converting data into a human-readable format

[0232] Output: The result shown to the user (e.g., "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer.")

[0233] This series of processes makes it possible to quickly and accurately determine the authenticity of the information text and provide the result to the user.

[0234] 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.

[0235] The system of the present invention determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[0236] overview

[0237] The user inputs a news text through their device and sends a request to confirm its authenticity. The device uses an emotion engine to obtain the user's emotional information along with the input news text, and sends it to the server. The server analyzes the received news text, extracts key keywords, and collects related information from internet search engines. Next, it uses a generative AI model to determine the authenticity of the news, calculating the confidence level and evidence information taking into account the emotion engine data. Finally, the determination result is sent to the device and appropriately displayed to the user.

[0238] Embodiment

[0239] Enter news and get sentiment

[0240] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice using, for example, a camera or microphone to obtain emotional data.

[0241] Terminal: Converts news text and emotion data (e.g., "surprise," "skepticism," "affirmation," etc.) into a JSON-formatted request and sends it to the server.

[0242] Receiving and analyzing news data

[0243] Server: Receives news text and emotion data sent from the device. Analyzes the news text and extracts key keywords. For example, keywords such as "famous athletes," "clubs," and "transfers" are obtained.

[0244] Internet information search

[0245] Server: Generates internet search queries based on the extracted keywords and collects related information from the internet via search engine APIs. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[0246] Information collection and analysis

[0247] Server: Compares the collected relevant information with past truth-determination data stored in a database. Using a generative AI model, analyzes the collected information and past cases to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[0248] Calculation of judgment results and confidence

[0249] Server: Based on the truth / falseness judgment result, calculates the confidence level of the news. Also, taking into account the user's emotional data provided by the emotion engine, adjust the tone and format of the displayed information. For example, if the user is "surprised," provide more detailed reasons.

[0250] Generation and notification of judgment results

[0251] Server: Generates a response containing the judgment result, confidence level, and rationale information, including adjusting the display format based on the emotion data.

[0252] Terminal: Receives and analyzes the response from the server.

[0253] Displaying the results

[0254] Device: The received judgment result, confidence level, and evidence information are displayed to the user. For example, it is displayed as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0255] User: Check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy.

[0256] Specific examples

[0257] For example, if a user inputs news that "a famous athlete has transferred to a new club," the process proceeds as follows:

[0258] 1. The user enters the news text into the device and presses the "Confirm" button. At this time, the device's camera and microphone analyze the user's facial expressions and voice, and "surprise" is captured as emotional data.

[0259] 2. The device sends the input text and the "surprise" emotion data to the server.

[0260] 3. The server analyzes the news text and extracts the main keywords "athlete," "club," and "transfer."

[0261] 4. The server generates internet search queries based on these keywords and gathers relevant information from internet search engines.

[0262] 5. The server analyzes the collected information and determines its authenticity. For example, it may determine that "there is a high probability that the information is true because the player's official website has announced the transfer," and calculate a confidence level of 85%. It also adjusts the display of information to be more detailed, taking into account the emotional data "surprise."

[0263] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[0264] 7. The device analyzes the results received and displays the message, "There is a high probability that this news is true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[0265] 8. The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[0266] In this way, the system achieves efficient and reliable news veracity determination and provides information in a manner that takes into consideration the user's feelings.

[0267] The processing flow will be explained below.

[0268] Step 1:

[0269] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. For example, the user inputs the sentence "A famous athlete has transferred to a new club."

[0270] Step 2:

[0271] The device receives the news text entered by the user, and at the same time, it uses a camera and microphone to record the user's facial expressions and voice, and then uses the emotion engine to obtain emotional data. In this case, the emotion of "surprise" is recognized.

[0272] Step 3:

[0273] The device generates a request in JSON format containing the input news text and the acquired emotion data (for example, data indicating "surprise") and sends it to the server.

[0274] Step 4:

[0275] The server receives the request sent from the terminal and analyzes the news text. It then performs a process to extract key keywords from the news text, such as "athlete," "club," and "transfer."

[0276] Step 5:

[0277] The server generates an internet search query based on the extracted keywords, for example, "sports player transfer club," and uses a search engine API to gather related information.

[0278] Step 6:

[0279] The server uses search engine APIs to retrieve relevant information from the internet, collecting data from reliable sources (sports news sites, official social media accounts of players, official club announcements, etc.).

[0280] Step 7:

[0281] The server uses a generative AI model to determine the authenticity of news based on the information collected. It compares this with a past database and uses it as strong evidence when, for example, a player's official website announces a transfer.

[0282] Step 8:

[0283] The server calculates the confidence level based on the result of the truth / false judgment, and sets it to, for example, 85%. At the same time, it reflects the user's emotional data provided by the emotion engine and adjusts the level to provide more detailed information and evidence because the user is feeling "surprised."

[0284] Step 9:

[0285] The server generates a response including the judgment result, the confidence level, and the evidence information, and the response includes adjusting the display format according to the emotion.

[0286] Step 10:

[0287] The server sends the generated response to the terminal, which receives the response.

[0288] Step 11:

[0289] The device analyzes the response received and displays it to the user in a format that is easy for humans to understand. For example, it displays, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0290] Step 12:

[0291] The user can check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy. At this time, the display format adjusted to take into account emotional data makes it easier for the user to understand the information.

[0292] Example 2

[0293] 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."

[0294] Conventional news authenticity determination systems have not been able to provide users with information that takes into account their emotions, and have been unable to improve their user experience. Furthermore, there has been a lack of means to provide a higher degree of certainty by taking emotional data into account when determining the authenticity of news.

[0295] 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.

[0296] In this invention, the server includes means for analyzing news texts and extracting key keywords, means for generating internet search queries based on the extracted keywords and collecting related information, means for determining the authenticity of the news using a generative AI model based on the collected data and calculating a confidence level, and means for adjusting the display format of the information in consideration of emotional data. This enables optimal information provision that takes user emotions into consideration and improves the confidence level of news authenticity determinations.

[0297] A "user" is someone who wants to operate the system to input news text and verify its authenticity.

[0298] "Device" refers to a device that receives news text and emotion data entered by a user and communicates with the server. This includes computers, smartphones, tablets, etc.

[0299] The "server" is a central computer system that receives news text and emotion data, analyzes them, and determines whether the news is true or false.

[0300] "News text" refers to information entered by a user, including content reporting new facts or events.

[0301] "Emotion data" refers to data that indicates the emotional state of the user, as obtained from facial expressions, tone of voice, and the like.

[0302] "News analysis" refers to the process of breaking down news texts linguistically and understanding their meaning.

[0303] "Keyword extraction" is the process of extracting important words and phrases from news text.

[0304] "Internet search query" refers to a search word or phrase used to retrieve information on the Internet.

[0305] "Collecting related information" is the process of obtaining information related to keywords from the Internet using an Internet search engine or the like.

[0306] A "generative AI model" is an algorithm that uses artificial intelligence to analyze input data and generate an output based on the results. Generative AI models are used to determine the veracity of news.

[0307] "Truth determination" is the process of determining whether a piece of news is true or not.

[0308] "Confidence" is a number that indicates how certain you are about whether the news is true.

[0309] "Adjusting the display format of information" refers to displaying the determination results and grounds information in an appropriate format taking into account the user's emotional data.

[0310] "Evidence" refers to the data and sources used to determine the veracity of news.

[0311] "Response JSON" refers to a data format (JSON) that is sent from the server to the terminal and contains the judgment result, certainty, and evidence information.

[0312] MODE FOR CARRYING OUT THE INVENTION

[0313] The present invention is a system that determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[0314] Entering news and obtaining sentiment data

[0315] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, emotion data is collected using the device's camera and microphone. For example, if a user enters news such as "A famous athlete has transferred to a new club," the device's camera captures the user's facial expressions (surprise, doubt, affirmation, etc.), and the microphone analyzes the tone of voice to collect emotion data.

[0316] Terminal: Converts the input news text and emotion data into JSON format and sends it to the server.

[0317] News data analysis and keyword extraction

[0318] Server: Analyzes the received news text and sentiment data to extract key keywords. For example, it uses a morphological analysis tool to extract keywords such as "athlete," "club," and "transfer."

[0319] Collecting Internet Information

[0320] Server: Generates internet search queries based on the extracted keywords and uses internet search engines (e.g., Google API) to collect related information, including reliable news sites and official announcements.

[0321] Analysis of information and determination of authenticity

[0322] Server: Analyzes the collected information using a generative AI model (e.g., OpenAI GPT-4) to determine the truth of the news. For example, if the collected related information is that "the player's official website has announced a transfer," it determines that "this news is highly likely to be true" and calculates the confidence level.

[0323] Calculating confidence and linking emotional data

[0324] Server: Calculates the confidence level of the news based on the truthfulness judgment results, and also adjusts the display format of the information taking into account emotional data. For example, if the user is feeling "surprised," the server adjusts the display format to provide detailed supporting information.

[0325] Generation and notification of judgment results

[0326] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal.

[0327] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0328] Specific examples

[0329] For example, if a user types in the news "A famous sports player has moved to a new club," the system will be prompted with the following:

[0330] 1. Example of news content input:

[0331] "A famous athlete has moved to a new club. Please tell me if this is true."

[0332] 2. Example prompts for determining whether a news story is true or false:

[0333] "Please determine whether the following news items are true or false. Please indicate the accuracy of the news items as a percentage. Also, please provide supporting information. News: 'A famous athlete has moved to a new club.'"

[0334] In this way, the invention can efficiently determine the truth of news while taking into consideration the user's feelings, and provide highly reliable information.

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] Step 1: Input news text and obtain sentiment data

[0337] User: Enters a news sentence and clicks the "Confirm" button. The input here is the news sentence. Specifically, the user enters "A famous athlete has transferred to a new club" into the device's input field and presses the "Confirm" button on the device. At this time, the device's camera captures the user's facial expression, and the microphone analyzes the user's tone of voice to collect emotional data. As a result, the input is the news sentence, and the output is emotional data.

[0338] Step 2: Send news and sentiment data

[0339] Terminal: The input news text and the acquired emotion data are converted into JSON format and sent to the server. In this process, the input is the news text and emotion data, and the output is JSON format data. Specifically, JSON data containing the news text "A famous athlete has transferred to a new club" and the emotion data "surprise" is generated and sent to the server.

[0340] Step 3: Analyzing news data and extracting keywords

[0341] Server: Receives JSON data and analyzes the news sentence to extract key keywords. The input of this step is news data in JSON format, and the output is the extracted keywords. Specifically, it uses a morphological analysis tool to analyze the news sentence "A famous athlete has transferred to a new club" and extracts keywords such as "athlete," "club," and "transfer."

[0342] Step 4: Collecting Internet Information

[0343] Server: Generates internet search queries based on the extracted keywords and collects related information. The input to this step is the extracted keywords, and the output is the collected related information. Specifically, using the Google API, an internet search for "sports player," "club," and "transfer" is performed, and related information is collected from reliable news sites and official announcements.

[0344] Step 5: Analyze the information and determine its authenticity

[0345] Server: Uses a generative AI model to determine the truth of the news based on the collected related information. The input to this step is the collected related information, and the output is the truth determination result and confidence level. Specifically, the collected information is analyzed using GPT-4, and it is determined that "there is a high probability that the news is true because the transfer announcement was made on the player's official website," with a confidence level of 85%.

[0346] Step 6: Calculating confidence and linking emotion data

[0347] Server: Calculates the confidence level of the news based on the truth judgment result, and also adjusts the display format of the information taking into account the user's emotional data. The input is the truth judgment result and emotional data, and the output is the information in the adjusted display format. Specifically, if the emotional data is "surprise," the server adjusts to provide more detailed supporting information.

[0348] Step 7: Generate judgment results and notify the device from the server

[0349] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal. The input to this step is the adjusted display format information, and the output is response JSON data. Specifically, JSON data containing the truth judgment result "True," confidence level "85%," and evidence information is generated and sent to the terminal.

[0350] Step 8: Displaying the results and evidence

[0351] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. The input to this step is the response JSON data from the server, and the output is the judgment result that is displayed to the user. Specifically, the terminal analyzes the result received and displays "This news is highly likely to be true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[0352] (Application example 2)

[0353] 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."

[0354] In recent years, the internet has become overflowing with news information, creating a need for a fast and accurate way to determine its veracity. Furthermore, it is necessary to consider how the emotions of users receiving news influence their judgments. To solve this problem, it is desirable to develop a system that not only determines the veracity of news, but also provides appropriate information based on users' emotional information. It is considered particularly important to apply this technology to fields where emotions have a direct impact, such as electronic payment services.

[0355] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0356] In this invention, the server includes means for a user to input a news text, means for transmitting the input news text to the server, means for the server to analyze the news text and extract key keywords, means for generating an Internet search query based on the extracted keywords and collecting related information, means for determining the authenticity of the news based on the collected data and calculating a confidence level, means for transmitting the determination result, the confidence level, and evidence information to a terminal, means for displaying the results received by the terminal to the user, and means for acquiring emotional information and adjusting the determination result. This makes it possible to accurately determine the authenticity of a news article taking into account the user's emotional information and provide appropriate information to the user.

[0357] "Means for users to input news text" refers to an interface that allows users to input news or information in text form.

[0358] "Means for sending input news text to a server" refers to a process that provides a function for sending news text input by a user to a server via a network.

[0359] "Means by which the server analyzes news texts and extracts key keywords" refers to the process by which the server analyzes the news texts it receives using natural language processing technology, etc., and finds key keywords from within them.

[0360] "Means for generating internet search queries based on the extracted keywords and collecting related information" refers to the function of using the extracted keywords to run queries on a search engine and collect related information from the internet.

[0361] "Means for determining the veracity of news based on collected data and calculating the degree of certainty" refers to the process of analyzing collected information using a generative AI model, determining whether the news is true, and then calculating the degree of certainty as a number.

[0362] "Means for transmitting the judgment result, the certainty factor, and the information on the basis thereof to the terminal" refers to the function of the server to transmit the judgment result of the truth of the news, the certainty factor, and the information on the basis thereof to the terminal.

[0363] "Means for displaying the results received by the terminal to the user" refers to an interface for displaying the news truth determination results and related information received by the terminal from the server in an easy-to-understand manner for the user.

[0364] "Means for acquiring emotional information and adjusting the judgment result" refers to a function for acquiring the user's emotional state using a device such as a camera or microphone, and reflecting that emotional information in the judgment result.

[0365] This invention is a system that allows users to input news text and judge its authenticity. This system is composed of a variety of hardware and software, including terminals, servers, emotion engines, and generative AI models.

[0366] Hardware and software used

[0367] Hardware:

[0368] Smartphone: Equipped with a camera and microphone.

[0369] software:

[0370] Emotion engine: EmotionsAPI

[0371] Generative AI model: GPT-4

[0372] Database: MySQL

[0373] Internet search engine: Google Search API

[0374] Payment service API: Stripe

[0375] Specific examples of processing

[0376] The user enters a news sentence into the input field on their smartphone and clicks the "Confirm" button. The device uses the camera and microphone to capture the entered news sentence along with the user's emotional information (e.g., "surprise," "skepticism," "affirmation," etc.) and sends it to the server.

[0377] The server analyzes the received news text and extracts key keywords. For example, if the news text contains the content "A famous athlete has transferred to a new club," the key keywords extracted are "famous athlete," "club," and "transfer." Based on these keywords, the server generates an internet search query and collects related information from the internet (e.g., sports news sites, the athlete's official social media, official club announcements, etc.) via the Google Search API.

[0378] The server compares the collected information with past truth-judgment data stored in a database and uses a generative AI model (GPT-4) to determine whether the news is true. For example, if a player's official website announces a transfer, this is used as strong evidence.

[0379] The server then calculates the confidence level of the news based on the truthfulness judgment result. Furthermore, it adjusts the tone and format of the displayed information taking into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "surprised," it provides more detailed supporting information.

[0380] Finally, a response containing the judgment result, confidence level, and evidence information is generated and sent to the device. The device then displays the received judgment result, confidence level, and evidence information to the user. For example, it may display something like, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0381] Prompt Sentence Examples

[0382] Please determine whether the following news statements are true or false, provide relevant supporting information, and indicate your confidence in the news as a percentage.

[0383] News text: "A well-known company has launched a new product."

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] The user enters a news sentence into the input field on the smartphone and clicks the "Confirm" button.

[0387] Input: News text entered by the user.

[0388] Output: The news text is sent to the terminal.

[0389] Step 2:

[0390] The device uses a camera and microphone to acquire information about the user's emotions.

[0391] Input: The user's facial expressions and tone of voice.

[0392] Output: The obtained emotion data (e.g., "surprise", "doubt", "affirmation", etc.).

[0393] Step 3:

[0394] The device converts the news text and emotion data into JSON format and sends it to the server.

[0395] Input: News text and sentiment data.

[0396] Output: JSON formatted data sent to the server.

[0397] Step 4:

[0398] The server analyzes the received news text and extracts key keywords.

[0399] Input: Received news article.

[0400] Output: Extracted key keywords, specifically, key words and phrases from news texts using natural language processing techniques.

[0401] Step 5:

[0402] The server generates internet search queries based on the extracted keywords and collects related information through the Google Search API.

[0403] Input: Extracted main keywords.

[0404] Output: Collected relevant information, including news sites, official social media accounts, and official announcements.

[0405] Step 6:

[0406] The server compares the collected information with past truth judgment data in the database and uses a generative AI model (GPT-4) to judge the truth of the news and calculate the confidence level.

[0407] Input: Collected information and past truth-check data.

[0408] Output: The truthfulness and confidence level of the news. Specifically, the collected information is compared with the data in the database, and a generative AI model is used to arrive at a conclusion.

[0409] Step 7:

[0410] The server takes into account the user's emotional data and adjusts the tone and display format of the judgment result.

[0411] Input: True / false result, confidence level, and sentiment data.

[0412] Output: A response with the adjusted verdict. For example, "If the user is surprised, provide further detailed justification information."

[0413] Step 8:

[0414] The server transmits the determination result, the confidence level, and the basis information to the terminal as a final response.

[0415] Input: The adjusted response.

[0416] Output: Data sent to the device.

[0417] Step 9:

[0418] The terminal displays the received determination result, confidence level, and grounds information to the user.

[0419] Input: The data received from the server.

[0420] Output: The result displayed to the user. For example, "This news is highly likely to be true. Confidence is 85%. Evidence: The official website has announced the transfer."

[0421] Step 10:

[0422] The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[0423] Input: The result displayed on the terminal.

[0424] Output: The user's next action, such as further research based on the information being trusted or purchasing action.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] [Second embodiment]

[0429] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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."

[0441] The system of the present invention includes a means for determining the authenticity of news texts entered by users and displaying the results. This system performs processing in cooperation with users, terminals, and a server.

[0442] overview

[0443] The user inputs a news text through their device and sends a request to verify its authenticity. The device analyzes the input news text and sends it to the server. The server analyzes the received news text to extract key keywords and collects related information from internet search engines. It then uses a generative AI model to determine the authenticity of the news and calculates the confidence level and evidence information. Finally, the determination result is sent to the device and displayed to the user.

[0444] Embodiment

[0445] Entering and sending news

[0446] User: Enter the news text into the input field on the device and click the "Confirm" button.

[0447] Terminal: Converts the input news text into a JSON format request and sends it to the server.

[0448] Receiving and analyzing news data

[0449] Server: Receives requests sent from the device and analyzes the news text. First, it extracts key keywords, such as "football player," "club," and "transfer."

[0450] Internet information search

[0451] Server: Generates search queries based on the extracted keywords and uses search engine APIs to collect relevant information from the Internet. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[0452] Information collection and analysis

[0453] Server: The collected relevant information is compared with past truth-determining data stored in a database. The generative AI model analyzes this data and executes a process to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[0454] Calculation of judgment results and confidence

[0455] Server: Calculates the confidence level based on the truthfulness judgment results. For example, if there are multiple highly reliable sources, the confidence level is calculated as 85%. It also compiles the links and content of each source used as evidence.

[0456] Generation and notification of judgment results

[0457] Server: Generates a response to send the judgment result, confidence level, and evidence information to the terminal.

[0458] Terminal: Analyzes the response received from the server and displays the result to the user in a human-readable format, for example, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0459] User: Check the displayed judgment result, confidence level, and supporting information, and use it as reliable information.

[0460] Specific examples

[0461] For example, if a user inputs the news that "a famous soccer player has transferred to a new club," the process proceeds as follows:

[0462] 1. The user enters the news text into the terminal and presses the "Confirm" button.

[0463] 2. The terminal sends the entered news text to the server.

[0464] 3. The server analyzes the news text and extracts the main keywords: "football player," "club," and "transfer."

[0465] 4. The server generates internet search queries based on these keywords and uses internet search engines to gather relevant information.

[0466] 5. The server determines the authenticity of the news based on the collected information and calculates the confidence level. For example, if the transfer is announced on the player's official website, it is determined to be true with a high probability, with a confidence level of 85%.

[0467] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[0468] 7. The device displays the received information to the user, for example, "This news is highly likely to be true. Confidence level is 85%. Basis: The player's official website has announced the transfer."

[0469] 8. The user acts based on the displayed judgment result, confidence level, and supporting information.

[0470] In this way, the system achieves efficient and reliable news authenticity determination.

[0471] The processing flow will be explained below.

[0472] Step 1:

[0473] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. The news sentence may include, for example, "A famous soccer player has transferred to a new club."

[0474] Step 2:

[0475] The device receives the news text entered by the user, converts it into an appropriate data format (e.g., JSON), and then sends a request containing the news text to the server.

[0476] Step 3:

[0477] The server receives a request from the device. It performs initial processing to analyze the news text and extracts key keywords from the text. For example, keywords such as "football player," "club," and "transfer" are extracted.

[0478] Step 4:

[0479] The server generates an internet search query based on the extracted keywords, and then combines the keywords appropriately to create a query to search for related information on the internet using a search engine API.

[0480] Step 5:

[0481] The server uses a search engine API to perform an internet search, collects relevant information, and retrieves data from sports news sites, players' official social media accounts, club official announcements, etc.

[0482] Step 6:

[0483] The server compares the collected information with past truth-determination data stored in a database, and uses a generative AI model to analyze the collected information and past cases to determine the truth of the news.

[0484] Step 7:

[0485] The server calculates the confidence level of the news based on the results of the truth judgment. For example, if there are many matches with highly reliable sources (such as official websites), the confidence level will be high. Specifically, the confidence level may be calculated as 85%.

[0486] Step 8:

[0487] The server compiles the news verdict, confidence level, and evidence and generates a response that includes a detailed explanation of the verdict and links to the sources used.

[0488] Step 9:

[0489] The server generates a response and sends it to the terminal, which receives it and analyzes it.

[0490] Step 10:

[0491] The device displays the received judgment result, confidence level, and evidence information to the user. For example, it displays, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0492] Step 11:

[0493] The user can check the displayed judgment result, confidence level, and supporting information, and use it as reliable information. The user can make a decision based on this information and decide on their next action.

[0494] Example 1

[0495] 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."

[0496] In recent years, the amount of false news and information on the Internet has been increasing, creating a need for a system that can quickly and accurately determine whether the news is true or false. However, conventional methods require time to collect and analyze information, making it difficult for users to make decisions based on reliable information. Therefore, there is a need to develop a system that can quickly and accurately determine the truth of news and provide the results to users.

[0497] 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.

[0498] In this invention, the server includes means for converting news texts into JSON format requests, means for using a natural language processing library to extract key keywords from the news texts, means for using a search engine API to collect related information from online sources using the extracted keywords, means for generating and inputting prompts into a generative AI model to determine the authenticity of the news, and means for converting the determination result into a JSON format response. This makes it possible to quickly and accurately determine the authenticity of news texts entered by users and provide the results to the users.

[0499] "News text" is text data that is provided in the form of user input and is intended to report news or provide information.

[0500] The "server" is a centralized computer system that performs multiple data processing operations, such as analyzing news text, extracting keywords, collecting internet information, determining authenticity using generative AI models, and providing the results.

[0501] A "terminal" is a device, such as a computer, smartphone, or tablet, that allows a user to input news text and receive and display responses from the server.

[0502] A "natural language processing library" is a software tool for analyzing news texts and extracting key keywords. Examples include NLTK and SpaCy.

[0503] A "search engine API" is a program interface for automatically collecting information related to specific keywords from the Internet. Examples include the Google Search API and the Bing Search API.

[0504] A "generative AI model" is an artificial intelligence model that determines the veracity of news based on collected data. A specific example is OpenAI's GPT series.

[0505] A "prompt" is text data that is input into a generative AI model and includes news text and related information.

[0506] "JSON" is a lightweight data interchange format for storing and transmitting data. It stands for JavaScript Object Notation.

[0507] An "HTTP POST request" is an Internet protocol for sending data from a client (terminal) to a server.

[0508] The system of the present invention provides a means for users to quickly and accurately determine the authenticity of news articles. The system is composed of a user, a terminal, and a server.

[0509] First, a user inputs a news sentence into the device, which then converts the input news sentence into a JSON-formatted request and sends it to the server as an HTTP POST request. JSON is a lightweight data exchange format used for data storage and transmission.

[0510] The server receives the request in JSON format and uses a natural language processing library (e.g., NLTK or SpaCy) to parse the news text, allowing it to extract key keywords (e.g., "football player," "club," "transfer," etc.) from the news text.

[0511] The server then generates an internet search query based on the extracted keywords and uses a search engine API (e.g., Google Search API or Bing Search API) to collect related information, which is set to come from reliable sources (e.g., news sites, official social media, official announcements, etc.).

[0512] The collected related information is stored on a server and compared with a database of past truth judgments. In this process, a generative AI model (such as OpenAI's GPT series) is used to judge the truth of the news. The prompts input to the generative AI model include the news text and related information, and the model outputs a result based on this.

[0513] For example, a concrete example of a prompt would be:

[0514] "Please determine whether this news statement is true or false: A famous soccer player has moved to a new club."

[0515] The generative AI model determines the veracity of news based on collected information and past data, calculates the confidence level, and generates a response in JSON format that is sent from the server to the device.

[0516] The device analyzes the JSON response and displays the results to the user. The results include the news's veracity, confidence level, and evidence, and may be displayed in a format such as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0517] As described above, the user, terminal, and server components work together to process and calculate data, enabling the truth or falsity of news to be determined quickly and accurately.

[0518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0519] Step 1:

[0520] The user inputs a news sentence.

[0521] Specific operation: The user enters a news sentence (e.g., "A famous soccer player has transferred to a new club") into the input field of the terminal and clicks the "Confirm" button.

[0522] Input: News article

[0523] Output: Triggered when the user presses the Enter button

[0524] Step 2:

[0525] The device converts the news text into a JSON format request and sends it to the server.

[0526] Specific operation: The device converts the news text into JSON format and sends it to the server as an HTTP POST request, including metadata such as the user ID and timestamp.

[0527] Input: news article, user ID, timestamp

[0528] Output: The request sent to the server in JSON format.

[0529] Step 3:

[0530] The server parses the JSON data and extracts the news text.

[0531] Specific operation: The server parses the received JSON data and extracts the news text.

[0532] Input: JSON formatted request

[0533] Output: News article

[0534] Step 4:

[0535] The server uses natural language processing libraries to extract key keywords from news texts.

[0536] What it does: The server uses a natural language processing library (e.g., NLTK or SpaCy) to analyze the news text and extract key keywords (e.g., "football player," "club," "transfer").

[0537] Input: News article

[0538] Output: Extracted keywords

[0539] Step 5:

[0540] The server generates a search query based on the extracted keywords and collects related information using a search engine API.

[0541] Specific operation: The server sends a search query to the Google Search API or Bing Search API to collect related information. The information obtained is obtained from reliable sources (news sites, official social media, official announcements, etc.).

[0542] Input: Extracted keywords

[0543] Output: Relevant information collected

[0544] Step 6:

[0545] The server compares the collected information with a database of past authenticity determinations.

[0546] Specific operation: The server stores the collected information in an internal database and compares it with a database of past authenticity judgments. In this process, it identifies highly reliable information.

[0547] Input: Relevant information collected

[0548] Output: Matching result

[0549] Step 7:

[0550] The server inputs prompts into the generative AI model to determine whether the news is true or false.

[0551] Specific operation: The server generates and inputs a prompt to a generative AI model (e.g., OpenAI's GPT-series). For example, the prompt might be in the form of "Please determine the truth or falsity of this news sentence: A famous soccer player has transferred to a new club." The generative AI model performs analysis based on this prompt.

[0552] Input: News article, collected related information

[0553] Output: True / false result, confidence level

[0554] Step 8:

[0555] The server converts the result of the judgment into a JSON format response and sends it to the terminal.

[0556] Specific operation: The server receives the output of the generative AI model, converts the judgment result, confidence level, and evidence information into a JSON-formatted response, and sends this to the terminal as an HTTP response.

[0557] Input: True / false judgment result, confidence level, evidence information

[0558] Output: JSON response

[0559] Step 9:

[0560] The terminal analyzes the received information and displays the results to the user.

[0561] Specific operation: The device analyzes the JSON response and displays the results in a format that is easy for the user to understand. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0562] Input: JSON format response

[0563] Output: Displayed judgment result, confidence level, and evidence information

[0564] Step 10:

[0565] The user checks the displayed information and makes a decision.

[0566] Specific operation: The user checks the displayed judgment result, confidence level, and supporting information to determine whether the news is true or false. This will help them decide their next action.

[0567] Input: Displayed judgment result, confidence level, and evidence information

[0568] Output: User decisions and actions

[0569] (Application example 1)

[0570] 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."

[0571] In today's information society, false information and misinformation circulating online have become a serious problem. Dealing with this problem is extremely difficult, especially because information spreads rapidly through news articles and social media. Existing methods struggle to quickly and accurately determine the authenticity of information, putting many people at risk of being misled by false information. To solve this problem, an efficient and reliable system for determining whether information is true or false is needed.

[0572] 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.

[0573] In this invention, the server includes a means for analyzing information text and extracting key words and phrases, a means for determining the authenticity of information based on collected data and calculating the degree of certainty, a means for determining the authenticity of information using a generative AI model, and a means for comparing the results with a database of past authenticity determinations, thereby enabling the authenticity of information to be determined quickly and accurately over the Internet.

[0574] "Information text" refers to textual data that users input into the system, including news articles and social media posts that are subject to evaluation.

[0575] "Communication equipment" refers to network equipment such as servers and devices that send and receive information and perform analysis and judgment.

[0576] "Key words" refer to important keywords and phrases extracted from the input information text to determine its authenticity.

[0577] An "information search query" is a set of search terms generated based on a key phrase to gather related information from the Internet.

[0578] "Related information" refers to data collected from the Internet through information search queries and used as the basis for determining authenticity.

[0579] "Confidence" is a percentage or score that indicates how certain you can determine whether a piece of information is true or false, based on the relevant information collected.

[0580] The "judgment result" is a final evaluation indicating whether the information text is true or not, and includes the degree of certainty and evidence information.

[0581] A "terminal" is a device used by a user for input and display, and includes a smartphone, a computer, and the like.

[0582] This invention is a system that judges the authenticity of information text input by a user. This system is mainly composed of three elements: a user, a terminal, and a server.

[0583] User operations

[0584] A user can use a device such as a smartphone or computer to input information text, such as the text of a news article or a social media post. After inputting, the user taps or clicks a "Confirm" button.

[0585] Device Features

[0586] The terminal receives information text entered by the user, converts it into JSON format, and sends it to the server. The terminal functions as an interface for sending and receiving information.

[0587] Server Processing

[0588] The server analyzes the received information text and extracts key words and phrases using natural language processing technology. Next, it generates an information search query based on the extracted key words and phrases and uses a search engine API to collect related information from the Internet. Data is collected from reliable sources (e.g., official websites, news sites, etc.).

[0589] Based on the collected data, the server uses a generative AI model to determine the truth of the information text and calculates its confidence level. This generative AI model also compares it with a database of past truth-based judgments. For example, if similar information has been judged to be true in the past, the confidence level will increase.

[0590] The server finally transmits the judgment result, the confidence level, and the basis information thereof to the terminal.

[0591] Display of judgment results

[0592] The device displays the judgment result received from the server to the user. Specifically, the result is provided in the form of "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer." This allows the user to quickly confirm the authenticity of the information.

[0593] Hardware and software used

[0594] Hardware: smartphones, computers, servers

[0595] Software: Python, Flask (server side), requests library (client side), generative AI model, search engine API

[0596] Specific examples

[0597] For example, if a user enters the news "A famous soccer player has transferred to a new club," the server analyzes the sentence and extracts key words such as "soccer player," "club," and "transfer." It then uses an information search query generated based on these words to gather related information from the internet. Based on the collected information, the generative AI model determines whether the information is true or false, and calculates the confidence level and supporting information. Finally, these results are sent to the device and displayed to the user.

[0598] Example prompt sentence:

[0599] "Based on structured data, determine whether the news item 'A famous soccer player has transferred to a new club' is true."

[0600] Thus, the present invention is a system that quickly and accurately determines the authenticity of information and provides the user with the results, thereby effectively resolving the issue of reliability in the information society.

[0601] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0602] Step 1:

[0603] The user enters the information text into the input field of the terminal and clicks the "Confirm" button.

[0604] Input: Informational text entered by the user (e.g., "A famous soccer player has moved to a new club.")

[0605] Output: The information text is sent to the next processing step.

[0606] Step 2:

[0607] The terminal receives the information text entered by the user, converts it into JSON format, and sends it to the server.

[0608] Input: Informational text

[0609] Data processing: Convert information text into JSON format

[0610] Output: Request data in JSON format

[0611] Step 3:

[0612] The server analyzes the information text received from the terminal and extracts key words and phrases using natural language processing technology.

[0613] Input: JSON formatted information text

[0614] Data analysis: Extraction of key terms (e.g. "football player", "club", "transfer")

[0615] Output: Key phrase list

[0616] Step 4:

[0617] The server generates an information search query based on the extracted key words and phrases and collects related information from the Internet using a search engine API.

[0618] Input: Key phrase list

[0619] Data Computing: Information Retrieval Query Generation and Internet Searching

[0620] Output: A list of collected relevant information

[0621] Step 5:

[0622] The server uses a generative AI model based on the collected related information to determine the authenticity of the information text and calculates its confidence level. It also compares it with a database of past authenticity determinations.

[0623] Input: List of collected related information, generative AI model, past truth judgment data

[0624] Data analysis: True / false determination and confidence calculation (e.g., confidence level 85%)

[0625] Output: Verification result, confidence level, and evidence

[0626] Step 6:

[0627] The server transmits the determination result, the confidence level, and the basis information to the terminal.

[0628] Input: Verification result, confidence level, and evidence

[0629] Output: Data sent as the judgment result

[0630] Step 7:

[0631] The terminal analyzes the judgment result received from the server and displays it to the user.

[0632] Input: Verification result, confidence level, and evidence received from the server

[0633] Data processing: converting data into a human-readable format

[0634] Output: The result shown to the user (e.g., "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer.")

[0635] This series of processes makes it possible to quickly and accurately determine the authenticity of the information text and provide the result to the user.

[0636] 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.

[0637] The system of the present invention determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[0638] overview

[0639] The user inputs a news text through their device and sends a request to confirm its authenticity. The device uses an emotion engine to obtain the user's emotional information along with the input news text, and sends it to the server. The server analyzes the received news text, extracts key keywords, and collects related information from internet search engines. Next, it uses a generative AI model to determine the authenticity of the news, calculating the confidence level and evidence information taking into account the emotion engine data. Finally, the determination result is sent to the device and appropriately displayed to the user.

[0640] Embodiment

[0641] Enter news and get sentiment

[0642] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice using, for example, a camera or microphone to obtain emotional data.

[0643] Terminal: Converts news text and emotion data (e.g., "surprise," "skepticism," "affirmation," etc.) into a JSON-formatted request and sends it to the server.

[0644] Receiving and analyzing news data

[0645] Server: Receives news text and emotion data sent from the device. Analyzes the news text and extracts key keywords. For example, keywords such as "famous athletes," "clubs," and "transfers" are obtained.

[0646] Internet information search

[0647] Server: Generates internet search queries based on the extracted keywords and collects related information from the internet via search engine APIs. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[0648] Information collection and analysis

[0649] Server: Compares the collected relevant information with past truth-determination data stored in a database. Using a generative AI model, analyzes the collected information and past cases to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[0650] Calculation of judgment results and confidence

[0651] Server: Based on the truth / falseness judgment result, calculates the confidence level of the news. Also, taking into account the user's emotional data provided by the emotion engine, adjust the tone and format of the displayed information. For example, if the user is "surprised," provide more detailed reasons.

[0652] Generation and notification of judgment results

[0653] Server: Generates a response containing the judgment result, confidence level, and rationale information, including adjusting the display format based on the emotion data.

[0654] Terminal: Receives and analyzes the response from the server.

[0655] Displaying the results

[0656] Device: The received judgment result, confidence level, and evidence information are displayed to the user. For example, it is displayed as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0657] User: Check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy.

[0658] Specific examples

[0659] For example, if a user inputs news that "a famous athlete has transferred to a new club," the process proceeds as follows:

[0660] 1. The user enters the news text into the device and presses the "Confirm" button. At this time, the device's camera and microphone analyze the user's facial expressions and voice, and "surprise" is captured as emotional data.

[0661] 2. The device sends the input text and the "surprise" emotion data to the server.

[0662] 3. The server analyzes the news text and extracts the main keywords "athlete," "club," and "transfer."

[0663] 4. The server generates internet search queries based on these keywords and gathers relevant information from internet search engines.

[0664] 5. The server analyzes the collected information and determines its authenticity. For example, it may determine that "there is a high probability that the information is true because the player's official website has announced the transfer," and calculate a confidence level of 85%. It also adjusts the display of information to be more detailed, taking into account the emotional data "surprise."

[0665] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[0666] 7. The device analyzes the results received and displays the message, "There is a high probability that this news is true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[0667] 8. The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[0668] In this way, the system achieves efficient and reliable news veracity determination and provides information in a manner that takes into consideration the user's feelings.

[0669] The processing flow will be explained below.

[0670] Step 1:

[0671] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. For example, the user inputs the sentence "A famous athlete has transferred to a new club."

[0672] Step 2:

[0673] The device receives the news text entered by the user, and at the same time, it uses a camera and microphone to record the user's facial expressions and voice, and then uses the emotion engine to obtain emotional data. In this case, the emotion of "surprise" is recognized.

[0674] Step 3:

[0675] The device generates a request in JSON format containing the input news text and the acquired emotion data (for example, data indicating "surprise") and sends it to the server.

[0676] Step 4:

[0677] The server receives the request sent from the terminal and analyzes the news text. It then performs a process to extract key keywords from the news text, such as "athlete," "club," and "transfer."

[0678] Step 5:

[0679] The server generates an internet search query based on the extracted keywords, for example, "sports player transfer club," and uses a search engine API to gather related information.

[0680] Step 6:

[0681] The server uses search engine APIs to retrieve relevant information from the internet, collecting data from reliable sources (sports news sites, official social media accounts of players, official club announcements, etc.).

[0682] Step 7:

[0683] The server uses a generative AI model to determine the authenticity of news based on the information collected. It compares this with a past database and uses it as strong evidence when, for example, a player's official website announces a transfer.

[0684] Step 8:

[0685] The server calculates the confidence level based on the result of the truth / false judgment, and sets it to, for example, 85%. At the same time, it reflects the user's emotional data provided by the emotion engine and adjusts the level to provide more detailed information and evidence because the user is feeling "surprised."

[0686] Step 9:

[0687] The server generates a response including the judgment result, the confidence level, and the evidence information, and the response includes adjusting the display format according to the emotion.

[0688] Step 10:

[0689] The server sends the generated response to the terminal, which receives the response.

[0690] Step 11:

[0691] The device analyzes the response received and displays it to the user in a format that is easy for humans to understand. For example, it displays, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0692] Step 12:

[0693] The user can check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy. At this time, the display format adjusted to take into account emotional data makes it easier for the user to understand the information.

[0694] Example 2

[0695] 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."

[0696] Conventional news authenticity determination systems have not been able to provide users with information that takes into account their emotions, and have been unable to improve their user experience. Furthermore, there has been a lack of means to provide a higher degree of certainty by taking emotional data into account when determining the authenticity of news.

[0697] 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.

[0698] In this invention, the server includes means for analyzing news texts and extracting key keywords, means for generating internet search queries based on the extracted keywords and collecting related information, means for determining the authenticity of the news using a generative AI model based on the collected data and calculating a confidence level, and means for adjusting the display format of the information in consideration of emotional data. This enables optimal information provision that takes user emotions into consideration and improves the confidence level of news authenticity determinations.

[0699] A "user" is someone who wants to operate the system to input news text and verify its authenticity.

[0700] "Device" refers to a device that receives news text and emotion data entered by a user and communicates with the server. This includes computers, smartphones, tablets, etc.

[0701] The "server" is a central computer system that receives news text and emotion data, analyzes them, and determines whether the news is true or false.

[0702] "News text" refers to information entered by a user, including content reporting new facts or events.

[0703] "Emotion data" refers to data that indicates the emotional state of the user, as obtained from facial expressions, tone of voice, and the like.

[0704] "News analysis" refers to the process of breaking down news texts linguistically and understanding their meaning.

[0705] "Keyword extraction" is the process of extracting important words and phrases from news text.

[0706] "Internet search query" refers to a search word or phrase used to retrieve information on the Internet.

[0707] "Collecting related information" is the process of obtaining information related to keywords from the Internet using an Internet search engine or the like.

[0708] A "generative AI model" is an algorithm that uses artificial intelligence to analyze input data and generate an output based on the results. Generative AI models are used to determine the veracity of news.

[0709] "Truth determination" is the process of determining whether a piece of news is true or not.

[0710] "Confidence" is a number that indicates how certain you are about whether the news is true.

[0711] "Adjusting the display format of information" refers to displaying the determination results and grounds information in an appropriate format taking into account the user's emotional data.

[0712] "Evidence" refers to the data and sources used to determine the veracity of news.

[0713] "Response JSON" refers to a data format (JSON) that is sent from the server to the terminal and contains the judgment result, certainty, and evidence information.

[0714] MODE FOR CARRYING OUT THE INVENTION

[0715] The present invention is a system that determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[0716] Entering news and obtaining sentiment data

[0717] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, emotion data is collected using the device's camera and microphone. For example, if a user enters news such as "A famous athlete has transferred to a new club," the device's camera captures the user's facial expressions (surprise, doubt, affirmation, etc.), and the microphone analyzes the tone of voice to collect emotion data.

[0718] Terminal: Converts the input news text and emotion data into JSON format and sends it to the server.

[0719] News data analysis and keyword extraction

[0720] Server: Analyzes the received news text and sentiment data to extract key keywords. For example, it uses a morphological analysis tool to extract keywords such as "athlete," "club," and "transfer."

[0721] Collecting Internet Information

[0722] Server: Generates internet search queries based on the extracted keywords and uses internet search engines (e.g., Google API) to collect related information, including reliable news sites and official announcements.

[0723] Analysis of information and determination of authenticity

[0724] Server: Analyzes the collected information using a generative AI model (e.g., OpenAI GPT-4) to determine the truth of the news. For example, if the collected related information is that "the player's official website has announced a transfer," it determines that "this news is highly likely to be true" and calculates the confidence level.

[0725] Calculating confidence and linking emotional data

[0726] Server: Calculates the confidence level of the news based on the truthfulness judgment results, and also adjusts the display format of the information taking into account emotional data. For example, if the user is feeling "surprised," the server adjusts the display format to provide detailed supporting information.

[0727] Generation and notification of judgment results

[0728] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal.

[0729] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0730] Specific examples

[0731] For example, if a user types in the news "A famous sports player has moved to a new club," the system will be prompted with the following:

[0732] 1. Example of news content input:

[0733] "A famous athlete has moved to a new club. Please tell me if this is true."

[0734] 2. Example prompts for determining whether a news story is true or false:

[0735] "Please determine whether the following news items are true or false. Please indicate the accuracy of the news items as a percentage. Also, please provide supporting information. News: 'A famous athlete has moved to a new club.'"

[0736] In this way, the invention can efficiently determine the truth of news while taking into consideration the user's feelings, and provide highly reliable information.

[0737] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0738] Step 1: Input news text and obtain sentiment data

[0739] User: Enters a news sentence and clicks the "Confirm" button. The input here is the news sentence. Specifically, the user enters "A famous athlete has transferred to a new club" into the device's input field and presses the "Confirm" button on the device. At this time, the device's camera captures the user's facial expression, and the microphone analyzes the user's tone of voice to collect emotional data. As a result, the input is the news sentence, and the output is emotional data.

[0740] Step 2: Send news and sentiment data

[0741] Terminal: The input news text and the acquired emotion data are converted into JSON format and sent to the server. In this process, the input is the news text and emotion data, and the output is JSON format data. Specifically, JSON data containing the news text "A famous athlete has transferred to a new club" and the emotion data "surprise" is generated and sent to the server.

[0742] Step 3: Analyzing news data and extracting keywords

[0743] Server: Receives JSON data and analyzes the news sentence to extract key keywords. The input of this step is news data in JSON format, and the output is the extracted keywords. Specifically, it uses a morphological analysis tool to analyze the news sentence "A famous athlete has transferred to a new club" and extracts keywords such as "athlete," "club," and "transfer."

[0744] Step 4: Collecting Internet Information

[0745] Server: Generates internet search queries based on the extracted keywords and collects related information. The input to this step is the extracted keywords, and the output is the collected related information. Specifically, using the Google API, an internet search for "sports player," "club," and "transfer" is performed, and related information is collected from reliable news sites and official announcements.

[0746] Step 5: Analyze the information and determine its authenticity

[0747] Server: Uses a generative AI model to determine the truth of the news based on the collected related information. The input to this step is the collected related information, and the output is the truth determination result and confidence level. Specifically, the collected information is analyzed using GPT-4, and it is determined that "there is a high probability that the news is true because the transfer announcement was made on the player's official website," with a confidence level of 85%.

[0748] Step 6: Calculating confidence and linking emotion data

[0749] Server: Calculates the confidence level of the news based on the truth judgment result, and also adjusts the display format of the information taking into account the user's emotional data. The input is the truth judgment result and emotional data, and the output is the information in the adjusted display format. Specifically, if the emotional data is "surprise," the server adjusts to provide more detailed supporting information.

[0750] Step 7: Generate judgment results and notify the device from the server

[0751] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal. The input to this step is the adjusted display format information, and the output is response JSON data. Specifically, JSON data containing the truth judgment result "True," confidence level "85%," and evidence information is generated and sent to the terminal.

[0752] Step 8: Displaying the results and evidence

[0753] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. The input to this step is the response JSON data from the server, and the output is the judgment result that is displayed to the user. Specifically, the terminal analyzes the result received and displays "This news is highly likely to be true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[0754] (Application example 2)

[0755] 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."

[0756] In recent years, the internet has become overflowing with news information, creating a need for a fast and accurate way to determine its veracity. Furthermore, it is necessary to consider how the emotions of users receiving news influence their judgments. To solve this problem, it is desirable to develop a system that not only determines the veracity of news, but also provides appropriate information based on users' emotional information. It is considered particularly important to apply this technology to fields where emotions have a direct impact, such as electronic payment services.

[0757] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0758] In this invention, the server includes means for a user to input a news text, means for transmitting the input news text to the server, means for the server to analyze the news text and extract key keywords, means for generating an Internet search query based on the extracted keywords and collecting related information, means for determining the authenticity of the news based on the collected data and calculating a confidence level, means for transmitting the determination result, the confidence level, and evidence information to a terminal, means for displaying the results received by the terminal to the user, and means for acquiring emotional information and adjusting the determination result. This makes it possible to accurately determine the authenticity of a news article taking into account the user's emotional information and provide appropriate information to the user.

[0759] "Means for users to input news text" refers to an interface that allows users to input news or information in text form.

[0760] "Means for sending input news text to a server" refers to a process that provides a function for sending news text input by a user to a server via a network.

[0761] "Means by which the server analyzes news texts and extracts key keywords" refers to the process by which the server analyzes the news texts it receives using natural language processing technology, etc., and finds key keywords from within them.

[0762] "Means for generating internet search queries based on the extracted keywords and collecting related information" refers to the function of using the extracted keywords to run queries on a search engine and collect related information from the internet.

[0763] "Means for determining the veracity of news based on collected data and calculating the degree of certainty" refers to the process of analyzing collected information using a generative AI model, determining whether the news is true, and then calculating the degree of certainty as a number.

[0764] "Means for transmitting the judgment result, the certainty factor, and the information on the basis thereof to the terminal" refers to the function of the server to transmit the judgment result of the truth of the news, the certainty factor, and the information on the basis thereof to the terminal.

[0765] "Means for displaying the results received by the terminal to the user" refers to an interface for displaying the news truth determination results and related information received by the terminal from the server in an easy-to-understand manner for the user.

[0766] "Means for acquiring emotional information and adjusting the judgment result" refers to a function for acquiring the user's emotional state using a device such as a camera or microphone, and reflecting that emotional information in the judgment result.

[0767] This invention is a system that allows users to input news text and judge its authenticity. This system is composed of a variety of hardware and software, including terminals, servers, emotion engines, and generative AI models.

[0768] Hardware and software used

[0769] Hardware:

[0770] Smartphone: Equipped with a camera and microphone.

[0771] software:

[0772] Emotion engine: EmotionsAPI

[0773] Generative AI model: GPT-4

[0774] Database: MySQL

[0775] Internet search engine: Google Search API

[0776] Payment service API: Stripe

[0777] Specific examples of processing

[0778] The user enters a news sentence into the input field on their smartphone and clicks the "Confirm" button. The device uses the camera and microphone to capture the entered news sentence along with the user's emotional information (e.g., "surprise," "skepticism," "affirmation," etc.) and sends it to the server.

[0779] The server analyzes the received news text and extracts key keywords. For example, if the news text contains the content "A famous athlete has transferred to a new club," the key keywords extracted are "famous athlete," "club," and "transfer." Based on these keywords, the server generates an internet search query and collects related information from the internet (e.g., sports news sites, the athlete's official social media, official club announcements, etc.) via the Google Search API.

[0780] The server compares the collected information with past truth-judgment data stored in a database and uses a generative AI model (GPT-4) to determine whether the news is true. For example, if a player's official website announces a transfer, this is used as strong evidence.

[0781] The server then calculates the confidence level of the news based on the truthfulness judgment result. Furthermore, it adjusts the tone and format of the displayed information taking into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "surprised," it provides more detailed supporting information.

[0782] Finally, a response containing the judgment result, confidence level, and evidence information is generated and sent to the device. The device then displays the received judgment result, confidence level, and evidence information to the user. For example, it may display something like, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0783] Prompt Sentence Examples

[0784] Please determine whether the following news statements are true or false, provide relevant supporting information, and indicate your confidence in the news as a percentage.

[0785] News text: "A well-known company has launched a new product."

[0786] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0787] Step 1:

[0788] The user enters a news sentence into the input field on the smartphone and clicks the "Confirm" button.

[0789] Input: News text entered by the user.

[0790] Output: The news text is sent to the terminal.

[0791] Step 2:

[0792] The device uses a camera and microphone to acquire information about the user's emotions.

[0793] Input: The user's facial expressions and tone of voice.

[0794] Output: The obtained emotion data (e.g., "surprise", "doubt", "affirmation", etc.).

[0795] Step 3:

[0796] The device converts the news text and emotion data into JSON format and sends it to the server.

[0797] Input: News text and sentiment data.

[0798] Output: JSON formatted data sent to the server.

[0799] Step 4:

[0800] The server analyzes the received news text and extracts key keywords.

[0801] Input: Received news article.

[0802] Output: Extracted key keywords, specifically, key words and phrases from news texts using natural language processing techniques.

[0803] Step 5:

[0804] The server generates internet search queries based on the extracted keywords and collects related information through the Google Search API.

[0805] Input: Extracted main keywords.

[0806] Output: Collected relevant information, including news sites, official social media accounts, and official announcements.

[0807] Step 6:

[0808] The server compares the collected information with past truth judgment data in the database and uses a generative AI model (GPT-4) to judge the truth of the news and calculate the confidence level.

[0809] Input: Collected information and past truth-check data.

[0810] Output: The truthfulness and confidence level of the news. Specifically, the collected information is compared with the data in the database, and a generative AI model is used to arrive at a conclusion.

[0811] Step 7:

[0812] The server takes into account the user's emotional data and adjusts the tone and display format of the judgment result.

[0813] Input: True / false result, confidence level, and sentiment data.

[0814] Output: A response with the adjusted verdict. For example, "If the user is surprised, provide further detailed justification information."

[0815] Step 8:

[0816] The server transmits the determination result, the confidence level, and the basis information to the terminal as a final response.

[0817] Input: The adjusted response.

[0818] Output: Data sent to the device.

[0819] Step 9:

[0820] The terminal displays the received determination result, confidence level, and grounds information to the user.

[0821] Input: The data received from the server.

[0822] Output: The result displayed to the user. For example, "This news is highly likely to be true. Confidence is 85%. Evidence: The official website has announced the transfer."

[0823] Step 10:

[0824] The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[0825] Input: The result displayed on the terminal.

[0826] Output: The user's next action, such as further research based on the information being trusted or purchasing action.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] [Third embodiment]

[0831] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0832] 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.

[0833] 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).

[0834] 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.

[0835] 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.

[0836] 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).

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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."

[0843] The system of the present invention includes a means for determining the authenticity of news texts entered by users and displaying the results. This system performs processing in cooperation with users, terminals, and a server.

[0844] overview

[0845] The user inputs a news text through their device and sends a request to verify its authenticity. The device analyzes the input news text and sends it to the server. The server analyzes the received news text to extract key keywords and collects related information from internet search engines. It then uses a generative AI model to determine the authenticity of the news and calculates the confidence level and evidence information. Finally, the determination result is sent to the device and displayed to the user.

[0846] Embodiment

[0847] Entering and sending news

[0848] User: Enter the news text into the input field on the device and click the "Confirm" button.

[0849] Terminal: Converts the input news text into a JSON format request and sends it to the server.

[0850] Receiving and analyzing news data

[0851] Server: Receives requests sent from the device and analyzes the news text. First, it extracts key keywords, such as "football player," "club," and "transfer."

[0852] Internet information search

[0853] Server: Generates search queries based on the extracted keywords and uses search engine APIs to collect relevant information from the Internet. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[0854] Information collection and analysis

[0855] Server: The collected relevant information is compared with past truth-determining data stored in a database. The generative AI model analyzes this data and executes a process to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[0856] Calculation of judgment results and confidence

[0857] Server: Calculates the confidence level based on the truthfulness judgment results. For example, if there are multiple highly reliable sources, the confidence level is calculated as 85%. It also compiles the links and content of each source used as evidence.

[0858] Generation and notification of judgment results

[0859] Server: Generates a response to send the judgment result, confidence level, and evidence information to the terminal.

[0860] Terminal: Analyzes the response received from the server and displays the result to the user in a human-readable format, for example, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0861] User: Check the displayed judgment result, confidence level, and supporting information, and use it as reliable information.

[0862] Specific examples

[0863] For example, if a user inputs the news that "a famous soccer player has transferred to a new club," the process proceeds as follows:

[0864] 1. The user enters the news text into the terminal and presses the "Confirm" button.

[0865] 2. The terminal sends the entered news text to the server.

[0866] 3. The server analyzes the news text and extracts the main keywords: "football player," "club," and "transfer."

[0867] 4. The server generates internet search queries based on these keywords and uses internet search engines to gather relevant information.

[0868] 5. The server determines the authenticity of the news based on the collected information and calculates the confidence level. For example, if the transfer is announced on the player's official website, it is determined to be true with a high probability, with a confidence level of 85%.

[0869] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[0870] 7. The device displays the received information to the user, for example, "This news is highly likely to be true. Confidence level is 85%. Basis: The player's official website has announced the transfer."

[0871] 8. The user acts based on the displayed judgment result, confidence level, and supporting information.

[0872] In this way, the system achieves efficient and reliable news authenticity determination.

[0873] The processing flow will be explained below.

[0874] Step 1:

[0875] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. The news sentence may include, for example, "A famous soccer player has transferred to a new club."

[0876] Step 2:

[0877] The device receives the news text entered by the user, converts it into an appropriate data format (e.g., JSON), and then sends a request containing the news text to the server.

[0878] Step 3:

[0879] The server receives a request from the device. It performs initial processing to analyze the news text and extracts key keywords from the text. For example, keywords such as "football player," "club," and "transfer" are extracted.

[0880] Step 4:

[0881] The server generates an internet search query based on the extracted keywords, and then combines the keywords appropriately to create a query to search for related information on the internet using a search engine API.

[0882] Step 5:

[0883] The server uses a search engine API to perform an internet search, collects relevant information, and retrieves data from sports news sites, players' official social media accounts, club official announcements, etc.

[0884] Step 6:

[0885] The server compares the collected information with past truth-determination data stored in a database, and uses a generative AI model to analyze the collected information and past cases to determine the truth of the news.

[0886] Step 7:

[0887] The server calculates the confidence level of the news based on the results of the truth judgment. For example, if there are many matches with highly reliable sources (such as official websites), the confidence level will be high. Specifically, the confidence level may be calculated as 85%.

[0888] Step 8:

[0889] The server compiles the news verdict, confidence level, and evidence and generates a response that includes a detailed explanation of the verdict and links to the sources used.

[0890] Step 9:

[0891] The server generates a response and sends it to the terminal, which receives it and analyzes it.

[0892] Step 10:

[0893] The device displays the received judgment result, confidence level, and evidence information to the user. For example, it displays, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0894] Step 11:

[0895] The user can check the displayed judgment result, confidence level, and supporting information, and use it as reliable information. The user can make a decision based on this information and decide on their next action.

[0896] Example 1

[0897] 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."

[0898] In recent years, the amount of false news and information on the Internet has been increasing, creating a need for a system that can quickly and accurately determine whether the news is true or false. However, conventional methods require time to collect and analyze information, making it difficult for users to make decisions based on reliable information. Therefore, there is a need to develop a system that can quickly and accurately determine the truth of news and provide the results to users.

[0899] 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.

[0900] In this invention, the server includes means for converting news texts into JSON format requests, means for using a natural language processing library to extract key keywords from the news texts, means for using a search engine API to collect related information from online sources using the extracted keywords, means for generating and inputting prompts into a generative AI model to determine the authenticity of the news, and means for converting the determination result into a JSON format response. This makes it possible to quickly and accurately determine the authenticity of news texts entered by users and provide the results to the users.

[0901] "News text" is text data that is provided in the form of user input and is intended to report news or provide information.

[0902] The "server" is a centralized computer system that performs multiple data processing operations, such as analyzing news text, extracting keywords, collecting internet information, determining authenticity using generative AI models, and providing the results.

[0903] A "terminal" is a device, such as a computer, smartphone, or tablet, that allows a user to input news text and receive and display responses from the server.

[0904] A "natural language processing library" is a software tool for analyzing news texts and extracting key keywords. Examples include NLTK and SpaCy.

[0905] A "search engine API" is a program interface for automatically collecting information related to specific keywords from the Internet. Examples include the Google Search API and the Bing Search API.

[0906] A "generative AI model" is an artificial intelligence model that determines the veracity of news based on collected data. A specific example is OpenAI's GPT series.

[0907] A "prompt" is text data that is input into a generative AI model and includes news text and related information.

[0908] "JSON" is a lightweight data interchange format for storing and transmitting data. It stands for JavaScript Object Notation.

[0909] An "HTTP POST request" is an Internet protocol for sending data from a client (terminal) to a server.

[0910] The system of the present invention provides a means for users to quickly and accurately determine the authenticity of news articles. The system is composed of a user, a terminal, and a server.

[0911] First, a user inputs a news sentence into the device, which then converts the input news sentence into a JSON-formatted request and sends it to the server as an HTTP POST request. JSON is a lightweight data exchange format used for data storage and transmission.

[0912] The server receives the request in JSON format and uses a natural language processing library (e.g., NLTK or SpaCy) to parse the news text, allowing it to extract key keywords (e.g., "football player," "club," "transfer," etc.) from the news text.

[0913] The server then generates an internet search query based on the extracted keywords and uses a search engine API (e.g., Google Search API or Bing Search API) to collect related information, which is set to come from reliable sources (e.g., news sites, official social media, official announcements, etc.).

[0914] The collected related information is stored on a server and compared with a database of past truth judgments. In this process, a generative AI model (such as OpenAI's GPT series) is used to judge the truth of the news. The prompts input to the generative AI model include the news text and related information, and the model outputs a result based on this.

[0915] For example, a concrete example of a prompt would be:

[0916] "Please determine whether this news statement is true or false: A famous soccer player has moved to a new club."

[0917] The generative AI model determines the veracity of news based on collected information and past data, calculates the confidence level, and generates a response in JSON format that is sent from the server to the device.

[0918] The device analyzes the JSON response and displays the results to the user. The results include the news's veracity, confidence level, and evidence, and may be displayed in a format such as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[0919] As described above, the user, terminal, and server components work together to process and calculate data, enabling the truth or falsity of news to be determined quickly and accurately.

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

[0921] Step 1:

[0922] The user inputs a news sentence.

[0923] Specific operation: The user enters a news sentence (e.g., "A famous soccer player has transferred to a new club") into the input field of the terminal and clicks the "Confirm" button.

[0924] Input: News article

[0925] Output: Triggered when the user presses the Enter button

[0926] Step 2:

[0927] The device converts the news text into a JSON format request and sends it to the server.

[0928] Specific operation: The device converts the news text into JSON format and sends it to the server as an HTTP POST request, including metadata such as the user ID and timestamp.

[0929] Input: news article, user ID, timestamp

[0930] Output: The request sent to the server in JSON format.

[0931] Step 3:

[0932] The server parses the JSON data and extracts the news text.

[0933] Specific operation: The server parses the received JSON data and extracts the news text.

[0934] Input: JSON formatted request

[0935] Output: News article

[0936] Step 4:

[0937] The server uses natural language processing libraries to extract key keywords from news texts.

[0938] What it does: The server uses a natural language processing library (e.g., NLTK or SpaCy) to analyze the news text and extract key keywords (e.g., "football player," "club," "transfer").

[0939] Input: News article

[0940] Output: Extracted keywords

[0941] Step 5:

[0942] The server generates a search query based on the extracted keywords and collects related information using a search engine API.

[0943] Specific operation: The server sends a search query to the Google Search API or Bing Search API to collect related information. The information obtained is obtained from reliable sources (news sites, official social media, official announcements, etc.).

[0944] Input: Extracted keywords

[0945] Output: Relevant information collected

[0946] Step 6:

[0947] The server compares the collected information with a database of past authenticity determinations.

[0948] Specific operation: The server stores the collected information in an internal database and compares it with a database of past authenticity judgments. In this process, it identifies highly reliable information.

[0949] Input: Relevant information collected

[0950] Output: Matching result

[0951] Step 7:

[0952] The server inputs prompts into the generative AI model to determine whether the news is true or false.

[0953] Specific operation: The server generates and inputs a prompt to a generative AI model (e.g., OpenAI's GPT-series). For example, the prompt might be in the form of "Please determine the truth or falsity of this news sentence: A famous soccer player has transferred to a new club." The generative AI model performs analysis based on this prompt.

[0954] Input: News article, collected related information

[0955] Output: True / false result, confidence level

[0956] Step 8:

[0957] The server converts the result of the judgment into a JSON format response and sends it to the terminal.

[0958] Specific operation: The server receives the output of the generative AI model, converts the judgment result, confidence level, and evidence information into a JSON-formatted response, and sends this to the terminal as an HTTP response.

[0959] Input: True / false judgment result, confidence level, evidence information

[0960] Output: JSON response

[0961] Step 9:

[0962] The terminal analyzes the received information and displays the results to the user.

[0963] Specific operation: The device analyzes the JSON response and displays the results in a format that is easy for the user to understand. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[0964] Input: JSON format response

[0965] Output: Displayed judgment result, confidence level, and evidence information

[0966] Step 10:

[0967] The user checks the displayed information and makes a decision.

[0968] Specific operation: The user checks the displayed judgment result, confidence level, and supporting information to determine whether the news is true or false. This will help them decide their next action.

[0969] Input: Displayed judgment result, confidence level, and evidence information

[0970] Output: User decisions and actions

[0971] (Application example 1)

[0972] 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."

[0973] In today's information society, false information and misinformation circulating online have become a serious problem. Dealing with this problem is extremely difficult, especially because information spreads rapidly through news articles and social media. Existing methods struggle to quickly and accurately determine the authenticity of information, putting many people at risk of being misled by false information. To solve this problem, an efficient and reliable system for determining whether information is true or false is needed.

[0974] 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.

[0975] In this invention, the server includes a means for analyzing information text and extracting key words and phrases, a means for determining the authenticity of information based on collected data and calculating the degree of certainty, a means for determining the authenticity of information using a generative AI model, and a means for comparing the results with a database of past authenticity determinations, thereby enabling the authenticity of information to be determined quickly and accurately over the Internet.

[0976] "Information text" refers to textual data that users input into the system, including news articles and social media posts that are subject to evaluation.

[0977] "Communication equipment" refers to network equipment such as servers and devices that send and receive information and perform analysis and judgment.

[0978] "Key words" refer to important keywords and phrases extracted from the input information text to determine its authenticity.

[0979] An "information search query" is a set of search terms generated based on a key phrase to gather related information from the Internet.

[0980] "Related information" refers to data collected from the Internet through information search queries and used as the basis for determining authenticity.

[0981] "Confidence" is a percentage or score that indicates how certain you can determine whether a piece of information is true or false, based on the relevant information collected.

[0982] The "judgment result" is a final evaluation indicating whether the information text is true or not, and includes the degree of certainty and evidence information.

[0983] A "terminal" is a device used by a user for input and display, and includes a smartphone, a computer, and the like.

[0984] This invention is a system that judges the authenticity of information text input by a user. This system is mainly composed of three elements: a user, a terminal, and a server.

[0985] User operations

[0986] A user can use a device such as a smartphone or computer to input information text, such as the text of a news article or a social media post. After inputting, the user taps or clicks a "Confirm" button.

[0987] Device Features

[0988] The terminal receives information text entered by the user, converts it into JSON format, and sends it to the server. The terminal functions as an interface for sending and receiving information.

[0989] Server Processing

[0990] The server analyzes the received information text and extracts key words and phrases using natural language processing technology. Next, it generates an information search query based on the extracted key words and phrases and uses a search engine API to collect related information from the Internet. Data is collected from reliable sources (e.g., official websites, news sites, etc.).

[0991] Based on the collected data, the server uses a generative AI model to determine the truth of the information text and calculates its confidence level. This generative AI model also compares it with a database of past truth-based judgments. For example, if similar information has been judged to be true in the past, the confidence level will increase.

[0992] The server finally transmits the judgment result, the confidence level, and the basis information thereof to the terminal.

[0993] Display of judgment results

[0994] The device displays the judgment result received from the server to the user. Specifically, the result is provided in the form of "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer." This allows the user to quickly confirm the authenticity of the information.

[0995] Hardware and software used

[0996] Hardware: smartphones, computers, servers

[0997] Software: Python, Flask (server side), requests library (client side), generative AI model, search engine API

[0998] Specific examples

[0999] For example, if a user enters the news "A famous soccer player has transferred to a new club," the server analyzes the sentence and extracts key words such as "soccer player," "club," and "transfer." It then uses an information search query generated based on these words to gather related information from the internet. Based on the collected information, the generative AI model determines whether the information is true or false, and calculates the confidence level and supporting information. Finally, these results are sent to the device and displayed to the user.

[1000] Example prompt sentence:

[1001] "Based on structured data, determine whether the news item 'A famous soccer player has transferred to a new club' is true."

[1002] Thus, the present invention is a system that quickly and accurately determines the authenticity of information and provides the user with the results, thereby effectively resolving the issue of reliability in the information society.

[1003] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1004] Step 1:

[1005] The user enters the information text into the input field of the terminal and clicks the "Confirm" button.

[1006] Input: Informational text entered by the user (e.g., "A famous soccer player has moved to a new club.")

[1007] Output: The information text is sent to the next processing step.

[1008] Step 2:

[1009] The terminal receives the information text entered by the user, converts it into JSON format, and sends it to the server.

[1010] Input: Informational text

[1011] Data processing: Convert information text into JSON format

[1012] Output: Request data in JSON format

[1013] Step 3:

[1014] The server analyzes the information text received from the terminal and extracts key words and phrases using natural language processing technology.

[1015] Input: JSON formatted information text

[1016] Data analysis: Extraction of key terms (e.g. "football player", "club", "transfer")

[1017] Output: Key phrase list

[1018] Step 4:

[1019] The server generates an information search query based on the extracted key words and phrases and collects related information from the Internet using a search engine API.

[1020] Input: Key phrase list

[1021] Data Computing: Information Retrieval Query Generation and Internet Searching

[1022] Output: A list of collected relevant information

[1023] Step 5:

[1024] The server uses a generative AI model based on the collected related information to determine the authenticity of the information text and calculates its confidence level. It also compares it with a database of past authenticity determinations.

[1025] Input: List of collected related information, generative AI model, past truth judgment data

[1026] Data analysis: True / false determination and confidence calculation (e.g., confidence level 85%)

[1027] Output: Verification result, confidence level, and evidence

[1028] Step 6:

[1029] The server transmits the determination result, the confidence level, and the basis information to the terminal.

[1030] Input: Verification result, confidence level, and evidence

[1031] Output: Data sent as the judgment result

[1032] Step 7:

[1033] The terminal analyzes the judgment result received from the server and displays it to the user.

[1034] Input: Verification result, confidence level, and evidence received from the server

[1035] Data processing: converting data into a human-readable format

[1036] Output: The result shown to the user (e.g., "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer.")

[1037] This series of processes makes it possible to quickly and accurately determine the authenticity of the information text and provide the result to the user.

[1038] 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.

[1039] The system of the present invention determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[1040] overview

[1041] The user inputs a news text through their device and sends a request to confirm its authenticity. The device uses an emotion engine to obtain the user's emotional information along with the input news text, and sends it to the server. The server analyzes the received news text, extracts key keywords, and collects related information from internet search engines. Next, it uses a generative AI model to determine the authenticity of the news, calculating the confidence level and evidence information taking into account the emotion engine data. Finally, the determination result is sent to the device and appropriately displayed to the user.

[1042] Embodiment

[1043] Enter news and get sentiment

[1044] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice using, for example, a camera or microphone to obtain emotional data.

[1045] Terminal: Converts news text and emotion data (e.g., "surprise," "skepticism," "affirmation," etc.) into a JSON-formatted request and sends it to the server.

[1046] Receiving and analyzing news data

[1047] Server: Receives news text and emotion data sent from the device. Analyzes the news text and extracts key keywords. For example, keywords such as "famous athletes," "clubs," and "transfers" are obtained.

[1048] Internet information search

[1049] Server: Generates internet search queries based on the extracted keywords and collects related information from the internet via search engine APIs. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[1050] Information collection and analysis

[1051] Server: Compares the collected relevant information with past truth-determination data stored in a database. Using a generative AI model, analyzes the collected information and past cases to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[1052] Calculation of judgment results and confidence

[1053] Server: Based on the truth / falseness judgment result, calculates the confidence level of the news. Also, taking into account the user's emotional data provided by the emotion engine, adjust the tone and format of the displayed information. For example, if the user is "surprised," provide more detailed reasons.

[1054] Generation and notification of judgment results

[1055] Server: Generates a response containing the judgment result, confidence level, and rationale information, including adjusting the display format based on the emotion data.

[1056] Terminal: Receives and analyzes the response from the server.

[1057] Displaying the results

[1058] Device: The received judgment result, confidence level, and evidence information are displayed to the user. For example, it is displayed as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[1059] User: Check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy.

[1060] Specific examples

[1061] For example, if a user inputs news that "a famous athlete has transferred to a new club," the process proceeds as follows:

[1062] 1. The user enters the news text into the device and presses the "Confirm" button. At this time, the device's camera and microphone analyze the user's facial expressions and voice, and "surprise" is captured as emotional data.

[1063] 2. The device sends the input text and the "surprise" emotion data to the server.

[1064] 3. The server analyzes the news text and extracts the main keywords "athlete," "club," and "transfer."

[1065] 4. The server generates internet search queries based on these keywords and gathers relevant information from internet search engines.

[1066] 5. The server analyzes the collected information and determines its authenticity. For example, it may determine that "there is a high probability that the information is true because the player's official website has announced the transfer," and calculate a confidence level of 85%. It also adjusts the display of information to be more detailed, taking into account the emotional data "surprise."

[1067] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[1068] 7. The device analyzes the results received and displays the message, "There is a high probability that this news is true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[1069] 8. The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[1070] In this way, the system achieves efficient and reliable news veracity determination and provides information in a manner that takes into consideration the user's feelings.

[1071] The processing flow will be explained below.

[1072] Step 1:

[1073] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. For example, the user inputs the sentence "A famous athlete has transferred to a new club."

[1074] Step 2:

[1075] The device receives the news text entered by the user, and at the same time, it uses a camera and microphone to record the user's facial expressions and voice, and then uses the emotion engine to obtain emotional data. In this case, the emotion of "surprise" is recognized.

[1076] Step 3:

[1077] The device generates a request in JSON format containing the input news text and the acquired emotion data (for example, data indicating "surprise") and sends it to the server.

[1078] Step 4:

[1079] The server receives the request sent from the terminal and analyzes the news text. It then performs a process to extract key keywords from the news text, such as "athlete," "club," and "transfer."

[1080] Step 5:

[1081] The server generates an internet search query based on the extracted keywords, for example, "sports player transfer club," and uses a search engine API to gather related information.

[1082] Step 6:

[1083] The server uses search engine APIs to retrieve relevant information from the internet, collecting data from reliable sources (sports news sites, official social media accounts of players, official club announcements, etc.).

[1084] Step 7:

[1085] The server uses a generative AI model to determine the authenticity of news based on the information collected. It compares this with a past database and uses it as strong evidence when, for example, a player's official website announces a transfer.

[1086] Step 8:

[1087] The server calculates the confidence level based on the result of the truth / false judgment, and sets it to, for example, 85%. At the same time, it reflects the user's emotional data provided by the emotion engine and adjusts the level to provide more detailed information and evidence because the user is feeling "surprised."

[1088] Step 9:

[1089] The server generates a response including the judgment result, the confidence level, and the evidence information, and the response includes adjusting the display format according to the emotion.

[1090] Step 10:

[1091] The server sends the generated response to the terminal, which receives the response.

[1092] Step 11:

[1093] The device analyzes the response received and displays it to the user in a format that is easy for humans to understand. For example, it displays, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[1094] Step 12:

[1095] The user can check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy. At this time, the display format adjusted to take into account emotional data makes it easier for the user to understand the information.

[1096] Example 2

[1097] 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."

[1098] Conventional news authenticity determination systems have not been able to provide users with information that takes into account their emotions, and have been unable to improve their user experience. Furthermore, there has been a lack of means to provide a higher degree of certainty by taking emotional data into account when determining the authenticity of news.

[1099] 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.

[1100] In this invention, the server includes means for analyzing news texts and extracting key keywords, means for generating internet search queries based on the extracted keywords and collecting related information, means for determining the authenticity of the news using a generative AI model based on the collected data and calculating a confidence level, and means for adjusting the display format of the information in consideration of emotional data. This enables optimal information provision that takes user emotions into consideration and improves the confidence level of news authenticity determinations.

[1101] A "user" is someone who wants to operate the system to input news text and verify its authenticity.

[1102] "Device" refers to a device that receives news text and emotion data entered by a user and communicates with the server. This includes computers, smartphones, tablets, etc.

[1103] The "server" is a central computer system that receives news text and emotion data, analyzes them, and determines whether the news is true or false.

[1104] "News text" refers to information entered by a user, including content reporting new facts or events.

[1105] "Emotion data" refers to data that indicates the emotional state of the user, as obtained from facial expressions, tone of voice, and the like.

[1106] "News analysis" refers to the process of breaking down news texts linguistically and understanding their meaning.

[1107] "Keyword extraction" is the process of extracting important words and phrases from news text.

[1108] "Internet search query" refers to a search word or phrase used to retrieve information on the Internet.

[1109] "Collecting related information" is the process of obtaining information related to keywords from the Internet using an Internet search engine or the like.

[1110] A "generative AI model" is an algorithm that uses artificial intelligence to analyze input data and generate an output based on the results. Generative AI models are used to determine the veracity of news.

[1111] "Truth determination" is the process of determining whether a piece of news is true or not.

[1112] "Confidence" is a number that indicates how certain you are about whether the news is true.

[1113] "Adjusting the display format of information" refers to displaying the determination results and grounds information in an appropriate format taking into account the user's emotional data.

[1114] "Evidence" refers to the data and sources used to determine the veracity of news.

[1115] "Response JSON" refers to a data format (JSON) that is sent from the server to the terminal and contains the judgment result, certainty, and evidence information.

[1116] MODE FOR CARRYING OUT THE INVENTION

[1117] The present invention is a system that determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[1118] Entering news and obtaining sentiment data

[1119] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, emotion data is collected using the device's camera and microphone. For example, if a user enters news such as "A famous athlete has transferred to a new club," the device's camera captures the user's facial expressions (surprise, doubt, affirmation, etc.), and the microphone analyzes the tone of voice to collect emotion data.

[1120] Terminal: Converts the input news text and emotion data into JSON format and sends it to the server.

[1121] News data analysis and keyword extraction

[1122] Server: Analyzes the received news text and sentiment data to extract key keywords. For example, it uses a morphological analysis tool to extract keywords such as "athlete," "club," and "transfer."

[1123] Collecting Internet Information

[1124] Server: Generates internet search queries based on the extracted keywords and uses internet search engines (e.g., Google API) to collect related information, including reliable news sites and official announcements.

[1125] Analysis of information and determination of authenticity

[1126] Server: Analyzes the collected information using a generative AI model (e.g., OpenAI GPT-4) to determine the truth of the news. For example, if the collected related information is that "the player's official website has announced a transfer," it determines that "this news is highly likely to be true" and calculates the confidence level.

[1127] Calculating confidence and linking emotional data

[1128] Server: Calculates the confidence level of the news based on the truthfulness judgment results, and also adjusts the display format of the information taking into account emotional data. For example, if the user is feeling "surprised," the server adjusts the display format to provide detailed supporting information.

[1129] Generation and notification of judgment results

[1130] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal.

[1131] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[1132] Specific examples

[1133] For example, if a user types in the news "A famous sports player has moved to a new club," the system will be prompted with the following:

[1134] 1. Example of news content input:

[1135] "A famous athlete has moved to a new club. Please tell me if this is true."

[1136] 2. Example prompts for determining whether a news story is true or false:

[1137] "Please determine whether the following news items are true or false. Please indicate the accuracy of the news items as a percentage. Also, please provide supporting information. News: 'A famous athlete has moved to a new club.'"

[1138] In this way, the invention can efficiently determine the truth of news while taking into consideration the user's feelings, and provide highly reliable information.

[1139] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1140] Step 1: Input news text and obtain sentiment data

[1141] User: Enters a news sentence and clicks the "Confirm" button. The input here is the news sentence. Specifically, the user enters "A famous athlete has transferred to a new club" into the device's input field and presses the "Confirm" button on the device. At this time, the device's camera captures the user's facial expression, and the microphone analyzes the user's tone of voice to collect emotional data. As a result, the input is the news sentence, and the output is emotional data.

[1142] Step 2: Send news and sentiment data

[1143] Terminal: The input news text and the acquired emotion data are converted into JSON format and sent to the server. In this process, the input is the news text and emotion data, and the output is JSON format data. Specifically, JSON data containing the news text "A famous athlete has transferred to a new club" and the emotion data "surprise" is generated and sent to the server.

[1144] Step 3: Analyzing news data and extracting keywords

[1145] Server: Receives JSON data and analyzes the news sentence to extract key keywords. The input of this step is news data in JSON format, and the output is the extracted keywords. Specifically, it uses a morphological analysis tool to analyze the news sentence "A famous athlete has transferred to a new club" and extracts keywords such as "athlete," "club," and "transfer."

[1146] Step 4: Collecting Internet Information

[1147] Server: Generates internet search queries based on the extracted keywords and collects related information. The input to this step is the extracted keywords, and the output is the collected related information. Specifically, using the Google API, an internet search for "sports player," "club," and "transfer" is performed, and related information is collected from reliable news sites and official announcements.

[1148] Step 5: Analyze the information and determine its authenticity

[1149] Server: Uses a generative AI model to determine the truth of the news based on the collected related information. The input to this step is the collected related information, and the output is the truth determination result and confidence level. Specifically, the collected information is analyzed using GPT-4, and it is determined that "there is a high probability that the news is true because the transfer announcement was made on the player's official website," with a confidence level of 85%.

[1150] Step 6: Calculating confidence and linking emotion data

[1151] Server: Calculates the confidence level of the news based on the truth judgment result, and also adjusts the display format of the information taking into account the user's emotional data. The input is the truth judgment result and emotional data, and the output is the information in the adjusted display format. Specifically, if the emotional data is "surprise," the server adjusts to provide more detailed supporting information.

[1152] Step 7: Generate judgment results and notify the device from the server

[1153] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal. The input to this step is the adjusted display format information, and the output is response JSON data. Specifically, JSON data containing the truth judgment result "True," confidence level "85%," and evidence information is generated and sent to the terminal.

[1154] Step 8: Displaying the results and evidence

[1155] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. The input to this step is the response JSON data from the server, and the output is the judgment result that is displayed to the user. Specifically, the terminal analyzes the result received and displays "This news is highly likely to be true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[1156] (Application example 2)

[1157] 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."

[1158] In recent years, the internet has become overflowing with news information, creating a need for a fast and accurate way to determine its veracity. Furthermore, it is necessary to consider how the emotions of users receiving news influence their judgments. To solve this problem, it is desirable to develop a system that not only determines the veracity of news, but also provides appropriate information based on users' emotional information. It is considered particularly important to apply this technology to fields where emotions have a direct impact, such as electronic payment services.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1160] In this invention, the server includes means for a user to input a news text, means for transmitting the input news text to the server, means for the server to analyze the news text and extract key keywords, means for generating an Internet search query based on the extracted keywords and collecting related information, means for determining the authenticity of the news based on the collected data and calculating a confidence level, means for transmitting the determination result, the confidence level, and evidence information to a terminal, means for displaying the results received by the terminal to the user, and means for acquiring emotional information and adjusting the determination result. This makes it possible to accurately determine the authenticity of a news article taking into account the user's emotional information and provide appropriate information to the user.

[1161] "Means for users to input news text" refers to an interface that allows users to input news or information in text form.

[1162] "Means for sending input news text to a server" refers to a process that provides a function for sending news text input by a user to a server via a network.

[1163] "Means by which the server analyzes news texts and extracts key keywords" refers to the process by which the server analyzes the news texts it receives using natural language processing technology, etc., and finds key keywords from within them.

[1164] "Means for generating internet search queries based on the extracted keywords and collecting related information" refers to the function of using the extracted keywords to run queries on a search engine and collect related information from the internet.

[1165] "Means for determining the veracity of news based on collected data and calculating the degree of certainty" refers to the process of analyzing collected information using a generative AI model, determining whether the news is true, and then calculating the degree of certainty as a number.

[1166] "Means for transmitting the judgment result, the certainty factor, and the information on the basis thereof to the terminal" refers to the function of the server to transmit the judgment result of the truth of the news, the certainty factor, and the information on the basis thereof to the terminal.

[1167] "Means for displaying the results received by the terminal to the user" refers to an interface for displaying the news truth determination results and related information received by the terminal from the server in an easy-to-understand manner for the user.

[1168] "Means for acquiring emotional information and adjusting the judgment result" refers to a function for acquiring the user's emotional state using a device such as a camera or microphone, and reflecting that emotional information in the judgment result.

[1169] This invention is a system that allows users to input news text and judge its authenticity. This system is composed of a variety of hardware and software, including terminals, servers, emotion engines, and generative AI models.

[1170] Hardware and software used

[1171] Hardware:

[1172] Smartphone: Equipped with a camera and microphone.

[1173] software:

[1174] Emotion engine: EmotionsAPI

[1175] Generative AI model: GPT-4

[1176] Database: MySQL

[1177] Internet search engine: Google Search API

[1178] Payment service API: Stripe

[1179] Specific examples of processing

[1180] The user enters a news sentence into the input field on their smartphone and clicks the "Confirm" button. The device uses the camera and microphone to capture the entered news sentence along with the user's emotional information (e.g., "surprise," "skepticism," "affirmation," etc.) and sends it to the server.

[1181] The server analyzes the received news text and extracts key keywords. For example, if the news text contains the content "A famous athlete has transferred to a new club," the key keywords extracted are "famous athlete," "club," and "transfer." Based on these keywords, the server generates an internet search query and collects related information from the internet (e.g., sports news sites, the athlete's official social media, official club announcements, etc.) via the Google Search API.

[1182] The server compares the collected information with past truth-judgment data stored in a database and uses a generative AI model (GPT-4) to determine whether the news is true. For example, if a player's official website announces a transfer, this is used as strong evidence.

[1183] The server then calculates the confidence level of the news based on the truthfulness judgment result. Furthermore, it adjusts the tone and format of the displayed information taking into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "surprised," it provides more detailed supporting information.

[1184] Finally, a response containing the judgment result, confidence level, and evidence information is generated and sent to the device. The device then displays the received judgment result, confidence level, and evidence information to the user. For example, it may display something like, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[1185] Prompt Sentence Examples

[1186] Please determine whether the following news statements are true or false, provide relevant supporting information, and indicate your confidence in the news as a percentage.

[1187] News text: "A well-known company has launched a new product."

[1188] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1189] Step 1:

[1190] The user enters a news sentence into the input field on the smartphone and clicks the "Confirm" button.

[1191] Input: News text entered by the user.

[1192] Output: The news text is sent to the terminal.

[1193] Step 2:

[1194] The device uses a camera and microphone to acquire information about the user's emotions.

[1195] Input: The user's facial expressions and tone of voice.

[1196] Output: The obtained emotion data (e.g., "surprise", "doubt", "affirmation", etc.).

[1197] Step 3:

[1198] The device converts the news text and emotion data into JSON format and sends it to the server.

[1199] Input: News text and sentiment data.

[1200] Output: JSON formatted data sent to the server.

[1201] Step 4:

[1202] The server analyzes the received news text and extracts key keywords.

[1203] Input: Received news article.

[1204] Output: Extracted key keywords, specifically, key words and phrases from news texts using natural language processing techniques.

[1205] Step 5:

[1206] The server generates internet search queries based on the extracted keywords and collects related information through the Google Search API.

[1207] Input: Extracted main keywords.

[1208] Output: Collected relevant information, including news sites, official social media accounts, and official announcements.

[1209] Step 6:

[1210] The server compares the collected information with past truth judgment data in the database and uses a generative AI model (GPT-4) to judge the truth of the news and calculate the confidence level.

[1211] Input: Collected information and past truth-check data.

[1212] Output: The truthfulness and confidence level of the news. Specifically, the collected information is compared with the data in the database, and a generative AI model is used to arrive at a conclusion.

[1213] Step 7:

[1214] The server takes into account the user's emotional data and adjusts the tone and display format of the judgment result.

[1215] Input: True / false result, confidence level, and sentiment data.

[1216] Output: A response with the adjusted verdict. For example, "If the user is surprised, provide further detailed justification information."

[1217] Step 8:

[1218] The server transmits the determination result, the confidence level, and the basis information to the terminal as a final response.

[1219] Input: The adjusted response.

[1220] Output: Data sent to the device.

[1221] Step 9:

[1222] The terminal displays the received determination result, confidence level, and grounds information to the user.

[1223] Input: The data received from the server.

[1224] Output: The result displayed to the user. For example, "This news is highly likely to be true. Confidence is 85%. Evidence: The official website has announced the transfer."

[1225] Step 10:

[1226] The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[1227] Input: The result displayed on the terminal.

[1228] Output: The user's next action, such as further research based on the information being trusted or purchasing action.

[1229] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1230] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1231] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1232] [Fourth embodiment]

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

[1234] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1235] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1236] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1237] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1238] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[1240] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1241] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1242] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1243] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1244] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1245] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1246] The system of the present invention includes a means for determining the authenticity of news texts entered by users and displaying the results. This system performs processing in cooperation with users, terminals, and a server.

[1247] overview

[1248] The user inputs a news text through their device and sends a request to verify its authenticity. The device analyzes the input news text and sends it to the server. The server analyzes the received news text to extract key keywords and collects related information from internet search engines. It then uses a generative AI model to determine the authenticity of the news and calculates the confidence level and evidence information. Finally, the determination result is sent to the device and displayed to the user.

[1249] Embodiment

[1250] Entering and sending news

[1251] User: Enter the news text into the input field on the device and click the "Confirm" button.

[1252] Terminal: Converts the input news text into a JSON format request and sends it to the server.

[1253] Receiving and analyzing news data

[1254] Server: Receives requests sent from the device and analyzes the news text. First, it extracts key keywords, such as "football player," "club," and "transfer."

[1255] Internet information search

[1256] Server: Generates search queries based on the extracted keywords and uses search engine APIs to collect relevant information from the Internet. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[1257] Information collection and analysis

[1258] Server: The collected relevant information is compared with past truth-determining data stored in a database. The generative AI model analyzes this data and executes a process to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[1259] Calculation of judgment results and confidence

[1260] Server: Calculates the confidence level based on the truthfulness judgment results. For example, if there are multiple highly reliable sources, the confidence level is calculated as 85%. It also compiles the links and content of each source used as evidence.

[1261] Generation and notification of judgment results

[1262] Server: Generates a response to send the judgment result, confidence level, and evidence information to the terminal.

[1263] Terminal: Analyzes the response received from the server and displays the result to the user in a human-readable format, for example, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[1264] User: Check the displayed judgment result, confidence level, and supporting information, and use it as reliable information.

[1265] Specific examples

[1266] For example, if a user inputs the news that "a famous soccer player has transferred to a new club," the process proceeds as follows:

[1267] 1. The user enters the news text into the terminal and presses the "Confirm" button.

[1268] 2. The terminal sends the entered news text to the server.

[1269] 3. The server analyzes the news text and extracts the main keywords: "football player," "club," and "transfer."

[1270] 4. The server generates internet search queries based on these keywords and uses internet search engines to gather relevant information.

[1271] 5. The server determines the authenticity of the news based on the collected information and calculates the confidence level. For example, if the transfer is announced on the player's official website, it is determined to be true with a high probability, with a confidence level of 85%.

[1272] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[1273] 7. The device displays the received information to the user, for example, "This news is highly likely to be true. Confidence level is 85%. Basis: The player's official website has announced the transfer."

[1274] 8. The user acts based on the displayed judgment result, confidence level, and supporting information.

[1275] In this way, the system achieves efficient and reliable news authenticity determination.

[1276] The processing flow will be explained below.

[1277] Step 1:

[1278] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. The news sentence may include, for example, "A famous soccer player has transferred to a new club."

[1279] Step 2:

[1280] The device receives the news text entered by the user, converts it into an appropriate data format (e.g., JSON), and then sends a request containing the news text to the server.

[1281] Step 3:

[1282] The server receives a request from the device. It performs initial processing to analyze the news text and extracts key keywords from the text. For example, keywords such as "football player," "club," and "transfer" are extracted.

[1283] Step 4:

[1284] The server generates an internet search query based on the extracted keywords, and then combines the keywords appropriately to create a query to search for related information on the internet using a search engine API.

[1285] Step 5:

[1286] The server uses a search engine API to perform an internet search, collects relevant information, and retrieves data from sports news sites, players' official social media accounts, club official announcements, etc.

[1287] Step 6:

[1288] The server compares the collected information with past truth-determination data stored in a database, and uses a generative AI model to analyze the collected information and past cases to determine the truth of the news.

[1289] Step 7:

[1290] The server calculates the confidence level of the news based on the results of the truth judgment. For example, if there are many matches with highly reliable sources (such as official websites), the confidence level will be high. Specifically, the confidence level may be calculated as 85%.

[1291] Step 8:

[1292] The server compiles the news verdict, confidence level, and evidence and generates a response that includes a detailed explanation of the verdict and links to the sources used.

[1293] Step 9:

[1294] The server generates a response and sends it to the terminal, which receives it and analyzes it.

[1295] Step 10:

[1296] The device displays the received judgment result, confidence level, and evidence information to the user. For example, it displays, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[1297] Step 11:

[1298] The user can check the displayed judgment result, confidence level, and supporting information, and use it as reliable information. The user can make a decision based on this information and decide on their next action.

[1299] Example 1

[1300] 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."

[1301] In recent years, the amount of false news and information on the Internet has been increasing, creating a need for a system that can quickly and accurately determine whether the news is true or false. However, conventional methods require time to collect and analyze information, making it difficult for users to make decisions based on reliable information. Therefore, there is a need to develop a system that can quickly and accurately determine the truth of news and provide the results to users.

[1302] 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.

[1303] In this invention, the server includes means for converting news texts into JSON format requests, means for using a natural language processing library to extract key keywords from the news texts, means for using a search engine API to collect related information from online sources using the extracted keywords, means for generating and inputting prompts into a generative AI model to determine the authenticity of the news, and means for converting the determination result into a JSON format response. This makes it possible to quickly and accurately determine the authenticity of news texts entered by users and provide the results to the users.

[1304] "News text" is text data that is provided in the form of user input and is intended to report news or provide information.

[1305] The "server" is a centralized computer system that performs multiple data processing operations, such as analyzing news text, extracting keywords, collecting internet information, determining authenticity using generative AI models, and providing the results.

[1306] A "terminal" is a device, such as a computer, smartphone, or tablet, that allows a user to input news text and receive and display responses from the server.

[1307] A "natural language processing library" is a software tool for analyzing news texts and extracting key keywords. Examples include NLTK and SpaCy.

[1308] A "search engine API" is a program interface for automatically collecting information related to specific keywords from the Internet. Examples include the Google Search API and the Bing Search API.

[1309] A "generative AI model" is an artificial intelligence model that determines the veracity of news based on collected data. A specific example is OpenAI's GPT series.

[1310] A "prompt" is text data that is input into a generative AI model and includes news text and related information.

[1311] "JSON" is a lightweight data interchange format for storing and transmitting data. It stands for JavaScript Object Notation.

[1312] An "HTTP POST request" is an Internet protocol for sending data from a client (terminal) to a server.

[1313] The system of the present invention provides a means for users to quickly and accurately determine the authenticity of news articles. The system is composed of a user, a terminal, and a server.

[1314] First, a user inputs a news sentence into the device, which then converts the input news sentence into a JSON-formatted request and sends it to the server as an HTTP POST request. JSON is a lightweight data exchange format used for data storage and transmission.

[1315] The server receives the request in JSON format and uses a natural language processing library (e.g., NLTK or SpaCy) to parse the news text, allowing it to extract key keywords (e.g., "football player," "club," "transfer," etc.) from the news text.

[1316] The server then generates an internet search query based on the extracted keywords and uses a search engine API (e.g., Google Search API or Bing Search API) to collect related information, which is set to come from reliable sources (e.g., news sites, official social media, official announcements, etc.).

[1317] The collected related information is stored on a server and compared with a database of past truth judgments. In this process, a generative AI model (such as OpenAI's GPT series) is used to judge the truth of the news. The prompts input to the generative AI model include the news text and related information, and the model outputs a result based on this.

[1318] For example, a concrete example of a prompt would be:

[1319] "Please determine whether this news statement is true or false: A famous soccer player has moved to a new club."

[1320] The generative AI model determines the veracity of news based on collected information and past data, calculates the confidence level, and generates a response in JSON format that is sent from the server to the device.

[1321] The device analyzes the JSON response and displays the results to the user. The results include the news's veracity, confidence level, and evidence, and may be displayed in a format such as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[1322] As described above, the user, terminal, and server components work together to process and calculate data, enabling the truth or falsity of news to be determined quickly and accurately.

[1323] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1324] Step 1:

[1325] The user inputs a news sentence.

[1326] Specific operation: The user enters a news sentence (e.g., "A famous soccer player has transferred to a new club") into the input field of the terminal and clicks the "Confirm" button.

[1327] Input: News article

[1328] Output: Triggered when the user presses the Enter button

[1329] Step 2:

[1330] The device converts the news text into a JSON format request and sends it to the server.

[1331] Specific operation: The device converts the news text into JSON format and sends it to the server as an HTTP POST request, including metadata such as the user ID and timestamp.

[1332] Input: news article, user ID, timestamp

[1333] Output: The request sent to the server in JSON format.

[1334] Step 3:

[1335] The server parses the JSON data and extracts the news text.

[1336] Specific operation: The server parses the received JSON data and extracts the news text.

[1337] Input: JSON formatted request

[1338] Output: News article

[1339] Step 4:

[1340] The server uses natural language processing libraries to extract key keywords from news texts.

[1341] What it does: The server uses a natural language processing library (e.g., NLTK or SpaCy) to analyze the news text and extract key keywords (e.g., "football player," "club," "transfer").

[1342] Input: News article

[1343] Output: Extracted keywords

[1344] Step 5:

[1345] The server generates a search query based on the extracted keywords and collects related information using a search engine API.

[1346] Specific operation: The server sends a search query to the Google Search API or Bing Search API to collect related information. The information obtained is obtained from reliable sources (news sites, official social media, official announcements, etc.).

[1347] Input: Extracted keywords

[1348] Output: Relevant information collected

[1349] Step 6:

[1350] The server compares the collected information with a database of past authenticity determinations.

[1351] Specific operation: The server stores the collected information in an internal database and compares it with a database of past authenticity judgments. In this process, it identifies highly reliable information.

[1352] Input: Relevant information collected

[1353] Output: Matching result

[1354] Step 7:

[1355] The server inputs prompts into the generative AI model to determine whether the news is true or false.

[1356] Specific operation: The server generates and inputs a prompt to a generative AI model (e.g., OpenAI's GPT-series). For example, the prompt might be in the form of "Please determine the truth or falsity of this news sentence: A famous soccer player has transferred to a new club." The generative AI model performs analysis based on this prompt.

[1357] Input: News article, collected related information

[1358] Output: True / false result, confidence level

[1359] Step 8:

[1360] The server converts the result of the judgment into a JSON format response and sends it to the terminal.

[1361] Specific operation: The server receives the output of the generative AI model, converts the judgment result, confidence level, and evidence information into a JSON-formatted response, and sends this to the terminal as an HTTP response.

[1362] Input: True / false judgment result, confidence level, evidence information

[1363] Output: JSON response

[1364] Step 9:

[1365] The terminal analyzes the received information and displays the results to the user.

[1366] Specific operation: The device analyzes the JSON response and displays the results in a format that is easy for the user to understand. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[1367] Input: JSON format response

[1368] Output: Displayed judgment result, confidence level, and evidence information

[1369] Step 10:

[1370] The user checks the displayed information and makes a decision.

[1371] Specific operation: The user checks the displayed judgment result, confidence level, and supporting information to determine whether the news is true or false. This will help them decide their next action.

[1372] Input: Displayed judgment result, confidence level, and evidence information

[1373] Output: User decisions and actions

[1374] (Application example 1)

[1375] 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."

[1376] In today's information society, false information and misinformation circulating online have become a serious problem. Dealing with this problem is extremely difficult, especially because information spreads rapidly through news articles and social media. Existing methods struggle to quickly and accurately determine the authenticity of information, putting many people at risk of being misled by false information. To solve this problem, an efficient and reliable system for determining whether information is true or false is needed.

[1377] 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.

[1378] In this invention, the server includes a means for analyzing information text and extracting key words and phrases, a means for determining the authenticity of information based on collected data and calculating the degree of certainty, a means for determining the authenticity of information using a generative AI model, and a means for comparing the results with a database of past authenticity determinations, thereby enabling the authenticity of information to be determined quickly and accurately over the Internet.

[1379] "Information text" refers to textual data that users input into the system, including news articles and social media posts that are subject to evaluation.

[1380] "Communication equipment" refers to network equipment such as servers and devices that send and receive information and perform analysis and judgment.

[1381] "Key words" refer to important keywords and phrases extracted from the input information text to determine its authenticity.

[1382] An "information search query" is a set of search terms generated based on a key phrase to gather related information from the Internet.

[1383] "Related information" refers to data collected from the Internet through information search queries and used as the basis for determining authenticity.

[1384] "Confidence" is a percentage or score that indicates how certain you can determine whether a piece of information is true or false, based on the relevant information collected.

[1385] The "judgment result" is a final evaluation indicating whether the information text is true or not, and includes the degree of certainty and evidence information.

[1386] A "terminal" is a device used by a user for input and display, and includes a smartphone, a computer, and the like.

[1387] This invention is a system that judges the authenticity of information text input by a user. This system is mainly composed of three elements: a user, a terminal, and a server.

[1388] User operations

[1389] A user can use a device such as a smartphone or computer to input information text, such as the text of a news article or a social media post. After inputting, the user taps or clicks a "Confirm" button.

[1390] Device Features

[1391] The terminal receives information text entered by the user, converts it into JSON format, and sends it to the server. The terminal functions as an interface for sending and receiving information.

[1392] Server Processing

[1393] The server analyzes the received information text and extracts key words and phrases using natural language processing technology. Next, it generates an information search query based on the extracted key words and phrases and uses a search engine API to collect related information from the Internet. Data is collected from reliable sources (e.g., official websites, news sites, etc.).

[1394] Based on the collected data, the server uses a generative AI model to determine the truth of the information text and calculates its confidence level. This generative AI model also compares it with a database of past truth-based judgments. For example, if similar information has been judged to be true in the past, the confidence level will increase.

[1395] The server finally transmits the judgment result, the confidence level, and the basis information thereof to the terminal.

[1396] Display of judgment results

[1397] The device displays the judgment result received from the server to the user. Specifically, the result is provided in the form of "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer." This allows the user to quickly confirm the authenticity of the information.

[1398] Hardware and software used

[1399] Hardware: smartphones, computers, servers

[1400] Software: Python, Flask (server side), requests library (client side), generative AI model, search engine API

[1401] Specific examples

[1402] For example, if a user enters the news "A famous soccer player has transferred to a new club," the server analyzes the sentence and extracts key words such as "soccer player," "club," and "transfer." It then uses an information search query generated based on these words to gather related information from the internet. Based on the collected information, the generative AI model determines whether the information is true or false, and calculates the confidence level and supporting information. Finally, these results are sent to the device and displayed to the user.

[1403] Example prompt sentence:

[1404] "Based on structured data, determine whether the news item 'A famous soccer player has transferred to a new club' is true."

[1405] Thus, the present invention is a system that quickly and accurately determines the authenticity of information and provides the user with the results, thereby effectively resolving the issue of reliability in the information society.

[1406] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1407] Step 1:

[1408] The user enters the information text into the input field of the terminal and clicks the "Confirm" button.

[1409] Input: Informational text entered by the user (e.g., "A famous soccer player has moved to a new club.")

[1410] Output: The information text is sent to the next processing step.

[1411] Step 2:

[1412] The terminal receives the information text entered by the user, converts it into JSON format, and sends it to the server.

[1413] Input: Informational text

[1414] Data processing: Convert information text into JSON format

[1415] Output: Request data in JSON format

[1416] Step 3:

[1417] The server analyzes the information text received from the terminal and extracts key words and phrases using natural language processing technology.

[1418] Input: JSON formatted information text

[1419] Data analysis: Extraction of key terms (e.g. "football player", "club", "transfer")

[1420] Output: Key phrase list

[1421] Step 4:

[1422] The server generates an information search query based on the extracted key words and phrases and collects related information from the Internet using a search engine API.

[1423] Input: Key phrase list

[1424] Data Computing: Information Retrieval Query Generation and Internet Searching

[1425] Output: A list of collected relevant information

[1426] Step 5:

[1427] The server uses a generative AI model based on the collected related information to determine the authenticity of the information text and calculates its confidence level. It also compares it with a database of past authenticity determinations.

[1428] Input: List of collected related information, generative AI model, past truth judgment data

[1429] Data analysis: True / false determination and confidence calculation (e.g., confidence level 85%)

[1430] Output: Verification result, confidence level, and evidence

[1431] Step 6:

[1432] The server transmits the determination result, the confidence level, and the basis information to the terminal.

[1433] Input: Verification result, confidence level, and evidence

[1434] Output: Data sent as the judgment result

[1435] Step 7:

[1436] The terminal analyzes the judgment result received from the server and displays it to the user.

[1437] Input: Verification result, confidence level, and evidence received from the server

[1438] Data processing: converting data into a human-readable format

[1439] Output: The result shown to the user (e.g., "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer.")

[1440] This series of processes makes it possible to quickly and accurately determine the authenticity of the information text and provide the result to the user.

[1441] 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.

[1442] The system of the present invention determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[1443] overview

[1444] The user inputs a news text through their device and sends a request to confirm its authenticity. The device uses an emotion engine to obtain the user's emotional information along with the input news text, and sends it to the server. The server analyzes the received news text, extracts key keywords, and collects related information from internet search engines. Next, it uses a generative AI model to determine the authenticity of the news, calculating the confidence level and evidence information taking into account the emotion engine data. Finally, the determination result is sent to the device and appropriately displayed to the user.

[1445] Embodiment

[1446] Enter news and get sentiment

[1447] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, the emotion engine analyzes the user's facial expressions and tone of voice using, for example, a camera or microphone to obtain emotional data.

[1448] Terminal: Converts news text and emotion data (e.g., "surprise," "skepticism," "affirmation," etc.) into a JSON-formatted request and sends it to the server.

[1449] Receiving and analyzing news data

[1450] Server: Receives news text and emotion data sent from the device. Analyzes the news text and extracts key keywords. For example, keywords such as "famous athletes," "clubs," and "transfers" are obtained.

[1451] Internet information search

[1452] Server: Generates internet search queries based on the extracted keywords and collects related information from the internet via search engine APIs. The collected information includes reliable sources such as sports news sites, official social media accounts of players, and official club announcements.

[1453] Information collection and analysis

[1454] Server: Compares the collected relevant information with past truth-determination data stored in a database. Using a generative AI model, analyzes the collected information and past cases to determine the truth of the news. For example, if a player's official website announces a transfer, this is used as strong evidence.

[1455] Calculation of judgment results and confidence

[1456] Server: Based on the truth / falseness judgment result, calculates the confidence level of the news. Also, taking into account the user's emotional data provided by the emotion engine, adjust the tone and format of the displayed information. For example, if the user is "surprised," provide more detailed reasons.

[1457] Generation and notification of judgment results

[1458] Server: Generates a response containing the judgment result, confidence level, and rationale information, including adjusting the display format based on the emotion data.

[1459] Terminal: Receives and analyzes the response from the server.

[1460] Displaying the results

[1461] Device: The received judgment result, confidence level, and evidence information are displayed to the user. For example, it is displayed as "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[1462] User: Check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy.

[1463] Specific examples

[1464] For example, if a user inputs news that "a famous athlete has transferred to a new club," the process proceeds as follows:

[1465] 1. The user enters the news text into the device and presses the "Confirm" button. At this time, the device's camera and microphone analyze the user's facial expressions and voice, and "surprise" is captured as emotional data.

[1466] 2. The device sends the input text and the "surprise" emotion data to the server.

[1467] 3. The server analyzes the news text and extracts the main keywords "athlete," "club," and "transfer."

[1468] 4. The server generates internet search queries based on these keywords and gathers relevant information from internet search engines.

[1469] 5. The server analyzes the collected information and determines its authenticity. For example, it may determine that "there is a high probability that the information is true because the player's official website has announced the transfer," and calculate a confidence level of 85%. It also adjusts the display of information to be more detailed, taking into account the emotional data "surprise."

[1470] 6. The server sends the judgment result, confidence level, and evidence information to the terminal.

[1471] 7. The device analyzes the results received and displays the message, "There is a high probability that this news is true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[1472] 8. The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[1473] In this way, the system achieves efficient and reliable news veracity determination and provides information in a manner that takes into consideration the user's feelings.

[1474] The processing flow will be explained below.

[1475] Step 1:

[1476] The user inputs a news sentence into the input field of the terminal and clicks the "Confirm" button. For example, the user inputs the sentence "A famous athlete has transferred to a new club."

[1477] Step 2:

[1478] The device receives the news text entered by the user, and at the same time, it uses a camera and microphone to record the user's facial expressions and voice, and then uses the emotion engine to obtain emotional data. In this case, the emotion of "surprise" is recognized.

[1479] Step 3:

[1480] The device generates a request in JSON format containing the input news text and the acquired emotion data (for example, data indicating "surprise") and sends it to the server.

[1481] Step 4:

[1482] The server receives the request sent from the terminal and analyzes the news text. It then performs a process to extract key keywords from the news text, such as "athlete," "club," and "transfer."

[1483] Step 5:

[1484] The server generates an internet search query based on the extracted keywords, for example, "sports player transfer club," and uses a search engine API to gather related information.

[1485] Step 6:

[1486] The server uses search engine APIs to retrieve relevant information from the internet, collecting data from reliable sources (sports news sites, official social media accounts of players, official club announcements, etc.).

[1487] Step 7:

[1488] The server uses a generative AI model to determine the authenticity of news based on the information collected. It compares this with a past database and uses it as strong evidence when, for example, a player's official website announces a transfer.

[1489] Step 8:

[1490] The server calculates the confidence level based on the result of the truth / false judgment, and sets it to, for example, 85%. At the same time, it reflects the user's emotional data provided by the emotion engine and adjusts the level to provide more detailed information and evidence because the user is feeling "surprised."

[1491] Step 9:

[1492] The server generates a response including the judgment result, the confidence level, and the evidence information, and the response includes adjusting the display format according to the emotion.

[1493] Step 10:

[1494] The server sends the generated response to the terminal, which receives the response.

[1495] Step 11:

[1496] The device analyzes the response received and displays it to the user in a format that is easy for humans to understand. For example, it displays, "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[1497] Step 12:

[1498] The user can check the displayed judgment result, confidence level, and supporting information, and act on the basis that the information is trustworthy. At this time, the display format adjusted to take into account emotional data makes it easier for the user to understand the information.

[1499] Example 2

[1500] 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."

[1501] Conventional news authenticity determination systems have not been able to provide users with information that takes into account their emotions, and have been unable to improve their user experience. Furthermore, there has been a lack of means to provide a higher degree of certainty by taking emotional data into account when determining the authenticity of news.

[1502] 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.

[1503] In this invention, the server includes means for analyzing news texts and extracting key keywords, means for generating internet search queries based on the extracted keywords and collecting related information, means for determining the authenticity of the news using a generative AI model based on the collected data and calculating a confidence level, and means for adjusting the display format of the information in consideration of emotional data. This enables optimal information provision that takes user emotions into consideration and improves the confidence level of news authenticity determinations.

[1504] A "user" is someone who wants to operate the system to input news text and verify its authenticity.

[1505] "Device" refers to a device that receives news text and emotion data entered by a user and communicates with the server. This includes computers, smartphones, tablets, etc.

[1506] The "server" is a central computer system that receives news text and emotion data, analyzes them, and determines whether the news is true or false.

[1507] "News text" refers to information entered by a user, including content reporting new facts or events.

[1508] "Emotion data" refers to data that indicates the emotional state of the user, as obtained from facial expressions, tone of voice, and the like.

[1509] "News analysis" refers to the process of breaking down news texts linguistically and understanding their meaning.

[1510] "Keyword extraction" is the process of extracting important words and phrases from news text.

[1511] "Internet search query" refers to a search word or phrase used to retrieve information on the Internet.

[1512] "Collecting related information" is the process of obtaining information related to keywords from the Internet using an Internet search engine or the like.

[1513] A "generative AI model" is an algorithm that uses artificial intelligence to analyze input data and generate an output based on the results. Generative AI models are used to determine the veracity of news.

[1514] "Truth determination" is the process of determining whether a piece of news is true or not.

[1515] "Confidence" is a number that indicates how certain you are about whether the news is true.

[1516] "Adjusting the display format of information" refers to displaying the determination results and grounds information in an appropriate format taking into account the user's emotional data.

[1517] "Evidence" refers to the data and sources used to determine the veracity of news.

[1518] "Response JSON" refers to a data format (JSON) that is sent from the server to the terminal and contains the judgment result, certainty, and evidence information.

[1519] MODE FOR CARRYING OUT THE INVENTION

[1520] The present invention is a system that determines the truth or falsity of news texts entered by users and optimizes the results using an emotion engine. This system performs processing in cooperation with the user, terminal, server, and emotion engine.

[1521] Entering news and obtaining sentiment data

[1522] User: Enters news text into the device's input field and clicks the "Confirm" button. At this time, emotion data is collected using the device's camera and microphone. For example, if a user enters news such as "A famous athlete has transferred to a new club," the device's camera captures the user's facial expressions (surprise, doubt, affirmation, etc.), and the microphone analyzes the tone of voice to collect emotion data.

[1523] Terminal: Converts the input news text and emotion data into JSON format and sends it to the server.

[1524] News data analysis and keyword extraction

[1525] Server: Analyzes the received news text and sentiment data to extract key keywords. For example, it uses a morphological analysis tool to extract keywords such as "athlete," "club," and "transfer."

[1526] Collecting Internet Information

[1527] Server: Generates internet search queries based on the extracted keywords and uses internet search engines (e.g., Google API) to collect related information, including reliable news sites and official announcements.

[1528] Analysis of information and determination of authenticity

[1529] Server: Analyzes the collected information using a generative AI model (e.g., OpenAI GPT-4) to determine the truth of the news. For example, if the collected related information is that "the player's official website has announced a transfer," it determines that "this news is highly likely to be true" and calculates the confidence level.

[1530] Calculating confidence and linking emotional data

[1531] Server: Calculates the confidence level of the news based on the truthfulness judgment results, and also adjusts the display format of the information taking into account emotional data. For example, if the user is feeling "surprised," the server adjusts the display format to provide detailed supporting information.

[1532] Generation and notification of judgment results

[1533] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal.

[1534] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. For example, it displays "This news is highly likely to be true. Confidence is 85%. Evidence: The player's official website has announced the transfer."

[1535] Specific examples

[1536] For example, if a user types in the news "A famous sports player has moved to a new club," the system will be prompted with the following:

[1537] 1. Example of news content input:

[1538] "A famous athlete has moved to a new club. Please tell me if this is true."

[1539] 2. Example prompts for determining whether a news story is true or false:

[1540] "Please determine whether the following news items are true or false. Please indicate the accuracy of the news items as a percentage. Also, please provide supporting information. News: 'A famous athlete has moved to a new club.'"

[1541] In this way, the invention can efficiently determine the truth of news while taking into consideration the user's feelings, and provide highly reliable information.

[1542] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1543] Step 1: Input news text and obtain sentiment data

[1544] User: Enters a news sentence and clicks the "Confirm" button. The input here is the news sentence. Specifically, the user enters "A famous athlete has transferred to a new club" into the device's input field and presses the "Confirm" button on the device. At this time, the device's camera captures the user's facial expression, and the microphone analyzes the user's tone of voice to collect emotional data. As a result, the input is the news sentence, and the output is emotional data.

[1545] Step 2: Send news and sentiment data

[1546] Terminal: The input news text and the acquired emotion data are converted into JSON format and sent to the server. In this process, the input is the news text and emotion data, and the output is JSON format data. Specifically, JSON data containing the news text "A famous athlete has transferred to a new club" and the emotion data "surprise" is generated and sent to the server.

[1547] Step 3: Analyzing news data and extracting keywords

[1548] Server: Receives JSON data and analyzes the news sentence to extract key keywords. The input of this step is news data in JSON format, and the output is the extracted keywords. Specifically, it uses a morphological analysis tool to analyze the news sentence "A famous athlete has transferred to a new club" and extracts keywords such as "athlete," "club," and "transfer."

[1549] Step 4: Collecting Internet Information

[1550] Server: Generates internet search queries based on the extracted keywords and collects related information. The input to this step is the extracted keywords, and the output is the collected related information. Specifically, using the Google API, an internet search for "sports player," "club," and "transfer" is performed, and related information is collected from reliable news sites and official announcements.

[1551] Step 5: Analyze the information and determine its authenticity

[1552] Server: Uses a generative AI model to determine the truth of the news based on the collected related information. The input to this step is the collected related information, and the output is the truth determination result and confidence level. Specifically, the collected information is analyzed using GPT-4, and it is determined that "there is a high probability that the news is true because the transfer announcement was made on the player's official website," with a confidence level of 85%.

[1553] Step 6: Calculating confidence and linking emotion data

[1554] Server: Calculates the confidence level of the news based on the truth judgment result, and also adjusts the display format of the information taking into account the user's emotional data. The input is the truth judgment result and emotional data, and the output is the information in the adjusted display format. Specifically, if the emotional data is "surprise," the server adjusts to provide more detailed supporting information.

[1555] Step 7: Generate judgment results and notify the device from the server

[1556] Server: Generates a response JSON containing the judgment result, confidence level, and evidence information, and sends it to the terminal. The input to this step is the adjusted display format information, and the output is response JSON data. Specifically, JSON data containing the truth judgment result "True," confidence level "85%," and evidence information is generated and sent to the terminal.

[1557] Step 8: Displaying the results and evidence

[1558] Terminal: Receives the response sent from the server, analyzes it, and displays it to the user in an appropriate format. The input to this step is the response JSON data from the server, and the output is the judgment result that is displayed to the user. Specifically, the terminal analyzes the result received and displays "This news is highly likely to be true. The confidence level is 85%. Reason: The transfer has been announced on the player's official website."

[1559] (Application example 2)

[1560] 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."

[1561] In recent years, the internet has become overflowing with news information, creating a need for a fast and accurate way to determine its veracity. Furthermore, it is necessary to consider how the emotions of users receiving news influence their judgments. To solve this problem, it is desirable to develop a system that not only determines the veracity of news, but also provides appropriate information based on users' emotional information. It is considered particularly important to apply this technology to fields where emotions have a direct impact, such as electronic payment services.

[1562] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1563] In this invention, the server includes means for a user to input a news text, means for transmitting the input news text to the server, means for the server to analyze the news text and extract key keywords, means for generating an Internet search query based on the extracted keywords and collecting related information, means for determining the authenticity of the news based on the collected data and calculating a confidence level, means for transmitting the determination result, the confidence level, and evidence information to a terminal, means for displaying the results received by the terminal to the user, and means for acquiring emotional information and adjusting the determination result. This makes it possible to accurately determine the authenticity of a news article taking into account the user's emotional information and provide appropriate information to the user.

[1564] "Means for users to input news text" refers to an interface that allows users to input news or information in text form.

[1565] "Means for sending input news text to a server" refers to a process that provides a function for sending news text input by a user to a server via a network.

[1566] "Means by which the server analyzes news texts and extracts key keywords" refers to the process by which the server analyzes the news texts it receives using natural language processing technology, etc., and finds key keywords from within them.

[1567] "Means for generating internet search queries based on the extracted keywords and collecting related information" refers to the function of using the extracted keywords to run queries on a search engine and collect related information from the internet.

[1568] "Means for determining the veracity of news based on collected data and calculating the degree of certainty" refers to the process of analyzing collected information using a generative AI model, determining whether the news is true, and then calculating the degree of certainty as a number.

[1569] "Means for transmitting the judgment result, the certainty factor, and the information on the basis thereof to the terminal" refers to the function of the server to transmit the judgment result of the truth of the news, the certainty factor, and the information on the basis thereof to the terminal.

[1570] "Means for displaying the results received by the terminal to the user" refers to an interface for displaying the news truth determination results and related information received by the terminal from the server in an easy-to-understand manner for the user.

[1571] "Means for acquiring emotional information and adjusting the judgment result" refers to a function for acquiring the user's emotional state using a device such as a camera or microphone, and reflecting that emotional information in the judgment result.

[1572] This invention is a system that allows users to input news text and judge its authenticity. This system is composed of a variety of hardware and software, including terminals, servers, emotion engines, and generative AI models.

[1573] Hardware and software used

[1574] Hardware:

[1575] Smartphone: Equipped with a camera and microphone.

[1576] software:

[1577] Emotion engine: EmotionsAPI

[1578] Generative AI model: GPT-4

[1579] Database: MySQL

[1580] Internet search engine: Google Search API

[1581] Payment service API: Stripe

[1582] Specific examples of processing

[1583] The user enters a news sentence into the input field on their smartphone and clicks the "Confirm" button. The device uses the camera and microphone to capture the entered news sentence along with the user's emotional information (e.g., "surprise," "skepticism," "affirmation," etc.) and sends it to the server.

[1584] The server analyzes the received news text and extracts key keywords. For example, if the news text contains the content "A famous athlete has transferred to a new club," the key keywords extracted are "famous athlete," "club," and "transfer." Based on these keywords, the server generates an internet search query and collects related information from the internet (e.g., sports news sites, the athlete's official social media, official club announcements, etc.) via the Google Search API.

[1585] The server compares the collected information with past truth-judgment data stored in a database and uses a generative AI model (GPT-4) to determine whether the news is true. For example, if a player's official website announces a transfer, this is used as strong evidence.

[1586] The server then calculates the confidence level of the news based on the truthfulness judgment result. Furthermore, it adjusts the tone and format of the displayed information taking into account the user's emotional data provided by the emotion engine. For example, if the user is feeling "surprised," it provides more detailed supporting information.

[1587] Finally, a response containing the judgment result, confidence level, and evidence information is generated and sent to the device. The device then displays the received judgment result, confidence level, and evidence information to the user. For example, it may display something like, "This news is highly likely to be true. Confidence level is 85%. Evidence: The player's official website has announced the transfer."

[1588] Prompt Sentence Examples

[1589] Please determine whether the following news statements are true or false, provide relevant supporting information, and indicate your confidence in the news as a percentage.

[1590] News text: "A well-known company has launched a new product."

[1591] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1592] Step 1:

[1593] The user enters a news sentence into the input field on the smartphone and clicks the "Confirm" button.

[1594] Input: News text entered by the user.

[1595] Output: The news text is sent to the terminal.

[1596] Step 2:

[1597] The device uses a camera and microphone to acquire information about the user's emotions.

[1598] Input: The user's facial expressions and tone of voice.

[1599] Output: The obtained emotion data (e.g., "surprise", "doubt", "affirmation", etc.).

[1600] Step 3:

[1601] The device converts the news text and emotion data into JSON format and sends it to the server.

[1602] Input: News text and sentiment data.

[1603] Output: JSON formatted data sent to the server.

[1604] Step 4:

[1605] The server analyzes the received news text and extracts key keywords.

[1606] Input: Received news article.

[1607] Output: Extracted key keywords, specifically, key words and phrases from news texts using natural language processing techniques.

[1608] Step 5:

[1609] The server generates internet search queries based on the extracted keywords and collects related information through the Google Search API.

[1610] Input: Extracted main keywords.

[1611] Output: Collected relevant information, including news sites, official social media accounts, and official announcements.

[1612] Step 6:

[1613] The server compares the collected information with past truth judgment data in the database and uses a generative AI model (GPT-4) to judge the truth of the news and calculate the confidence level.

[1614] Input: Collected information and past truth-check data.

[1615] Output: The truthfulness and confidence level of the news. Specifically, the collected information is compared with the data in the database, and a generative AI model is used to arrive at a conclusion.

[1616] Step 7:

[1617] The server takes into account the user's emotional data and adjusts the tone and display format of the judgment result.

[1618] Input: True / false result, confidence level, and sentiment data.

[1619] Output: A response with the adjusted verdict. For example, "If the user is surprised, provide further detailed justification information."

[1620] Step 8:

[1621] The server transmits the determination result, the confidence level, and the basis information to the terminal as a final response.

[1622] Input: The adjusted response.

[1623] Output: Data sent to the device.

[1624] Step 9:

[1625] The terminal displays the received determination result, confidence level, and grounds information to the user.

[1626] Input: The data received from the server.

[1627] Output: The result displayed to the user. For example, "This news is highly likely to be true. Confidence is 85%. Evidence: The official website has announced the transfer."

[1628] Step 10:

[1629] The user checks the displayed judgment result, confidence level, and supporting information, and decides on the next course of action.

[1630] Input: The result displayed on the terminal.

[1631] Output: The user's next action, such as further research based on the information being trusted or purchasing action.

[1632] 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.

[1633] 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.

[1634] 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.

[1635] 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.

[1636] 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.

[1637] 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.

[1638] 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).

[1639] 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.

[1640] 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."

[1641] 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.

[1642] 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).

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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.

[1652] 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.

[1653] The following is further disclosed regarding the above embodiment.

[1654] (Claim 1)

[1655] a means for a user to input news text;

[1656] means for transmitting the input news text to a server;

[1657] A means for the server to analyze the news text and extract key keywords;

[1658] A means for generating an internet search query based on the extracted keywords and collecting related information;

[1659] A means of determining the truth of news based on the collected data and calculating the degree of certainty;

[1660] means for transmitting the determination result, the confidence level, and the grounds information to a terminal;

[1661] means for displaying the results received by the terminal to the user;

[1662] A system including:

[1663] (Claim 2)

[1664] The system of claim 1, wherein the server includes a generative AI model that determines the authenticity of news.

[1665] (Claim 3)

[1666] 2. The system according to claim 1, wherein the server includes means for comparing the collected information with a database of past authenticity determinations.

[1667] "Example 1"

[1668] (Claim 1)

[1669] a means for a user to input news text;

[1670] means for transmitting the input news text to a server;

[1671] A means for the server to analyze the news text and extract key keywords;

[1672] A means for generating an internet search query based on the extracted keywords and collecting related information;

[1673] A means of determining the truth of news based on the collected data and calculating the degree of certainty;

[1674] means for transmitting the determination result, the confidence level, and the grounds information to a terminal;

[1675] means for displaying the results received by the terminal to the user;

[1676] A way to convert news text into JSON format requests,

[1677] using a natural language processing library to extract key keywords from news texts;

[1678] A means for collecting related information from sources on the Internet using the extracted keywords through a search engine API;

[1679] A means to determine the authenticity of news by generating and inputting prompts into a generative AI model;

[1680] A means to convert the judgment result into a JSON format response,

[1681] A system including:

[1682] (Claim 2)

[1683] The system of claim 1, wherein the server includes a generative AI model that determines the authenticity of news.

[1684] (Claim 3)

[1685] 2. The system according to claim 1, wherein the server includes means for comparing the collected information with a database of past authenticity determinations.

[1686] "Application Example 1"

[1687] (Claim 1)

[1688] means for a user to input information text;

[1689] means for transmitting the input information text to a communication device;

[1690] A means for the communication device to analyze the information text and extract key words and phrases;

[1691] A means for generating an information search query based on the extracted phrases and collecting related information;

[1692] A means for determining the authenticity of information based on the collected data and calculating the degree of certainty;

[1693] means for transmitting the determination result, the confidence level, and the grounds information to a terminal;

[1694] means for displaying the results received by the terminal to the user;

[1695] A system including:

[1696] (Claim 2)

[1697] The system of claim 1, wherein the communication device includes a generative AI model that determines the authenticity of information.

[1698] (Claim 3)

[1699] 2. The system of claim 1, wherein the communication device includes means for comparing the collected information with a database of past authenticity determinations.

[1700] "Example 2: Combining Emotion Engines"

[1701] (Claim 1)

[1702] a means for a user to input news text;

[1703] means for transmitting the input news text and emotion data to a server;

[1704] A means for the server to analyze the news text and extract key keywords;

[1705] A means for generating an internet search query based on the extracted keywords and collecting related information;

[1706] A means of determining the truth of news based on the collected data and calculating the degree of certainty;

[1707] A means for taking into account sentiment data generated in the process of determining the authenticity of news;

[1708] means for transmitting the determination result, the confidence level, and the grounds information to a terminal;

[1709] means for displaying the results received by the terminal to the user;

[1710] A system including:

[1711] (Claim 2)

[1712] The system of claim 1, wherein the server includes a generative AI model that determines the authenticity of news.

[1713] (Claim 3)

[1714] 2. The system according to claim 1, wherein the server includes means for comparing the collected information with a database of past authenticity determinations.

[1715] "Application example 2 when combining emotion engines"

[1716] (Claim 1)

[1717] a means for a user to input news text;

[1718] means for transmitting the input news text to a server;

[1719] A means for the server to analyze the news text and extract key keywords;

[1720] A means for generating an internet search query based on the extracted keywords and collecting related information;

[1721] A means of determining the truth of news based on the collected data and calculating the degree of certainty;

[1722] means for transmitting the determination result, the confidence level, and the grounds information to a terminal;

[1723] means for displaying the results received by the terminal to the user;

[1724] The system includes a means for obtaining emotion information and adjusting the determination result.

[1725] (Claim 2)

[1726] The system of claim 1, wherein the server includes a generative AI model that determines the authenticity of news.

[1727] (Claim 3)

[1728] 2. The system according to claim 1, wherein the server includes means for comparing the collected information with a database of past authenticity determinations. [Explanation of symbols]

[1729] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to input news text; means for transmitting the input news text to a server; A means for the server to analyze the news text and extract key keywords; A means for generating an internet search query based on the extracted keywords and collecting related information; A means for determining the truth of news based on collected data and calculating the degree of certainty; means for transmitting the determination result, the confidence level, and the grounds information to a terminal; means for displaying the results received by the terminal to the user; A system including:

2. The system of claim 1, further comprising a generative AI model on a server that determines the authenticity of news.

3. 2. The system according to claim 1, wherein the server includes means for comparing the collected information with a database of past authenticity determinations.

Images