System

Abstract

A system is provided.SOLUTION: A system comprising: means for determining whether information transmitted from a user is true or false using a fact check database managed by an information processing apparatus; means for periodically updating the fact check database from a media organization and a fact check organization; and means for transmitting a true / false result determined by the information processing apparatus to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, with the spread of the internet and social media, there has been an increasing number of cases of false and misinformation spreading rapidly, causing social unrest. Conventional legal and regulatory measures have the potential to restrict freedom of expression and are therefore inappropriate in a democratic society. Furthermore, the cost of providing accurate information is high, making it difficult for news organizations and fact-checking groups to secure the necessary resources. Therefore, there is a need for methods that can effectively prevent the spread of false and misinformation while reducing the cost of accessing accurate information. [Means for solving the problem]

[0005] The present invention provides a system that uses a fact-checking database managed by an information processing device to determine the veracity of information submitted by users. Specifically, the system uses a fact-checking database that is regularly updated by news organizations and fact-checking organizations, and uses an AI model to determine the veracity of the information. This enables easy access to accurate information and prevents the spread of false and misleading information. Furthermore, the user device sends and receives information requests via a chat app such as the LINE app, and the information processing device transmits the determination results to the user device. Furthermore, by providing a means for distributing rewards based on the number of times the fact-checking database is used, the system solves the resource challenges faced by news organizations and fact-checking organizations.

[0006] "Information processing device" refers to a device that receives information requests from users, queries a fact-checking database, determines the veracity of the information using an AI model, and transmits the results to the user's terminal.

[0007] A "fact-checking database" refers to a database that accumulates and manages data provided by news organizations and fact-checking organizations that is necessary to identify false or misinformation.

[0008] An "AI model" refers to an algorithm that uses technologies such as machine learning and deep learning to automatically determine the veracity of information based on a fact-checking database.

[0009] The term "user terminal" refers to a device through which a user inputs an information request and receives a truthfulness determination result from an information processing device. Specifically, this refers to a device including a chat app, such as a smartphone.

[0010] The "LINE app" refers to an example of a chat app that users use to send and receive messages. In the present invention, information requests can be made using the LINE app or other chat apps.

[0011] "News organizations" refer to organizations that provide users with reliable information, such as newspapers, broadcasting stations, and internet news sites.

[0012] A "fact-checking organization" is an organization with specialized knowledge that verifies the accuracy of information provided and identifies false or misleading information.

[0013] A "request" refers to a request that a user inputs information or a link to a news article that the user wants to check and sends it to an information processing device.

[0014] "Remuneration" refers to compensation paid to news organizations and fact-checking organizations based on the number of times they use a fact-checking database.

[0015] "Use count" refers to the number of times the fact-checking database is queried based on a user request. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This paper describes a fake check system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). Specific means and processes for effectively detecting fake and misleading information and providing it to users are described.

[0038] Server Features

[0039] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[0040] Maintaining a fact-checking database

[0041] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[0042] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[0043] Handling the request

[0044] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[0045] Example: When a user asks "Is this true?" on LINE, the server searches the information in its database and replies, "This is false information."

[0046] Compensation distribution management

[0047] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[0048] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[0049] User device functions

[0050] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[0051] Sending information

[0052] The user terminal transmits the information and questions entered by the user to the server.

[0053] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[0054] Receiving the results

[0055] The fact-check results sent from the server are received and displayed on the chat screen of the LINE app.

[0056] Example: When the server responds, "This news is fake," the result is displayed on the LINE chat screen.

[0057] User Roles

[0058] Users can interact with the system using apps such as LINE to verify the authenticity of the information.

[0059] Entering information

[0060] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[0061] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[0062] Review and share your results

[0063] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[0064] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[0065] Specific examples of implementation

[0066] For example, suppose a user receives the news that "The latest major earthquake is predicted." The user enters this information into the LINE app and sends a message asking, "Is this true?" The information sent from the user's device is received by the server, which searches the information in a fact-checking database. The AI ​​model determines the result, and if it determines, for example, that "this information is false," the result is sent back to the user's device and displayed on the LINE chat screen. The user sees this result, realizes that it is false information, and shares it with their friends.

[0067] In this way, a system is realized in which the server, user terminals, and users cooperate to prevent the spread of false and misinformation and promote access to accurate information. This system ensures the accuracy of information and also contributes to the activation of news organizations and fact-checking organizations.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[0071] Step 2:

[0072] Users enter the information they want to check or a link to a news article in the message field, add the question "Is this true?" and press the send button.

[0073] Step 3:

[0074] The terminal generates a request to send the message entered by the user to the server.

[0075] Step 4:

[0076] The device sends the generated request to the FNT account server.

[0077] Step 5:

[0078] The server receives the request sent from the terminal.

[0079] Step 6:

[0080] The server analyzes the received message and extracts the user's question and the information they wish to confirm.

[0081] Step 7:

[0082] The server queries (searches) a fact-checking database based on the extracted information.

[0083] Step 8:

[0084] The server inputs the search results into an AI model to determine whether the information is true or false.

[0085] Step 9:

[0086] The server generates a message to respond to the user based on the AI ​​model's judgment results.

[0087] Step 10:

[0088] The server sends the generated response message to the terminal.

[0089] Step 11:

[0090] The terminal receives the response message sent from the server.

[0091] Step 12:

[0092] The device will display the received message on the chat screen of the LINE app.

[0093] Step 13:

[0094] The user opens the chat screen in the LINE app and checks the response message from the server.

[0095] Step 14:

[0096] Based on the results received, users can determine the authenticity of the information and share their results with friends and family.

[0097] Example 1

[0098] 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."

[0099] False and misleading information is frequently circulating on the Internet, making it difficult for users to quickly and accurately verify the authenticity of information. In particular, ordinary users who lack the ability to verify the reliability of information are at high risk of being misled by misinformation. For this reason, there is a need for a system that can effectively identify false and misleading information based on reliable information sources and provide it to users.

[0100] 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.

[0101] In this invention, the server includes means for determining the authenticity of information sent from a user terminal, means for periodically updating a fact-check database from an information source, means for transmitting the authenticity results determined by the information processing device to the user terminal, means for determining the authenticity of the information using a generative AI model, and means for the user terminal to send and receive information requests via a chat app. This allows users to quickly check the authenticity of information via the chat app and prevents the spread of false information.

[0102] An "information processing device" is a computer system for processing, managing, and analyzing data.

[0103] A "fact-checking database" is a collection of data used to accumulate and manage highly reliable information and determine whether the information is true or false.

[0104] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet, that provides a means for sending and receiving information.

[0105] "Means for determining authenticity" refers to the algorithms or models used to determine the authenticity of received information.

[0106] A "source" is a source used to provide accurate information, such as a reputable news organization or fact-checking organization.

[0107] A "generative AI model" is a model generated using artificial intelligence, which analyzes and judges information based on natural language processing.

[0108] "Chat app" means a software application that allows users to send and receive messages in real time, including LINE and other messaging apps.

[0109] An "information request" is an inquiry that a user sends by specifying the information they want to confirm.

[0110] The "true / false result" is the result of determining whether the received information is true or false.

[0111] The present invention is a fact-checking system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). This system effectively identifies false and misleading information and provides users with accurate results.

[0112] The server manages a fact-checking database and plays an important role in determining the veracity of information sent by users. The fact-checking database stores reliable information, and the server searches and analyzes information based on this database.

[0113] Hardware and software used

[0114] The server uses a high-performance computer system to build and manage the fact-checking database. It uses a database management system (e.g., MySQL, PostgreSQL, etc.) to efficiently process and store large amounts of data. It also uses a generative AI model (e.g., GPT-4) to determine the veracity of the information it receives.

[0115] User devices are devices such as smartphones, tablets, and PCs, and communicate with the server primarily using chat apps (e.g., LINE). Users send information via the chat app and receive the judgment results from the server.

[0116] Specific actions

[0117] User submits information

[0118] A user uses a chat app (such as LINE) installed on a smartphone or tablet to enter and send the information they want to check. For example, a user might type "Is this news true?" into the LINE app and send it.

[0119] The server receives and processes the request

[0120] The server receives user requests through the LINE API, converts them into an appropriate format, and then queries the fact-check database to retrieve relevant information.

[0121] The server uses a generative AI model to determine the authenticity of the information

[0122] The server inputs the acquired information into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing technology to determine whether the received information is true or false.

[0123] The server returns the result of the judgment to the user device.

[0124] The server generates a judgment result and sends it back to the user's device via the LINE API. For example, the result may say, "This news is false information."

[0125] Users review and share results

[0126] Users receive notifications in chat apps, review the information displayed on their screens, and share their findings with friends and family to help prevent the spread of misinformation.

[0127] Prompt Sentence Examples

[0128] Example: A user receives a news item on the LINE app that says, "The latest major earthquake is predicted," and sends a message asking, "Is this news true?"

[0129] This system allows users to quickly obtain reliable information and protects them from misinformation and disinformation. Furthermore, news organizations and fact-checking organizations, which are the sources of information, regularly update their databases to provide the latest information, thereby ensuring the accuracy of the system.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] Process for users to submit information

[0133] Input: Information or questions that users type into a chat app (e.g., "Is this news true?")

[0134] Output: The request sent from the user's device to the server

[0135] How it works: A user uses a chat app (e.g., LINE) on their smartphone or tablet to enter the information they want to check and press the send button. This action sends an information request from the user device to the server.

[0136] Step 2:

[0137] The process by which the server receives and processes the request

[0138] Input: Information request sent from the user's terminal

[0139] Output: Search criteria to run the query

[0140] How it works: The server receives user requests through the LINE API, converts them into an appropriate format, and then generates a query to the fact-checking database based on the received information to search for relevant data.

[0141] Step 3:

[0142] The process by which the server queries the fact-check database

[0143] Input: Server-generated query

[0144] Output: Relevant information retrieved from a fact-checking database

[0145] How it works: The server uses the generated query to search the fact-checking database and retrieve relevant data. For example, it searches for articles and data related to the information "latest major earthquakes."

[0146] Step 4:

[0147] Processing by the server to determine the authenticity of information using a generative AI model

[0148] Input: Search results from a fact-checking database

[0149] Output: The truth or falsity result determined by the generative AI model

[0150] How it works: The server inputs the acquired data into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing to determine whether the given information is true or false.

[0151] Step 5:

[0152] Processing for the server to return the judgment result to the user terminal

[0153] Input: Judgment result of generative AI model

[0154] Output: True or false result sent to user terminal

[0155] How it works: Based on the judgment results generated by the AI ​​model, the server generates a message for the user and sends it back to the user's device using the LINE API. For example, it sends a message saying, "This news is false information."

[0156] Step 6:

[0157] Processing for the user terminal to receive and display the results

[0158] Input: True or false result sent from the server

[0159] Output: The result displayed on the chat app screen

[0160] Operation: The user device receives the truth result sent from the server and displays the result on the chat screen of the LINE app. For example, the text "This news is false" is displayed.

[0161] Step 7:

[0162] Process for users to review and share results

[0163] Input: True or false result displayed in chat app

[0164] Output: Perception and behavior of the user who receives the results

[0165] How it works: Users can view fact-check results displayed in chat and optionally share them with friends and family, helping to prevent the spread of misinformation.

[0166] (Application example 1)

[0167] 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."

[0168] In today's digital information society, the spread of misinformation and false information has become a problem, causing confusion and misunderstanding among users, and even causing harm to users. In particular, in advertising, if consumers act on false information, it could result in economic losses and a loss of trust. In response, there is a demand for systems that allow users to obtain accurate information in real time.

[0169] 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.

[0170] In this invention, the server includes means for determining the authenticity of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from information sources and fact-checking organizations, means for transmitting the authenticity results determined by the information processing device to a user terminal, means for analyzing advertising information captured by a display device that displays advertisements and determining its authenticity, and means for instantly displaying the determination results on the display device, thereby enabling users to check the authenticity of advertising information in real time and make decisions based on accurate information.

[0171] An "information processing device" is a device that manages a fact-check database and determines the truth of information sent by a user.

[0172] A "fact-checking database" is a database that accumulates data obtained from reliable sources and fact-checking organizations and is used to determine the veracity of information.

[0173] A "source" is a primary source of accurate information, such as a reliable news organization or official institution.

[0174] A "fact-checking organization" is an organization that professionally verifies the veracity of information and publishes the results.

[0175] A "user terminal" is a communication device used by a user to send and receive information requests.

[0176] "Advertising" is information intended to promote a particular product or service to consumers.

[0177] A "display device" is a device that allows a user to visually view information. An example is smart glasses.

[0178] A "generative AI model" is an algorithm that uses artificial intelligence technology to automatically determine the veracity of information.

[0179] "Searching" is the process of looking through data in a fact-checking database to find the information you need.

[0180] A "user" is someone who uses the system to verify the authenticity of information.

[0181] "Periodic updating" refers to the operation of collecting the latest data at regular intervals and adding it to the database.

[0182] The "true / false result" is the result of determining whether the information is true or false.

[0183] "Analysis" is the process of examining advertising information in detail and evaluating the authenticity of the content.

[0184] "Real-time" means processing information almost immediately and without delay.

[0185] A "communication application" is software that allows users to exchange messages with a server.

[0186] The present invention is a fact-checking system that operates in cooperation with a user terminal and is centered around an information processing device. The purpose of this system is to determine the authenticity of advertisements in real time and provide the results to users immediately. A specific implementation method is shown below.

[0187] Server Features

[0188] Maintaining a fact-checking database

[0189] The server periodically retrieves data from trusted sources and fact-checking organizations and stores it in a fact-checking database.

[0190] Example: Every day at 2 AM, the server retrieves updated fact-checking data from reliable source A and fact-checking organization B and updates the database.

[0191] Handling the request

[0192] The server receives information requests from users, queries (searches) a fact-checking database, uses a generative AI model to determine the veracity of the information, and returns the results to the user.

[0193] Example: When a user asks "Is this true?" in a chat app, the server searches the information in a database and replies "It's fake."

[0194] Analysis of advertising information

[0195] The server analyzes the advertising information captured by a display device such as smart glasses using OCR technology and determines its authenticity.

[0196] Example: When a user sees an advertisement on their smart glasses that says "Get a huge discount!", this information is sent to a server and checked against a database.

[0197] Display of judgment results

[0198] The server immediately transmits the determined true or false result to the display device so that the user can visually confirm it.

[0199] Example: The server sends the result "This ad is false information" and the result is displayed on the display of the smart glasses.

[0200] User device functions

[0201] Sending information

[0202] The user terminal transmits the information and questions entered by the user to the server.

[0203] Example: When a user types "Is this news true?" in a chat app and sends it, the message is sent to the server.

[0204] Advertisement information capture

[0205] The display device captures the advertising text and sends it to the server.

[0206] Example: Smart glasses convert advertising information that comes into the user's field of vision into text using OCR technology and send it to a server.

[0207] Receiving and displaying results

[0208] The fact check results sent from the server are received and displayed on the display device.

[0209] Example: The server sends the result "This ad is fake" and the result is displayed on the smart glasses.

[0210] User Roles

[0211] Entering information

[0212] The user inputs the information they want to check (e.g., a link or text of a news article) and sends it to the server.

[0213] Example: A user pastes a news link sent by a friend into a chat app and asks, "Is this true?"

[0214] Review and share your results

[0215] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[0216] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[0217] Prompt Sentence Examples

[0218] Describe an application that uses OCR technology to capture advertisement text viewed by users on the street and then checks its veracity against a fact-checking database. This application runs on smart glasses and has the ability to instantly display whether an advertisement is true or false.

[0219] As described above, the present invention is embodied as a system that enables users to check the authenticity of advertisements and information in real time, prevent the spread of false information, and act based on accurate information.

[0220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0221] Step 1:

[0222] A user wears smart glasses and walks around town looking at advertisements. The smart glasses use a camera to capture the advertisement information. Specifically, the smart glasses capture the text information of the advertisement and convert it into text data using OCR technology. The input is the captured image data, and the output is the converted text data.

[0223] Step 2:

[0224] The smart glasses send the text data converted by OCR technology to the server. Specifically, they send the advertisement text as an HTTP request to the server's API endpoint. The input is the text data converted by OCR, and the output is an HTTP request to the server.

[0225] Step 3:

[0226] The server searches the fact-checking database based on the received ad text. Specifically, it issues an SQL query to the database based on the text data sent and retrieves relevant fact-checking information. The input is the ad text data, and the output is the search results from the fact-checking database.

[0227] Step 4:

[0228] The server inputs the search results from the fact-checking database into the generative AI model to evaluate the truth of the advertising information. Specifically, the search results are input into the generative AI model and the probability of determining whether the information is true or false is calculated. The input is the search results from the fact-checking database, and the output is a probability evaluation of the truth or falsehood.

[0229] Step 5:

[0230] The server makes a final judgment on the authenticity of the advertising information based on the probability evaluation obtained from the generative AI model. Specifically, a certain threshold is set and a judgment is made, for example, whether the information is considered true with a probability of 0.8 or higher, or whether it is considered false. The input is the probability evaluation, and the output is the final truth / falseness judgment result.

[0231] Step 6:

[0232] The server sends the final truth-or-false judgment result to the smart glasses. Specifically, it returns the judgment result to the smart glasses as an HTTP response. The input is the truth-or-false judgment result, and the output is the HTTP response.

[0233] Step 7:

[0234] The smart glasses display the received truthfulness result on the display. Specifically, to visually present the truthfulness result to the user, they display a message on the display saying "This advertisement is true" or "This advertisement is false." The input is the truthfulness result of the HTTP response, and the output is the display visible to the user.

[0235] Through these steps, users can verify the authenticity of advertising information in real time, preventing the spread of misinformation and enabling users to make decisions based on accurate information.

[0236] 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.

[0237] This invention is a fact-checking system that combines a user terminal and an emotion engine with an information processing device (hereinafter referred to as a server) at its core. We will explain the specific means and process for effectively identifying false and misleading information and providing appropriate messages based on the user's emotions.

[0238] Server Features

[0239] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[0240] Maintaining a fact-checking database

[0241] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[0242] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[0243] Handling the request

[0244] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[0245] Example: When a user asks "Is this true?" on LINE, the server searches the database for the information and replies "This is false information."

[0246] Compensation distribution management

[0247] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[0248] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[0249] Collaboration with emotion engine

[0250] The server receives the user's emotion data from the emotion engine and adjusts the response message based on the data.

[0251] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[0252] User device functions

[0253] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[0254] Sending information

[0255] The user terminal transmits the information and questions entered by the user to the server.

[0256] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[0257] Receiving the results

[0258] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[0259] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[0260] User Roles

[0261] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[0262] Entering information

[0263] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[0264] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[0265] Review and share your results

[0266] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[0267] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[0268] Emotion Engine Functions

[0269] The emotion engine analyzes information requests from users and determines the user's emotions.

[0270] Emotion determination

[0271] The emotion engine analyzes the user's text data to determine the emotion, and transmits the emotion data to the server.

[0272] Example: If a user sends a request saying "I am very worried about this news," the emotion engine will determine the answer as "worried" and send that data to the server.

[0273] Sending emotional data

[0274] The emotion engine sends the determined emotion data to the server, which uses it to tailor a response message.

[0275] Example: The emotion engine determines emotion data as "worry" and sends it to the server, which then generates a message saying, "This news is fake. Don't worry."

[0276] In this way, the server, user device, and emotion engine work together to realize a system that prevents the spread of false and misleading information and provides appropriate responses according to the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[0277] The processing flow will be explained below.

[0278] Step 1:

[0279] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[0280] Step 2:

[0281] Users enter the information they want to check or a link to a news article in the message field, add a question like "Is this true? I'm very worried," and press the send button.

[0282] Step 3:

[0283] The terminal generates a request to send the message input by the user to the emotion engine.

[0284] Step 4:

[0285] The device sends the generated request to the emotion engine.

[0286] Step 5:

[0287] The emotion engine receives the message sent by the user and analyzes the text data.

[0288] Step 6:

[0289] The emotion engine analyzes the text data, determines the user's emotion as "worry," and generates emotion data.

[0290] Step 7:

[0291] The emotion engine returns the generated emotion data to the terminal.

[0292] Step 8:

[0293] The terminal generates a request to transmit the emotion data received from the emotion engine to the server.

[0294] Step 9:

[0295] The terminal sends the generated request to the server.

[0296] Step 10:

[0297] The server receives the emotion data sent from the terminal and the user's information request.

[0298] Step 11:

[0299] The server queries (searches) the fact-checking database based on the received user information request.

[0300] Step 12:

[0301] The server inputs the search results into an AI model to determine whether the information is true or false.

[0302] Step 13:

[0303] The server generates a message to respond to the user based on the AI ​​model's judgment and emotional data, such as "Don't worry. This information is fake."

[0304] Step 14:

[0305] The server sends the generated response message to the terminal.

[0306] Step 15:

[0307] The terminal receives the response message sent from the server.

[0308] Step 16:

[0309] The device will display the received message on the chat screen of the LINE app.

[0310] Step 17:

[0311] The user opens the chat screen of the LINE app and checks the response message from the server, which may say, for example, "Don't worry. This news is fake."

[0312] Step 18:

[0313] Users can judge the authenticity of the information based on the results they receive, and share their judgment with friends and family. They can also feel reassured by receiving messages that correspond to their emotions.

[0314] Example 2

[0315] 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."

[0316] In modern society, false and misinformation often spreads rapidly on the Internet, resulting in a decline in the reliability of information. Another issue is that users' exposure to such uncertain information can easily cause anxiety and confusion. Conventional fact-checking systems struggle to reduce the psychological burden placed on users by simply determining the veracity of information. Therefore, there is a need for systems that can accurately determine the veracity of false and misinformation and provide appropriate messages tailored to the user's emotions, thereby increasing the user's sense of security.

[0317] 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.

[0318] In this invention, the server includes means for determining the truth of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for transmitting the truthfulness results determined by the information processing device to a user terminal, means for determining the user's emotions using an emotion analysis engine, and means for adjusting a response message to the user based on the user's emotion data. This makes it possible to accurately determine false information and misinformation, as well as provide an appropriate response message according to the user's emotions.

[0319] An "information processing device" is a device that has the function of receiving information sent from a user, analyzing and processing the information, and sending the results.

[0320] A "fact-checking database" is a database that accumulates data used to determine the veracity of false information or misinformation.

[0321] "News organizations" are organizations that provide information to the public, such as newspapers, television stations, and internet news sites.

[0322] A "fact-checking organization" is an organization that verifies the accuracy of information provided by media outlets and individuals and publishes the results.

[0323] A "user terminal" is a device that allows a user to input information and communicate with a server, such as a smartphone or a personal computer.

[0324] An "emotion analysis engine" is software or a system that analyzes text data sent by a user and determines the user's emotions.

[0325] A "generative AI model" is a model that uses artificial intelligence to automatically determine the truth or falsity of information.

[0326] A "prompt sentence" is a text sentence that indicates a question or request that a user enters into the system.

[0327] The "true / false result" is the result of determining whether the transmitted information is true or false.

[0328] A "response message" is a message generated by a server to reply to a user.

[0329] This invention relates to a fact-checking system that combines a user terminal and a sentiment analysis engine with an information processing device as its core. This system effectively identifies false and misleading information and provides appropriate messages based on the user's sentiment.

[0330] Server Features

[0331] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[0332] Maintaining a fact-checking database

[0333] The server regularly retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[0334] Example: A server retrieves updated data from news organizations and fact-checking groups every day at 2 AM and updates the database.

[0335] Handling the request

[0336] The server receives information requests from users, queries (searches) the database, uses a generative AI model to determine the authenticity of the information, and returns the results to the user.

[0337] Example: If a user asks "Is this news true?" on the LINE app, the server searches the information in the database and replies "It's fake news."

[0338] Collaboration with sentiment analysis engine

[0339] The server receives the user's emotional data from the emotion analysis engine and adjusts the response message based on that data.

[0340] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[0341] User device functions

[0342] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[0343] Sending information

[0344] The user terminal transmits the information and questions entered by the user to the server.

[0345] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[0346] Receiving the results

[0347] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[0348] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[0349] User Roles

[0350] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[0351] Entering information

[0352] The user enters the information they want to check into the LINE app and sends it to the server.

[0353] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[0354] Review and share your results

[0355] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[0356] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[0357] Sentiment Analysis Engine Features

[0358] The emotion analysis engine analyzes information requests from users and determines their emotions.

[0359] Emotion determination

[0360] The emotion analysis engine analyzes the user's text data to determine their emotion and transmits the emotion data to the server.

[0361] Example: If a user sends a request saying "I am very worried about this news," the sentiment analysis engine will determine the answer as "worried" and send that data to the server.

[0362] Sending emotional data

[0363] The emotion analysis engine sends the determined emotion data to the server, which uses it to tailor a response message.

[0364] Example: An emotion analysis engine sends emotional data that it determines to be "worried" to a server, which then generates a message saying, "This news is fake. Don't worry."

[0365] This allows the server, user devices, and emotion analysis engine to work together to create a system that prevents the spread of false and misleading information and provides appropriate responses based on the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[0366] Prompt Sentence Examples

[0367] Is this news true?

[0368] I heard about this information, but I would like to know if it is true.

[0369] I am very concerned about this information. Please confirm if it is correct.

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] Step 1:

[0372] Users open the LINE app, enter the information or question they want to have fact-checked, and tap the send button.

[0373] Specific action: The user types "Is this news true?" and taps the send button.

[0374] Input: Text data entered by the user.

[0375] Output: Text data sent through the LINE app.

[0376] Step 2:

[0377] The user device sends the entered information to the fact-checking system server via the LINE server.

[0378] Specific operation: The text data sent by the user passes through the LINE server and arrives at the system server.

[0379] Input: Text data sent from the LINE app.

[0380] Output: The text data received by the server.

[0381] Step 3:

[0382] The server uses a natural language processing (NLP) engine to analyze the received text data.

[0383] Specific operation: The server uses an NLP engine to analyze text data, extract keywords, and decompose sentences.

[0384] Input: Text data received by the server.

[0385] Output: Parsed text data (keywords and sentences).

[0386] Step 4:

[0387] The server sends the received information to an emotion analysis engine to determine the user's emotion.

[0388] Specific operation: The server sends the parsed text data to the sentiment analysis engine, which analyzes the text and generates sentiment labels.

[0389] Input: Parsed text data.

[0390] Output: Sentiment data returned by the sentiment analysis engine (e.g., "worried").

[0391] Step 5:

[0392] The server queries a fact-checking database and uses a generative AI model to determine whether the information is true or false.

[0393] Specific operation: The server searches the fact-check database, and the generative AI model scores the degree of agreement and obtains a truth judgment result.

[0394] Input: Parsed text data.

[0395] Output: The truth-check result obtained from the fact-check database.

[0396] Step 6:

[0397] The server receives the emotion data returned from the emotion analysis engine.

[0398] Specific operation: The server receives the emotion data sent from the emotion analysis engine.

[0399] Input: Sentiment data sent from the sentiment analysis engine.

[0400] Output: Emotion data received by the server.

[0401] Step 7:

[0402] The server generates a response message to be sent to the user based on the fact-check results and emotion data.

[0403] Specific operation: The server combines the fact-check results with the emotion data to generate an appropriate response message for the user, such as "This news is fake. Don't worry."

[0404] Input: Fact-check results and sentiment data.

[0405] Output: The generated response message.

[0406] Step 8:

[0407] The server sends the generated response message to the user terminal.

[0408] Specific operation: The server generates a response message and sends it to the user's device via the LINE server.

[0409] Input: The generated response message.

[0410] Output: The response message sent to the user terminal.

[0411] Step 9:

[0412] The user device receives the message sent from the server and displays it on the chat screen of the LINE app.

[0413] Specific operation: The LINE app receives the message sent from the server and displays it on the chat screen.

[0414] Input: The response message sent by the server.

[0415] Output: The response message displayed on the LINE app chat screen.

[0416] Step 10:

[0417] The user checks the chat screen in the LINE app and reads the response from the server.

[0418] Specific operation: The user opens the LINE app and checks the reply message displayed on the chat screen. They feel reassured when they see that the message is false.

[0419] Input: The message displayed on the chat screen of the LINE app.

[0420] Output: The message the user acknowledged and their relief.

[0421] (Application example 2)

[0422] 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."

[0423] Conventional fact-checking systems require users to manually input information and obtain results based on that information, which can be time-consuming and tedious to operate. Furthermore, because the system does not take the user's feelings into account when determining the veracity of information, the anxiety and concerns of users who receive the results may not be fully alleviated. Furthermore, the lack of a function to assess visually viewed information in real time makes it difficult to quickly prevent the spread of misinformation and disinformation.

[0424] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for determining the veracity of information sent by a user using a fact-checking database managed by the information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for capturing information viewed from the user terminal, automatically converting it to text, and sending the result to the information processing device, means for analyzing the user's emotions using an emotion engine and sending the result to the information processing device, and means for sending to the user terminal a response message based on the veracity result determined by the information processing device and the analyzed emotion. This makes it possible to capture information viewed by the user in real time, instantly determine its veracity, and provide feedback that takes the user's emotions into consideration.

[0425] An "information processing device" is a device that determines the veracity of information sent by users and manages and updates the fact-check database.

[0426] A "fact-checking database" is a database that accumulates and manages data provided by trusted news organizations and fact-checking organizations and is used to determine the veracity of information.

[0427] A "news organization" is an organization or group that creates and disseminates news, articles, etc.

[0428] A "fact-checking organization" is an organization or group that specializes in verifying the veracity of information and publishing it.

[0429] A "user terminal" is a device that a user uses to communicate with an information processing device, and includes a smartphone, smart glasses, and the like.

[0430] "Viewing" refers to a user visually checking information through a device.

[0431] "Capture" refers to obtaining visually recognized information as digital data.

[0432] "Textualization" refers to converting visually recognized information into text data.

[0433] An "emotion engine" is a system that analyzes user input data, determines emotions, and provides the results to other systems.

[0434] A "generative AI model" is a machine learning model that is trained on large datasets to perform tasks such as natural language processing.

[0435] The "response message" is a feedback message that is generated by the information processing device based on the determination result and sent to the user.

[0436] This invention can be realized as a system consisting of an information processing device (hereinafter referred to as a server), a user terminal, and an emotion engine. Each element of this system will be described in detail below.

[0437] server

[0438] The server has the following main functions:

[0439] 1. Maintaining and updating the fact-check database:

[0440] The server periodically retrieves fact-checking data from trusted news outlets and fact-checking organizations and updates the fact-checking database, which is managed using a database management system such as MySQL.

[0441] 2. Authenticity determination:

[0442] The server searches the information sent by the user against a fact-checking database and determines the authenticity of the information using a generative AI model (e.g., BERT or GPT-based models).

[0443] 3. Sentiment analysis and response message generation:

[0444] The server receives the user's emotion data sent from the emotion engine and adjusts the response message based on that information.

[0445] User terminal

[0446] User devices include smartphones and smart glasses, and have the following functions:

[0447] 1. Information capture and transcription:

[0448] The information the user sees is captured by a camera and automatically converted into text using OCR (Optical Character Recognition) technology.

[0449] 2. Sending and Receiving Information:

[0450] The textual information and the user's emotional data are sent to the server, and a response message is received from the server and displayed to the user.

[0451] Emotion Engine

[0452] The emotion engine is a system that analyzes user input data and determines emotions. It has the following functions:

[0453] 1. Emotion determination:

[0454] The user's text data is analyzed to determine their emotions. This process is carried out using IBM Watson's sentiment analysis API.

[0455] 2. Sending Emotional Data:

[0456] The determined emotion data is transmitted to the server.

[0457] Example of processing flow

[0458] Here is a concrete example of how the system actually works.

[0459] 1. The user views information on a social networking site using smart glasses.

[0460] 2. Information is captured by the camera and converted into text using OCR technology.

[0461] 3. The textual information is sent to the server.

[0462] 4. Check the accuracy of information using fact-checking databases.

[0463] 5. The emotion engine analyzes the user's emotion and determines, for example, "worry."

[0464] 6. The server generates a response message saying, "This information is fake. Don't worry."

[0465] 7. The message will appear on the smart glasses display.

[0466] Example prompts to input to the generative AI model

[0467] Below is an example of a prompt sentence to input to the generative AI model.

[0468] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[0469] Such a system configuration and processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into consideration the user's feelings.

[0470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0471] Step 1:

[0472] A user visually views information on a social networking site using smart glasses. The camera installed in the smart glasses captures the viewed information and converts it into text using OCR (Optical Character Recognition) technology. The input at this time is the viewed image data, and the output is the converted text information.

[0473] Step 2:

[0474] The textual information is sent from the smart glasses to the server. This process involves data communication from the device to the server. The server then begins analyzing the received text data.

[0475] Step 3:

[0476] The server searches a fact-checking database based on the received text data to verify the authenticity of the information. The input here is the text data, and the output from the fact-checking database is the truthfulness determination result. Additional analysis is performed using an AI model (e.g., BERT or GPT-based models).

[0477] Step 4:

[0478] The emotion engine analyzes the text data sent by the user and determines the user's emotion. The input is the user's text data, and the output is the emotion determination result. The emotion engine performs this process using, for example, IBM Watson's emotion analysis API.

[0479] Step 5:

[0480] The emotion data determined by the emotion engine is sent to the server. The server integrates this emotion data and generates an appropriate response message along with the truth / false judgment result. The input here is the truth / false judgment result and emotion data, and the output is the response message sent to the user.

[0481] Step 6:

[0482] The server then sends the generated response message to the user's smart glasses, where data communication occurs to provide the message to the user in real time, with the final output being the response message displayed on the smart glasses' display.

[0483] Example of processing flow

[0484] Here is a concrete example of how the system actually works.

[0485] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[0486] This processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into account the user's feelings.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] [Second embodiment]

[0491] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0492] 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.

[0493] 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).

[0494] 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.

[0495] 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.

[0496] 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).

[0497] 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.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] In the smart glasses 214, 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.

[0502] 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."

[0503] This paper describes a fake check system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). Specific means and processes for effectively detecting fake and misleading information and providing it to users are described.

[0504] Server Features

[0505] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[0506] Maintaining a fact-checking database

[0507] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[0508] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[0509] Handling the request

[0510] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[0511] Example: When a user asks "Is this true?" on LINE, the server searches the information in its database and replies, "This is false information."

[0512] Compensation distribution management

[0513] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[0514] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[0515] User device functions

[0516] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[0517] Sending information

[0518] The user terminal transmits the information and questions entered by the user to the server.

[0519] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[0520] Receiving the results

[0521] The fact-check results sent from the server are received and displayed on the chat screen of the LINE app.

[0522] Example: When the server responds, "This news is fake," the result is displayed on the LINE chat screen.

[0523] User Roles

[0524] Users can interact with the system using apps such as LINE to verify the authenticity of the information.

[0525] Entering information

[0526] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[0527] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[0528] Review and share your results

[0529] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[0530] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[0531] Specific examples of implementation

[0532] For example, suppose a user receives the news that "The latest major earthquake is predicted." The user enters this information into the LINE app and sends a message asking, "Is this true?" The information sent from the user's device is received by the server, which searches the information in a fact-checking database. The AI ​​model determines the result, and if it determines, for example, that "this information is false," the result is sent back to the user's device and displayed on the LINE chat screen. The user sees this result, realizes that it is false information, and shares it with their friends.

[0533] In this way, a system is realized in which the server, user terminals, and users cooperate to prevent the spread of false and misinformation and promote access to accurate information. This system ensures the accuracy of information and also contributes to the activation of news organizations and fact-checking organizations.

[0534] The processing flow will be explained below.

[0535] Step 1:

[0536] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[0537] Step 2:

[0538] Users enter the information they want to check or a link to a news article in the message field, add the question "Is this true?" and press the send button.

[0539] Step 3:

[0540] The terminal generates a request to send the message entered by the user to the server.

[0541] Step 4:

[0542] The device sends the generated request to the FNT account server.

[0543] Step 5:

[0544] The server receives the request sent from the terminal.

[0545] Step 6:

[0546] The server analyzes the received message and extracts the user's question and the information they wish to confirm.

[0547] Step 7:

[0548] The server queries (searches) a fact-checking database based on the extracted information.

[0549] Step 8:

[0550] The server inputs the search results into an AI model to determine whether the information is true or false.

[0551] Step 9:

[0552] The server generates a message to respond to the user based on the AI ​​model's judgment results.

[0553] Step 10:

[0554] The server sends the generated response message to the terminal.

[0555] Step 11:

[0556] The terminal receives the response message sent from the server.

[0557] Step 12:

[0558] The device will display the received message on the chat screen of the LINE app.

[0559] Step 13:

[0560] The user opens the chat screen in the LINE app and checks the response message from the server.

[0561] Step 14:

[0562] Based on the results received, users can determine the authenticity of the information and share their results with friends and family.

[0563] Example 1

[0564] 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."

[0565] False and misleading information is frequently circulating on the Internet, making it difficult for users to quickly and accurately verify the authenticity of information. In particular, ordinary users who lack the ability to verify the reliability of information are at high risk of being misled by misinformation. For this reason, there is a need for a system that can effectively identify false and misleading information based on reliable information sources and provide it to users.

[0566] 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.

[0567] In this invention, the server includes means for determining the authenticity of information sent from a user terminal, means for periodically updating a fact-check database from an information source, means for transmitting the authenticity results determined by the information processing device to the user terminal, means for determining the authenticity of the information using a generative AI model, and means for the user terminal to send and receive information requests via a chat app. This allows users to quickly check the authenticity of information via the chat app and prevents the spread of false information.

[0568] An "information processing device" is a computer system for processing, managing, and analyzing data.

[0569] A "fact-checking database" is a collection of data used to accumulate and manage highly reliable information and determine whether the information is true or false.

[0570] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet, that provides a means for sending and receiving information.

[0571] "Means for determining authenticity" refers to the algorithms or models used to determine the authenticity of received information.

[0572] A "source" is a source used to provide accurate information, such as a reputable news organization or fact-checking organization.

[0573] A "generative AI model" is a model generated using artificial intelligence, which analyzes and judges information based on natural language processing.

[0574] "Chat app" means a software application that allows users to send and receive messages in real time, including LINE and other messaging apps.

[0575] An "information request" is an inquiry that a user sends by specifying the information they want to confirm.

[0576] The "true / false result" is the result of determining whether the received information is true or false.

[0577] The present invention is a fact-checking system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). This system effectively identifies false and misleading information and provides users with accurate results.

[0578] The server manages a fact-checking database and plays an important role in determining the veracity of information sent by users. The fact-checking database stores reliable information, and the server searches and analyzes information based on this database.

[0579] Hardware and software used

[0580] The server uses a high-performance computer system to build and manage the fact-checking database. It uses a database management system (e.g., MySQL, PostgreSQL, etc.) to efficiently process and store large amounts of data. It also uses a generative AI model (e.g., GPT-4) to determine the veracity of the information it receives.

[0581] User devices are devices such as smartphones, tablets, and PCs, and communicate with the server primarily using chat apps (e.g., LINE). Users send information via the chat app and receive the judgment results from the server.

[0582] Specific actions

[0583] User submits information

[0584] A user uses a chat app (such as LINE) installed on a smartphone or tablet to enter and send the information they want to check. For example, a user might type "Is this news true?" into the LINE app and send it.

[0585] The server receives and processes the request

[0586] The server receives user requests through the LINE API, converts them into an appropriate format, and then queries the fact-check database to retrieve relevant information.

[0587] The server uses a generative AI model to determine the authenticity of the information

[0588] The server inputs the acquired information into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing technology to determine whether the received information is true or false.

[0589] The server returns the result of the judgment to the user device.

[0590] The server generates a judgment result and sends it back to the user's device via the LINE API. For example, the result may say, "This news is false information."

[0591] Users review and share results

[0592] Users receive notifications in chat apps, review the information displayed on their screens, and share their findings with friends and family to help prevent the spread of misinformation.

[0593] Prompt Sentence Examples

[0594] Example: A user receives a news item on the LINE app that says, "The latest major earthquake is predicted," and sends a message asking, "Is this news true?"

[0595] This system allows users to quickly obtain reliable information and protects them from misinformation and disinformation. Furthermore, news organizations and fact-checking organizations, which are the sources of information, regularly update their databases to provide the latest information, thereby ensuring the accuracy of the system.

[0596] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0597] Step 1:

[0598] Process for users to submit information

[0599] Input: Information or questions that users type into a chat app (e.g., "Is this news true?")

[0600] Output: The request sent from the user's device to the server

[0601] How it works: A user uses a chat app (e.g., LINE) on their smartphone or tablet to enter the information they want to check and press the send button. This action sends an information request from the user device to the server.

[0602] Step 2:

[0603] The process by which the server receives and processes the request

[0604] Input: Information request sent from the user's terminal

[0605] Output: Search criteria to run the query

[0606] How it works: The server receives user requests through the LINE API, converts them into an appropriate format, and then generates a query to the fact-checking database based on the received information to search for relevant data.

[0607] Step 3:

[0608] The process by which the server queries the fact-check database

[0609] Input: Server-generated query

[0610] Output: Relevant information retrieved from a fact-checking database

[0611] How it works: The server uses the generated query to search the fact-checking database and retrieve relevant data. For example, it searches for articles and data related to the information "latest major earthquakes."

[0612] Step 4:

[0613] Processing by the server to determine the authenticity of information using a generative AI model

[0614] Input: Search results from a fact-checking database

[0615] Output: The truth or falsity result determined by the generative AI model

[0616] How it works: The server inputs the acquired data into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing to determine whether the given information is true or false.

[0617] Step 5:

[0618] Processing for the server to return the judgment result to the user terminal

[0619] Input: Judgment result of generative AI model

[0620] Output: True or false result sent to user terminal

[0621] How it works: Based on the judgment results generated by the AI ​​model, the server generates a message for the user and sends it back to the user's device using the LINE API. For example, it sends a message saying, "This news is false information."

[0622] Step 6:

[0623] Processing for the user terminal to receive and display the results

[0624] Input: True or false result sent from the server

[0625] Output: The result displayed on the chat app screen

[0626] Operation: The user device receives the truth result sent from the server and displays the result on the chat screen of the LINE app. For example, the text "This news is false" is displayed.

[0627] Step 7:

[0628] Process for users to review and share results

[0629] Input: True or false result displayed in chat app

[0630] Output: Perception and behavior of the user who receives the results

[0631] How it works: Users can view fact-check results in the chat and optionally share them with friends and family, helping to prevent the spread of misinformation.

[0632] (Application example 1)

[0633] 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."

[0634] In today's digital information society, the spread of misinformation and false information has become a problem, causing confusion and misunderstanding among users, and even causing harm to users. In particular, in advertising, if consumers act on false information, it could result in economic losses and a loss of trust. In response, there is a demand for systems that allow users to obtain accurate information in real time.

[0635] 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.

[0636] In this invention, the server includes means for determining the authenticity of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from information sources and fact-checking organizations, means for transmitting the authenticity results determined by the information processing device to a user terminal, means for analyzing advertising information captured by a display device that displays advertisements and determining its authenticity, and means for instantly displaying the determination results on the display device, thereby enabling users to check the authenticity of advertising information in real time and make decisions based on accurate information.

[0637] An "information processing device" is a device that manages a fact-check database and determines the truth of information sent by a user.

[0638] A "fact-checking database" is a database that accumulates data obtained from reliable sources and fact-checking organizations and is used to determine the veracity of information.

[0639] A "source" is a primary source of accurate information, such as a reliable news organization or official institution.

[0640] A "fact-checking organization" is an organization that professionally verifies the veracity of information and publishes the results.

[0641] A "user terminal" is a communication device used by a user to send and receive information requests.

[0642] "Advertising" is information intended to promote a particular product or service to consumers.

[0643] A "display device" is a device that allows a user to visually view information. An example is smart glasses.

[0644] A "generative AI model" is an algorithm that uses artificial intelligence technology to automatically determine the veracity of information.

[0645] "Searching" is the process of looking through data in a fact-checking database to find the information you need.

[0646] A "user" is someone who uses the system to verify the authenticity of information.

[0647] "Periodic updating" refers to the operation of collecting the latest data at regular intervals and adding it to the database.

[0648] The "true / false result" is the result of determining whether the information is true or false.

[0649] "Analysis" is the process of examining advertising information in detail and evaluating the authenticity of the content.

[0650] "Real-time" means processing information almost immediately and without delay.

[0651] A "communication application" is software that allows users to exchange messages with a server.

[0652] The present invention is a fact-checking system that operates in cooperation with a user terminal and is centered around an information processing device. The purpose of this system is to determine the authenticity of advertisements in real time and provide the results to users immediately. The specific implementation method is shown below.

[0653] Server Features

[0654] Maintaining a fact-checking database

[0655] The server periodically retrieves data from trusted sources and fact-checking organizations and stores it in a fact-checking database.

[0656] Example: Every day at 2 AM, the server retrieves updated fact-checking data from reliable source A and fact-checking organization B and updates the database.

[0657] Handling the request

[0658] The server receives information requests from users, queries (searches) a fact-checking database, uses a generative AI model to determine the veracity of the information, and returns the results to the user.

[0659] Example: When a user asks "Is this true?" in a chat app, the server searches the information in a database and replies "It's fake."

[0660] Analysis of advertising information

[0661] The server analyzes the advertising information captured by a display device such as smart glasses using OCR technology and determines its authenticity.

[0662] Example: When a user sees an advertisement on their smart glasses that says "Get a huge discount!", this information is sent to a server and checked against a database.

[0663] Display of judgment results

[0664] The server immediately transmits the determined true or false result to the display device so that the user can visually confirm it.

[0665] Example: The server sends the result "This ad is false information" and the result is displayed on the display of the smart glasses.

[0666] User device functions

[0667] Sending information

[0668] The user terminal transmits the information and questions entered by the user to the server.

[0669] Example: When a user types "Is this news true?" in a chat app and sends it, the message is sent to the server.

[0670] Advertisement information capture

[0671] The display device captures the advertising text and sends it to the server.

[0672] Example: Smart glasses convert advertising information that comes into the user's field of vision into text using OCR technology and send it to a server.

[0673] Receiving and displaying results

[0674] The fact check results sent from the server are received and displayed on the display device.

[0675] Example: The server sends the result "This ad is fake" and the result is displayed on the smart glasses.

[0676] User Roles

[0677] Entering information

[0678] The user inputs the information they want to check (e.g., a link or text of a news article) and sends it to the server.

[0679] Example: A user pastes a news link sent by a friend into a chat app and asks, "Is this true?"

[0680] Review and share your results

[0681] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[0682] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[0683] Prompt Sentence Examples

[0684] Describe an application that uses OCR technology to capture advertisement text viewed by users on the street and then checks its veracity against a fact-checking database. This application runs on smart glasses and has the ability to instantly display whether an advertisement is true or false.

[0685] As described above, the present invention is embodied as a system that enables users to check the authenticity of advertisements and information in real time, prevent the spread of false information, and act based on accurate information.

[0686] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0687] Step 1:

[0688] A user wears smart glasses and walks around town looking at advertisements. The smart glasses use a camera to capture the advertisement information. Specifically, the smart glasses capture the text information of the advertisement and convert it into text data using OCR technology. The input is the captured image data, and the output is the converted text data.

[0689] Step 2:

[0690] The smart glasses send the text data converted by OCR technology to the server. Specifically, they send the advertisement text as an HTTP request to the server's API endpoint. The input is the text data converted by OCR, and the output is an HTTP request to the server.

[0691] Step 3:

[0692] The server searches the fact-checking database based on the received ad text. Specifically, it issues an SQL query to the database based on the text data sent and retrieves relevant fact-checking information. The input is the ad text data, and the output is the search results from the fact-checking database.

[0693] Step 4:

[0694] The server inputs the search results from the fact-checking database into the generative AI model to evaluate the truth of the advertising information. Specifically, the search results are input into the generative AI model and the probability of determining whether the information is true or false is calculated. The input is the search results from the fact-checking database, and the output is a probability evaluation of the truth or falsehood.

[0695] Step 5:

[0696] The server makes a final judgment on the authenticity of the advertising information based on the probability evaluation obtained from the generative AI model. Specifically, a certain threshold is set and a judgment is made, for example, whether the information is considered true with a probability of 0.8 or higher, or whether it is considered false. The input is the probability evaluation, and the output is the final truth / falseness judgment result.

[0697] Step 6:

[0698] The server sends the final truth-or-false judgment result to the smart glasses. Specifically, it returns the judgment result to the smart glasses as an HTTP response. The input is the truth-or-false judgment result, and the output is the HTTP response.

[0699] Step 7:

[0700] The smart glasses display the received truthfulness result on the display. Specifically, to visually present the truthfulness result to the user, they display a message on the display saying "This advertisement is true" or "This advertisement is false." The input is the truthfulness result of the HTTP response, and the output is the display visible to the user.

[0701] Through these steps, users can verify the authenticity of advertising information in real time, preventing the spread of misinformation and enabling users to make decisions based on accurate information.

[0702] 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.

[0703] This invention is a fact-checking system that combines a user terminal and an emotion engine with an information processing device (hereinafter referred to as a server) at its core. We will explain the specific means and process for effectively identifying false and misleading information and providing appropriate messages based on the user's emotions.

[0704] Server Features

[0705] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[0706] Maintaining a fact-checking database

[0707] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[0708] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[0709] Handling the request

[0710] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[0711] Example: When a user asks "Is this true?" on LINE, the server searches the information in its database and replies, "This is false information."

[0712] Compensation distribution management

[0713] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[0714] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[0715] Collaboration with emotion engine

[0716] The server receives the user's emotion data from the emotion engine and adjusts the response message based on the data.

[0717] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[0718] User device functions

[0719] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[0720] Sending information

[0721] The user terminal transmits the information and questions entered by the user to the server.

[0722] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[0723] Receiving the results

[0724] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[0725] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[0726] User Roles

[0727] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[0728] Entering information

[0729] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[0730] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[0731] Review and share your results

[0732] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[0733] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[0734] Emotion Engine Functions

[0735] The emotion engine analyzes information requests from users and determines the user's emotions.

[0736] Emotion determination

[0737] The emotion engine analyzes the user's text data to determine the emotion, and transmits the emotion data to the server.

[0738] Example: If a user sends a request saying "I am very worried about this news," the emotion engine will determine the answer as "worried" and send that data to the server.

[0739] Sending emotional data

[0740] The emotion engine sends the determined emotion data to the server, which uses it to tailor a response message.

[0741] Example: The emotion engine determines emotion data as "worry" and sends it to the server, which then generates a message saying, "This news is fake. Don't worry."

[0742] In this way, the server, user device, and emotion engine work together to realize a system that prevents the spread of false and misleading information and provides appropriate responses according to the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[0743] The processing flow will be explained below.

[0744] Step 1:

[0745] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[0746] Step 2:

[0747] Users enter the information they want to check or a link to a news article in the message field, add a question like "Is this true? I'm very worried," and press the send button.

[0748] Step 3:

[0749] The terminal generates a request to send the message input by the user to the emotion engine.

[0750] Step 4:

[0751] The device sends the generated request to the emotion engine.

[0752] Step 5:

[0753] The emotion engine receives the message sent by the user and analyzes the text data.

[0754] Step 6:

[0755] The emotion engine analyzes the text data, determines the user's emotion as "worry," and generates emotion data.

[0756] Step 7:

[0757] The emotion engine returns the generated emotion data to the terminal.

[0758] Step 8:

[0759] The terminal generates a request to transmit the emotion data received from the emotion engine to the server.

[0760] Step 9:

[0761] The terminal sends the generated request to the server.

[0762] Step 10:

[0763] The server receives the emotion data sent from the terminal and the user's information request.

[0764] Step 11:

[0765] The server queries (searches) the fact-checking database based on the received user information request.

[0766] Step 12:

[0767] The server inputs the search results into an AI model to determine whether the information is true or false.

[0768] Step 13:

[0769] The server generates a message to respond to the user based on the AI ​​model's judgment and emotional data, such as "Don't worry. This information is fake."

[0770] Step 14:

[0771] The server sends the generated response message to the terminal.

[0772] Step 15:

[0773] The terminal receives the response message sent from the server.

[0774] Step 16:

[0775] The device will display the received message on the chat screen of the LINE app.

[0776] Step 17:

[0777] The user opens the chat screen of the LINE app and checks the response message from the server, which may say, for example, "Don't worry. This news is fake."

[0778] Step 18:

[0779] Users can judge the authenticity of the information based on the results they receive, and share their judgment with friends and family. They can also feel reassured by receiving messages that correspond to their emotions.

[0780] Example 2

[0781] 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."

[0782] In modern society, false and misinformation often spreads rapidly on the Internet, resulting in a decline in the reliability of information. Another issue is that users' exposure to such uncertain information can easily cause anxiety and confusion. Conventional fact-checking systems struggle to reduce the psychological burden placed on users by simply determining the veracity of information. Therefore, there is a need for systems that can accurately determine the veracity of false and misinformation and provide appropriate messages tailored to the user's emotions, thereby increasing the user's sense of security.

[0783] 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.

[0784] In this invention, the server includes means for determining the truth of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for transmitting the truthfulness results determined by the information processing device to a user terminal, means for determining the user's emotions using an emotion analysis engine, and means for adjusting a response message to the user based on the user's emotion data. This makes it possible to accurately determine false information and misinformation, as well as provide an appropriate response message according to the user's emotions.

[0785] An "information processing device" is a device that has the function of receiving information sent from a user, analyzing and processing the information, and sending the results.

[0786] A "fact-checking database" is a database that accumulates data used to determine the veracity of false information or misinformation.

[0787] "News organizations" are organizations that provide information to the public, such as newspapers, television stations, and internet news sites.

[0788] A "fact-checking organization" is an organization that verifies the accuracy of information provided by media outlets and individuals and publishes the results.

[0789] A "user terminal" is a device that allows a user to input information and communicate with a server, such as a smartphone or a personal computer.

[0790] An "emotion analysis engine" is software or a system that analyzes text data sent by a user and determines the user's emotions.

[0791] A "generative AI model" is a model that uses artificial intelligence to automatically determine the truth or falsity of information.

[0792] A "prompt sentence" is a text sentence that indicates a question or request that a user enters into the system.

[0793] The "true / false result" is the result of determining whether the transmitted information is true or false.

[0794] A "response message" is a message generated by a server to reply to a user.

[0795] This invention relates to a fact-checking system that combines a user terminal and a sentiment analysis engine with an information processing device as its core. This system effectively identifies false and misleading information and provides appropriate messages based on the user's sentiment.

[0796] Server Features

[0797] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[0798] Maintaining a fact-checking database

[0799] The server regularly retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[0800] Example: A server retrieves updated data from news organizations and fact-checking organizations every day at 2 AM and updates the database.

[0801] Handling the request

[0802] The server receives information requests from users, queries (searches) the database, uses a generative AI model to determine the authenticity of the information, and returns the results to the user.

[0803] Example: If a user asks "Is this news true?" on the LINE app, the server searches the information in the database and replies "It's fake news."

[0804] Collaboration with sentiment analysis engine

[0805] The server receives the user's emotional data from the emotion analysis engine and adjusts the response message based on that data.

[0806] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[0807] User device functions

[0808] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[0809] Sending information

[0810] The user terminal transmits the information and questions entered by the user to the server.

[0811] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[0812] Receiving the results

[0813] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[0814] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[0815] User Roles

[0816] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[0817] Entering information

[0818] The user enters the information they want to check into the LINE app and sends it to the server.

[0819] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[0820] Review and share your results

[0821] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[0822] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[0823] Sentiment Analysis Engine Features

[0824] The emotion analysis engine analyzes information requests from users and determines their emotions.

[0825] Emotion determination

[0826] The emotion analysis engine analyzes the user's text data to determine their emotion and transmits the emotion data to the server.

[0827] Example: If a user sends a request saying "I am very worried about this news," the sentiment analysis engine will determine the answer as "worried" and send that data to the server.

[0828] Sending emotional data

[0829] The emotion analysis engine sends the determined emotion data to the server, which uses it to tailor a response message.

[0830] Example: An emotion analysis engine sends emotional data that it determines to be "worried" to a server, which then generates a message saying, "This news is fake. Don't worry."

[0831] This allows the server, user devices, and emotion analysis engine to work together to create a system that prevents the spread of false and misleading information and provides appropriate responses based on the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[0832] Prompt Sentence Examples

[0833] Is this news true?

[0834] I heard about this information, but I would like to know if it is true.

[0835] I am very concerned about this information. Please confirm if it is correct.

[0836] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0837] Step 1:

[0838] Users open the LINE app, enter the information or question they want to have fact-checked, and tap the send button.

[0839] Specific action: The user types "Is this news true?" and taps the send button.

[0840] Input: Text data entered by the user.

[0841] Output: Text data sent through the LINE app.

[0842] Step 2:

[0843] The user device sends the entered information to the fact-checking system server via the LINE server.

[0844] Specific operation: The text data sent by the user passes through the LINE server and arrives at the system server.

[0845] Input: Text data sent from the LINE app.

[0846] Output: The text data received by the server.

[0847] Step 3:

[0848] The server uses a natural language processing (NLP) engine to analyze the received text data.

[0849] Specific operation: The server uses an NLP engine to analyze text data, extract keywords, and decompose sentences.

[0850] Input: Text data received by the server.

[0851] Output: Parsed text data (keywords and sentences).

[0852] Step 4:

[0853] The server sends the received information to an emotion analysis engine to determine the user's emotion.

[0854] Specific operation: The server sends the parsed text data to the sentiment analysis engine, which analyzes the text and generates sentiment labels.

[0855] Input: Parsed text data.

[0856] Output: Sentiment data returned by the sentiment analysis engine (e.g., "worried").

[0857] Step 5:

[0858] The server queries a fact-checking database and uses a generative AI model to determine whether the information is true or false.

[0859] Specific operation: The server searches the fact-check database, and the generative AI model scores the degree of agreement and obtains a truth judgment result.

[0860] Input: Parsed text data.

[0861] Output: The truth-check result obtained from the fact-check database.

[0862] Step 6:

[0863] The server receives the emotion data returned from the emotion analysis engine.

[0864] Specific operation: The server receives the emotion data sent from the emotion analysis engine.

[0865] Input: Sentiment data sent from the sentiment analysis engine.

[0866] Output: Emotion data received by the server.

[0867] Step 7:

[0868] The server generates a response message to be sent to the user based on the fact-check results and emotion data.

[0869] Specific operation: The server combines the fact-check results with the emotion data to generate an appropriate response message for the user, such as "This news is fake. Don't worry."

[0870] Input: Fact-check results and sentiment data.

[0871] Output: The generated response message.

[0872] Step 8:

[0873] The server sends the generated response message to the user terminal.

[0874] Specific operation: The server generates a response message and sends it to the user's device via the LINE server.

[0875] Input: The generated response message.

[0876] Output: The response message sent to the user terminal.

[0877] Step 9:

[0878] The user device receives the message sent from the server and displays it on the chat screen of the LINE app.

[0879] Specific operation: The LINE app receives the message sent from the server and displays it on the chat screen.

[0880] Input: The response message sent by the server.

[0881] Output: The response message displayed on the LINE app chat screen.

[0882] Step 10:

[0883] The user checks the chat screen in the LINE app and reads the response from the server.

[0884] Specific operation: The user opens the LINE app and checks the reply message displayed on the chat screen. They feel reassured when they see that the message is false.

[0885] Input: The message displayed on the chat screen of the LINE app.

[0886] Output: The message the user acknowledged and their relief.

[0887] (Application example 2)

[0888] 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."

[0889] Conventional fact-checking systems require users to manually input information and obtain results based on that information, which can be time-consuming and tedious to operate. Furthermore, because the system does not take the user's feelings into account when determining the veracity of information, the anxiety and concerns of users who receive the results may not be fully alleviated. Furthermore, the lack of a function to assess visually viewed information in real time makes it difficult to quickly prevent the spread of misinformation and disinformation.

[0890] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for determining the veracity of information sent by a user using a fact-checking database managed by the information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for capturing information viewed from the user terminal, automatically converting it to text, and sending the result to the information processing device, means for analyzing the user's emotions using an emotion engine and sending the result to the information processing device, and means for sending to the user terminal a response message based on the veracity result determined by the information processing device and the analyzed emotion. This makes it possible to capture information viewed by the user in real time, instantly determine its veracity, and provide feedback that takes the user's emotions into consideration.

[0891] An "information processing device" is a device that determines the veracity of information sent by users and manages and updates the fact-check database.

[0892] A "fact-checking database" is a database that accumulates and manages data provided by trusted news organizations and fact-checking organizations and is used to determine the veracity of information.

[0893] A "news organization" is an organization or group that creates and disseminates news, articles, etc.

[0894] A "fact-checking organization" is an organization or group that specializes in verifying the veracity of information and publishing it.

[0895] A "user terminal" is a device that a user uses to communicate with an information processing device, and includes a smartphone, smart glasses, and the like.

[0896] "Viewing" refers to a user visually checking information through a device.

[0897] "Capture" refers to obtaining visually recognized information as digital data.

[0898] "Textualization" refers to converting visually recognized information into text data.

[0899] An "emotion engine" is a system that analyzes user input data, determines emotions, and provides the results to other systems.

[0900] A "generative AI model" is a machine learning model that is trained on large datasets to perform tasks such as natural language processing.

[0901] The "response message" is a feedback message that is generated by the information processing device based on the determination result and sent to the user.

[0902] This invention can be realized as a system consisting of an information processing device (hereinafter referred to as a server), a user terminal, and an emotion engine. Each element of this system will be described in detail below.

[0903] server

[0904] The server has the following main functions:

[0905] 1. Maintaining and updating the fact-check database:

[0906] The server periodically retrieves fact-checking data from trusted news outlets and fact-checking organizations and updates the fact-checking database, which is managed using a database management system such as MySQL.

[0907] 2. Authenticity determination:

[0908] The server searches the information sent by the user against a fact-checking database and determines the authenticity of the information using a generative AI model (e.g., BERT or GPT-based models).

[0909] 3. Sentiment analysis and response message generation:

[0910] The server receives the user's emotion data sent from the emotion engine and adjusts the response message based on that information.

[0911] User terminal

[0912] User devices include smartphones and smart glasses, and have the following functions:

[0913] 1. Information capture and transcription:

[0914] The information the user sees is captured by a camera and automatically converted into text using OCR (Optical Character Recognition) technology.

[0915] 2. Sending and Receiving Information:

[0916] The textual information and the user's emotional data are sent to the server, and a response message is received from the server and displayed to the user.

[0917] Emotion Engine

[0918] The emotion engine is a system that analyzes user input data and determines emotions. It has the following functions:

[0919] 1. Emotion determination:

[0920] The user's text data is analyzed to determine their emotions. This process is carried out using IBM Watson's sentiment analysis API.

[0921] 2. Sending Emotional Data:

[0922] The determined emotion data is transmitted to the server.

[0923] Example of processing flow

[0924] Here is a concrete example of how the system actually works.

[0925] 1. The user views information on a social networking site using smart glasses.

[0926] 2. Information is captured by the camera and converted into text using OCR technology.

[0927] 3. The textual information is sent to the server.

[0928] 4. Check the accuracy of information using fact-checking databases.

[0929] 5. The emotion engine analyzes the user's emotion and determines, for example, "worry."

[0930] 6. The server generates a response message saying, "This information is fake. Don't worry."

[0931] 7. The message will appear on the smart glasses display.

[0932] Example prompts to be input to the generative AI model

[0933] Below is an example of a prompt sentence to input to the generative AI model.

[0934] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[0935] Such a system configuration and processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into consideration the user's feelings.

[0936] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0937] Step 1:

[0938] A user visually views information on a social networking site using smart glasses. The camera installed in the smart glasses captures the viewed information and converts it into text using OCR (Optical Character Recognition) technology. The input at this time is the viewed image data, and the output is the converted text information.

[0939] Step 2:

[0940] The textual information is sent from the smart glasses to the server. This process involves data communication from the device to the server. The server then begins analyzing the received text data.

[0941] Step 3:

[0942] The server searches a fact-checking database based on the received text data to verify the authenticity of the information. The input here is the text data, and the output from the fact-checking database is the truthfulness determination result. Additional analysis is performed using an AI model (e.g., BERT or GPT-based models).

[0943] Step 4:

[0944] The emotion engine analyzes the text data sent by the user and determines the user's emotion. The input is the user's text data, and the output is the emotion determination result. The emotion engine performs this process using, for example, IBM Watson's emotion analysis API.

[0945] Step 5:

[0946] The emotion data determined by the emotion engine is sent to the server. The server integrates this emotion data and generates an appropriate response message along with the truth / false judgment result. The input here is the truth / false judgment result and emotion data, and the output is the response message sent to the user.

[0947] Step 6:

[0948] The server then sends the generated response message to the user's smart glasses, where data communication occurs to provide the message to the user in real time, with the final output being the response message displayed on the smart glasses' display.

[0949] Example of processing flow

[0950] Here is a concrete example of how the system actually works.

[0951] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[0952] This processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into account the user's feelings.

[0953] 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.

[0954] 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.

[0955] 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.

[0956] [Third embodiment]

[0957] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0958] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0959] 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).

[0960] 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.

[0961] 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.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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."

[0969] This paper describes a fake check system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). Specific means and processes for effectively detecting fake and misleading information and providing it to users are described.

[0970] Server Features

[0971] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[0972] Maintaining a fact-checking database

[0973] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[0974] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[0975] Handling the request

[0976] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[0977] Example: When a user asks "Is this true?" on LINE, the server searches the information in its database and replies, "This is false information."

[0978] Compensation distribution management

[0979] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[0980] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[0981] User device functions

[0982] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[0983] Sending information

[0984] The user terminal transmits the information and questions entered by the user to the server.

[0985] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[0986] Receiving the results

[0987] The fact-check results sent from the server are received and displayed on the chat screen of the LINE app.

[0988] Example: When the server responds, "This news is fake," the result is displayed on the LINE chat screen.

[0989] User Roles

[0990] Users can interact with the system using apps such as LINE to verify the authenticity of the information.

[0991] Entering information

[0992] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[0993] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[0994] Review and share your results

[0995] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[0996] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[0997] Specific examples of implementation

[0998] For example, suppose a user receives the news that "The latest major earthquake is predicted." The user enters this information into the LINE app and sends a message asking, "Is this true?" The information sent from the user's device is received by the server, which searches the information in a fact-checking database. The AI ​​model determines the result, and if it determines, for example, that "this information is false," the result is sent back to the user's device and displayed on the LINE chat screen. The user sees this result, realizes that it is false information, and shares it with their friends.

[0999] In this way, a system is realized in which the server, user terminals, and users cooperate to prevent the spread of false and misinformation and promote access to accurate information. This system ensures the accuracy of information and also contributes to the activation of news organizations and fact-checking organizations.

[1000] The processing flow will be explained below.

[1001] Step 1:

[1002] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[1003] Step 2:

[1004] Users enter the information they want to check or a link to a news article in the message field, add the question "Is this true?" and press the send button.

[1005] Step 3:

[1006] The terminal generates a request to send the message entered by the user to the server.

[1007] Step 4:

[1008] The device sends the generated request to the FNT account server.

[1009] Step 5:

[1010] The server receives the request sent from the terminal.

[1011] Step 6:

[1012] The server analyzes the received message and extracts the user's question and the information they wish to confirm.

[1013] Step 7:

[1014] The server queries (searches) a fact-checking database based on the extracted information.

[1015] Step 8:

[1016] The server inputs the search results into an AI model to determine whether the information is true or false.

[1017] Step 9:

[1018] The server generates a message to respond to the user based on the AI ​​model's judgment results.

[1019] Step 10:

[1020] The server sends the generated response message to the terminal.

[1021] Step 11:

[1022] The terminal receives the response message sent from the server.

[1023] Step 12:

[1024] The device will display the received message on the chat screen of the LINE app.

[1025] Step 13:

[1026] The user opens the chat screen in the LINE app and checks the response message from the server.

[1027] Step 14:

[1028] Based on the results received, users can determine the authenticity of the information and share their results with friends and family.

[1029] Example 1

[1030] 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."

[1031] False and misleading information is frequently circulating on the Internet, making it difficult for users to quickly and accurately verify the authenticity of information. In particular, ordinary users who lack the ability to verify the reliability of information are at high risk of being misled by misinformation. For this reason, there is a need for a system that can effectively identify false and misleading information based on reliable information sources and provide it to users.

[1032] 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.

[1033] In this invention, the server includes means for determining the authenticity of information sent from a user terminal, means for periodically updating a fact-check database from an information source, means for transmitting the authenticity results determined by the information processing device to the user terminal, means for determining the authenticity of the information using a generative AI model, and means for the user terminal to send and receive information requests via a chat app. This allows users to quickly check the authenticity of information via the chat app and prevents the spread of false information.

[1034] An "information processing device" is a computer system for processing, managing, and analyzing data.

[1035] A "fact-checking database" is a collection of data used to accumulate and manage highly reliable information and determine whether the information is true or false.

[1036] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet, that provides a means for sending and receiving information.

[1037] "Means for determining authenticity" refers to the algorithms or models used to determine the authenticity of received information.

[1038] A "source" is a source used to provide accurate information, such as a reputable news organization or fact-checking organization.

[1039] A "generative AI model" is a model generated using artificial intelligence, which analyzes and judges information based on natural language processing.

[1040] "Chat app" means a software application that allows users to send and receive messages in real time, including LINE and other messaging apps.

[1041] An "information request" is an inquiry that a user sends by specifying the information they want to confirm.

[1042] The "true / false result" is the result of determining whether the received information is true or false.

[1043] The present invention is a fact-checking system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). This system effectively identifies false and misleading information and provides users with accurate results.

[1044] The server manages a fact-checking database and plays an important role in determining the veracity of information sent by users. The fact-checking database stores reliable information, and the server searches and analyzes information based on this database.

[1045] Hardware and software used

[1046] The server uses a high-performance computer system to build and manage the fact-checking database. It uses a database management system (e.g., MySQL, PostgreSQL, etc.) to efficiently process and store large amounts of data. It also uses a generative AI model (e.g., GPT-4) to determine the veracity of the information it receives.

[1047] User devices are devices such as smartphones, tablets, and PCs, and communicate with the server primarily using chat apps (e.g., LINE). Users send information via the chat app and receive the judgment results from the server.

[1048] Specific actions

[1049] User submits information

[1050] A user uses a chat app (such as LINE) installed on a smartphone or tablet to enter and send the information they want to check. For example, a user might type "Is this news true?" into the LINE app and send it.

[1051] The server receives and processes the request

[1052] The server receives user requests through the LINE API, converts them into an appropriate format, and then queries the fact-check database to retrieve relevant information.

[1053] The server uses a generative AI model to determine the authenticity of the information

[1054] The server inputs the acquired information into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing technology to determine whether the received information is true or false.

[1055] The server returns the result of the judgment to the user device.

[1056] The server generates a judgment result and sends it back to the user's device via the LINE API. For example, the result may say, "This news is false information."

[1057] Users review and share results

[1058] Users receive notifications in chat apps, review the information displayed on their screens, and share their findings with friends and family to help prevent the spread of misinformation.

[1059] Prompt Sentence Examples

[1060] Example: A user receives a news item on the LINE app that says, "The latest major earthquake is predicted," and sends a message asking, "Is this news true?"

[1061] This system allows users to quickly obtain reliable information and protects them from misinformation and disinformation. Furthermore, news organizations and fact-checking organizations, which are the sources of information, regularly update their databases to provide the latest information, thereby ensuring the accuracy of the system.

[1062] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1063] Step 1:

[1064] Process for users to submit information

[1065] Input: Information or questions that users type into a chat app (e.g., "Is this news true?")

[1066] Output: The request sent from the user's device to the server

[1067] How it works: A user uses a chat app (e.g., LINE) on their smartphone or tablet to enter the information they want to check and press the send button. This action sends an information request from the user device to the server.

[1068] Step 2:

[1069] The process by which the server receives and processes the request

[1070] Input: Information request sent from the user's terminal

[1071] Output: Search criteria to run the query

[1072] How it works: The server receives user requests through the LINE API, converts them into an appropriate format, and then generates a query to the fact-checking database based on the received information to search for relevant data.

[1073] Step 3:

[1074] The process by which the server queries the fact-check database

[1075] Input: Server-generated query

[1076] Output: Relevant information retrieved from a fact-checking database

[1077] How it works: The server uses the generated query to search the fact-checking database and retrieve relevant data. For example, it searches for articles and data related to the information "latest major earthquakes."

[1078] Step 4:

[1079] Processing by the server to determine the authenticity of information using a generative AI model

[1080] Input: Search results from a fact-checking database

[1081] Output: The truth or falsity result determined by the generative AI model

[1082] How it works: The server inputs the acquired data into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing to determine whether the given information is true or false.

[1083] Step 5:

[1084] Processing for the server to return the judgment result to the user terminal

[1085] Input: Judgment result of generative AI model

[1086] Output: True or false result sent to user terminal

[1087] How it works: Based on the judgment results generated by the AI ​​model, the server generates a message for the user and sends it back to the user's device using the LINE API. For example, it sends a message saying, "This news is false information."

[1088] Step 6:

[1089] Processing for the user terminal to receive and display the results

[1090] Input: True or false result sent from the server

[1091] Output: The result displayed on the chat app screen

[1092] Operation: The user device receives the truth result sent from the server and displays the result on the chat screen of the LINE app. For example, the text "This news is false" is displayed.

[1093] Step 7:

[1094] Process for users to review and share results

[1095] Input: True or false result displayed in chat app

[1096] Output: Perception and behavior of the user who receives the results

[1097] How it works: Users can view fact-check results in the chat and optionally share them with friends and family, helping to prevent the spread of misinformation.

[1098] (Application example 1)

[1099] 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."

[1100] In today's digital information society, the spread of misinformation and false information has become a problem, causing confusion and misunderstanding among users, and even causing harm to users. In particular, in advertising, if consumers act on false information, it could result in economic losses and a loss of trust. In response, there is a demand for systems that allow users to obtain accurate information in real time.

[1101] 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.

[1102] In this invention, the server includes means for determining the authenticity of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from information sources and fact-checking organizations, means for transmitting the authenticity results determined by the information processing device to a user terminal, means for analyzing advertising information captured by a display device that displays advertisements and determining its authenticity, and means for instantly displaying the determination results on the display device, thereby enabling users to check the authenticity of advertising information in real time and make decisions based on accurate information.

[1103] An "information processing device" is a device that manages a fact-check database and determines the truth of information sent by a user.

[1104] A "fact-checking database" is a database that accumulates data obtained from reliable sources and fact-checking organizations and is used to determine the veracity of information.

[1105] A "source" is a primary source of accurate information, such as a reliable news organization or official institution.

[1106] A "fact-checking organization" is an organization that professionally verifies the veracity of information and publishes the results.

[1107] A "user terminal" is a communication device used by a user to send and receive information requests.

[1108] "Advertising" is information intended to promote a particular product or service to consumers.

[1109] A "display device" is a device that allows a user to visually view information. An example is smart glasses.

[1110] A "generative AI model" is an algorithm that uses artificial intelligence technology to automatically determine the veracity of information.

[1111] "Searching" is the process of looking through data in a fact-checking database to find the information you need.

[1112] A "user" is someone who uses the system to verify the authenticity of information.

[1113] "Periodic updating" refers to the operation of collecting the latest data at regular intervals and adding it to the database.

[1114] The "true / false result" is the result of determining whether the information is true or false.

[1115] "Analysis" is the process of examining advertising information in detail and evaluating the authenticity of the content.

[1116] "Real-time" means processing information almost immediately and without delay.

[1117] A "communication application" is software that allows users to exchange messages with a server.

[1118] The present invention is a fact-checking system that operates in cooperation with a user terminal and is centered around an information processing device. The purpose of this system is to determine the authenticity of advertisements in real time and provide the results to users immediately. The specific implementation method is shown below.

[1119] Server Features

[1120] Maintaining a fact-checking database

[1121] The server periodically retrieves data from trusted sources and fact-checking organizations and stores it in a fact-checking database.

[1122] Example: Every day at 2 AM, the server retrieves updated fact-checking data from reliable source A and fact-checking organization B and updates the database.

[1123] Handling the request

[1124] The server receives information requests from users, queries (searches) a fact-checking database, uses a generative AI model to determine the veracity of the information, and returns the results to the user.

[1125] Example: When a user asks "Is this true?" in a chat app, the server searches the information in a database and replies "It's fake."

[1126] Analysis of advertising information

[1127] The server analyzes the advertising information captured by a display device such as smart glasses using OCR technology and determines its authenticity.

[1128] Example: When a user sees an advertisement on their smart glasses that says "Get a huge discount!", this information is sent to a server and checked against a database.

[1129] Display of judgment results

[1130] The server immediately transmits the determined true or false result to the display device so that the user can visually confirm it.

[1131] Example: The server sends the result "This ad is false information" and the result is displayed on the display of the smart glasses.

[1132] User device functions

[1133] Sending information

[1134] The user terminal transmits the information and questions entered by the user to the server.

[1135] Example: When a user types "Is this news true?" in a chat app and sends it, the message is sent to the server.

[1136] Advertisement information capture

[1137] The display device captures the advertising text and sends it to the server.

[1138] Example: Smart glasses convert advertising information that comes into the user's field of vision into text using OCR technology and send it to a server.

[1139] Receiving and displaying results

[1140] The fact check results sent from the server are received and displayed on the display device.

[1141] Example: The server sends the result "This ad is fake" and the result is displayed on the smart glasses.

[1142] User Roles

[1143] Entering information

[1144] The user inputs the information they want to check (e.g., a link or text of a news article) and sends it to the server.

[1145] Example: A user pastes a news link sent by a friend into a chat app and asks, "Is this true?"

[1146] Review and share your results

[1147] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[1148] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[1149] Prompt Sentence Examples

[1150] Describe an application that uses OCR technology to capture advertisement text viewed by users on the street and then checks its veracity against a fact-checking database. This application runs on smart glasses and has the ability to instantly display whether an advertisement is true or false.

[1151] As described above, the present invention is embodied as a system that enables users to check the authenticity of advertisements and information in real time, prevent the spread of false information, and act based on accurate information.

[1152] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1153] Step 1:

[1154] A user wears smart glasses and walks around town looking at advertisements. The smart glasses use a camera to capture the advertisement information. Specifically, the smart glasses capture the text information of the advertisement and convert it into text data using OCR technology. The input is the captured image data, and the output is the converted text data.

[1155] Step 2:

[1156] The smart glasses send the text data converted by OCR technology to the server. Specifically, they send the advertisement text as an HTTP request to the server's API endpoint. The input is the text data converted by OCR, and the output is an HTTP request to the server.

[1157] Step 3:

[1158] The server searches the fact-checking database based on the received ad text. Specifically, it issues an SQL query to the database based on the text data sent and retrieves relevant fact-checking information. The input is the ad text data, and the output is the search results from the fact-checking database.

[1159] Step 4:

[1160] The server inputs the search results from the fact-checking database into the generative AI model to evaluate the truth of the advertising information. Specifically, the search results are input into the generative AI model and the probability of determining whether the information is true or false is calculated. The input is the search results from the fact-checking database, and the output is a probability evaluation of the truth or falsehood.

[1161] Step 5:

[1162] The server makes a final judgment on the authenticity of the advertising information based on the probability evaluation obtained from the generative AI model. Specifically, a certain threshold is set and a judgment is made, for example, whether the information is considered true with a probability of 0.8 or higher, or whether it is considered false. The input is the probability evaluation, and the output is the final truth / falseness judgment result.

[1163] Step 6:

[1164] The server sends the final truth-or-false judgment result to the smart glasses. Specifically, it returns the judgment result to the smart glasses as an HTTP response. The input is the truth-or-false judgment result, and the output is the HTTP response.

[1165] Step 7:

[1166] The smart glasses display the received truthfulness result on the display. Specifically, to visually present the truthfulness result to the user, they display a message on the display saying "This advertisement is true" or "This advertisement is false." The input is the truthfulness result of the HTTP response, and the output is the display visible to the user.

[1167] Through these steps, users can verify the authenticity of advertising information in real time, preventing the spread of misinformation and enabling users to make decisions based on accurate information.

[1168] 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.

[1169] This invention is a fact-checking system that combines a user terminal and an emotion engine with an information processing device (hereinafter referred to as a server) at its core. We will explain the specific means and process for effectively identifying false and misleading information and providing appropriate messages based on the user's emotions.

[1170] Server Features

[1171] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[1172] Maintaining a fact-checking database

[1173] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[1174] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[1175] Handling the request

[1176] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[1177] Example: When a user asks "Is this true?" on LINE, the server searches the information in its database and replies, "This is false information."

[1178] Compensation distribution management

[1179] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[1180] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[1181] Collaboration with emotion engine

[1182] The server receives the user's emotion data from the emotion engine and adjusts the response message based on the data.

[1183] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[1184] User device functions

[1185] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[1186] Sending information

[1187] The user terminal transmits the information and questions entered by the user to the server.

[1188] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[1189] Receiving the results

[1190] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[1191] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[1192] User Roles

[1193] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[1194] Entering information

[1195] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[1196] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[1197] Review and share your results

[1198] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[1199] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[1200] Emotion Engine Functions

[1201] The emotion engine analyzes information requests from users and determines the user's emotions.

[1202] Emotion determination

[1203] The emotion engine analyzes the user's text data to determine the emotion, and transmits the emotion data to the server.

[1204] Example: If a user sends a request saying "I am very worried about this news," the emotion engine will determine the answer as "worried" and send that data to the server.

[1205] Sending emotional data

[1206] The emotion engine sends the determined emotion data to the server, which uses it to tailor a response message.

[1207] Example: The emotion engine determines emotion data as "worry" and sends it to the server, which then generates a message saying, "This news is fake. Don't worry."

[1208] In this way, the server, user device, and emotion engine work together to realize a system that prevents the spread of false and misleading information and provides appropriate responses according to the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[1209] The processing flow will be explained below.

[1210] Step 1:

[1211] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[1212] Step 2:

[1213] Users enter the information they want to check or a link to a news article in the message field, add a question like "Is this true? I'm very worried," and press the send button.

[1214] Step 3:

[1215] The terminal generates a request to send the message input by the user to the emotion engine.

[1216] Step 4:

[1217] The device sends the generated request to the emotion engine.

[1218] Step 5:

[1219] The emotion engine receives the message sent by the user and analyzes the text data.

[1220] Step 6:

[1221] The emotion engine analyzes the text data, determines the user's emotion as "worry," and generates emotion data.

[1222] Step 7:

[1223] The emotion engine returns the generated emotion data to the terminal.

[1224] Step 8:

[1225] The terminal generates a request to transmit the emotion data received from the emotion engine to the server.

[1226] Step 9:

[1227] The terminal sends the generated request to the server.

[1228] Step 10:

[1229] The server receives the emotion data sent from the terminal and the user's information request.

[1230] Step 11:

[1231] The server queries (searches) the fact-checking database based on the received user information request.

[1232] Step 12:

[1233] The server inputs the search results into an AI model to determine whether the information is true or false.

[1234] Step 13:

[1235] The server generates a message to respond to the user based on the AI ​​model's judgment and emotional data, such as "Don't worry. This information is fake."

[1236] Step 14:

[1237] The server sends the generated response message to the terminal.

[1238] Step 15:

[1239] The terminal receives the response message sent from the server.

[1240] Step 16:

[1241] The device will display the received message on the chat screen of the LINE app.

[1242] Step 17:

[1243] The user opens the chat screen of the LINE app and checks the response message from the server, which may say, for example, "Don't worry. This news is fake."

[1244] Step 18:

[1245] Users can judge the authenticity of the information based on the results they receive, and share their judgment with friends and family. They can also feel reassured by receiving messages that correspond to their emotions.

[1246] Example 2

[1247] 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."

[1248] In modern society, false and misinformation often spreads rapidly on the Internet, resulting in a decline in the reliability of information. Another issue is that users' exposure to such uncertain information can easily cause anxiety and confusion. Conventional fact-checking systems struggle to reduce the psychological burden placed on users by simply determining the veracity of information. Therefore, there is a need for systems that can accurately determine the veracity of false and misinformation and provide appropriate messages tailored to the user's emotions, thereby increasing the user's sense of security.

[1249] 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.

[1250] In this invention, the server includes means for determining the truth of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for transmitting the truthfulness results determined by the information processing device to a user terminal, means for determining the user's emotions using an emotion analysis engine, and means for adjusting a response message to the user based on the user's emotion data. This makes it possible to accurately determine false information and misinformation, as well as provide an appropriate response message according to the user's emotions.

[1251] An "information processing device" is a device that has the function of receiving information sent from a user, analyzing and processing the information, and sending the results.

[1252] A "fact-checking database" is a database that accumulates data used to determine the veracity of false information or misinformation.

[1253] "News organizations" are organizations that provide information to the public, such as newspapers, television stations, and internet news sites.

[1254] A "fact-checking organization" is an organization that verifies the accuracy of information provided by media outlets and individuals and publishes the results.

[1255] A "user terminal" is a device that allows a user to input information and communicate with a server, such as a smartphone or a personal computer.

[1256] An "emotion analysis engine" is software or a system that analyzes text data sent by a user and determines the user's emotions.

[1257] A "generative AI model" is a model that uses artificial intelligence to automatically determine the truth or falsity of information.

[1258] A "prompt sentence" is a text sentence that indicates a question or request that a user enters into the system.

[1259] The "true / false result" is the result of determining whether the transmitted information is true or false.

[1260] A "response message" is a message generated by a server to reply to a user.

[1261] This invention relates to a fact-checking system that combines a user terminal and a sentiment analysis engine with an information processing device as its core. This system effectively identifies false and misleading information and provides appropriate messages based on the user's sentiment.

[1262] Server Features

[1263] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[1264] Maintaining a fact-checking database

[1265] The server regularly retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[1266] Example: A server retrieves updated data from news organizations and fact-checking organizations every day at 2 AM and updates the database.

[1267] Handling the request

[1268] The server receives information requests from users, queries (searches) the database, uses a generative AI model to determine the authenticity of the information, and returns the results to the user.

[1269] Example: If a user asks "Is this news true?" on the LINE app, the server searches the information in the database and replies "It's fake news."

[1270] Collaboration with sentiment analysis engine

[1271] The server receives the user's emotional data from the emotion analysis engine and adjusts the response message based on that data.

[1272] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[1273] User device functions

[1274] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[1275] Sending information

[1276] The user terminal transmits the information and questions entered by the user to the server.

[1277] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[1278] Receiving the results

[1279] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[1280] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[1281] User Roles

[1282] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[1283] Entering information

[1284] The user enters the information they want to check into the LINE app and sends it to the server.

[1285] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[1286] Review and share your results

[1287] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[1288] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[1289] Sentiment Analysis Engine Features

[1290] The emotion analysis engine analyzes information requests from users and determines their emotions.

[1291] Emotion determination

[1292] The emotion analysis engine analyzes the user's text data to determine their emotion and transmits the emotion data to the server.

[1293] Example: If a user sends a request saying "I am very worried about this news," the sentiment analysis engine will determine the answer as "worried" and send that data to the server.

[1294] Sending emotional data

[1295] The emotion analysis engine sends the determined emotion data to the server, which uses it to tailor a response message.

[1296] Example: An emotion analysis engine sends emotional data that it determines to be "worried" to a server, which then generates a message saying, "This news is fake. Don't worry."

[1297] This allows the server, user devices, and emotion analysis engine to work together to create a system that prevents the spread of false and misleading information and provides appropriate responses based on the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[1298] Prompt Sentence Examples

[1299] Is this news true?

[1300] I heard about this information, but I would like to know if it is true.

[1301] I am very concerned about this information. Please confirm if it is correct.

[1302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1303] Step 1:

[1304] Users open the LINE app, enter the information or question they want to have fact-checked, and tap the send button.

[1305] Specific action: The user types "Is this news true?" and taps the send button.

[1306] Input: Text data entered by the user.

[1307] Output: Text data sent through the LINE app.

[1308] Step 2:

[1309] The user device sends the entered information to the fact-checking system server via the LINE server.

[1310] Specific operation: The text data sent by the user passes through the LINE server and arrives at the system server.

[1311] Input: Text data sent from the LINE app.

[1312] Output: The text data received by the server.

[1313] Step 3:

[1314] The server uses a natural language processing (NLP) engine to analyze the received text data.

[1315] Specific operation: The server uses an NLP engine to analyze text data, extract keywords, and decompose sentences.

[1316] Input: Text data received by the server.

[1317] Output: Parsed text data (keywords and sentences).

[1318] Step 4:

[1319] The server sends the received information to an emotion analysis engine to determine the user's emotion.

[1320] Specific operation: The server sends the parsed text data to the sentiment analysis engine, which analyzes the text and generates sentiment labels.

[1321] Input: Parsed text data.

[1322] Output: Sentiment data returned by the sentiment analysis engine (e.g., "worried").

[1323] Step 5:

[1324] The server queries a fact-checking database and uses a generative AI model to determine whether the information is true or false.

[1325] Specific operation: The server searches the fact-check database, and the generative AI model scores the degree of agreement and obtains a truth judgment result.

[1326] Input: Parsed text data.

[1327] Output: The truth-check result obtained from the fact-check database.

[1328] Step 6:

[1329] The server receives the emotion data returned from the emotion analysis engine.

[1330] Specific operation: The server receives the emotion data sent from the emotion analysis engine.

[1331] Input: Sentiment data sent from the sentiment analysis engine.

[1332] Output: Emotion data received by the server.

[1333] Step 7:

[1334] The server generates a response message to be sent to the user based on the fact-check results and emotion data.

[1335] Specific operation: The server combines the fact-check results with the emotion data to generate an appropriate response message for the user, such as "This news is fake. Don't worry."

[1336] Input: Fact-check results and sentiment data.

[1337] Output: The generated response message.

[1338] Step 8:

[1339] The server sends the generated response message to the user terminal.

[1340] Specific operation: The server generates a response message and sends it to the user's device via the LINE server.

[1341] Input: The generated response message.

[1342] Output: The response message sent to the user terminal.

[1343] Step 9:

[1344] The user device receives the message sent from the server and displays it on the chat screen of the LINE app.

[1345] Specific operation: The LINE app receives the message sent from the server and displays it on the chat screen.

[1346] Input: The response message sent by the server.

[1347] Output: The response message displayed on the LINE app chat screen.

[1348] Step 10:

[1349] The user checks the chat screen in the LINE app and reads the response from the server.

[1350] Specific operation: The user opens the LINE app and checks the reply message displayed on the chat screen. They feel reassured when they see that the message is false.

[1351] Input: The message displayed on the chat screen of the LINE app.

[1352] Output: The message the user acknowledged and their relief.

[1353] (Application example 2)

[1354] 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."

[1355] Conventional fact-checking systems require users to manually input information and obtain results based on that information, which can be time-consuming and tedious to operate. Furthermore, because the system does not take the user's feelings into account when determining the veracity of information, the anxiety and concerns of users who receive the results may not be fully alleviated. Furthermore, the lack of a function to assess visually viewed information in real time makes it difficult to quickly prevent the spread of misinformation and disinformation.

[1356] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for determining the veracity of information sent by a user using a fact-checking database managed by the information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for capturing information viewed from the user terminal, automatically converting it to text, and sending the result to the information processing device, means for analyzing the user's emotions using an emotion engine and sending the result to the information processing device, and means for sending to the user terminal a response message based on the veracity result determined by the information processing device and the analyzed emotion. This makes it possible to capture information viewed by the user in real time, instantly determine its veracity, and provide feedback that takes the user's emotions into consideration.

[1357] An "information processing device" is a device that determines the veracity of information sent by users and manages and updates the fact-check database.

[1358] A "fact-checking database" is a database that accumulates and manages data provided by trusted news organizations and fact-checking organizations and is used to determine the veracity of information.

[1359] A "news organization" is an organization or group that creates and disseminates news, articles, etc.

[1360] A "fact-checking organization" is an organization or group that specializes in verifying the veracity of information and publishing it.

[1361] A "user terminal" is a device that a user uses to communicate with an information processing device, and includes a smartphone, smart glasses, and the like.

[1362] "Viewing" refers to a user visually checking information through a device.

[1363] "Capture" refers to obtaining visually recognized information as digital data.

[1364] "Textualization" refers to converting visually recognized information into text data.

[1365] An "emotion engine" is a system that analyzes user input data, determines emotions, and provides the results to other systems.

[1366] A "generative AI model" is a machine learning model that is trained on large datasets to perform tasks such as natural language processing.

[1367] The "response message" is a feedback message that is generated by the information processing device based on the determination result and sent to the user.

[1368] This invention can be realized as a system consisting of an information processing device (hereinafter referred to as a server), a user terminal, and an emotion engine. Each element of this system will be described in detail below.

[1369] server

[1370] The server has the following main functions:

[1371] 1. Maintaining and updating the fact-check database:

[1372] The server periodically retrieves fact-checking data from trusted news outlets and fact-checking organizations and updates the fact-checking database, which is managed using a database management system such as MySQL.

[1373] 2. Authenticity determination:

[1374] The server searches the information sent by the user against a fact-checking database and determines the authenticity of the information using a generative AI model (e.g., BERT or GPT-based models).

[1375] 3. Sentiment analysis and response message generation:

[1376] The server receives the user's emotion data sent from the emotion engine and adjusts the response message based on that information.

[1377] User terminal

[1378] User devices include smartphones and smart glasses, and have the following functions:

[1379] 1. Information capture and transcription:

[1380] The information the user sees is captured by a camera and automatically converted into text using OCR (Optical Character Recognition) technology.

[1381] 2. Sending and Receiving Information:

[1382] The textual information and the user's emotional data are sent to the server, and a response message is received from the server and displayed to the user.

[1383] Emotion Engine

[1384] The emotion engine is a system that analyzes user input data and determines emotions. It has the following functions:

[1385] 1. Emotion determination:

[1386] The user's text data is analyzed to determine their emotions. This process is carried out using IBM Watson's sentiment analysis API.

[1387] 2. Sending Emotional Data:

[1388] The determined emotion data is transmitted to the server.

[1389] Example of processing flow

[1390] Here is a concrete example of how the system actually works.

[1391] 1. The user views information on a social networking site using smart glasses.

[1392] 2. Information is captured by the camera and converted into text using OCR technology.

[1393] 3. The textual information is sent to the server.

[1394] 4. Check the accuracy of information using fact-checking databases.

[1395] 5. The emotion engine analyzes the user's emotion and determines, for example, "worry."

[1396] 6. The server generates a response message saying, "This information is fake. Don't worry."

[1397] 7. The message will appear on the smart glasses display.

[1398] Example prompts to be input to the generative AI model

[1399] Below is an example of a prompt sentence to input to the generative AI model.

[1400] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[1401] Such a system configuration and processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into consideration the user's feelings.

[1402] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1403] Step 1:

[1404] A user visually views information on a social networking site using smart glasses. The camera installed in the smart glasses captures the viewed information and converts it into text using OCR (Optical Character Recognition) technology. The input at this time is the viewed image data, and the output is the converted text information.

[1405] Step 2:

[1406] The textual information is sent from the smart glasses to the server. This process involves data communication from the device to the server. The server then begins analyzing the received text data.

[1407] Step 3:

[1408] The server searches a fact-checking database based on the received text data to verify the authenticity of the information. The input here is the text data, and the output from the fact-checking database is the truthfulness determination result. Additional analysis is performed using an AI model (e.g., BERT or GPT-based models).

[1409] Step 4:

[1410] The emotion engine analyzes the text data sent by the user and determines the user's emotion. The input is the user's text data, and the output is the emotion determination result. The emotion engine performs this process using, for example, IBM Watson's emotion analysis API.

[1411] Step 5:

[1412] The emotion data determined by the emotion engine is sent to the server. The server integrates this emotion data and generates an appropriate response message along with the truth / false judgment result. The input here is the truth / false judgment result and emotion data, and the output is the response message sent to the user.

[1413] Step 6:

[1414] The server then sends the generated response message to the user's smart glasses, where data communication occurs to provide the message to the user in real time, with the final output being the response message displayed on the smart glasses' display.

[1415] Example of processing flow

[1416] Here is a concrete example of how the system actually works.

[1417] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[1418] This processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into account the user's feelings.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] [Fourth embodiment]

[1423] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1424] 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.

[1425] 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).

[1426] 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.

[1427] 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.

[1428] 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).

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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."

[1436] This paper describes a fake check system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). Specific means and processes for effectively detecting fake and misleading information and providing it to users are described.

[1437] Server Features

[1438] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[1439] Maintaining a fact-checking database

[1440] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[1441] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[1442] Handling the request

[1443] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[1444] Example: When a user asks "Is this true?" on LINE, the server searches the information in its database and replies, "This is false information."

[1445] Compensation distribution management

[1446] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[1447] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[1448] User device functions

[1449] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[1450] Sending information

[1451] The user terminal transmits the information and questions entered by the user to the server.

[1452] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[1453] Receiving the results

[1454] The fact-check results sent from the server are received and displayed on the chat screen of the LINE app.

[1455] Example: When the server responds, "This news is fake," the result is displayed on the LINE chat screen.

[1456] User Roles

[1457] Users can interact with the system using apps such as LINE to verify the authenticity of the information.

[1458] Entering information

[1459] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[1460] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[1461] Review and share your results

[1462] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[1463] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[1464] Specific examples of implementation

[1465] For example, suppose a user receives the news that "The latest major earthquake is predicted." The user enters this information into the LINE app and sends a message asking, "Is this true?" The information sent from the user's device is received by the server, which searches the information in a fact-checking database. The AI ​​model determines the result, and if it determines, for example, that "this information is false," the result is sent back to the user's device and displayed on the LINE chat screen. The user sees this result, realizes that it is false information, and shares it with their friends.

[1466] In this way, a system is realized in which the server, user terminals, and users cooperate to prevent the spread of false and misinformation and promote access to accurate information. This system ensures the accuracy of information and also contributes to the activation of news organizations and fact-checking organizations.

[1467] The processing flow will be explained below.

[1468] Step 1:

[1469] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[1470] Step 2:

[1471] Users enter the information they want to check or a link to a news article in the message field, add the question "Is this true?" and press the send button.

[1472] Step 3:

[1473] The terminal generates a request to send the message entered by the user to the server.

[1474] Step 4:

[1475] The device sends the generated request to the FNT account server.

[1476] Step 5:

[1477] The server receives the request sent from the terminal.

[1478] Step 6:

[1479] The server analyzes the received message and extracts the user's question and the information they wish to confirm.

[1480] Step 7:

[1481] The server queries (searches) a fact-checking database based on the extracted information.

[1482] Step 8:

[1483] The server inputs the search results into an AI model to determine whether the information is true or false.

[1484] Step 9:

[1485] The server generates a message to respond to the user based on the AI ​​model's judgment results.

[1486] Step 10:

[1487] The server sends the generated response message to the terminal.

[1488] Step 11:

[1489] The terminal receives the response message sent from the server.

[1490] Step 12:

[1491] The device will display the received message on the chat screen of the LINE app.

[1492] Step 13:

[1493] The user opens the chat screen in the LINE app and checks the response message from the server.

[1494] Step 14:

[1495] Based on the results received, users can determine the authenticity of the information and share their results with friends and family.

[1496] Example 1

[1497] 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."

[1498] False and misleading information is frequently circulating on the Internet, making it difficult for users to quickly and accurately verify the authenticity of information. In particular, ordinary users who lack the ability to verify the reliability of information are at high risk of being misled by misinformation. For this reason, there is a need for a system that can effectively identify false and misleading information based on reliable information sources and provide it to users.

[1499] 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.

[1500] In this invention, the server includes means for determining the authenticity of information sent from a user terminal, means for periodically updating a fact-check database from an information source, means for transmitting the authenticity results determined by the information processing device to the user terminal, means for determining the authenticity of the information using a generative AI model, and means for the user terminal to send and receive information requests via a chat app. This allows users to quickly check the authenticity of information via the chat app and prevents the spread of false information.

[1501] An "information processing device" is a computer system for processing, managing, and analyzing data.

[1502] A "fact-checking database" is a collection of data used to accumulate and manage highly reliable information and determine whether the information is true or false.

[1503] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet, that provides a means for sending and receiving information.

[1504] "Means for determining authenticity" refers to the algorithms or models used to determine the authenticity of received information.

[1505] A "source" is a source used to provide accurate information, such as a reputable news organization or fact-checking organization.

[1506] A "generative AI model" is a model generated using artificial intelligence, which analyzes and judges information based on natural language processing.

[1507] "Chat app" means a software application that allows users to send and receive messages in real time, including LINE and other messaging apps.

[1508] An "information request" is an inquiry that a user sends by specifying the information they want to confirm.

[1509] The "true / false result" is the result of determining whether the received information is true or false.

[1510] The present invention is a fact-checking system that operates in cooperation with user terminals, centered around an information processing device (hereinafter referred to as a server). This system effectively identifies false and misleading information and provides users with accurate results.

[1511] The server manages a fact-checking database and plays an important role in determining the veracity of information sent by users. The fact-checking database stores reliable information, and the server searches and analyzes information based on this database.

[1512] Hardware and software used

[1513] The server uses a high-performance computer system to build and manage the fact-checking database. It uses a database management system (e.g., MySQL, PostgreSQL, etc.) to efficiently process and store large amounts of data. It also uses a generative AI model (e.g., GPT-4) to determine the veracity of the information it receives.

[1514] User devices are devices such as smartphones, tablets, and PCs, and communicate with the server primarily using chat apps (e.g., LINE). Users send information via the chat app and receive the judgment results from the server.

[1515] Specific actions

[1516] User submits information

[1517] A user uses a chat app (such as LINE) installed on a smartphone or tablet to enter and send the information they want to check. For example, a user might type "Is this news true?" into the LINE app and send it.

[1518] The server receives and processes the request

[1519] The server receives user requests through the LINE API, converts them into an appropriate format, and then queries the fact-check database to retrieve relevant information.

[1520] The server uses a generative AI model to determine the authenticity of the information

[1521] The server inputs the acquired information into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing technology to determine whether the received information is true or false.

[1522] The server returns the result of the judgment to the user device.

[1523] The server generates a judgment result and sends it back to the user's device via the LINE API. For example, the result may say, "This news is false information."

[1524] Users review and share results

[1525] Users receive notifications in chat apps, review the information displayed on their screens, and share their findings with friends and family to help prevent the spread of misinformation.

[1526] Prompt Sentence Examples

[1527] Example: A user receives a news item on the LINE app that says, "The latest major earthquake is predicted," and sends a message asking, "Is this news true?"

[1528] This system allows users to quickly obtain reliable information and protects them from misinformation and disinformation. Furthermore, news organizations and fact-checking organizations, which are the sources of information, regularly update their databases to provide the latest information, thereby ensuring the accuracy of the system.

[1529] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1530] Step 1:

[1531] Process for users to submit information

[1532] Input: Information or questions that users type into a chat app (e.g., "Is this news true?")

[1533] Output: The request sent from the user's device to the server

[1534] How it works: A user uses a chat app (e.g., LINE) on their smartphone or tablet to enter the information they want to check and press the send button. This action sends an information request from the user device to the server.

[1535] Step 2:

[1536] The process by which the server receives and processes the request

[1537] Input: Information request sent from the user's terminal

[1538] Output: Search criteria to run the query

[1539] How it works: The server receives user requests through the LINE API, converts them into an appropriate format, and then generates a query to the fact-checking database based on the received information to search for relevant data.

[1540] Step 3:

[1541] The process by which the server queries the fact-check database

[1542] Input: Server-generated query

[1543] Output: Relevant information retrieved from a fact-checking database

[1544] How it works: The server uses the generated query to search the fact-checking database and retrieve relevant data. For example, it searches for articles and data related to the information "latest major earthquakes."

[1545] Step 4:

[1546] Processing by the server to determine the authenticity of information using a generative AI model

[1547] Input: Search results from a fact-checking database

[1548] Output: The truth or falsity result determined by the generative AI model

[1549] How it works: The server inputs the acquired data into a generative AI model (e.g., GPT-4) to determine whether the information is true or false. The AI ​​model uses natural language processing to determine whether the given information is true or false.

[1550] Step 5:

[1551] Processing for the server to return the judgment result to the user terminal

[1552] Input: Judgment result of generative AI model

[1553] Output: True or false result sent to user terminal

[1554] How it works: Based on the judgment results generated by the AI ​​model, the server generates a message for the user and sends it back to the user's device using the LINE API. For example, it sends a message saying, "This news is false information."

[1555] Step 6:

[1556] Processing for the user terminal to receive and display the results

[1557] Input: True or false result sent from the server

[1558] Output: The result displayed on the chat app screen

[1559] Operation: The user device receives the truth result sent from the server and displays the result on the chat screen of the LINE app. For example, the text "This news is false" is displayed.

[1560] Step 7:

[1561] Process for users to review and share results

[1562] Input: True or false result displayed in chat app

[1563] Output: Perception and behavior of the user who receives the results

[1564] How it works: Users can view fact-check results in the chat and optionally share them with friends and family, helping to prevent the spread of misinformation.

[1565] (Application example 1)

[1566] 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."

[1567] In today's digital information society, the spread of misinformation and false information has become a problem, causing confusion and misunderstanding among users, and even causing harm to users. In particular, in advertising, if consumers act on false information, it could result in economic losses and a loss of trust. In response, there is a demand for systems that allow users to obtain accurate information in real time.

[1568] 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.

[1569] In this invention, the server includes means for determining the authenticity of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from information sources and fact-checking organizations, means for transmitting the authenticity results determined by the information processing device to a user terminal, means for analyzing advertising information captured by a display device that displays advertisements and determining its authenticity, and means for instantly displaying the determination results on the display device, thereby enabling users to check the authenticity of advertising information in real time and make decisions based on accurate information.

[1570] An "information processing device" is a device that manages a fact-check database and determines the truth of information sent by a user.

[1571] A "fact-checking database" is a database that accumulates data obtained from reliable sources and fact-checking organizations and is used to determine the veracity of information.

[1572] A "source" is a primary source of accurate information, such as a reliable news organization or official institution.

[1573] A "fact-checking organization" is an organization that professionally verifies the veracity of information and publishes the results.

[1574] A "user terminal" is a communication device used by a user to send and receive information requests.

[1575] "Advertising" is information intended to promote a particular product or service to consumers.

[1576] A "display device" is a device that allows a user to visually view information. An example is smart glasses.

[1577] A "generative AI model" is an algorithm that uses artificial intelligence technology to automatically determine the veracity of information.

[1578] "Searching" is the process of looking through data in a fact-checking database to find the information you need.

[1579] A "user" is someone who uses the system to verify the authenticity of information.

[1580] "Periodic updating" refers to the operation of collecting the latest data at regular intervals and adding it to the database.

[1581] The "true / false result" is the result of determining whether the information is true or false.

[1582] "Analysis" is the process of examining advertising information in detail and evaluating the authenticity of the content.

[1583] "Real-time" means processing information almost immediately and without delay.

[1584] A "communication application" is software that allows users to exchange messages with a server.

[1585] The present invention is a fact-checking system that operates in cooperation with a user terminal and is centered around an information processing device. The purpose of this system is to determine the authenticity of advertisements in real time and provide the results to users immediately. The specific implementation method is shown below.

[1586] Server Features

[1587] Maintaining a fact-checking database

[1588] The server periodically retrieves data from trusted sources and fact-checking organizations and stores it in a fact-checking database.

[1589] Example: Every day at 2 AM, the server retrieves updated fact-checking data from reliable source A and fact-checking organization B and updates the database.

[1590] Handling the request

[1591] The server receives information requests from users, queries (searches) a fact-checking database, uses a generative AI model to determine the veracity of the information, and returns the results to the user.

[1592] Example: When a user asks "Is this true?" in a chat app, the server searches the information in a database and replies "It's fake."

[1593] Analysis of advertising information

[1594] The server analyzes the advertising information captured by a display device such as smart glasses using OCR technology and determines its authenticity.

[1595] Example: When a user sees an advertisement on their smart glasses that says "Get a huge discount!", this information is sent to a server and checked against a database.

[1596] Display of judgment results

[1597] The server immediately transmits the determined true or false result to the display device so that the user can visually confirm it.

[1598] Example: The server sends the result "This ad is false information" and the result is displayed on the display of the smart glasses.

[1599] User device functions

[1600] Sending information

[1601] The user terminal transmits the information and questions entered by the user to the server.

[1602] Example: When a user types "Is this news true?" in a chat app and sends it, the message is sent to the server.

[1603] Advertisement information capture

[1604] The display device captures the advertising text and sends it to the server.

[1605] Example: Smart glasses convert advertising information that comes into the user's field of vision into text using OCR technology and send it to a server.

[1606] Receiving and displaying results

[1607] The fact check results sent from the server are received and displayed on the display device.

[1608] Example: The server sends the result "This ad is fake" and the result is displayed on the smart glasses.

[1609] User Roles

[1610] Entering information

[1611] The user inputs the information they want to check (e.g., a link or text of a news article) and sends it to the server.

[1612] Example: A user pastes a news link sent by a friend into a chat app and asks, "Is this true?"

[1613] Review and share your results

[1614] Based on the response from the server, you can verify the authenticity of the information and share the results with others.

[1615] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation.

[1616] Prompt Sentence Examples

[1617] Describe an application that uses OCR technology to capture advertisement text viewed by users on the street and then checks its veracity against a fact-checking database. This application runs on smart glasses and has the ability to instantly display whether an advertisement is true or false.

[1618] As described above, the present invention is embodied as a system that enables users to check the authenticity of advertisements and information in real time, prevent the spread of false information, and act based on accurate information.

[1619] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1620] Step 1:

[1621] A user wears smart glasses and walks around town looking at advertisements. The smart glasses use a camera to capture the advertisement information. Specifically, the smart glasses capture the text information of the advertisement and convert it into text data using OCR technology. The input is the captured image data, and the output is the converted text data.

[1622] Step 2:

[1623] The smart glasses send the text data converted by OCR technology to the server. Specifically, they send the advertisement text as an HTTP request to the server's API endpoint. The input is the text data converted by OCR, and the output is an HTTP request to the server.

[1624] Step 3:

[1625] The server searches the fact-checking database based on the received ad text. Specifically, it issues an SQL query to the database based on the text data sent and retrieves relevant fact-checking information. The input is the ad text data, and the output is the search results from the fact-checking database.

[1626] Step 4:

[1627] The server inputs the search results from the fact-checking database into the generative AI model to evaluate the truth of the advertising information. Specifically, the search results are input into the generative AI model and the probability of determining whether the information is true or false is calculated. The input is the search results from the fact-checking database, and the output is a probability evaluation of the truth or falsehood.

[1628] Step 5:

[1629] The server makes a final judgment on the authenticity of the advertising information based on the probability evaluation obtained from the generative AI model. Specifically, a certain threshold is set and a judgment is made, for example, whether the information is considered true with a probability of 0.8 or higher, or whether it is considered false. The input is the probability evaluation, and the output is the final truth / falseness judgment result.

[1630] Step 6:

[1631] The server sends the final truth-or-false judgment result to the smart glasses. Specifically, it returns the judgment result to the smart glasses as an HTTP response. The input is the truth-or-false judgment result, and the output is the HTTP response.

[1632] Step 7:

[1633] The smart glasses display the received truthfulness result on the display. Specifically, to visually present the truthfulness result to the user, they display a message on the display saying "This advertisement is true" or "This advertisement is false." The input is the truthfulness result of the HTTP response, and the output is the display visible to the user.

[1634] Through these steps, users can verify the authenticity of advertising information in real time, preventing the spread of misinformation and enabling users to make decisions based on accurate information.

[1635] 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.

[1636] This invention is a fact-checking system that combines a user terminal and an emotion engine with an information processing device (hereinafter referred to as a server) at its core. We will explain the specific means and process for effectively identifying false and misleading information and providing appropriate messages based on the user's emotions.

[1637] Server Features

[1638] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[1639] Maintaining a fact-checking database

[1640] The server periodically retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[1641] Example: Every day at 2 AM, the server retrieves updated fact-checking data from news source A and fact-checking organization B and updates the database.

[1642] Handling the request

[1643] It receives information requests from users, queries (searches) a database, uses an AI model to determine the authenticity of the information, and returns the results to the user.

[1644] Example: When a user asks "Is this true?" on LINE, the server searches the information in its database and replies, "This is false information."

[1645] Compensation distribution management

[1646] The server distributes rewards to news organizations and fact-checking organizations that provide fact-checking data based on the number of times the data is used.

[1647] Example: At the end of the month, the server tallies the number of times the fact-checking data has been used and distributes 100,000 yen to news organization A and 50,000 yen to fact-checking organization B.

[1648] Collaboration with emotion engine

[1649] The server receives the user's emotion data from the emotion engine and adjusts the response message based on the data.

[1650] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[1651] User device functions

[1652] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[1653] Sending information

[1654] The user terminal transmits the information and questions entered by the user to the server.

[1655] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[1656] Receiving the results

[1657] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[1658] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[1659] User Roles

[1660] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[1661] Entering information

[1662] Users enter the information they want to check (e.g., a link or text of a news article) into the LINE app and send it to the server.

[1663] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[1664] Review and share your results

[1665] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[1666] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[1667] Emotion Engine Functions

[1668] The emotion engine analyzes information requests from users and determines the user's emotions.

[1669] Emotion determination

[1670] The emotion engine analyzes the user's text data to determine the emotion, and transmits the emotion data to the server.

[1671] Example: If a user sends a request saying "I am very worried about this news," the emotion engine will determine the answer as "worried" and send that data to the server.

[1672] Sending emotional data

[1673] The emotion engine sends the determined emotion data to the server, which uses it to tailor a response message.

[1674] Example: The emotion engine determines emotion data as "worry" and sends it to the server, which then generates a message saying, "This news is fake. Don't worry."

[1675] In this way, the server, user device, and emotion engine work together to realize a system that prevents the spread of false and misleading information and provides appropriate responses according to the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[1676] The processing flow will be explained below.

[1677] Step 1:

[1678] Users launch the LINE app on their smartphone and open the chat screen of the official account for combating fake news.

[1679] Step 2:

[1680] Users enter the information they want to check or a link to a news article in the message field, add a question like "Is this true? I'm very worried," and press the send button.

[1681] Step 3:

[1682] The terminal generates a request to send the message input by the user to the emotion engine.

[1683] Step 4:

[1684] The device sends the generated request to the emotion engine.

[1685] Step 5:

[1686] The emotion engine receives the message sent by the user and analyzes the text data.

[1687] Step 6:

[1688] The emotion engine analyzes the text data, determines the user's emotion as "worry," and generates emotion data.

[1689] Step 7:

[1690] The emotion engine returns the generated emotion data to the terminal.

[1691] Step 8:

[1692] The terminal generates a request to transmit the emotion data received from the emotion engine to the server.

[1693] Step 9:

[1694] The terminal sends the generated request to the server.

[1695] Step 10:

[1696] The server receives the emotion data sent from the terminal and the user's information request.

[1697] Step 11:

[1698] The server queries (searches) the fact-checking database based on the received user information request.

[1699] Step 12:

[1700] The server inputs the search results into an AI model to determine whether the information is true or false.

[1701] Step 13:

[1702] The server generates a message to respond to the user based on the AI ​​model's judgment and emotional data, such as "Don't worry. This information is fake."

[1703] Step 14:

[1704] The server sends the generated response message to the terminal.

[1705] Step 15:

[1706] The terminal receives the response message sent from the server.

[1707] Step 16:

[1708] The device will display the received message on the chat screen of the LINE app.

[1709] Step 17:

[1710] The user opens the chat screen of the LINE app and checks the response message from the server, which may say, for example, "Don't worry. This news is fake."

[1711] Step 18:

[1712] Users can judge the authenticity of the information based on the results they receive, and share their judgment with friends and family. They can also feel reassured by receiving messages that correspond to their emotions.

[1713] Example 2

[1714] 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."

[1715] In modern society, false and misinformation often spreads rapidly on the Internet, resulting in a decline in the reliability of information. Another issue is that users' exposure to such uncertain information can easily cause anxiety and confusion. Conventional fact-checking systems struggle to reduce the psychological burden placed on users by simply determining the veracity of information. Therefore, there is a need for systems that can accurately determine the veracity of false and misinformation and provide appropriate messages tailored to the user's emotions, thereby increasing the user's sense of security.

[1716] 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.

[1717] In this invention, the server includes means for determining the truth of information sent by a user using a fact-checking database managed by an information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for transmitting the truthfulness results determined by the information processing device to a user terminal, means for determining the user's emotions using an emotion analysis engine, and means for adjusting a response message to the user based on the user's emotion data. This makes it possible to accurately determine false information and misinformation, as well as provide an appropriate response message according to the user's emotions.

[1718] An "information processing device" is a device that has the function of receiving information sent from a user, analyzing and processing the information, and sending the results.

[1719] A "fact-checking database" is a database that accumulates data used to determine the veracity of false information or misinformation.

[1720] "News organizations" are organizations that provide information to the public, such as newspapers, television stations, and internet news sites.

[1721] A "fact-checking organization" is an organization that verifies the accuracy of information provided by media outlets and individuals and publishes the results.

[1722] A "user terminal" is a device that allows a user to input information and communicate with a server, such as a smartphone or a personal computer.

[1723] An "emotion analysis engine" is software or a system that analyzes text data sent by a user and determines the user's emotions.

[1724] A "generative AI model" is a model that uses artificial intelligence to automatically determine the truth or falsity of information.

[1725] A "prompt sentence" is a text sentence that indicates a question or request that a user enters into the system.

[1726] The "true / false result" is the result of determining whether the transmitted information is true or false.

[1727] A "response message" is a message generated by a server to reply to a user.

[1728] This invention relates to a fact-checking system that combines a user terminal and a sentiment analysis engine with an information processing device as its core. This system effectively identifies false and misleading information and provides appropriate messages based on the user's sentiment.

[1729] Server Features

[1730] The server manages a fact-checking database and plays a central role in determining the veracity of information submitted by users.

[1731] Maintaining a fact-checking database

[1732] The server regularly retrieves data from trusted news outlets and fact-checking organizations and stores it in a fact-checking database.

[1733] Example: A server retrieves updated data from news organizations and fact-checking organizations every day at 2 AM and updates the database.

[1734] Handling the request

[1735] The server receives information requests from users, queries (searches) the database, uses a generative AI model to determine the authenticity of the information, and returns the results to the user.

[1736] Example: If a user asks "Is this news true?" on the LINE app, the server searches the information in the database and replies "It's fake news."

[1737] Collaboration with sentiment analysis engine

[1738] The server receives the user's emotional data from the emotion analysis engine and adjusts the response message based on that data.

[1739] Example: When a user sends an anxious message asking, "Is this news true?", the server determines the emotion as "anxiety" and replies with a comforting message along with the result.

[1740] User device functions

[1741] The user's device communicates with the server through a chat app such as the LINE app to send and receive information.

[1742] Sending information

[1743] The user terminal transmits the information and questions entered by the user to the server.

[1744] Example: When a user types "Is this news true?" into the LINE app and sends it, the message is sent to the server.

[1745] Receiving the results

[1746] The system receives the fact-check results and messages corresponding to the emotions sent from the server and displays them on the chat screen of the LINE app.

[1747] Example: When the server responds, "This news is fake. Don't worry," the result is displayed on the LINE chat screen.

[1748] User Roles

[1749] Users can interact with the system using apps such as LINE to confirm the authenticity of the information and receive corresponding messages based on their emotions.

[1750] Entering information

[1751] The user enters the information they want to check into the LINE app and sends it to the server.

[1752] Example: A user pastes a news link sent by a friend into the LINE app and sends a message asking, "Is this true?"

[1753] Review and share your results

[1754] Based on the response from the server, users can check the authenticity of the information and share the results with others. Users can also receive messages based on their emotions, providing reassurance and comfort.

[1755] Example: A user who receives a reply saying "This news is fake" can notify their friends of the result to prevent the spread of misinformation. Also, the message "Don't worry" can reduce anxiety.

[1756] Sentiment Analysis Engine Features

[1757] The emotion analysis engine analyzes information requests from users and determines their emotions.

[1758] Emotion determination

[1759] The emotion analysis engine analyzes the user's text data to determine their emotion and transmits the emotion data to the server.

[1760] Example: If a user sends a request saying "I am very worried about this news," the sentiment analysis engine will determine the answer as "worried" and send that data to the server.

[1761] Sending emotional data

[1762] The emotion analysis engine sends the determined emotion data to the server, which uses it to tailor a response message.

[1763] Example: An emotion analysis engine sends emotional data that it determines to be "worried" to a server, which then generates a message saying, "This news is fake. Don't worry."

[1764] This allows the server, user devices, and emotion analysis engine to work together to create a system that prevents the spread of false and misleading information and provides appropriate responses based on the user's emotions. This system guarantees the accuracy of information and increases the user's sense of security.

[1765] Prompt Sentence Examples

[1766] Is this news true?

[1767] I heard about this information, but I would like to know if it is true.

[1768] I am very concerned about this information. Please confirm if it is correct.

[1769] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1770] Step 1:

[1771] Users open the LINE app, enter the information or question they want to have fact-checked, and tap the send button.

[1772] Specific action: The user types "Is this news true?" and taps the send button.

[1773] Input: Text data entered by the user.

[1774] Output: Text data sent through the LINE app.

[1775] Step 2:

[1776] The user device sends the entered information to the fact-checking system server via the LINE server.

[1777] Specific operation: The text data sent by the user passes through the LINE server and arrives at the system server.

[1778] Input: Text data sent from the LINE app.

[1779] Output: The text data received by the server.

[1780] Step 3:

[1781] The server uses a natural language processing (NLP) engine to analyze the received text data.

[1782] Specific operation: The server uses an NLP engine to analyze text data, extract keywords, and decompose sentences.

[1783] Input: Text data received by the server.

[1784] Output: Parsed text data (keywords and sentences).

[1785] Step 4:

[1786] The server sends the received information to an emotion analysis engine to determine the user's emotion.

[1787] Specific operation: The server sends the parsed text data to the sentiment analysis engine, which analyzes the text and generates sentiment labels.

[1788] Input: Parsed text data.

[1789] Output: Sentiment data returned by the sentiment analysis engine (e.g., "worried").

[1790] Step 5:

[1791] The server queries a fact-checking database and uses a generative AI model to determine whether the information is true or false.

[1792] Specific operation: The server searches the fact-check database, and the generative AI model scores the degree of agreement and obtains a truth judgment result.

[1793] Input: Parsed text data.

[1794] Output: The truth-check result obtained from the fact-check database.

[1795] Step 6:

[1796] The server receives the emotion data returned from the emotion analysis engine.

[1797] Specific operation: The server receives the emotion data sent from the emotion analysis engine.

[1798] Input: Sentiment data sent from the sentiment analysis engine.

[1799] Output: Emotion data received by the server.

[1800] Step 7:

[1801] The server generates a response message to be sent to the user based on the fact-check results and emotion data.

[1802] Specific operation: The server combines the fact-check results with the emotion data to generate an appropriate response message for the user, such as "This news is fake. Don't worry."

[1803] Input: Fact-check results and sentiment data.

[1804] Output: The generated response message.

[1805] Step 8:

[1806] The server sends the generated response message to the user terminal.

[1807] Specific operation: The server generates a response message and sends it to the user's device via the LINE server.

[1808] Input: The generated response message.

[1809] Output: The response message sent to the user terminal.

[1810] Step 9:

[1811] The user device receives the message sent from the server and displays it on the chat screen of the LINE app.

[1812] Specific operation: The LINE app receives the message sent from the server and displays it on the chat screen.

[1813] Input: The response message sent by the server.

[1814] Output: The response message displayed on the LINE app chat screen.

[1815] Step 10:

[1816] The user checks the chat screen in the LINE app and reads the response from the server.

[1817] Specific operation: The user opens the LINE app and checks the reply message displayed on the chat screen. They feel reassured when they see that the message is false.

[1818] Input: The message displayed on the chat screen of the LINE app.

[1819] Output: The message the user acknowledged and their relief.

[1820] (Application example 2)

[1821] 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."

[1822] Conventional fact-checking systems require users to manually input information and obtain results based on that information, which can be time-consuming and tedious to operate. Furthermore, because the system does not take the user's feelings into account when determining the veracity of information, the anxiety and concerns of users who receive the results may not be fully alleviated. Furthermore, the lack of a function to assess visually viewed information in real time makes it difficult to quickly prevent the spread of misinformation and disinformation.

[1823] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for determining the veracity of information sent by a user using a fact-checking database managed by the information processing device, means for periodically updating the fact-checking database from news organizations and fact-checking organizations, means for capturing information viewed from the user terminal, automatically converting it to text, and sending the result to the information processing device, means for analyzing the user's emotions using an emotion engine and sending the result to the information processing device, and means for sending to the user terminal a response message based on the veracity result determined by the information processing device and the analyzed emotion. This makes it possible to capture information viewed by the user in real time, instantly determine its veracity, and provide feedback that takes the user's emotions into consideration.

[1824] An "information processing device" is a device that determines the veracity of information sent by users and manages and updates the fact-check database.

[1825] A "fact-checking database" is a database that accumulates and manages data provided by trusted news organizations and fact-checking organizations and is used to determine the veracity of information.

[1826] A "news organization" is an organization or group that creates and disseminates news, articles, etc.

[1827] A "fact-checking organization" is an organization or group that specializes in verifying the veracity of information and publishing it.

[1828] A "user terminal" is a device that a user uses to communicate with an information processing device, and includes a smartphone, smart glasses, and the like.

[1829] "Viewing" refers to a user visually checking information through a device.

[1830] "Capture" refers to obtaining visually recognized information as digital data.

[1831] "Textualization" refers to converting visually recognized information into text data.

[1832] An "emotion engine" is a system that analyzes user input data, determines emotions, and provides the results to other systems.

[1833] A "generative AI model" is a machine learning model that is trained on large datasets to perform tasks such as natural language processing.

[1834] The "response message" is a feedback message that is generated by the information processing device based on the determination result and sent to the user.

[1835] This invention can be realized as a system consisting of an information processing device (hereinafter referred to as a server), a user terminal, and an emotion engine. Each element of this system will be described in detail below.

[1836] server

[1837] The server has the following main functions:

[1838] 1. Maintaining and updating the fact-check database:

[1839] The server periodically retrieves fact-checking data from trusted news outlets and fact-checking organizations and updates the fact-checking database, which is managed using a database management system such as MySQL.

[1840] 2. Authenticity determination:

[1841] The server searches the information sent by the user against a fact-checking database and determines the authenticity of the information using a generative AI model (e.g., BERT or GPT-based models).

[1842] 3. Sentiment analysis and response message generation:

[1843] The server receives the user's emotion data sent from the emotion engine and adjusts the response message based on that information.

[1844] User terminal

[1845] User devices include smartphones and smart glasses, and have the following functions:

[1846] 1. Information capture and transcription:

[1847] The information the user sees is captured by a camera and automatically converted into text using OCR (Optical Character Recognition) technology.

[1848] 2. Sending and Receiving Information:

[1849] The textual information and the user's emotional data are sent to the server, and a response message is received from the server and displayed to the user.

[1850] Emotion Engine

[1851] The emotion engine is a system that analyzes user input data and determines emotions. It has the following functions:

[1852] 1. Emotion determination:

[1853] The user's text data is analyzed to determine their emotions. This process is carried out using IBM Watson's sentiment analysis API.

[1854] 2. Sending Emotional Data:

[1855] The determined emotion data is transmitted to the server.

[1856] Example of processing flow

[1857] Here is a concrete example of how the system actually works.

[1858] 1. The user views information on a social networking site using smart glasses.

[1859] 2. Information is captured by the camera and converted into text using OCR technology.

[1860] 3. The textual information is sent to the server.

[1861] 4. Check the accuracy of information using fact-checking databases.

[1862] 5. The emotion engine analyzes the user's emotion and determines, for example, "worry."

[1863] 6. The server generates a response message saying, "This information is fake. Don't worry."

[1864] 7. The message will appear on the smart glasses display.

[1865] Example prompts to be input to the generative AI model

[1866] Below is an example of a prompt sentence to input to the generative AI model.

[1867] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[1868] Such a system configuration and processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into consideration the user's feelings.

[1869] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1870] Step 1:

[1871] A user visually views information on a social networking site using smart glasses. The camera installed in the smart glasses captures the viewed information and converts it into text using OCR (Optical Character Recognition) technology. The input at this time is the viewed image data, and the output is the converted text information.

[1872] Step 2:

[1873] The textual information is sent from the smart glasses to the server. This process involves data communication from the device to the server. The server then begins analyzing the received text data.

[1874] Step 3:

[1875] The server searches a fact-checking database based on the received text data to verify the authenticity of the information. The input here is the text data, and the output from the fact-checking database is the truthfulness determination result. Additional analysis is performed using an AI model (e.g., BERT or GPT-based models).

[1876] Step 4:

[1877] The emotion engine analyzes the text data sent by the user and determines the user's emotion. The input is the user's text data, and the output is the emotion determination result. The emotion engine performs this process using, for example, IBM Watson's emotion analysis API.

[1878] Step 5:

[1879] The emotion data determined by the emotion engine is sent to the server. The server integrates this emotion data and generates an appropriate response message along with the truth / false judgment result. The input here is the truth / false judgment result and emotion data, and the output is the response message sent to the user.

[1880] Step 6:

[1881] The server then sends the generated response message to the user's smart glasses, where data communication occurs to provide the message to the user in real time, with the final output being the response message displayed on the smart glasses' display.

[1882] Example of processing flow

[1883] Here is a concrete example of how the system actually works.

[1884] A user is concerned. Is the following news item true?: "News that the world will end in 20XX is rapidly spreading."

[1885] This processing flow makes it possible to capture information visually recognized by the user in real time, instantly determine its authenticity, and provide feedback that takes into account the user's feelings.

[1886] 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.

[1887] 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.

[1888] 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.

[1889] 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.

[1890] 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.

[1891] 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.

[1892] 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).

[1893] 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.

[1894] 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."

[1895] 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.

[1896] 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).

[1897] 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.

[1898] 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.

[1899] 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.

[1900] 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.

[1901] 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.

[1902] 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.

[1903] 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.

[1904] 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.

[1905] 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.

[1906] 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.

[1907] The following is further disclosed regarding the above embodiment.

[1908] (Claim 1)

[1909] A means for determining the authenticity of information transmitted by a user using a fact-check database managed by an information processing device;

[1910] means for regularly updating said fact-checking database from news organizations and fact-checking organizations;

[1911] means for transmitting the authenticity result determined by the information processing device to a user terminal;

[1912] A system including:

[1913] (Claim 2)

[1914] The system according to claim 1, wherein the information processing device performs a search based on a fact-checking database and determines the truth of the information using an AI model.

[1915] (Claim 3)

[1916] 2. The system according to claim 1, wherein the user terminal sends and receives information requests from users via a chat app such as a LINE app.

[1917] (Claim 4)

[1918] 2. The system according to claim 1, wherein the information processing device includes means for distributing rewards to data providers of the fact-checking database based on the number of uses.

[1919] "Example 1"

[1920] (Claim 1)

[1921] means for determining the authenticity of information transmitted from a user terminal;

[1922] means for periodically updating said fact-checking database from sources;

[1923] means for transmitting the truth result determined by the information processing device to a user terminal;

[1924] A means for an information processing device to determine the authenticity of information using a generative AI model;

[1925] means for the user terminal to send and receive information requests via a chat application;

[1926] A system including:

[1927] (Claim 2)

[1928] The system of claim 1, wherein the information processing device queries a fact-checking database and uses a generative AI model to determine the truth of the information based on the search results.

[1929] (Claim 3)

[1930] 2. The system according to claim 1, wherein the user terminal receives and displays the fact-check results sent from the information processing device via a chat app.

[1931] "Application Example 1"

[1932] (Claim 1)

[1933] A means for determining the authenticity of information transmitted by a user using a fact-check database managed by an information processing device;

[1934] means for periodically updating said fact-checking database from sources and fact-checking organizations;

[1935] means for transmitting the authenticity result determined by the information processing device to a user terminal;

[1936] means for analyzing advertisement information captured by a display device that displays advertisements and determining its authenticity;

[1937] means for instantly displaying the determination result on the display device;

[1938] A system including:

[1939] (Claim 2)

[1940] The system according to claim 1, wherein the information processing device performs a search based on a fact-checking database and determines the truth of the information using a generative AI model.

[1941] (Claim 3)

[1942] 10. The system of claim 1, wherein the user terminal sends and receives information requests from a user via a communication application.

[1943] "Example 2: Combining Emotion Engines"

[1944] (Claim 1)

[1945] A means for determining the authenticity of information transmitted by a user using a fact-check database managed by an information processing device;

[1946] means for regularly updating said fact-checking database from news organizations and fact-checking organizations;

[1947] means for transmitting the authenticity result determined by the information processing device to a user terminal;

[1948] a means for determining a user's emotion using a sentiment analysis engine;

[1949] means for adjusting a message to be sent in response to the user based on the emotion data of the user;

[1950] A system including:

[1951] (Claim 2)

[1952] The system according to claim 1, wherein the information processing device performs a search based on a fact-checking database and determines the truth of the information using a generative AI model.

[1953] (Claim 3)

[1954] 10. The system of claim 1, wherein the user terminal sends and receives information requests from users via a chat app.

[1955] "Application example 2 when combining emotion engines"

[1956] (Claim 1)

[1957] A means for determining the authenticity of information transmitted by a user using a fact-check database managed by an information processing device;

[1958] means for regularly updating said fact-checking database from news organizations and fact-checking organizations;

[1959] a means for capturing visually recognized information from a user terminal, automatically converting the information into text, and transmitting the text to the information processing device;

[1960] means for analyzing a user's emotion using an emotion engine and transmitting the result to the information processing device;

[1961] means for transmitting a response message based on the truth result determined by the information processing device and the analyzed emotion to a user terminal;

[1962] A system including:

[1963] (Claim 2)

[1964] The system according to claim 1, wherein the information processing device performs a search based on a fact-checking database and determines the truth of the information using a generative AI model.

[1965] (Claim 3)

[1966] 10. The system of claim 1, wherein the user terminal utilizes a smart device to capture information and send and receive information requests from users via a chat app. [Explanation of symbols]

[1967] 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 determining the authenticity of information transmitted by a user using a fact-check database managed by an information processing device; means for regularly updating said fact-checking database from news organizations and fact-checking organizations; means for transmitting the authenticity result determined by the information processing device to a user terminal; A system including:

2. The system according to claim 1, wherein the information processing device performs a search based on a fact-checking database and determines the truth of the information using an AI model.

3. The system according to claim 1 , wherein the user terminal sends and receives information requests from users via a chat app such as a LINE app.

4. 2. The system according to claim 1, wherein the information processing device includes means for distributing rewards to data providers of the fact-check database based on the number of uses.

Images