system

Abstract

Provide a system. A means for receiving information and URLs input from a user's terminal; A means of querying the database for received information and URLs; If there is no corresponding data in the database, a means for sending a request to an external reliability evaluation API and receiving the result; A means for generating a reliability evaluation result based on the database query result and the external API result; means for transmitting the generated reliability evaluation result to a user terminal; A means for displaying the reliability evaluation results on the user's terminal A system including:

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, the number of hoaxes, fake news, and fraudulent websites on the Internet has increased, increasing the risk of users being deceived by this information. This could lead to social unrest and personal harm. Conventional methods have limited the means by which users can verify the reliability of information themselves, making it difficult to identify unreliable information and websites. There is a need to develop a system that can solve these problems and provide users with reliable information. [Means for solving the problem]

[0005] The present invention relates to a system that receives information or URLs entered from a user's device and queries a database for that information. If the corresponding data is not found in the database, a request is sent to an external credibility evaluation API and the result is received. Based on the received database query result and the external API result, a credibility evaluation result is generated and sent to the user's device for display, allowing the user to easily confirm the credibility of information and sites on the Internet. This system utilizes an external credibility evaluation API based on a database containing information on online hoaxes and fraudulent sites, as well as data sources including certificate information from public institutions, enabling more accurate and reliable evaluations.

[0006] A "user terminal" is an electronic device used by a user, such as a computer or smartphone.

[0007] "Input information or URL" refers to text information, web addresses, or other digital data that a user inputs through a terminal.

[0008] The "receiving means" refers to a method or device for transmitting the input information or URL to a server via a communication network and receiving the data.

[0009] A "database querying means" is a method or device for matching received information or URLs with data in an existing database to locate matching or related information.

[0010] An "external trustworthiness assessment API" is an API provided by an external service provider, and is an interface that utilizes external data necessary to assess the trustworthiness of received information or URLs.

[0011] The "means for receiving the result" is a method or device for receiving a response from an external trustworthiness evaluation API and using the result within the system.

[0012] The "means for generating the reliability evaluation result" refers to a method or device that evaluates the reliability of information or URLs based on the query results of a database or responses from an external API, and organizes and outputs the results.

[0013] The "means for transmitting to the user's terminal" refers to a method or apparatus for transmitting the generated trustworthiness evaluation result to the user's electronic device via a communication network.

[0014] The "means for displaying on the user's terminal" refers to a method or apparatus for displaying the transmitted trustworthiness evaluation result on the screen of an electronic device so that the user can visually recognize it.

[0015] "Online rumours" are false or misleading information that is circulated on the internet.

[0016] "Fraudulent site information" is information about fraudulent websites that are set up with the purpose of deceiving users.

[0017] "Certificate information from a public organization" is information based on an authentication certificate issued by a highly reliable public organization. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention relates to a system for verifying the reliability of information and websites on the Internet. Specifically, this system checks information and URLs entered by users through an app using a database and an external reliability evaluation API, and provides the results to the user.

[0040] System configuration

[0041] 1. On the user's device:

[0042] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications and provide an interface where users can enter information and URLs.

[0043] 2. Server:

[0044] A central server receives information from users' devices, queries the database for that information, and, if necessary, sends requests to external trust assessment APIs, receiving and analyzing the results.

[0045] 3. Database:

[0046] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[0047] 4. External Trust Assessment API:

[0048] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[0049] Program implementation example

[0050] 1. Launch the app and enter your information

[0051] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[0052] 2. Sending and Receiving Information

[0053] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[0054] 3. Querying the database

[0055] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[0056] 4. Use of external APIs

[0057] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[0058] 5. Generating reliability evaluation results

[0059] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[0060] 6. Sending and displaying results

[0061] The generated credibility evaluation results are sent from the server to the user's device. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the credibility of the information or site.

[0062] Specific examples

[0063] Example 1: Checking news articles

[0064] 1. The user launches the app and enters the URL of a news article.

[0065] 2. The device sends the input information to the server.

[0066] 3. The server queries the database and, if there is no matching entry, sends a request to an external API.

[0067] 4. The server receives the results of the external API and generates a trust rating and sends it to the device.

[0068] 5. The device will display "This news is trustworthy."

[0069] Example 2: Checking the safety of a shopping site

[0070] 1. The user launches the app and enters the URL of a shopping site.

[0071] 2. The device sends the input information to the server.

[0072] 3. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[0073] 4. The server sends the evaluation results to the device, which then displays the message "This shopping site is not trustworthy."

[0074] Error Handling

[0075] The system also has the ability to display an error message to the user if a database query or external API request fails, such as "Evaluation failed. Please try again."

[0076] In this way, this system allows users to easily check the reliability of information and sites on the Internet, reducing user risks and providing support that leads users to more reliable information.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The user launches the application. The user enters the information or URL they want to check into an input field. For example, they enter the URL of a news article.

[0080] Step 2:

[0081] The user presses the "Check" button. The device retrieves the entered information and URL.

[0082] Step 3:

[0083] The device sends the acquired information and URL to the server using a secure communication protocol such as HTTPS.

[0084] Step 4:

[0085] The server receives the input information, connects to the database, and searches the database based on the received information and URL.

[0086] Step 5:

[0087] The server queries the database to see if there is a matching entry, and if there is a matching entry in the database, retrieves its claims.

[0088] Step 6:

[0089] If there is no matching entry in the database, the server sends a request to an external trust assessment API, including the input information and URL.

[0090] Step 7:

[0091] The server receives a response from the external trust evaluation API, analyzes the received result, and obtains the trust information.

[0092] Step 8:

[0093] The server generates a final trust rating based on the results from the database and external APIs, which can be "trusted," "untrusted," or "unknown."

[0094] Step 9:

[0095] The server sends the generated trust evaluation results to the user's device using a secure communication protocol.

[0096] Step 10:

[0097] The device displays the trust evaluation results it received. The evaluation results are displayed in the user interface (UI) so that the user can confirm the results. For example, a message such as "This news is trustworthy" is displayed.

[0098] Step 11:

[0099] If the database query or external API request fails, the server generates an error message, which is sent to the user's device and displays "Evaluation failed. Please try again."

[0100] Example 1

[0101] 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."

[0102] Rapid and accurate evaluation of the reliability of information and websites on the Internet is an important issue in modern society. However, previous systems have been inadequate in detecting fake information and fraudulent websites, making it difficult for users to easily access reliable information. Furthermore, because systems rely solely on databases, they have had the problem of being slow to respond to newly emerging fraudulent information and hoaxes.

[0103] 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.

[0104] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for sending the generated trustworthiness evaluation result to the user's terminal, means for displaying the trustworthiness evaluation result on the user's terminal, means for sending an HTTP POST request from the user's terminal to the server, means for the server to execute an SQL query on the database and search for information, means for receiving the result returned from the external API via an HTTP request, means for the server to generate a trustworthiness evaluation in JSON format based on the received result, and means for displaying the JSON data received by the terminal on a user interface. This allows users to access highly reliable information quickly and accurately.

[0105] A "user's terminal" is a computing device used by a user, such as a smartphone, tablet, or PC.

[0106] "Means for receiving" refers to functions or programs that enable receiving data via a communications network.

[0107] "Means for querying a database" refers to a program or function that searches for entries in a database based on received information and retrieves matching data.

[0108] The "external trustworthiness evaluation API" is an interface for accessing external services to perform trustworthiness evaluation on the Internet and obtaining the necessary evaluation information.

[0109] "Reliability evaluation result" is the evaluation result regarding the reliability of specific information or URL, calculated based on the database query results and results from external APIs.

[0110] An "HTTP POST request" is a type of HTTP protocol used by a client to send data to a server.

[0111] An "SQL query" is a structured query language used to retrieve or manipulate specific data from a relational database.

[0112] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a standard format for expressing data in a concise, easy-to-read text format.

[0113] "User interface" refers to the screen and operating means by which a user interacts with a computer system.

[0114] This invention relates to a system for evaluating the reliability of information and websites on the Internet. Specifically, the system is a system in which a server queries information and URLs entered from a user's terminal using a database and an external reliability evaluation API, and provides the results to the user.

[0115] System configuration

[0116] 1. User's device

[0117] This includes smartphones, tablets, and PCs used by users. These devices run dedicated applications and provide an interface for users to enter information and URLs.

[0118] 2. Server

[0119] The server has the function of receiving information and URLs sent from the user's device. It also executes SQL queries on the database to search for information. If necessary, it also sends requests to an external trust evaluation API and receives the results. These processes are performed to generate trust evaluation results and send them to the user's device in JSON format.

[0120] 3. Database

[0121] The database contains information about online hoaxes and fraudulent websites, and the server queries the database to find entries that match the information or URLs it receives.

[0122] 4. External Trust Assessment API

[0123] The external API provides a data source for trust assessment, including certificate information from public institutions, etc. The server uses this external API if the corresponding information does not exist in the database.

[0124] Specific examples of programs

[0125] Launching the app and entering information

[0126] A user launches a smartphone app and enters the information or URL they want to check in the input field displayed on the screen. For example, they enter the URL of a news article, "https: / / example.com / news123."

[0127] Sending and Receiving Information

[0128] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request, and the server receives the data encoded in JSON format.

[0129] Querying the database

[0130] The server uses the received information to query its internal database with an SQL query, for example "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[0131] Using external APIs

[0132] If there is no corresponding information in the database, the server will send an HTTP request to an external trust evaluation API. For example, it will send the following data: { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"}.

[0133] Generating reliability evaluation results

[0134] The server generates a trust evaluation result based on the database query results and the results of the external API. For example, if the database records it as "fraud," it will be evaluated as "untrustworthy," but if the external API returns "verified," it will be evaluated as "trustworthy."

[0135] Sending and displaying results

[0136] The generated trust evaluation results are sent from the server to the device in JSON format. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the trustworthiness of the information or site.

[0137] Specific prompt examples

[0138] The specific prompt text is shown below.

[0139] 1. "Confirm the trustworthiness of this news article (URL: https: / / example.com / news123)"

[0140] 2. "Evaluate the security of the following shopping site (URL: https: / / example-shop.com)"

[0141] In this way, this system helps users access highly reliable information by quickly and accurately evaluating the reliability of information and sites on the Internet.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] A user launches a smartphone app. They enter the information or URL they want to check into the input field displayed on the app screen. For example, the user enters the URL of a news article, "https: / / example.com / news123." As input, the user provides the URL, and as output, the device stores the URL in the input form. Specifically, the user enters the URL in the text field and presses the "Check" button.

[0145] Step 2:

[0146] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request. As input, the user provides a URL, and as output, the device sends data encoded in JSON format to the server. Specifically, the device generates JSON data {"url": "https: / / example.com / news123"} and sends this data to the server via an HTTP POST request.

[0147] Step 3:

[0148] The server queries its internal database with an SQL query based on the received information. As input, it receives JSON data from the device, and as output, it executes an SQL query to retrieve matching entries in the database. Specifically, the server executes the query "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[0149] Step 4:

[0150] If the server does not find the corresponding data in its database, it sends an HTTP request to an external trust evaluation API. As input, it checks whether there are any database query results, and as output, it generates and sends a request to the external API. Specifically, the server sends the data { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"} to the external API.

[0151] Step 5:

[0152] The server receives the results returned from the external API via an HTTP request. It receives the response from the external API as input and parses the results as output. Specifically, the server receives the response data from the external API and parses it as JSON format data.

[0153] Step 6:

[0154] The server generates a trust evaluation result based on the database query results and external API results. It takes the database query results and external API results as input and generates a trust evaluation as output. Specifically, the server analyzes the database and external API results and creates a trust evaluation result in JSON format (e.g., "trusted" or "not trustworthy").

[0155] Step 7:

[0156] The server sends the generated trust evaluation result to the user's device. It uses the trust evaluation result as input and sends JSON data to the device as output. Specifically, the server sends JSON data {"trustResult": "trusted"} to the device.

[0157] Step 8:

[0158] The terminal displays the reliability evaluation results it receives on the user interface. It uses the JSON data received from the server as input and displays the evaluation results to the user as output. Specifically, the terminal displays the message "This news is reliable" on the screen.

[0159] (Application example 1)

[0160] 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."

[0161] The Internet is plagued by a wealth of false information and fraudulent websites. Users lack the means to quickly assess the reliability of such information, making it difficult to verify its authenticity. Manually checking the reliability of URLs is time-consuming and laborious, placing a heavy burden on users. Furthermore, there is a lack of functionality for saving and reusing the reliability evaluation results of previously checked URLs, forcing users to repeatedly evaluate the same sites. The purpose of this invention is to solve these problems, efficiently evaluate the reliability of information on the Internet, and support users' safe access to information.

[0162] 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.

[0163] In this invention, the server includes: means for receiving information and URLs entered from a user's mobile device; means for querying a data storage for the received information and URLs; means for sending a request to an external trust evaluation API and receiving the result if the corresponding data is not found in the data storage; means for generating a trust evaluation result based on the data storage query result and the external API result; means for transmitting the generated trust evaluation result to the user's mobile device; means for displaying the trust evaluation result on the user's mobile device; means for automatically checking URLs from the clipboard; means for saving and reviewing the history; and means for setting a custom alert that warns the user about access to unsafe sites. This allows the user to automatically check URLs from the clipboard, quickly and efficiently receive and display the results, and reuse past history to avoid duplicate checks. The custom alert setting also makes it possible to prevent access to unsafe sites.

[0164] "User's Mobile Device" refers to a smartphone, tablet, or other portable device used by a User.

[0165] "Means for receiving information or URLs" refers to the function for sending information or URLs entered by the user to the server and receiving them on the server side.

[0166] "Data storage" refers to a storage device for managing and querying data, including information about false information and fraudulent websites on the Internet.

[0167] "Means for querying data storage" refers to the function for searching for received information or URLs in data storage and confirming their existence.

[0168] "Means for sending requests to an external trust assessment API and receiving the results" refers to the function for sending requests to an API that uses public institutions or other reliable information sources to perform assessments when there is no relevant data in the data storage, and receiving the results.

[0169] "Means for generating trustworthiness assessment results" refers to the function of making decisions to assess the trustworthiness of information or URLs based on results from data storage and external APIs.

[0170] "Means for transmitting to the user's mobile device" refers to a function for transmitting the generated reliability evaluation results to the user's smartphone or tablet.

[0171] The "means for displaying the reliability evaluation result" refers to a function for visually displaying the reliability evaluation result to the user on the user's mobile device.

[0172] "Means for automatically checking URLs from the clipboard" refers to a function that automatically detects URLs that a user has copied to the clipboard and evaluates the trustworthiness of those URLs.

[0173] "A means to save and review history" refers to a function that allows you to save the results of the reliability evaluation of URLs and information that you have checked in the past and review them later.

[0174] "Custom alert setting means" refers to a function for setting a custom alert when a user accesses an unstable site and providing that alert.

[0175] System Overview:

[0176] This invention is a system for verifying the reliability of information and websites on the Internet, checking information and URLs entered by users using data storage and an external reliability evaluation API, and providing the results to the users. Specific embodiments of the system are described below.

[0177] Hardware and software used:

[0178] Hardware: User devices such as smartphones, tablets, and PCs.

[0179] software:

[0180] SQLite: A local database for storing the reliability evaluation results.

[0181] requests module: A software component for handling HTTP requests to external APIs.

[0182] Python: The programming language used to implement the server and applications.

[0183] System configuration:

[0184] 1. On the user's device:

[0185] The user's device is a mobile device such as a smartphone, where the user runs the application and inputs information or URLs. For example, if the user copies the URL of a news article or a shopping site to the clipboard, the application automatically detects the URL and begins rating it.

[0186] 2. Server:

[0187] The server queries the data storage for the received information and URL, and if there is no corresponding data, it sends a request to an external trust evaluation API. It also generates a trust evaluation result based on the results of the data storage query and the results from the external API.

[0188] 3. Data Storage:

[0189] Data storage manages data, including information about false and fraudulent websites on the Internet, using database management systems such as SQLite.

[0190] 4. External Trust Assessment API:

[0191] External APIs are APIs based on public or other trusted data sources, for example, providing certification information.

[0192] Processing Details:

[0193] 1. Enter and submit your information:

[0194] When a user types a URL into their mobile device or copies it to their clipboard, the application automatically reads the URL and sends it to the server.

[0195] 2. Data storage query:

[0196] The server checks the received URL in the data storage to see if the corresponding information exists. If a matching entry is found in the data storage, it evaluates its credibility based on the results and notifies the user.

[0197] 3. Use of external APIs:

[0198] If there is no corresponding information in the data storage, the server sends a request to an external trust evaluation API and receives the response. It then obtains the trust evaluation information from the API and generates a new evaluation result based on this information.

[0199] 4. Submit and view the evaluation results:

[0200] The server generates the final trust evaluation result and sends it to the user's mobile device, which receives the evaluation result and displays it on the application screen.

[0201] Examples and prompts:

[0202] Example: When a user launches an application and copies the URL "https: / / example-news.com / article123" to the clipboard, the application automatically starts a process to evaluate the trustworthiness of the URL. The result of the evaluation is displayed on the device screen, informing the user that "This site is not trustworthy."

[0203] Example prompt sentence:

[0204] When a user copies the URL "https: / / example-news.com / article123" to their clipboard, they should rate its trustworthiness. They should receive some kind of notification about the trustworthiness of this site, including details of whether it has been reported as a hoax in the past.

[0205] This allows users to easily access reliable information and reduces the risk of false information and fraudulent sites on the Internet.

[0206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0207] Step 1:

[0208] A user launches an application on a mobile device and inputs or copies a URL to the clipboard. The application then automatically detects the contents of the clipboard and prepares to parse the URL. Specifically, the application performs an input process that reads the contents of the clipboard and interprets the data as a URL.

[0209] Input: The URL that the user copied to the clipboard

[0210] Output: The URL is recognized in the application

[0211] Step 2:

[0212] The device sends the recognized URL to the server, the application sends the URL as an HTTP request to the server, and the server receives the request. This process initiates the evaluation of the trustworthiness of the data based on the URL.

[0213] Input: URL sent from the device

[0214] Output: URL sent to server

[0215] Step 3:

[0216] The server queries the data storage for the received URL to find the trust information for that URL. The server accesses the SQLite database and finds an entry that matches the received URL.

[0217] Input: URL received by the server

[0218] Output: Whether or not there is a matching entry in the data storage

[0219] Step 4:

[0220] If the server does not find a corresponding entry in its data storage, it sends a request to an external trust evaluation API. It sends a URL as a request to the external API and waits for the trust evaluation result. During this time, the server monitors the response from the API.

[0221] Input: URL where no corresponding data is found after querying the data storage

[0222] Output: Trust evaluation result from external API

[0223] Step 5:

[0224] The server receives the evaluation results from the external API and analyzes them. The server analyzes the data received from the external API and extracts the relevant evaluation information. This data includes the credibility evaluation results and related evidence information.

[0225] Input: Evaluation result from external API

[0226] Output: Analyze the evaluation results and extract the evaluation information

[0227] Step 6:

[0228] The server generates a final trust evaluation result based on the data storage query results and external API results. Based on the analyzed data, it generates an evaluation result such as "trusted," "untrusted," or "unknown."

[0229] Input: Data storage query results and external API evaluation results

[0230] Output: Final reliability evaluation result

[0231] Step 7:

[0232] The generated trust evaluation results are sent to the user's mobile device and notified to the user. The server sends the evaluation results to the user's terminal as an HTTP response, and the user's terminal displays the received results within the application.

[0233] Input: Final reliability evaluation result

[0234] Output: The evaluation result is displayed on the user's terminal.

[0235] Step 8:

[0236] Users can check the evaluation results on their mobile devices and judge the reliability of the information or site. Based on the displayed results, users can decide whether to continue using the information or browsing the site.

[0237] Input: Evaluation result displayed on the user's terminal

[0238] Output: User reviews the evaluation results and makes a decision

[0239] This allows users to efficiently obtain reliable information and avoid accessing suspicious sites.

[0240] 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.

[0241] This invention relates to a system that recognizes user emotions and verifies the reliability of information and websites on the Internet. Specifically, the system checks information and URLs entered by users through apps using a database and an external reliability evaluation API, and displays information appropriately based on the results, taking the user's emotions into consideration.

[0242] System configuration

[0243] 1. On the user's device:

[0244] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications, provide an interface for users to input information and URLs, and an emotion engine that recognizes users' emotions.

[0245] 2. Server:

[0246] A central server receives information from users' devices, queries the database, and optionally sends requests to external trust assessment APIs, receives and analyzes the results, and adjusts the received assessment results based on the user's sentiment.

[0247] 3. Database:

[0248] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[0249] 4. External Trust Assessment API:

[0250] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[0251] 5. Emotion Engine:

[0252] The emotion recognition function installed in the user's device analyzes the user's facial expressions, voice, input operations, etc. to identify the user's emotions.

[0253] Program implementation example

[0254] 1. Launch the app and enter your information

[0255] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[0256] 2. Emotional Recognition

[0257] When a user is entering information or pressing the "check" button, the device's built-in emotion engine analyzes the user's facial expressions, voice, and input operations to recognize their current emotion. For example, if the user looks anxious, the emotion will be recognized as "anxiety."

[0258] 3. Sending and Receiving Information

[0259] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[0260] 4. Querying the Database

[0261] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[0262] 5. Use of external APIs

[0263] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[0264] 6. Generating reliability evaluation results

[0265] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[0266] 7. Adjustment and submission of results

[0267] Based on the user's emotional information recognized by the emotion engine, the server adjusts the way it displays the trust assessment results. For example, if the user is anxious, it will display a more understandable and polite message. The adjusted results are then sent from the server to the user's device.

[0268] 8. Displaying the results

[0269] The user's device displays the received reliability evaluation results. For example, if the user looks anxious, the device displays the message "This news is reliable" along with detailed reasons and an explanation of the evaluation process.

[0270] Specific examples

[0271] Example 1: Checking news articles

[0272] 1. The user launches the app and enters the URL of a news article.

[0273] 2. While typing, the emotion engine analyzes the user's facial expressions to recognize emotions (e.g., surprise).

[0274] 3. The device sends the input information to the server.

[0275] 4. The server queries the database and, if there is no matching entry, sends a request to an external API.

[0276] 5. The server that receives the results of the external API generates a trust rating.

[0277] 6. Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[0278] 7. Your device will display the message "This news is trustworthy" along with a detailed explanation.

[0279] Example 2: Checking the safety of a shopping site

[0280] 1. The user launches the app and enters the URL of a shopping site.

[0281] 2. As you type, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[0282] 3. The device sends the input information to the server.

[0283] 4. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[0284] 5. The server generates the evaluation results, adjusts them based on the results of the emotion engine, and sends them to the device.

[0285] 6. Your device will display a message saying "This shopping site is untrustworthy" along with details about the specific risks.

[0286] Error Handling

[0287] In the system, if a database query or external API request fails, the server generates an error message, which is adjusted based on the results of the emotion engine, and the user's device displays "Evaluation failed. Please try again."

[0288] In this way, this system takes into account the user's feelings and allows them to easily check the reliability of information and sites on the Internet, thereby reducing user risks and providing support that leads them to more reliable information.

[0289] The processing flow will be explained below.

[0290] Step 1:

[0291] A user launches the app on their smartphone. The app screen displays fields for entering information and URLs. The user enters the URL of the news article they want to check.

[0292] Step 2:

[0293] While the user is entering information, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion. For example, if the user is frowning, the emotion engine will detect anxiety.

[0294] Step 3:

[0295] The user presses the "Check" button. The device retrieves the entered information and URL and sends them to the server. A secure communication protocol such as HTTPS is used for transmission.

[0296] Step 4:

[0297] The server receives the input information and first queries the database. The server connects to the database and searches for entries that match the received information and URL. At the same time, it also processes the user's emotional information.

[0298] Step 5:

[0299] If there is a matching entry in the database, the server retrieves its credibility information, for example, "this site has been reported as a scam in the past."

[0300] Step 6:

[0301] If there is no matching entry in the database, the server sends a request to an external trust assessment API, which includes the user-entered information and a URL.

[0302] Step 7:

[0303] The server receives a response from an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources, and returns the result.

[0304] Step 8:

[0305] The server generates a final trust rating based on the results from the database and the external API, which may include ratings such as "trusted," "untrusted," or "unknown."

[0306] Step 9:

[0307] Based on the emotion engine's recognition results, the server adjusts the way it displays the trust assessment results. For example, if the user expresses anxiety, it adds detailed reasons and instructions on what to do next in addition to the assessment result.

[0308] Step 10:

[0309] The server then sends the adjusted trust evaluation results to the user's device using a secure communication protocol.

[0310] Step 11:

[0311] The device displays the results of the trust assessment it receives. For example, if the user looks anxious, it displays the message "This news is trustworthy" along with a detailed explanation of why it is trustworthy.

[0312] Step 12:

[0313] If the database query or external API request fails, the server generates an error message. Based on the result of the emotion engine, the message "Evaluation failed. Please try again" is displayed on the user's device.

[0314] Specific examples

[0315] Example 1: Checking news articles

[0316] 1. Step 1 - User launches the app and enters the URL of a news article.

[0317] 2. Step 2 - While the user is typing, the emotion engine analyzes the user's facial expressions and recognizes the emotion (e.g. surprise).

[0318] 3. Step 3 - The device sends the input information to the server.

[0319] 4. Step 4 - The server queries the database and if there is no matching entry, it sends a request to an external API.

[0320] 5. Step 7 - The server receives the results of the external API and generates a trust rating.

[0321] 6. Step 9 - Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[0322] 7. Step 11 - Your device will display the message "This news is trustworthy" along with a detailed explanation.

[0323] Example 2: Checking the safety of a shopping site

[0324] 1. Step 1 - User launches the app and enters the URL of a shopping site.

[0325] 2. Step 2 - While typing, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[0326] 3. Step 3 - The device sends the input information to the server.

[0327] 4. Step 4 - The server queries the database and if a matching entry is found, it retrieves the fraud information.

[0328] 5. Step 7 - The server generates the evaluation result, adjusts it based on the emotion engine results, and sends it to the device.

[0329] 6. Step 11 - Your device will display a message saying "This shopping site is not trusted" along with details about the specific risks.

[0330] In this way, this system takes into account the user's feelings and displays the results of credibility evaluation appropriately, allowing users to use information on the Internet with peace of mind.

[0331] Example 2

[0332] 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."

[0333] Conventional information reliability evaluation systems were unable to consider the user's emotions when determining the reliability of information or URLs entered by the user. As a result, users may receive the results with anxiety or doubt, and even reliable information cannot be conveyed appropriately in accordance with the user's feelings. Furthermore, when there is no relevant data in the database, the evaluation method is uniform, making it difficult to provide users with an appropriate sense of security.

[0334] 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.

[0335] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for recognizing the user's emotion and transmitting the result to the server, means for adjusting the trustworthiness evaluation result based on the user's emotion information, means for transmitting the generated trustworthiness evaluation result to the user's terminal, and means for displaying the trustworthiness evaluation result on the user's terminal. This makes it possible to provide a trustworthiness evaluation result that reflects the user's emotion, thereby creating an environment in which users can check information with peace of mind.

[0336] "User device" refers to the device used by the user to enter information and check results, including smartphones, tablets, PCs, etc.

[0337] "Means for receiving" refers to a method or device that allows the server to obtain information or a URL sent from the user's terminal.

[0338] "Means for querying a database" refers to a method or device that allows the server to query an existing database for input information and confirm the presence or absence of the information and its contents.

[0339] "External Trust Assessment API" refers to an application programming interface that utilizes external data sources for trust assessment, including certificate information from public organizations.

[0340] "Means for generating reliability evaluation results" refers to a method or device for evaluating reliability and generating results based on information in a database or data from an external API.

[0341] "Means for recognizing emotions" refers to a function that analyzes the user's facial expressions, tone of voice, input operations, etc. to identify the user's current emotions.

[0342] The "means for adjusting the trustworthiness evaluation result" refers to a function for appropriately changing the display method and content of the trustworthiness evaluation result based on the recognized emotional information of the user.

[0343] The "means for transmitting" refers to a method or device for transmitting the generated reliability evaluation result or adjusted information to the user's terminal.

[0344] The "display means" refers to a method or device for visually displaying the reliability evaluation result on the user's terminal.

[0345] The system of this invention recognizes user emotions and evaluates the reliability of information and websites on the Internet based on the emotions. The system consists of the following main components:

[0346] 1. User's device

[0347] A device used by users to input information and check the results. It includes smartphones, tablets, PCs, etc. It runs a dedicated application and provides an interface for inputting information and URLs, as well as an emotion engine for recognizing the user's emotions. The emotion engine uses facial recognition and voice recognition technology to analyze the user's emotions. Specific software used includes a facial recognition API and a voice analysis API.

[0348] 2. Server

[0349] It is centrally located and receives information sent from user devices. It queries the received information against a database, sends requests to an external trust evaluation API as needed, and receives the results. It then generates trust evaluation results based on the database query results and external API results, and adjusts them based on user sentiment information. To perform these tasks, the server requires a database management system (DBMS) and software to process API requests.

[0350] 3. Database

[0351] This is a database that contains information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant information exists. RDBMS such as MySQL (registered trademark) or PostgreSQL is often used as the database software.

[0352] 4. External Trust Assessment API

[0353] It is an external service for evaluating the reliability of information, and uses certificate information from public institutions as a data source. This allows for reliable evaluation results to be obtained even if the relevant data is not available in the database. Specific APIs may apply generative AI models such as OpenAI (registered trademark).

[0354] 5. Emotion Engine

[0355] This function is installed on the user's device and identifies the user's emotions by analyzing their facial expressions, voice, input operations, etc. It applies computer vision and natural language processing technology to analyze emotions in real time.

[0356] Specific examples

[0357] Example 1: Checking news articles

[0358] The user launches a dedicated app on their smartphone and enters the URL of a news article. As they type, the emotion engine analyzes their facial expressions and recognizes the emotion of surprise. When the user presses the "Check" button, the input information is sent to the server. The server queries the database and, if no matching entry is found, sends a request to an external credibility assessment API. After receiving the result from the external API, the server generates a credibility assessment, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This news is trustworthy" along with a detailed explanation.

[0359] Example 2: Checking the safety of a shopping site

[0360] A user launches a dedicated app on a tablet and enters the URL of a shopping site. As they type, the emotion engine analyzes the user's tone of voice to recognize the emotion of anxiety. When the user presses the "Check" button, the URL is sent to the server. The server queries the database and, if it finds a matching entry, retrieves the information reported as fraud. The server generates an evaluation result, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This shopping site is untrustworthy" along with details about the specific risks.

[0361] Prompt Sentence Examples

[0362] "I want to enter the URL of a news article to check its authenticity. I'm a little unsure."

[0363] In this way, the system of the present invention allows users to easily check the reliability of information and websites on the Internet while taking into account their feelings, thereby reducing user risks and providing support that leads users to more reliable information.

[0364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0365] Step 1:

[0366] The user launches a dedicated app on a device such as a smartphone or PC, and the app screen displays fields for entering information and URLs.

[0367] Input: Information or URL the user wants to check (e.g., URL of a news article)

[0368] What happens: A user taps or clicks an app icon to launch the app and enters information or a URL into an on-screen input field.

[0369] Output: Information entered into input fields within the app and URLs

[0370] Step 2:

[0371] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and typing speed while they are typing or when they press the "check" button, and recognizes the user's emotions.

[0372] Input: User facial expressions, tone of voice, typing speed, etc.

[0373] How it works: Your device uses the camera to capture your facial expressions and the microphone to analyze the tone of your voice and record the speed and strength of your typing.

[0374] Output: Recognized user emotion (e.g., anxiety, surprise)

[0375] Step 3:

[0376] When the user presses the "Check" button, the device sends the entered information and URL to the server.

[0377] Input: User-entered information, URLs, and recognized emotions

[0378] How it works: The user presses the "Check" button, and the device generates and sends a request to send information and a URL to the server.

[0379] Output: Information sent to the server, URL, and recognized emotion

[0380] Step 4:

[0381] The server queries the database based on the received information to find a matching entry.

[0382] Input: Information or URL sent from the device

[0383] How it works: The server sends a query to the database, receives a response from the database, and checks whether the information is available.

[0384] Output: Database query results (e.g., information on reported fraudulent sites)

[0385] Step 5:

[0386] If the server does not have the relevant information in its database, it sends a request to an external trust evaluation API.

[0387] Input: Information or URL if the corresponding information does not exist in the database

[0388] How it works: The server generates a request for an external API and sends the request over the internet to the external API.

[0389] Output: Trust evaluation result from external API

[0390] Step 6:

[0391] The server generates a trust evaluation result based on the results from the database and external APIs.

[0392] Input: Database query results, trust evaluation results from external API

[0393] How it works: The server combines the responses from the database and the external API, analyzes key elements, and generates a final rating.

[0394] Output: Generated reliability evaluation result (e.g., "reliable", "unreliable", "unknown")

[0395] Step 7:

[0396] The server adjusts the display method of the reliability evaluation result based on the user's emotion information recognized by the emotion engine.

[0397] Input: Generated trust rating results, perceived user sentiment

[0398] How it works: The server formats the evaluation results based on emotional information to create a clear and polite message.

[0399] Output: Emotion-adjusted trustworthiness assessment results

[0400] Step 8:

[0401] The server transmits the adjusted trustworthiness evaluation result to the user's terminal.

[0402] Input: Emotion-adjusted trustworthiness assessment results

[0403] Action: The server sends the formatted evaluation results to the user's device.

[0404] Output: The trust evaluation result sent to the user's device

[0405] Step 9:

[0406] The user's terminal displays the received reliability evaluation result on the screen.

[0407] Input: Trustworthiness evaluation result sent from the server

[0408] How it works: The device displays the evaluation results received from the server on the screen, along with additional information and explanations based on the emotion.

[0409] Output: The credibility assessment result displayed to the user (e.g., "This news is trustworthy")

[0410] Error handling (if necessary)

[0411] If the server fails a database query or external API request, it generates an error message.

[0412] Input: Database query or external API request failure

[0413] How it works: The server generates error messages and adjusts them based on emotion information from the emotion engine.

[0414] Output: Tailored error message (e.g. "Evaluation failed. Please try again.")

[0415] In this way, the system takes into account the user's feelings and makes it easy to check the reliability of information and websites on the Internet, allowing users to check the information with peace of mind.

[0416] (Application example 2)

[0417] 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."

[0418] To enable users to easily determine the reliability of information and websites on the Internet, and to adjust the results of the determination based on the user's feelings and display them more appropriately, thereby enabling users to use the Internet with peace of mind without being misled by fraud or false information.

[0419] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0420] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the external API result, means for transmitting the generated trustworthiness evaluation result to the user's terminal, means for recognizing the user's emotion and adjusting the display method of the trustworthiness evaluation result based on the recognized emotion, thereby enabling appropriate feedback according to the user's emotion.

[0421] A "user's terminal" is a device that a user uses to input information and perform operations, and specifically refers to a smartphone, tablet, PC, etc.

[0422] "Input information or URL" refers to the address or text data of the website that the user wishes to check or evaluate.

[0423] "Means for receiving" refers to a module or interface that has the function of importing information or URLs sent from the user's terminal into the server.

[0424] The "means for querying a database" is a module that has the function of checking the received information or URL against a database to see if there is a corresponding entry.

[0425] An "external trustworthiness assessment API" is an external service for assessing trustworthiness, and refers to an API provided by a public institution or a reliable data source.

[0426] The "means for sending a request and receiving the result" is a module that enables the server to send a request to an external trustworthiness evaluation API and receive the evaluation result.

[0427] The "means for generating a reliability evaluation result" is a module that has the function of generating a final reliability evaluation based on the database query result and the evaluation result of the external API.

[0428] The "means for transmitting the reliability evaluation result to the user's terminal" is a module having a function for transmitting the reliability evaluation result generated by the server to the user's terminal.

[0429] The "means for displaying the reliability evaluation result" is a module or interface for visually displaying the reliability evaluation result received on the user's terminal in an easy-to-read manner.

[0430] The "means for recognizing the user's emotions" is a module that has the function of analyzing the user's facial expressions, voice, operation methods, etc. to identify the emotions at that time.

[0431] The "means for adjusting the display method" is a module that has the function of appropriately changing the content and method of display based on the recognized user emotion.

[0432] This invention relates to a system that recognizes user emotions and evaluates the reliability of information and websites on the Internet. Specifically, it realizes an application in the advertising field where a user evaluates the reliability of advertisements displayed to them, adjusts the results according to the user's emotions, and provides feedback.

[0433] System configuration

[0434] The system consists of the following main elements:

[0435] 1. User device: This is the device where the user enters information and checks the results, and includes smartphones, tablets, etc. It also has an emotion engine that recognizes the user's emotions.

[0436] 2. Server: A central server receives information from users' devices, communicates with a database and an external trust evaluation API, generates trust evaluation results, and adjusts the results based on user sentiment.

[0437] 3. Database: A database containing information on false information and fraudulent websites on the Internet, which serves as a primary source of information for assessing credibility.

[0438] 4. External Trust Assessment API: An external service that assesses trust, using APIs provided by public institutions or trusted data sources.

[0439] 5. Emotion engine: A module that has the function of identifying emotions by analyzing the user's facial expressions, voice, and operation methods.

[0440] Program processing flow

[0441] 1. Entering and receiving information: The user enters the URL of the advertisement into the device and presses the "Check" button. The device then sends the entered information to the server.

[0442] 2. Emotion Recognition: While the user is inputting or interacting with the device, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion, for example, identifying emotions such as anxiety or anger.

[0443] 3. Database query: The server queries the database based on the received information to search for the corresponding entry. If the corresponding data is found, it retrieves the information.

[0444] 4. Use of external API: If there is no corresponding data in the database, the server sends a request to an external trust evaluation API to obtain the evaluation results.

[0445] 5. Generating the trust evaluation results: The server generates the trust evaluation results based on the results from the database and the evaluation results from the external API.

[0446] 6. Adjustment and transmission of results: Based on the user's emotional information recognized by the emotion engine, the server adjusts the trust assessment results. For example, if anxiety is recognized, the server adds a detailed explanation to make the results easier to understand. The adjusted results are then sent to the user's device.

[0447] 7. Displaying the results: The user's device displays the results of the trust assessment. For example, it may display a message saying "This advertising site is untrustworthy," along with detailed risk information and warnings.

[0448] Hardware and software used

[0449] Hardware: Smartphone

[0450] Software: Flask (web framework), EmotionEngine (emotion recognition library), requests (external API requests)

[0451] Specific examples

[0452] Example 1

[0453] If a user enters an ad URL (e.g., https: / / fakeads.com) into the app and displays anxiety when viewing the ad:

[0454] 1. The user enters the ad URL into the app.

[0455] 2. The emotion engine recognizes anxiety from the user's facial expression.

[0456] 3. The URL is sent to the server and a database check is performed.

[0457] 4. A rating is received from the database saying "This advertising site has been reported in the past."

[0458] 5. Based on the results of the sentiment engine, a message is added saying "More information follows."

[0459] 6. Final message: "This advertising site has been reported in the past. More information below."

[0460] Example 2

[0461] If a user enters the ad URL (e.g., https: / / legitads.com) into the app and displays an angry expression when viewing the ad:

[0462] 1. The user enters the ad URL into the app.

[0463] 2. The emotion engine recognizes anger from the user's facial expression.

[0464] 3. The URL is sent to the server and a database check is performed.

[0465] 4. A rating is received from the database saying "This advertising site is trustworthy."

[0466] 5. Based on the results of the emotion engine, a message is added saying "Caution required."

[0467] 6. The final message appears: "This advertising site is trustworthy, but be careful."

[0468] Prompt Sentence Examples

[0469] Below is an example of a prompt used to generate a program for this system for the generative AI model:

[0470] A user enters an ad URL into the app. Write a program that recognizes the emotion of the user's facial expression when viewing the ad, and adjusts the display of the trust rating message based on that emotion. Specifically, this is a Python program that checks the URL against a database and an external API, and adjusts the display result according to the user's emotion.

[0471] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0472] Step 1:

[0473] The user enters the URL of the advertisement into the device and presses the "Check" button.

[0474] The entered URL is acquired by the terminal and sent to the server.

[0475] Step 2:

[0476] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotions.

[0477] Input data: User's facial expressions and tone of voice

[0478] Output data: Recognized emotion (e.g., anxiety, anger)

[0479] Specific operation: Facial expression and voice data is acquired using the built-in camera and microphone, and analyzed by the emotion engine.

[0480] Step 3:

[0481] The server checks the URL received from the terminal against the database.

[0482] Input data: Ad URL

[0483] Output data: Reliability information retrieved from the database (if available)

[0484] Specific operation: The received URL is queried against an existing database to find the corresponding entry.

[0485] Step 4:

[0486] If there is no corresponding data in the database, the server sends a request to an external trust evaluation API.

[0487] Input data: Ad URL

[0488] Output data: Reliability evaluation results obtained from external API

[0489] Specific operation: Sends an HTTP request to an external API, parses the response from the API, and obtains the evaluation result.

[0490] Step 5:

[0491] The server generates a reliability evaluation result based on the database query result and the evaluation result of the external API.

[0492] Input data: Results from databases, results from external APIs

[0493] Output data: Reliability assessment result (e.g., reliable, unreliable)

[0494] Specific operation: Run an algorithm to integrate the results of each evaluation and generate a final reliability evaluation.

[0495] Step 6:

[0496] Based on the user's emotional information recognized by the emotion engine, the server adjusts the display method of the reliability evaluation result.

[0497] Input data: Emotion recognition results, reliability evaluation results

[0498] Output data: Adjusted reliability evaluation results

[0499] Specific actions: Change the message content and display method of the trust evaluation results in response to the user's emotions (e.g., add a detailed explanation if the user is anxious).

[0500] Step 7:

[0501] The server sends the adjusted results to the user's terminal.

[0502] Input data: Adjusted reliability assessment results

[0503] Output data: Evaluation results sent to the user's device

[0504] Specific operation: A communication protocol (such as HTTP) is used to transmit the generated evaluation results to the user's terminal.

[0505] Step 8:

[0506] The received reliability evaluation result is displayed on the user's terminal.

[0507] Input data: Adjusted reliability assessment results

[0508] Output data: Display of evaluation results (e.g., messages on the screen)

[0509] Specific actions: The evaluation results are displayed in an appropriate format using the user interface. The user confirms the results.

[0510] 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.

[0511] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0512] 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.

[0513] [Second embodiment]

[0514] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0515] 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.

[0516] 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).

[0517] 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.

[0518] 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.

[0519] 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).

[0520] 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. 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.

[0521] 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.

[0522] 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.

[0523] 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.

[0524] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0525] 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."

[0526] This invention relates to a system for verifying the reliability of information and websites on the Internet. Specifically, this system checks information and URLs entered by users through an app using a database and an external reliability evaluation API, and provides the results to the user.

[0527] System configuration

[0528] 1. On the user's device:

[0529] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications and provide an interface where users can enter information and URLs.

[0530] 2. Server:

[0531] A central server receives information from users' devices, queries the database for that information, and, if necessary, sends requests to external trust assessment APIs, receiving and analyzing the results.

[0532] 3. Database:

[0533] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[0534] 4. External Trust Assessment API:

[0535] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[0536] Program implementation example

[0537] 1. Launch the app and enter your information

[0538] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[0539] 2. Sending and Receiving Information

[0540] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[0541] 3. Querying the database

[0542] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[0543] 4. Use of external APIs

[0544] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[0545] 5. Generating reliability evaluation results

[0546] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[0547] 6. Sending and displaying results

[0548] The generated credibility evaluation results are sent from the server to the user's device. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the credibility of the information or site.

[0549] Specific examples

[0550] Example 1: Checking news articles

[0551] 1. The user launches the app and enters the URL of a news article.

[0552] 2. The device sends the input information to the server.

[0553] 3. The server queries the database and, if there is no matching entry, sends a request to an external API.

[0554] 4. The server receives the results of the external API and generates a trust rating and sends it to the device.

[0555] 5. The device will display "This news is trustworthy."

[0556] Example 2: Checking the safety of a shopping site

[0557] 1. The user launches the app and enters the URL of a shopping site.

[0558] 2. The device sends the input information to the server.

[0559] 3. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[0560] 4. The server sends the evaluation results to the device, which then displays the message "This shopping site is not trustworthy."

[0561] Error Handling

[0562] The system also has the ability to display an error message to the user if a database query or external API request fails, such as "Evaluation failed. Please try again."

[0563] In this way, this system allows users to easily check the reliability of information and sites on the Internet, reducing user risks and providing support that leads users to more reliable information.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] The user launches the application. The user enters the information or URL they want to check into an input field. For example, they enter the URL of a news article.

[0567] Step 2:

[0568] The user presses the "Check" button. The device retrieves the entered information and URL.

[0569] Step 3:

[0570] The device sends the acquired information and URL to the server using a secure communication protocol such as HTTPS.

[0571] Step 4:

[0572] The server receives the input information, connects to the database, and searches the database based on the received information and URL.

[0573] Step 5:

[0574] The server queries the database to see if there is a matching entry, and if there is a matching entry in the database, retrieves its claims.

[0575] Step 6:

[0576] If there is no matching entry in the database, the server sends a request to an external trust assessment API, including the input information and URL.

[0577] Step 7:

[0578] The server receives a response from the external trust evaluation API, analyzes the received result, and obtains the trust information.

[0579] Step 8:

[0580] The server generates a final trust rating based on the results from the database and external APIs, which can be "trusted," "untrusted," or "unknown."

[0581] Step 9:

[0582] The server sends the generated trust evaluation results to the user's device using a secure communication protocol.

[0583] Step 10:

[0584] The device displays the trust evaluation results it received. The evaluation results are displayed in the user interface (UI) so that the user can confirm the results. For example, a message such as "This news is trustworthy" is displayed.

[0585] Step 11:

[0586] If the database query or external API request fails, the server generates an error message, which is sent to the user's device and displays "Evaluation failed. Please try again."

[0587] Example 1

[0588] 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."

[0589] Rapid and accurate evaluation of the reliability of information and websites on the Internet is an important issue in modern society. However, previous systems have been inadequate in detecting fake information and fraudulent websites, making it difficult for users to easily access reliable information. Furthermore, because systems rely solely on databases, they have had the problem of being slow to respond to newly emerging fraudulent information and hoaxes.

[0590] 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.

[0591] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for sending the generated trustworthiness evaluation result to the user's terminal, means for displaying the trustworthiness evaluation result on the user's terminal, means for sending an HTTP POST request from the user's terminal to the server, means for the server to execute an SQL query on the database and search for information, means for receiving the result returned from the external API via an HTTP request, means for the server to generate a trustworthiness evaluation in JSON format based on the received result, and means for displaying the JSON data received by the terminal on a user interface. This allows users to access highly reliable information quickly and accurately.

[0592] A "user's terminal" is a computing device used by a user, such as a smartphone, tablet, or PC.

[0593] "Means for receiving" refers to functions or programs that enable receiving data via a communications network.

[0594] "Means for querying a database" refers to a program or function that searches for entries in a database based on received information and retrieves matching data.

[0595] The "external trustworthiness evaluation API" is an interface for accessing external services to perform trustworthiness evaluation on the Internet and obtaining the necessary evaluation information.

[0596] "Reliability evaluation result" is the evaluation result regarding the reliability of specific information or URL, calculated based on the database query results and results from external APIs.

[0597] An "HTTP POST request" is a type of HTTP protocol used by a client to send data to a server.

[0598] An "SQL query" is a structured query language used to retrieve or manipulate specific data from a relational database.

[0599] "JSON format" stands for JavaScript Object Notation and is a standard format for representing data in a concise, easy-to-read text format.

[0600] "User interface" refers to the screen and operating means by which a user interacts with a computer system.

[0601] This invention relates to a system for evaluating the reliability of information and websites on the Internet. Specifically, the system is a system in which a server queries information and URLs entered from a user's terminal using a database and an external reliability evaluation API, and provides the results to the user.

[0602] System configuration

[0603] 1. User's device

[0604] This includes smartphones, tablets, and PCs used by users. These devices run dedicated applications and provide an interface for users to enter information and URLs.

[0605] 2. Server

[0606] The server has the function of receiving information and URLs sent from the user's device. It also executes SQL queries on the database to search for information. If necessary, it also sends requests to an external trust evaluation API and receives the results. These processes are performed to generate trust evaluation results and send them to the user's device in JSON format.

[0607] 3. Database

[0608] The database contains information about online hoaxes and fraudulent websites, and the server queries the database to find entries that match the information or URLs it receives.

[0609] 4. External Trust Assessment API

[0610] The external API provides a data source for trust assessment, including certificate information from public institutions, etc. The server uses this external API if the corresponding information does not exist in the database.

[0611] Specific examples of programs

[0612] Launching the app and entering information

[0613] A user launches a smartphone app and enters the information or URL they want to check in the input field displayed on the screen. For example, they enter the URL of a news article, "https: / / example.com / news123."

[0614] Sending and Receiving Information

[0615] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request, and the server receives the data encoded in JSON format.

[0616] Querying the database

[0617] The server uses the received information to query its internal database with an SQL query, for example "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[0618] Using external APIs

[0619] If there is no corresponding information in the database, the server will send an HTTP request to an external trust evaluation API. For example, it will send the following data: { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"}.

[0620] Generating reliability evaluation results

[0621] The server generates a trust evaluation result based on the database query results and the results of the external API. For example, if the database records it as "fraud," it will be evaluated as "untrustworthy," but if the external API returns "verified," it will be evaluated as "trustworthy."

[0622] Sending and displaying results

[0623] The generated trust evaluation results are sent from the server to the device in JSON format. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the trustworthiness of the information or site.

[0624] Specific prompt examples

[0625] The specific prompt text is shown below.

[0626] 1. "Confirm the trustworthiness of this news article (URL: https: / / example.com / news123)"

[0627] 2. "Evaluate the security of the following shopping site (URL: https: / / example-shop.com)"

[0628] In this way, this system helps users access highly reliable information by quickly and accurately evaluating the reliability of information and sites on the Internet.

[0629] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0630] Step 1:

[0631] A user launches a smartphone app. They enter the information or URL they want to check into the input field displayed on the app screen. For example, the user enters the URL of a news article, "https: / / example.com / news123." As input, the user provides the URL, and as output, the device stores the URL in the input form. Specifically, the user enters the URL in the text field and presses the "Check" button.

[0632] Step 2:

[0633] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request. As input, the user provides a URL, and as output, the device sends data encoded in JSON format to the server. Specifically, the device generates JSON data {"url": "https: / / example.com / news123"} and sends this data to the server via an HTTP POST request.

[0634] Step 3:

[0635] The server queries its internal database with an SQL query based on the received information. As input, it receives JSON data from the device, and as output, it executes an SQL query to retrieve matching entries in the database. Specifically, the server executes the query "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[0636] Step 4:

[0637] If the server does not find the corresponding data in its database, it sends an HTTP request to an external trust evaluation API. As input, it checks whether there are any database query results, and as output, it generates and sends a request to the external API. Specifically, the server sends the data { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"} to the external API.

[0638] Step 5:

[0639] The server receives the results returned from the external API via an HTTP request. It receives the response from the external API as input and parses the results as output. Specifically, the server receives the response data from the external API and parses it as JSON format data.

[0640] Step 6:

[0641] The server generates a trust evaluation result based on the database query results and external API results. It takes the database query results and external API results as input and generates a trust evaluation as output. Specifically, the server analyzes the database and external API results and creates a trust evaluation result in JSON format (e.g., "trusted" or "not trustworthy").

[0642] Step 7:

[0643] The server sends the generated trust evaluation result to the user's device. It uses the trust evaluation result as input and sends JSON data to the device as output. Specifically, the server sends JSON data {"trustResult": "trusted"} to the device.

[0644] Step 8:

[0645] The terminal displays the reliability evaluation results it receives on the user interface. It uses the JSON data received from the server as input and displays the evaluation results to the user as output. Specifically, the terminal displays the message "This news is reliable" on the screen.

[0646] (Application example 1)

[0647] 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."

[0648] The Internet is plagued by a wealth of false information and fraudulent websites. Users lack the means to quickly assess the reliability of such information, making it difficult to verify its authenticity. Manually checking the reliability of URLs is time-consuming and laborious, placing a heavy burden on users. Furthermore, there is a lack of functionality for saving and reusing the reliability evaluation results of previously checked URLs, forcing users to repeatedly evaluate the same sites. The purpose of this invention is to solve these problems, efficiently evaluate the reliability of information on the Internet, and support users' safe access to information.

[0649] 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.

[0650] In this invention, the server includes: means for receiving information and URLs entered from a user's mobile device; means for querying a data storage for the received information and URLs; means for sending a request to an external trust evaluation API and receiving the result if the corresponding data is not found in the data storage; means for generating a trust evaluation result based on the data storage query result and the external API result; means for transmitting the generated trust evaluation result to the user's mobile device; means for displaying the trust evaluation result on the user's mobile device; means for automatically checking URLs from the clipboard; means for saving and reviewing the history; and means for setting a custom alert that warns the user about access to unsafe sites. This allows the user to automatically check URLs from the clipboard, quickly and efficiently receive and display the results, and reuse past history to avoid duplicate checks. The custom alert setting also makes it possible to prevent access to unsafe sites.

[0651] "User's Mobile Device" refers to a smartphone, tablet, or other portable device used by a User.

[0652] "Means for receiving information or URLs" refers to the function for sending information or URLs entered by the user to the server and receiving them on the server side.

[0653] "Data storage" refers to a storage device for managing and querying data, including information about false information and fraudulent websites on the Internet.

[0654] "Means for querying data storage" refers to the function for searching for received information or URLs in data storage and confirming their existence.

[0655] "Means for sending requests to an external trust assessment API and receiving the results" refers to the function for sending requests to an API that uses public institutions or other reliable information sources to perform assessments when there is no relevant data in the data storage, and receiving the results.

[0656] "Means for generating trustworthiness assessment results" refers to the function of making decisions to assess the trustworthiness of information or URLs based on results from data storage and external APIs.

[0657] "Means for transmitting to the user's mobile device" refers to a function for transmitting the generated reliability evaluation results to the user's smartphone or tablet.

[0658] The "means for displaying the reliability evaluation result" refers to a function for visually displaying the reliability evaluation result to the user on the user's mobile device.

[0659] "Means for automatically checking URLs from the clipboard" refers to a function that automatically detects URLs that a user has copied to the clipboard and evaluates the trustworthiness of those URLs.

[0660] "A means to save and review history" refers to a function that allows you to save the results of the reliability evaluation of URLs and information that you have checked in the past and review them later.

[0661] "Custom alert setting means" refers to a function for setting a custom alert when a user accesses an unstable site and providing that alert.

[0662] System Overview:

[0663] This invention is a system for verifying the reliability of information and websites on the Internet, checking information and URLs entered by users using data storage and an external reliability evaluation API, and providing the results to the users. Specific embodiments of the system are described below.

[0664] Hardware and software used:

[0665] Hardware: User devices such as smartphones, tablets, and PCs.

[0666] software:

[0667] SQLite: A local database for storing the reliability evaluation results.

[0668] requests module: A software component for handling HTTP requests to external APIs.

[0669] Python: The programming language used to implement the server and applications.

[0670] System configuration:

[0671] 1. On the user's device:

[0672] The user's device is a mobile device such as a smartphone, where the user runs the application and inputs information or URLs. For example, if the user copies the URL of a news article or a shopping site to the clipboard, the application automatically detects the URL and begins rating it.

[0673] 2. Server:

[0674] The server queries the data storage for the received information and URL, and if there is no corresponding data, it sends a request to an external trust evaluation API. It also generates a trust evaluation result based on the results of the data storage query and the results from the external API.

[0675] 3. Data Storage:

[0676] Data storage manages data, including information about false and fraudulent websites on the Internet, using database management systems such as SQLite.

[0677] 4. External Trust Assessment API:

[0678] External APIs are APIs based on public or other trusted data sources, for example, providing certification information.

[0679] Processing Details:

[0680] 1. Enter and submit your information:

[0681] When a user types a URL into their mobile device or copies it to their clipboard, the application automatically reads the URL and sends it to the server.

[0682] 2. Data storage query:

[0683] The server checks the received URL in the data storage to see if the corresponding information exists. If a matching entry is found in the data storage, it evaluates its credibility based on the results and notifies the user.

[0684] 3. Use of external APIs:

[0685] If there is no corresponding information in the data storage, the server sends a request to an external trust evaluation API and receives the response. It then obtains the trust evaluation information from the API and generates a new evaluation result based on this information.

[0686] 4. Submit and view the evaluation results:

[0687] The server generates the final trust evaluation result and sends it to the user's mobile device, which receives the evaluation result and displays it on the application screen.

[0688] Examples and prompts:

[0689] Example: When a user launches an application and copies the URL "https: / / example-news.com / article123" to the clipboard, the application automatically starts a process to evaluate the trustworthiness of the URL. The result of the evaluation is displayed on the device screen, informing the user that "This site is not trustworthy."

[0690] Example prompt sentence:

[0691] When a user copies the URL "https: / / example-news.com / article123" to their clipboard, they should rate its trustworthiness. They should receive some kind of notification about the trustworthiness of this site, including details of whether it has been reported as a hoax in the past.

[0692] This allows users to easily access reliable information and reduces the risk of false information and fraudulent sites on the Internet.

[0693] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0694] Step 1:

[0695] A user launches an application on a mobile device and inputs or copies a URL to the clipboard. The application then automatically detects the contents of the clipboard and prepares to parse the URL. Specifically, the application performs an input process that reads the contents of the clipboard and interprets the data as a URL.

[0696] Input: The URL that the user copied to the clipboard

[0697] Output: The URL is recognized in the application

[0698] Step 2:

[0699] The device sends the recognized URL to the server, the application sends the URL as an HTTP request to the server, and the server receives the request. This process initiates the evaluation of the trustworthiness of the data based on the URL.

[0700] Input: URL sent from the device

[0701] Output: URL sent to server

[0702] Step 3:

[0703] The server queries the data storage for the received URL to find the trust information for that URL. The server accesses the SQLite database and finds an entry that matches the received URL.

[0704] Input: URL received by the server

[0705] Output: Whether or not there is a matching entry in the data storage

[0706] Step 4:

[0707] If the server does not find a corresponding entry in its data storage, it sends a request to an external trust evaluation API. It sends a URL as a request to the external API and waits for the trust evaluation result. During this time, the server monitors the response from the API.

[0708] Input: URL where no corresponding data is found after querying the data storage

[0709] Output: Trust evaluation result from external API

[0710] Step 5:

[0711] The server receives the evaluation results from the external API and analyzes them. The server analyzes the data received from the external API and extracts the relevant evaluation information. This data includes the credibility evaluation results and related evidence information.

[0712] Input: Evaluation result from external API

[0713] Output: Analyze the evaluation results and extract the evaluation information

[0714] Step 6:

[0715] The server generates a final trust evaluation result based on the data storage query results and external API results. Based on the analyzed data, it generates an evaluation result such as "trusted," "untrusted," or "unknown."

[0716] Input: Data storage query results and external API evaluation results

[0717] Output: Final reliability evaluation result

[0718] Step 7:

[0719] The generated trust evaluation results are sent to the user's mobile device and notified to the user. The server sends the evaluation results to the user's terminal as an HTTP response, and the user's terminal displays the received results within the application.

[0720] Input: Final reliability evaluation result

[0721] Output: The evaluation result is displayed on the user's terminal.

[0722] Step 8:

[0723] Users can check the evaluation results on their mobile devices and judge the reliability of the information or site. Based on the displayed results, users can decide whether to continue using the information or browsing the site.

[0724] Input: Evaluation result displayed on the user's terminal

[0725] Output: User reviews the evaluation results and makes a decision

[0726] This allows users to efficiently obtain reliable information and avoid accessing suspicious sites.

[0727] 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.

[0728] This invention relates to a system that recognizes user emotions and verifies the reliability of information and websites on the Internet. Specifically, the system checks information and URLs entered by users through apps using a database and an external reliability evaluation API, and displays information appropriately based on the results, taking the user's emotions into consideration.

[0729] System configuration

[0730] 1. On the user's device:

[0731] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications, provide an interface for users to input information and URLs, and an emotion engine that recognizes users' emotions.

[0732] 2. Server:

[0733] A central server receives information from users' devices, queries the database, and optionally sends requests to external trust assessment APIs, receives and analyzes the results, and adjusts the received assessment results based on the user's sentiment.

[0734] 3. Database:

[0735] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[0736] 4. External Trust Assessment API:

[0737] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[0738] 5. Emotion Engine:

[0739] The emotion recognition function installed in the user's device analyzes the user's facial expressions, voice, input operations, etc. to identify the user's emotions.

[0740] Program implementation example

[0741] 1. Launch the app and enter your information

[0742] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[0743] 2. Emotional Recognition

[0744] When a user is entering information or pressing the "check" button, the device's built-in emotion engine analyzes the user's facial expressions, voice, and input operations to recognize their current emotion. For example, if the user looks anxious, the emotion will be recognized as "anxiety."

[0745] 3. Sending and Receiving Information

[0746] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[0747] 4. Querying the Database

[0748] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[0749] 5. Use of external APIs

[0750] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[0751] 6. Generating reliability evaluation results

[0752] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[0753] 7. Adjustment and submission of results

[0754] Based on the user's emotional information recognized by the emotion engine, the server adjusts the way it displays the trust assessment results. For example, if the user is anxious, it will display a more understandable and polite message. The adjusted results are then sent from the server to the user's device.

[0755] 8. Displaying the results

[0756] The user's device displays the received reliability evaluation results. For example, if the user looks anxious, the device displays the message "This news is reliable" along with detailed reasons and an explanation of the evaluation process.

[0757] Specific examples

[0758] Example 1: Checking news articles

[0759] 1. The user launches the app and enters the URL of a news article.

[0760] 2. While typing, the emotion engine analyzes the user's facial expressions to recognize emotions (e.g., surprise).

[0761] 3. The device sends the input information to the server.

[0762] 4. The server queries the database and, if there is no matching entry, sends a request to an external API.

[0763] 5. The server that receives the results of the external API generates a trust rating.

[0764] 6. Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[0765] 7. Your device will display the message "This news is trustworthy" along with a detailed explanation.

[0766] Example 2: Checking the safety of a shopping site

[0767] 1. The user launches the app and enters the URL of a shopping site.

[0768] 2. As you type, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[0769] 3. The device sends the input information to the server.

[0770] 4. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[0771] 5. The server generates the evaluation results, adjusts them based on the results of the emotion engine, and sends them to the device.

[0772] 6. Your device will display a message saying "This shopping site is untrustworthy" along with details about the specific risks.

[0773] Error Handling

[0774] In the system, if a database query or external API request fails, the server generates an error message, which is adjusted based on the results of the emotion engine, and the user's device displays "Evaluation failed. Please try again."

[0775] In this way, this system takes into account the user's feelings and allows them to easily check the reliability of information and sites on the Internet, thereby reducing user risks and providing support that leads them to more reliable information.

[0776] The processing flow will be explained below.

[0777] Step 1:

[0778] A user launches the app on their smartphone. The app screen displays fields for entering information and URLs. The user enters the URL of the news article they want to check.

[0779] Step 2:

[0780] While the user is entering information, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion. For example, if the user is frowning, the emotion engine will detect anxiety.

[0781] Step 3:

[0782] The user presses the "Check" button. The device retrieves the entered information and URL and sends them to the server. A secure communication protocol such as HTTPS is used for transmission.

[0783] Step 4:

[0784] The server receives the input information and first queries the database. The server connects to the database and searches for entries that match the received information and URL. At the same time, it also processes the user's emotional information.

[0785] Step 5:

[0786] If there is a matching entry in the database, the server retrieves its credibility information, for example, "this site has been reported as a scam in the past."

[0787] Step 6:

[0788] If there is no matching entry in the database, the server sends a request to an external trust assessment API, which includes the user-entered information and a URL.

[0789] Step 7:

[0790] The server receives a response from an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources, and returns the result.

[0791] Step 8:

[0792] The server generates a final trust rating based on the results from the database and the external API, which may include ratings such as "trusted," "untrusted," or "unknown."

[0793] Step 9:

[0794] Based on the emotion engine's recognition results, the server adjusts the way it displays the trust assessment results. For example, if the user expresses anxiety, it adds detailed reasons and instructions on what to do next in addition to the assessment result.

[0795] Step 10:

[0796] The server then sends the adjusted trust evaluation results to the user's device using a secure communication protocol.

[0797] Step 11:

[0798] The device displays the results of the trust assessment it receives. For example, if the user looks anxious, it displays the message "This news is trustworthy" along with a detailed explanation of why it is trustworthy.

[0799] Step 12:

[0800] If the database query or external API request fails, the server generates an error message. Based on the result of the emotion engine, the message "Evaluation failed. Please try again" is displayed on the user's device.

[0801] Specific examples

[0802] Example 1: Checking news articles

[0803] 1. Step 1 - User launches the app and enters the URL of a news article.

[0804] 2. Step 2 - While the user is typing, the emotion engine analyzes the user's facial expressions and recognizes the emotion (e.g. surprise).

[0805] 3. Step 3 - The device sends the input information to the server.

[0806] 4. Step 4 - The server queries the database and if there is no matching entry, it sends a request to an external API.

[0807] 5. Step 7 - The server receives the results of the external API and generates a trust rating.

[0808] 6. Step 9 - Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[0809] 7. Step 11 - Your device will display the message "This news is trustworthy" along with a detailed explanation.

[0810] Example 2: Checking the safety of a shopping site

[0811] 1. Step 1 - User launches the app and enters the URL of a shopping site.

[0812] 2. Step 2 - While typing, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[0813] 3. Step 3 - The device sends the input information to the server.

[0814] 4. Step 4 - The server queries the database and if a matching entry is found, it retrieves the fraud information.

[0815] 5. Step 7 - The server generates the evaluation result, adjusts it based on the emotion engine results, and sends it to the device.

[0816] 6. Step 11 - Your device will display a message saying "This shopping site is not trusted" along with details about the specific risks.

[0817] In this way, this system takes into account the user's feelings and displays the results of credibility evaluation appropriately, allowing users to use information on the Internet with peace of mind.

[0818] Example 2

[0819] 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."

[0820] Conventional information reliability evaluation systems were unable to consider the user's emotions when determining the reliability of information or URLs entered by the user. As a result, users may receive the results with anxiety or doubt, and even reliable information cannot be conveyed appropriately in accordance with the user's feelings. Furthermore, when there is no relevant data in the database, the evaluation method is uniform, making it difficult to provide users with an appropriate sense of security.

[0821] 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.

[0822] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for recognizing the user's emotion and transmitting the result to the server, means for adjusting the trustworthiness evaluation result based on the user's emotion information, means for transmitting the generated trustworthiness evaluation result to the user's terminal, and means for displaying the trustworthiness evaluation result on the user's terminal. This makes it possible to provide a trustworthiness evaluation result that reflects the user's emotion, thereby creating an environment in which users can check information with peace of mind.

[0823] "User device" refers to the device used by the user to enter information and check results, including smartphones, tablets, PCs, etc.

[0824] "Means for receiving" refers to a method or device that allows the server to obtain information or a URL sent from the user's terminal.

[0825] "Means for querying a database" refers to a method or device that allows the server to query an existing database for input information and confirm the presence or absence of the information and its contents.

[0826] "External Trust Assessment API" refers to an application programming interface that utilizes external data sources for trust assessment, including certificate information from public organizations.

[0827] "Means for generating reliability evaluation results" refers to a method or device for evaluating reliability and generating results based on information in a database or data from an external API.

[0828] "Means for recognizing emotions" refers to a function that analyzes the user's facial expressions, tone of voice, input operations, etc. to identify the user's current emotions.

[0829] The "means for adjusting the trustworthiness evaluation result" refers to a function for appropriately changing the display method and content of the trustworthiness evaluation result based on the recognized emotional information of the user.

[0830] The "means for transmitting" refers to a method or device for transmitting the generated reliability evaluation result or adjusted information to the user's terminal.

[0831] The "display means" refers to a method or device for visually displaying the reliability evaluation result on the user's terminal.

[0832] The system of this invention recognizes user emotions and evaluates the reliability of information and websites on the Internet based on the emotions. The system consists of the following main components:

[0833] 1. User's device

[0834] A device used by users to input information and check the results. It includes smartphones, tablets, PCs, etc. It runs a dedicated application and provides an interface for inputting information and URLs, as well as an emotion engine for recognizing the user's emotions. The emotion engine uses facial recognition and voice recognition technology to analyze the user's emotions. Specific software used includes a facial recognition API and a voice analysis API.

[0835] 2. Server

[0836] It is centrally located and receives information sent from user devices. It queries the received information against a database, sends requests to an external trust evaluation API as needed, and receives the results. It then generates trust evaluation results based on the database query results and external API results, and adjusts them based on user sentiment information. To perform these tasks, the server requires a database management system (DBMS) and software to process API requests.

[0837] 3. Database

[0838] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant information exists. RDBMS such as MySQL or PostgreSQL is often used as the database software.

[0839] 4. External Trust Assessment API

[0840] It is an external service for evaluating the reliability of information, using data sources such as certificate information from public institutions. This allows for reliable evaluation results even when the relevant data is not available in the database. Specific APIs may use generative AI models such as those from OpenAI.

[0841] 5. Emotion Engine

[0842] This function is installed on the user's device and identifies the user's emotions by analyzing their facial expressions, voice, input operations, etc. It applies computer vision and natural language processing technology to analyze emotions in real time.

[0843] Specific examples

[0844] Example 1: Checking news articles

[0845] The user launches a dedicated app on their smartphone and enters the URL of a news article. As they type, the emotion engine analyzes their facial expressions and recognizes the emotion of surprise. When the user presses the "Check" button, the input information is sent to the server. The server queries the database and, if no matching entry is found, sends a request to an external credibility assessment API. After receiving the result from the external API, the server generates a credibility assessment, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This news is trustworthy" along with a detailed explanation.

[0846] Example 2: Checking the safety of a shopping site

[0847] A user launches a dedicated app on a tablet and enters the URL of a shopping site. As they type, the emotion engine analyzes the user's tone of voice to recognize the emotion of anxiety. When the user presses the "Check" button, the URL is sent to the server. The server queries the database and, if it finds a matching entry, retrieves the information reported as fraud. The server generates an evaluation result, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This shopping site is untrustworthy" along with details about the specific risks.

[0848] Prompt Sentence Examples

[0849] "I want to enter the URL of a news article to check its authenticity. I'm a little unsure."

[0850] In this way, the system of the present invention allows users to easily check the reliability of information and websites on the Internet while taking into account their feelings, thereby reducing user risks and providing support that leads users to more reliable information.

[0851] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0852] Step 1:

[0853] The user launches a dedicated app on a device such as a smartphone or PC, and the app screen displays fields for entering information and URLs.

[0854] Input: Information or URL the user wants to check (e.g., URL of a news article)

[0855] What happens: A user taps or clicks an app icon to launch the app and enters information or a URL into an on-screen input field.

[0856] Output: Information entered into input fields within the app and URLs

[0857] Step 2:

[0858] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and typing speed while they are typing or when they press the "check" button, and recognizes the user's emotions.

[0859] Input: User facial expressions, tone of voice, typing speed, etc.

[0860] How it works: Your device uses the camera to capture your facial expressions and the microphone to analyze the tone of your voice and record the speed and strength of your typing.

[0861] Output: Recognized user emotion (e.g., anxiety, surprise)

[0862] Step 3:

[0863] When the user presses the "Check" button, the device sends the entered information and URL to the server.

[0864] Input: User-entered information, URLs, and recognized emotions

[0865] How it works: The user presses the "Check" button, and the device generates and sends a request to send information and a URL to the server.

[0866] Output: Information sent to the server, URL, and recognized emotion

[0867] Step 4:

[0868] The server queries the database based on the received information to find a matching entry.

[0869] Input: Information or URL sent from the device

[0870] How it works: The server sends a query to the database, receives a response from the database, and checks whether the information is available.

[0871] Output: Database query results (e.g., information on reported fraudulent sites)

[0872] Step 5:

[0873] If the server does not have the relevant information in its database, it sends a request to an external trust evaluation API.

[0874] Input: Information or URL if the corresponding information does not exist in the database

[0875] How it works: The server generates a request for an external API and sends the request over the internet to the external API.

[0876] Output: Trust evaluation result from external API

[0877] Step 6:

[0878] The server generates a trust evaluation result based on the results from the database and external APIs.

[0879] Input: Database query results, trust evaluation results from external API

[0880] How it works: The server combines the responses from the database and the external API, analyzes key elements, and generates a final rating.

[0881] Output: Generated reliability evaluation result (e.g., "reliable", "unreliable", "unknown")

[0882] Step 7:

[0883] The server adjusts the display method of the reliability evaluation result based on the user's emotion information recognized by the emotion engine.

[0884] Input: Generated trust rating results, perceived user sentiment

[0885] How it works: The server formats the evaluation results based on emotional information to create a clear and polite message.

[0886] Output: Emotion-adjusted trustworthiness assessment results

[0887] Step 8:

[0888] The server transmits the adjusted trustworthiness evaluation result to the user's terminal.

[0889] Input: Emotion-adjusted trustworthiness assessment results

[0890] Action: The server sends the formatted evaluation results to the user's device.

[0891] Output: The trust evaluation result sent to the user's device

[0892] Step 9:

[0893] The user's terminal displays the received reliability evaluation result on the screen.

[0894] Input: Trustworthiness evaluation result sent from the server

[0895] How it works: The device displays the evaluation results received from the server on the screen, along with additional information and explanations based on the emotion.

[0896] Output: The credibility assessment result displayed to the user (e.g., "This news is trustworthy")

[0897] Error handling (if necessary)

[0898] If the server fails a database query or external API request, it generates an error message.

[0899] Input: Database query or external API request failure

[0900] How it works: The server generates error messages and adjusts them based on emotion information from the emotion engine.

[0901] Output: Tailored error message (e.g. "Evaluation failed. Please try again.")

[0902] In this way, the system takes into account the user's feelings and makes it easy to check the reliability of information and websites on the Internet, allowing users to check the information with peace of mind.

[0903] (Application example 2)

[0904] 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."

[0905] To enable users to easily determine the reliability of information and websites on the Internet, and to adjust the results of the determination based on the user's feelings and display them more appropriately, thereby enabling users to use the Internet with peace of mind without being misled by fraud or false information.

[0906] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0907] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the external API result, means for transmitting the generated trustworthiness evaluation result to the user's terminal, means for recognizing the user's emotion and adjusting the display method of the trustworthiness evaluation result based on the recognized emotion, thereby enabling appropriate feedback according to the user's emotion.

[0908] A "user's terminal" is a device that a user uses to input information and perform operations, and specifically refers to a smartphone, tablet, PC, etc.

[0909] "Input information or URL" refers to the address or text data of the website that the user wishes to check or evaluate.

[0910] "Means for receiving" refers to a module or interface that has the function of importing information or URLs sent from the user's terminal into the server.

[0911] The "means for querying a database" is a module that has the function of checking the received information or URL against a database to see if there is a corresponding entry.

[0912] An "external trustworthiness assessment API" is an external service for assessing trustworthiness, and refers to an API provided by a public institution or a reliable data source.

[0913] The "means for sending a request and receiving the result" is a module that enables the server to send a request to an external trustworthiness evaluation API and receive the evaluation result.

[0914] The "means for generating a reliability evaluation result" is a module that has the function of generating a final reliability evaluation based on the database query result and the evaluation result of the external API.

[0915] The "means for transmitting the reliability evaluation result to the user's terminal" is a module having a function for transmitting the reliability evaluation result generated by the server to the user's terminal.

[0916] The "means for displaying the reliability evaluation result" is a module or interface for visually displaying the reliability evaluation result received on the user's terminal in an easy-to-read manner.

[0917] The "means for recognizing the user's emotions" is a module that has the function of analyzing the user's facial expressions, voice, operation methods, etc. to identify the emotions at that time.

[0918] The "means for adjusting the display method" is a module that has the function of appropriately changing the content and method of display based on the recognized user emotion.

[0919] This invention relates to a system that recognizes user emotions and evaluates the reliability of information and websites on the Internet. Specifically, it realizes an application in the advertising field where a user evaluates the reliability of advertisements displayed to them, adjusts the results according to the user's emotions, and provides feedback.

[0920] System configuration

[0921] The system consists of the following main elements:

[0922] 1. User device: This is the device where the user enters information and checks the results, and includes smartphones, tablets, etc. It also has an emotion engine that recognizes the user's emotions.

[0923] 2. Server: A central server receives information from users' devices, communicates with a database and an external trust evaluation API, generates trust evaluation results, and adjusts the results based on user sentiment.

[0924] 3. Database: A database containing information on false information and fraudulent websites on the Internet, which serves as a primary source of information for assessing credibility.

[0925] 4. External Trust Assessment API: An external service that assesses trust, using APIs provided by public institutions or trusted data sources.

[0926] 5. Emotion engine: A module that has the function of identifying emotions by analyzing the user's facial expressions, voice, and operation methods.

[0927] Program processing flow

[0928] 1. Entering and receiving information: The user enters the URL of the advertisement into the device and presses the "Check" button. The device then sends the entered information to the server.

[0929] 2. Emotion Recognition: While the user is inputting or interacting with the device, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion, for example, identifying emotions such as anxiety or anger.

[0930] 3. Database query: The server queries the database based on the received information to search for the corresponding entry. If the corresponding data is found, it retrieves the information.

[0931] 4. Use of external API: If there is no corresponding data in the database, the server sends a request to an external trust evaluation API to obtain the evaluation results.

[0932] 5. Generating the trust evaluation results: The server generates the trust evaluation results based on the results from the database and the evaluation results from the external API.

[0933] 6. Adjustment and transmission of results: Based on the user's emotional information recognized by the emotion engine, the server adjusts the trust assessment results. For example, if anxiety is recognized, the server adds a detailed explanation to make the results easier to understand. The adjusted results are then sent to the user's device.

[0934] 7. Displaying the results: The user's device displays the results of the trust assessment. For example, it may display a message saying "This advertising site is untrustworthy," along with detailed risk information and warnings.

[0935] Hardware and software used

[0936] Hardware: Smartphone

[0937] Software: Flask (web framework), EmotionEngine (emotion recognition library), requests (external API requests)

[0938] Specific examples

[0939] Example 1

[0940] If a user enters an ad URL (e.g., https: / / fakeads.com) into the app and displays anxiety when viewing the ad:

[0941] 1. The user enters the ad URL into the app.

[0942] 2. The emotion engine recognizes anxiety from the user's facial expression.

[0943] 3. The URL is sent to the server and a database check is performed.

[0944] 4. A rating is received from the database saying "This advertising site has been reported in the past."

[0945] 5. Based on the results of the sentiment engine, a message is added saying "More information follows."

[0946] 6. Final message: "This advertising site has been reported in the past. More information below."

[0947] Example 2

[0948] If a user enters the ad URL (e.g., https: / / legitads.com) into the app and displays an angry expression when viewing the ad:

[0949] 1. The user enters the ad URL into the app.

[0950] 2. The emotion engine recognizes anger from the user's facial expression.

[0951] 3. The URL is sent to the server and a database check is performed.

[0952] 4. A rating is received from the database saying "This advertising site is trustworthy."

[0953] 5. Based on the results of the emotion engine, a message is added saying "Caution required."

[0954] 6. The final message appears: "This advertising site is trustworthy, but be careful."

[0955] Prompt Sentence Examples

[0956] Below is an example of a prompt used to generate a program for this system for the generative AI model:

[0957] A user enters an ad URL into the app. Write a program that recognizes the emotion of the user's facial expression when viewing the ad, and adjusts the display of the trust rating message based on that emotion. Specifically, this is a Python program that checks the URL against a database and an external API, and adjusts the display result according to the user's emotion.

[0958] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0959] Step 1:

[0960] The user enters the URL of the advertisement into the device and presses the "Check" button.

[0961] The entered URL is acquired by the terminal and sent to the server.

[0962] Step 2:

[0963] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotions.

[0964] Input data: User's facial expressions and tone of voice

[0965] Output data: Recognized emotion (e.g., anxiety, anger)

[0966] Specific operation: Facial expression and voice data is acquired using the built-in camera and microphone, and analyzed by the emotion engine.

[0967] Step 3:

[0968] The server checks the URL received from the terminal against the database.

[0969] Input data: Ad URL

[0970] Output data: Reliability information retrieved from the database (if available)

[0971] Specific operation: The received URL is queried against an existing database to find the corresponding entry.

[0972] Step 4:

[0973] If there is no corresponding data in the database, the server sends a request to an external trust evaluation API.

[0974] Input data: Ad URL

[0975] Output data: Reliability evaluation results obtained from external API

[0976] Specific operation: Sends an HTTP request to an external API, parses the response from the API, and obtains the evaluation result.

[0977] Step 5:

[0978] The server generates a reliability evaluation result based on the database query result and the evaluation result of the external API.

[0979] Input data: Results from databases, results from external APIs

[0980] Output data: Reliability assessment result (e.g., reliable, unreliable)

[0981] Specific operation: Run an algorithm to integrate the results of each evaluation and generate a final reliability evaluation.

[0982] Step 6:

[0983] Based on the user's emotional information recognized by the emotion engine, the server adjusts the display method of the reliability evaluation result.

[0984] Input data: Emotion recognition results, reliability evaluation results

[0985] Output data: Adjusted reliability evaluation results

[0986] Specific actions: Change the message content and display method of the trust evaluation results in response to the user's emotions (e.g., add a detailed explanation if the user is anxious).

[0987] Step 7:

[0988] The server sends the adjusted results to the user's terminal.

[0989] Input data: Adjusted reliability assessment results

[0990] Output data: Evaluation results sent to the user's device

[0991] Specific operation: A communication protocol (such as HTTP) is used to transmit the generated evaluation results to the user's terminal.

[0992] Step 8:

[0993] The received reliability evaluation result is displayed on the user's terminal.

[0994] Input data: Adjusted reliability assessment results

[0995] Output data: Display of evaluation results (e.g., messages on the screen)

[0996] Specific actions: The evaluation results are displayed in an appropriate format using the user interface. The user confirms the results.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] [Third embodiment]

[1001] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1002] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1003] 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).

[1004] 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.

[1005] 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.

[1006] 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).

[1007] 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. 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.

[1008] 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.

[1009] 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.

[1010] 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.

[1011] 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.

[1012] 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."

[1013] This invention relates to a system for verifying the reliability of information and websites on the Internet. Specifically, this system checks information and URLs entered by users through an app using a database and an external reliability evaluation API, and provides the results to the user.

[1014] System configuration

[1015] 1. On the user's device:

[1016] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications and provide an interface where users can enter information and URLs.

[1017] 2. Server:

[1018] A central server receives information from users' devices, queries the database for that information, and, if necessary, sends requests to external trust assessment APIs, receiving and analyzing the results.

[1019] 3. Database:

[1020] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[1021] 4. External Trust Assessment API:

[1022] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[1023] Program implementation example

[1024] 1. Launch the app and enter your information

[1025] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[1026] 2. Sending and Receiving Information

[1027] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[1028] 3. Querying the database

[1029] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[1030] 4. Use of external APIs

[1031] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[1032] 5. Generating reliability evaluation results

[1033] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[1034] 6. Sending and displaying results

[1035] The generated credibility evaluation results are sent from the server to the user's device. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the credibility of the information or site.

[1036] Specific examples

[1037] Example 1: Checking news articles

[1038] 1. The user launches the app and enters the URL of a news article.

[1039] 2. The device sends the input information to the server.

[1040] 3. The server queries the database and, if there is no matching entry, sends a request to an external API.

[1041] 4. The server receives the results of the external API and generates a trust rating and sends it to the device.

[1042] 5. The device will display "This news is trustworthy."

[1043] Example 2: Checking the safety of a shopping site

[1044] 1. The user launches the app and enters the URL of a shopping site.

[1045] 2. The device sends the input information to the server.

[1046] 3. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[1047] 4. The server sends the evaluation results to the device, which then displays the message "This shopping site is not trustworthy."

[1048] Error Handling

[1049] The system also has the ability to display an error message to the user if a database query or external API request fails, such as "Evaluation failed. Please try again."

[1050] In this way, this system allows users to easily check the reliability of information and sites on the Internet, reducing user risks and providing support that leads users to more reliable information.

[1051] The processing flow will be explained below.

[1052] Step 1:

[1053] The user launches the application. The user enters the information or URL they want to check into an input field. For example, they enter the URL of a news article.

[1054] Step 2:

[1055] The user presses the "Check" button. The device retrieves the entered information and URL.

[1056] Step 3:

[1057] The device sends the acquired information and URL to the server using a secure communication protocol such as HTTPS.

[1058] Step 4:

[1059] The server receives the input information, connects to the database, and searches the database based on the received information and URL.

[1060] Step 5:

[1061] The server queries the database to see if there is a matching entry, and if there is a matching entry in the database, retrieves its claims.

[1062] Step 6:

[1063] If there is no matching entry in the database, the server sends a request to an external trust assessment API, including the input information and URL.

[1064] Step 7:

[1065] The server receives a response from the external trust evaluation API, analyzes the received result, and obtains the trust information.

[1066] Step 8:

[1067] The server generates a final trust rating based on the results from the database and external APIs, which can be "trusted," "untrusted," or "unknown."

[1068] Step 9:

[1069] The server sends the generated trust evaluation results to the user's device using a secure communication protocol.

[1070] Step 10:

[1071] The device displays the trust evaluation results it received. The evaluation results are displayed in the user interface (UI) so that the user can confirm the results. For example, a message such as "This news is trustworthy" is displayed.

[1072] Step 11:

[1073] If the database query or external API request fails, the server generates an error message, which is sent to the user's device and displays "Evaluation failed. Please try again."

[1074] Example 1

[1075] 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."

[1076] Rapid and accurate evaluation of the reliability of information and websites on the Internet is an important issue in modern society. However, previous systems have been inadequate in detecting fake information and fraudulent websites, making it difficult for users to easily access reliable information. Furthermore, because systems rely solely on databases, they have had the problem of being slow to respond to newly emerging fraudulent information and hoaxes.

[1077] 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.

[1078] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for sending the generated trustworthiness evaluation result to the user's terminal, means for displaying the trustworthiness evaluation result on the user's terminal, means for sending an HTTP POST request from the user's terminal to the server, means for the server to execute an SQL query on the database and search for information, means for receiving the result returned from the external API via an HTTP request, means for the server to generate a trustworthiness evaluation in JSON format based on the received result, and means for displaying the JSON data received by the terminal on a user interface. This allows users to access highly reliable information quickly and accurately.

[1079] A "user's terminal" is a computing device used by a user, such as a smartphone, tablet, or PC.

[1080] "Means for receiving" refers to functions or programs that enable receiving data via a communications network.

[1081] "Means for querying a database" refers to a program or function that searches for entries in a database based on received information and retrieves matching data.

[1082] The "external trustworthiness evaluation API" is an interface for accessing external services to perform trustworthiness evaluation on the Internet and obtaining the necessary evaluation information.

[1083] "Reliability evaluation result" is the evaluation result regarding the reliability of specific information or URL, calculated based on the database query results and results from external APIs.

[1084] An "HTTP POST request" is a type of HTTP protocol used by a client to send data to a server.

[1085] An "SQL query" is a structured query language used to retrieve or manipulate specific data from a relational database.

[1086] "JSON format" stands for JavaScript Object Notation and is a standard format for representing data in a concise, easy-to-read text format.

[1087] "User interface" refers to the screen and operating means by which a user interacts with a computer system.

[1088] This invention relates to a system for evaluating the reliability of information and websites on the Internet. Specifically, the system is a system in which a server queries information and URLs entered from a user's terminal using a database and an external reliability evaluation API, and provides the results to the user.

[1089] System configuration

[1090] 1. User's device

[1091] This includes smartphones, tablets, and PCs used by users. These devices run dedicated applications and provide an interface for users to enter information and URLs.

[1092] 2. Server

[1093] The server has the function of receiving information and URLs sent from the user's device. It also executes SQL queries on the database to search for information. If necessary, it also sends requests to an external trust evaluation API and receives the results. These processes are performed to generate trust evaluation results and send them to the user's device in JSON format.

[1094] 3. Database

[1095] The database contains information about online hoaxes and fraudulent websites, and the server queries the database to find entries that match the information or URLs it receives.

[1096] 4. External Trust Assessment API

[1097] The external API provides a data source for trust assessment, including certificate information from public institutions, etc. The server uses this external API if the corresponding information does not exist in the database.

[1098] Specific examples of programs

[1099] Launching the app and entering information

[1100] A user launches a smartphone app and enters the information or URL they want to check in the input field displayed on the screen. For example, they enter the URL of a news article, "https: / / example.com / news123."

[1101] Sending and Receiving Information

[1102] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request, and the server receives the data encoded in JSON format.

[1103] Querying the database

[1104] The server uses the received information to query its internal database with an SQL query, for example "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[1105] Using external APIs

[1106] If there is no corresponding information in the database, the server will send an HTTP request to an external trust evaluation API. For example, it will send the following data: { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"}.

[1107] Generating reliability evaluation results

[1108] The server generates a trust evaluation result based on the database query results and the results of the external API. For example, if the database records it as "fraud," it will be evaluated as "untrustworthy," but if the external API returns "verified," it will be evaluated as "trustworthy."

[1109] Sending and displaying results

[1110] The generated trust evaluation results are sent from the server to the device in JSON format. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the trustworthiness of the information or site.

[1111] Specific prompt examples

[1112] The specific prompt text is shown below.

[1113] 1. "Confirm the trustworthiness of this news article (URL: https: / / example.com / news123)"

[1114] 2. "Evaluate the security of the following shopping site (URL: https: / / example-shop.com)"

[1115] In this way, this system helps users access highly reliable information by quickly and accurately evaluating the reliability of information and sites on the Internet.

[1116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1117] Step 1:

[1118] A user launches a smartphone app. They enter the information or URL they want to check into the input field displayed on the app screen. For example, the user enters the URL of a news article, "https: / / example.com / news123." As input, the user provides the URL, and as output, the device stores the URL in the input form. Specifically, the user enters the URL in the text field and presses the "Check" button.

[1119] Step 2:

[1120] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request. As input, the user provides a URL, and as output, the device sends data encoded in JSON format to the server. Specifically, the device generates JSON data {"url": "https: / / example.com / news123"} and sends this data to the server via an HTTP POST request.

[1121] Step 3:

[1122] The server queries its internal database with an SQL query based on the received information. As input, it receives JSON data from the device, and as output, it executes an SQL query to retrieve matching entries in the database. Specifically, the server executes the query "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[1123] Step 4:

[1124] If the server does not find the corresponding data in its database, it sends an HTTP request to an external trust evaluation API. As input, it checks whether there are any database query results, and as output, it generates and sends a request to the external API. Specifically, the server sends the data { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"} to the external API.

[1125] Step 5:

[1126] The server receives the results returned from the external API via an HTTP request. It receives the response from the external API as input and parses the results as output. Specifically, the server receives the response data from the external API and parses it as JSON format data.

[1127] Step 6:

[1128] The server generates a trust evaluation result based on the database query results and external API results. It takes the database query results and external API results as input and generates a trust evaluation as output. Specifically, the server analyzes the database and external API results and creates a trust evaluation result in JSON format (e.g., "trusted" or "not trustworthy").

[1129] Step 7:

[1130] The server sends the generated trust evaluation result to the user's device. It uses the trust evaluation result as input and sends JSON data to the device as output. Specifically, the server sends JSON data {"trustResult": "trusted"} to the device.

[1131] Step 8:

[1132] The terminal displays the reliability evaluation results it receives on the user interface. It uses the JSON data received from the server as input and displays the evaluation results to the user as output. Specifically, the terminal displays the message "This news is reliable" on the screen.

[1133] (Application example 1)

[1134] 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."

[1135] The Internet is plagued by a wealth of false information and fraudulent websites. Users lack the means to quickly assess the reliability of such information, making it difficult to verify its authenticity. Manually checking the reliability of URLs is time-consuming and laborious, placing a heavy burden on users. Furthermore, there is a lack of functionality for saving and reusing the reliability evaluation results of previously checked URLs, forcing users to repeatedly evaluate the same sites. The purpose of this invention is to solve these problems, efficiently evaluate the reliability of information on the Internet, and support users' safe access to information.

[1136] 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.

[1137] In this invention, the server includes: means for receiving information and URLs entered from a user's mobile device; means for querying a data storage for the received information and URLs; means for sending a request to an external trust evaluation API and receiving the result if the corresponding data is not found in the data storage; means for generating a trust evaluation result based on the data storage query result and the external API result; means for transmitting the generated trust evaluation result to the user's mobile device; means for displaying the trust evaluation result on the user's mobile device; means for automatically checking URLs from the clipboard; means for saving and reviewing the history; and means for setting a custom alert that warns the user about access to unsafe sites. This allows the user to automatically check URLs from the clipboard, quickly and efficiently receive and display the results, and reuse past history to avoid duplicate checks. The custom alert setting also makes it possible to prevent access to unsafe sites.

[1138] "User's Mobile Device" refers to a smartphone, tablet, or other portable device used by a User.

[1139] "Means for receiving information or URLs" refers to the function for sending information or URLs entered by the user to the server and receiving them on the server side.

[1140] "Data storage" refers to a storage device for managing and querying data, including information about false information and fraudulent websites on the Internet.

[1141] "Means for querying data storage" refers to the function for searching for received information or URLs in data storage and confirming their existence.

[1142] "Means for sending requests to an external trust assessment API and receiving the results" refers to the function for sending requests to an API that uses public institutions or other reliable information sources to perform assessments when there is no relevant data in the data storage, and receiving the results.

[1143] "Means for generating trustworthiness assessment results" refers to the function of making decisions to assess the trustworthiness of information or URLs based on results from data storage and external APIs.

[1144] "Means for transmitting to the user's mobile device" refers to a function for transmitting the generated reliability evaluation results to the user's smartphone or tablet.

[1145] The "means for displaying the reliability evaluation result" refers to a function for visually displaying the reliability evaluation result to the user on the user's mobile device.

[1146] "Means for automatically checking URLs from the clipboard" refers to a function that automatically detects URLs that a user has copied to the clipboard and evaluates the trustworthiness of those URLs.

[1147] "A means to save and review history" refers to a function that allows you to save the results of the reliability evaluation of URLs and information that you have checked in the past and review them later.

[1148] "Custom alert setting means" refers to a function for setting a custom alert when a user accesses an unstable site and providing that alert.

[1149] System Overview:

[1150] This invention is a system for verifying the reliability of information and websites on the Internet, checking information and URLs entered by users using data storage and an external reliability evaluation API, and providing the results to the users. Specific embodiments of the system are described below.

[1151] Hardware and software used:

[1152] Hardware: User devices such as smartphones, tablets, and PCs.

[1153] software:

[1154] SQLite: A local database for storing the reliability evaluation results.

[1155] requests module: A software component for handling HTTP requests to external APIs.

[1156] Python: The programming language used to implement the server and applications.

[1157] System configuration:

[1158] 1. On the user's device:

[1159] The user's device is a mobile device such as a smartphone, where the user runs the application and inputs information or URLs. For example, if the user copies the URL of a news article or a shopping site to the clipboard, the application automatically detects the URL and begins rating it.

[1160] 2. Server:

[1161] The server queries the data storage for the received information and URL, and if there is no corresponding data, it sends a request to an external trust evaluation API. It also generates a trust evaluation result based on the results of the data storage query and the results from the external API.

[1162] 3. Data Storage:

[1163] Data storage manages data, including information about false and fraudulent websites on the Internet, using database management systems such as SQLite.

[1164] 4. External Trust Assessment API:

[1165] External APIs are APIs based on public or other trusted data sources, for example, providing certification information.

[1166] Processing Details:

[1167] 1. Enter and submit your information:

[1168] When a user types a URL into their mobile device or copies it to their clipboard, the application automatically reads the URL and sends it to the server.

[1169] 2. Data storage query:

[1170] The server checks the received URL in the data storage to see if the corresponding information exists. If a matching entry is found in the data storage, it evaluates its credibility based on the results and notifies the user.

[1171] 3. Use of external APIs:

[1172] If there is no corresponding information in the data storage, the server sends a request to an external trust evaluation API and receives the response. It then obtains the trust evaluation information from the API and generates a new evaluation result based on this information.

[1173] 4. Submit and view the evaluation results:

[1174] The server generates the final trust evaluation result and sends it to the user's mobile device, which receives the evaluation result and displays it on the application screen.

[1175] Examples and prompts:

[1176] Example: When a user launches an application and copies the URL "https: / / example-news.com / article123" to the clipboard, the application automatically starts a process to evaluate the trustworthiness of the URL. The result of the evaluation is displayed on the device screen, informing the user that "This site is not trustworthy."

[1177] Example prompt sentence:

[1178] When a user copies the URL "https: / / example-news.com / article123" to their clipboard, they should rate its trustworthiness. They should receive some kind of notification about the trustworthiness of this site, including details of whether it has been reported as a hoax in the past.

[1179] This allows users to easily access reliable information and reduces the risk of false information and fraudulent sites on the Internet.

[1180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1181] Step 1:

[1182] A user launches an application on a mobile device and inputs or copies a URL to the clipboard. The application then automatically detects the contents of the clipboard and prepares to parse the URL. Specifically, the application performs an input process that reads the contents of the clipboard and interprets the data as a URL.

[1183] Input: The URL that the user copied to the clipboard

[1184] Output: The URL is recognized in the application

[1185] Step 2:

[1186] The device sends the recognized URL to the server, the application sends the URL as an HTTP request to the server, and the server receives the request. This process initiates the evaluation of the trustworthiness of the data based on the URL.

[1187] Input: URL sent from the device

[1188] Output: URL sent to server

[1189] Step 3:

[1190] The server queries the data storage for the received URL to find the trust information for that URL. The server accesses the SQLite database and finds an entry that matches the received URL.

[1191] Input: URL received by the server

[1192] Output: Whether or not there is a matching entry in the data storage

[1193] Step 4:

[1194] If the server does not find a corresponding entry in its data storage, it sends a request to an external trust evaluation API. It sends a URL as a request to the external API and waits for the trust evaluation result. During this time, the server monitors the response from the API.

[1195] Input: URL where no corresponding data is found after querying the data storage

[1196] Output: Trust evaluation result from external API

[1197] Step 5:

[1198] The server receives the evaluation results from the external API and analyzes them. The server analyzes the data received from the external API and extracts the relevant evaluation information. This data includes the credibility evaluation results and related evidence information.

[1199] Input: Evaluation result from external API

[1200] Output: Analyze the evaluation results and extract the evaluation information

[1201] Step 6:

[1202] The server generates a final trust evaluation result based on the data storage query results and external API results. Based on the analyzed data, it generates an evaluation result such as "trusted," "untrusted," or "unknown."

[1203] Input: Data storage query results and external API evaluation results

[1204] Output: Final reliability evaluation result

[1205] Step 7:

[1206] The generated trust evaluation results are sent to the user's mobile device and notified to the user. The server sends the evaluation results to the user's terminal as an HTTP response, and the user's terminal displays the received results within the application.

[1207] Input: Final reliability evaluation result

[1208] Output: The evaluation result is displayed on the user's terminal.

[1209] Step 8:

[1210] Users can check the evaluation results on their mobile devices and judge the reliability of the information or site. Based on the displayed results, users can decide whether to continue using the information or browsing the site.

[1211] Input: Evaluation result displayed on the user's terminal

[1212] Output: User reviews the evaluation results and makes a decision

[1213] This allows users to efficiently obtain reliable information and avoid accessing suspicious sites.

[1214] 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.

[1215] This invention relates to a system that recognizes user emotions and verifies the reliability of information and websites on the Internet. Specifically, the system checks information and URLs entered by users through apps using a database and an external reliability evaluation API, and displays information appropriately based on the results, taking the user's emotions into consideration.

[1216] System configuration

[1217] 1. On the user's device:

[1218] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications, provide an interface for users to input information and URLs, and an emotion engine that recognizes users' emotions.

[1219] 2. Server:

[1220] A central server receives information from users' devices, queries the database, and optionally sends requests to external trust assessment APIs, receives and analyzes the results, and adjusts the received assessment results based on the user's sentiment.

[1221] 3. Database:

[1222] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[1223] 4. External Trust Assessment API:

[1224] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[1225] 5. Emotion Engine:

[1226] The emotion recognition function installed in the user's device analyzes the user's facial expressions, voice, input operations, etc. to identify the user's emotions.

[1227] Program implementation example

[1228] 1. Launch the app and enter your information

[1229] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[1230] 2. Emotional Recognition

[1231] When a user is entering information or pressing the "check" button, the device's built-in emotion engine analyzes the user's facial expressions, voice, and input operations to recognize their current emotion. For example, if the user looks anxious, the emotion will be recognized as "anxiety."

[1232] 3. Sending and Receiving Information

[1233] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[1234] 4. Querying the Database

[1235] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[1236] 5. Use of external APIs

[1237] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[1238] 6. Generating reliability evaluation results

[1239] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[1240] 7. Adjustment and submission of results

[1241] Based on the user's emotional information recognized by the emotion engine, the server adjusts the way it displays the trust assessment results. For example, if the user is anxious, it will display a more understandable and polite message. The adjusted results are then sent from the server to the user's device.

[1242] 8. Displaying the results

[1243] The user's device displays the received reliability evaluation results. For example, if the user looks anxious, the device displays the message "This news is reliable" along with detailed reasons and an explanation of the evaluation process.

[1244] Specific examples

[1245] Example 1: Checking news articles

[1246] 1. The user launches the app and enters the URL of a news article.

[1247] 2. While typing, the emotion engine analyzes the user's facial expressions to recognize emotions (e.g., surprise).

[1248] 3. The device sends the input information to the server.

[1249] 4. The server queries the database and, if there is no matching entry, sends a request to an external API.

[1250] 5. The server that receives the results of the external API generates a trust rating.

[1251] 6. Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[1252] 7. Your device will display the message "This news is trustworthy" along with a detailed explanation.

[1253] Example 2: Checking the safety of a shopping site

[1254] 1. The user launches the app and enters the URL of a shopping site.

[1255] 2. As you type, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[1256] 3. The device sends the input information to the server.

[1257] 4. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[1258] 5. The server generates the evaluation results, adjusts them based on the results of the emotion engine, and sends them to the device.

[1259] 6. Your device will display a message saying "This shopping site is untrustworthy" along with details about the specific risks.

[1260] Error Handling

[1261] In the system, if a database query or external API request fails, the server generates an error message, which is adjusted based on the results of the emotion engine, and the user's device displays "Evaluation failed. Please try again."

[1262] In this way, this system takes into account the user's feelings and allows them to easily check the reliability of information and sites on the Internet, thereby reducing user risks and providing support that leads them to more reliable information.

[1263] The processing flow will be explained below.

[1264] Step 1:

[1265] A user launches the app on their smartphone. The app screen displays fields for entering information and URLs. The user enters the URL of the news article they want to check.

[1266] Step 2:

[1267] While the user is entering information, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion. For example, if the user is frowning, the emotion engine will detect anxiety.

[1268] Step 3:

[1269] The user presses the "Check" button. The device retrieves the entered information and URL and sends them to the server. A secure communication protocol such as HTTPS is used for transmission.

[1270] Step 4:

[1271] The server receives the input information and first queries the database. The server connects to the database and searches for entries that match the received information and URL. At the same time, it also processes the user's emotional information.

[1272] Step 5:

[1273] If there is a matching entry in the database, the server retrieves its credibility information, for example, "this site has been reported as a scam in the past."

[1274] Step 6:

[1275] If there is no matching entry in the database, the server sends a request to an external trust assessment API, which includes the user-entered information and a URL.

[1276] Step 7:

[1277] The server receives a response from an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources, and returns the result.

[1278] Step 8:

[1279] The server generates a final trust rating based on the results from the database and the external API, which may include ratings such as "trusted," "untrusted," or "unknown."

[1280] Step 9:

[1281] Based on the emotion engine's recognition results, the server adjusts the way it displays the trust assessment results. For example, if the user expresses anxiety, it adds detailed reasons and instructions on what to do next in addition to the assessment result.

[1282] Step 10:

[1283] The server then sends the adjusted trust evaluation results to the user's device using a secure communication protocol.

[1284] Step 11:

[1285] The device displays the results of the trust assessment it receives. For example, if the user looks anxious, it displays the message "This news is trustworthy" along with a detailed explanation of why it is trustworthy.

[1286] Step 12:

[1287] If the database query or external API request fails, the server generates an error message. Based on the result of the emotion engine, the message "Evaluation failed. Please try again" is displayed on the user's device.

[1288] Specific examples

[1289] Example 1: Checking news articles

[1290] 1. Step 1 - User launches the app and enters the URL of a news article.

[1291] 2. Step 2 - While the user is typing, the emotion engine analyzes the user's facial expressions and recognizes the emotion (e.g. surprise).

[1292] 3. Step 3 - The device sends the input information to the server.

[1293] 4. Step 4 - The server queries the database and if there is no matching entry, it sends a request to an external API.

[1294] 5. Step 7 - The server receives the results of the external API and generates a trust rating.

[1295] 6. Step 9 - Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[1296] 7. Step 11 - Your device will display the message "This news is trustworthy" along with a detailed explanation.

[1297] Example 2: Checking the safety of a shopping site

[1298] 1. Step 1 - User launches the app and enters the URL of a shopping site.

[1299] 2. Step 2 - While typing, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[1300] 3. Step 3 - The device sends the input information to the server.

[1301] 4. Step 4 - The server queries the database and if a matching entry is found, it retrieves the fraud information.

[1302] 5. Step 7 - The server generates the evaluation result, adjusts it based on the emotion engine results, and sends it to the device.

[1303] 6. Step 11 - Your device will display a message saying "This shopping site is not trusted" along with details about the specific risks.

[1304] In this way, this system takes into account the user's feelings and displays the results of credibility evaluation appropriately, allowing users to use information on the Internet with peace of mind.

[1305] Example 2

[1306] 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."

[1307] Conventional information reliability evaluation systems were unable to consider the user's emotions when determining the reliability of information or URLs entered by the user. As a result, users may receive the results with anxiety or doubt, and even reliable information cannot be conveyed appropriately in accordance with the user's feelings. Furthermore, when there is no relevant data in the database, the evaluation method is uniform, making it difficult to provide users with an appropriate sense of security.

[1308] 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.

[1309] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for recognizing the user's emotion and transmitting the result to the server, means for adjusting the trustworthiness evaluation result based on the user's emotion information, means for transmitting the generated trustworthiness evaluation result to the user's terminal, and means for displaying the trustworthiness evaluation result on the user's terminal. This makes it possible to provide a trustworthiness evaluation result that reflects the user's emotion, thereby creating an environment in which users can check information with peace of mind.

[1310] "User device" refers to the device used by the user to enter information and check results, including smartphones, tablets, PCs, etc.

[1311] "Means for receiving" refers to a method or device that allows the server to obtain information or a URL sent from the user's terminal.

[1312] "Means for querying a database" refers to a method or device that allows the server to query an existing database for input information and confirm the presence or absence of the information and its contents.

[1313] "External Trust Assessment API" refers to an application programming interface that utilizes external data sources for trust assessment, including certificate information from public organizations.

[1314] "Means for generating reliability evaluation results" refers to a method or device for evaluating reliability and generating results based on information in a database or data from an external API.

[1315] "Means for recognizing emotions" refers to a function that analyzes the user's facial expressions, tone of voice, input operations, etc. to identify the user's current emotions.

[1316] The "means for adjusting the trustworthiness evaluation result" refers to a function for appropriately changing the display method and content of the trustworthiness evaluation result based on the recognized emotional information of the user.

[1317] The "means for transmitting" refers to a method or device for transmitting the generated reliability evaluation result or adjusted information to the user's terminal.

[1318] The "display means" refers to a method or device for visually displaying the reliability evaluation result on the user's terminal.

[1319] The system of this invention recognizes user emotions and evaluates the reliability of information and websites on the Internet based on the emotions. The system consists of the following main components:

[1320] 1. User's device

[1321] A device used by users to input information and check the results. It includes smartphones, tablets, PCs, etc. It runs a dedicated application and provides an interface for inputting information and URLs, as well as an emotion engine for recognizing the user's emotions. The emotion engine uses facial recognition and voice recognition technology to analyze the user's emotions. Specific software used includes a facial recognition API and a voice analysis API.

[1322] 2. Server

[1323] It is centrally located and receives information sent from user devices. It queries the received information against a database, sends requests to an external trust evaluation API as needed, and receives the results. It then generates trust evaluation results based on the database query results and external API results, and adjusts them based on user sentiment information. To perform these tasks, the server requires a database management system (DBMS) and software to process API requests.

[1324] 3. Database

[1325] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant information exists. RDBMS such as MySQL or PostgreSQL is often used as the database software.

[1326] 4. External Trust Assessment API

[1327] It is an external service for evaluating the reliability of information, using data sources such as certificate information from public institutions. This allows for reliable evaluation results even when the relevant data is not available in the database. Specific APIs may use generative AI models such as those from OpenAI.

[1328] 5. Emotion Engine

[1329] This function is installed on the user's device and identifies the user's emotions by analyzing their facial expressions, voice, input operations, etc. It applies computer vision and natural language processing technology to analyze emotions in real time.

[1330] Specific examples

[1331] Example 1: Checking news articles

[1332] The user launches a dedicated app on their smartphone and enters the URL of a news article. As they type, the emotion engine analyzes their facial expressions and recognizes the emotion of surprise. When the user presses the "Check" button, the input information is sent to the server. The server queries the database and, if no matching entry is found, sends a request to an external credibility assessment API. After receiving the result from the external API, the server generates a credibility assessment, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This news is trustworthy" along with a detailed explanation.

[1333] Example 2: Checking the safety of a shopping site

[1334] A user launches a dedicated app on a tablet and enters the URL of a shopping site. As they type, the emotion engine analyzes the user's tone of voice to recognize the emotion of anxiety. When the user presses the "Check" button, the URL is sent to the server. The server queries the database and, if it finds a matching entry, retrieves the information reported as fraud. The server generates an evaluation result, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This shopping site is untrustworthy" along with details about the specific risks.

[1335] Prompt Sentence Examples

[1336] "I want to enter the URL of a news article to check its authenticity. I'm a little unsure."

[1337] In this way, the system of the present invention allows users to easily check the reliability of information and websites on the Internet while taking into account their feelings, thereby reducing user risks and providing support that leads users to more reliable information.

[1338] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1339] Step 1:

[1340] The user launches a dedicated app on a device such as a smartphone or PC, and the app screen displays fields for entering information and URLs.

[1341] Input: Information or URL the user wants to check (e.g., URL of a news article)

[1342] What happens: A user taps or clicks an app icon to launch the app and enters information or a URL into an on-screen input field.

[1343] Output: Information entered into input fields within the app and URLs

[1344] Step 2:

[1345] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and typing speed while they are typing or when they press the "check" button, and recognizes the user's emotions.

[1346] Input: User facial expressions, tone of voice, typing speed, etc.

[1347] How it works: Your device uses the camera to capture your facial expressions and the microphone to analyze the tone of your voice and record the speed and strength of your typing.

[1348] Output: Recognized user emotion (e.g., anxiety, surprise)

[1349] Step 3:

[1350] When the user presses the "Check" button, the device sends the entered information and URL to the server.

[1351] Input: User-entered information, URLs, and recognized emotions

[1352] How it works: The user presses the "Check" button, and the device generates and sends a request to send information and a URL to the server.

[1353] Output: Information sent to the server, URL, and recognized emotion

[1354] Step 4:

[1355] The server queries the database based on the received information to find a matching entry.

[1356] Input: Information or URL sent from the device

[1357] How it works: The server sends a query to the database, receives a response from the database, and checks whether the information is available.

[1358] Output: Database query results (e.g., information on reported fraudulent sites)

[1359] Step 5:

[1360] If the server does not have the relevant information in its database, it sends a request to an external trust evaluation API.

[1361] Input: Information or URL if the corresponding information does not exist in the database

[1362] How it works: The server generates a request for an external API and sends the request over the internet to the external API.

[1363] Output: Trust evaluation result from external API

[1364] Step 6:

[1365] The server generates a trust evaluation result based on the results from the database and external APIs.

[1366] Input: Database query results, trust evaluation results from external API

[1367] How it works: The server combines the responses from the database and the external API, analyzes key elements, and generates a final rating.

[1368] Output: Generated reliability evaluation result (e.g., "reliable", "unreliable", "unknown")

[1369] Step 7:

[1370] The server adjusts the display method of the reliability evaluation result based on the user's emotion information recognized by the emotion engine.

[1371] Input: Generated trust rating results, perceived user sentiment

[1372] How it works: The server formats the evaluation results based on emotional information to create a clear and polite message.

[1373] Output: Emotion-adjusted trustworthiness assessment results

[1374] Step 8:

[1375] The server transmits the adjusted trustworthiness evaluation result to the user's terminal.

[1376] Input: Emotion-adjusted trustworthiness assessment results

[1377] Action: The server sends the formatted evaluation results to the user's device.

[1378] Output: The trust evaluation result sent to the user's device

[1379] Step 9:

[1380] The user's terminal displays the received reliability evaluation result on the screen.

[1381] Input: Trustworthiness evaluation result sent from the server

[1382] How it works: The device displays the evaluation results received from the server on the screen, along with additional information and explanations based on the emotion.

[1383] Output: The credibility assessment result displayed to the user (e.g., "This news is trustworthy")

[1384] Error handling (if necessary)

[1385] If the server fails a database query or external API request, it generates an error message.

[1386] Input: Database query or external API request failure

[1387] How it works: The server generates error messages and adjusts them based on emotion information from the emotion engine.

[1388] Output: Tailored error message (e.g. "Evaluation failed. Please try again.")

[1389] In this way, the system takes into account the user's feelings and makes it easy to check the reliability of information and websites on the Internet, allowing users to check the information with peace of mind.

[1390] (Application example 2)

[1391] 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."

[1392] To enable users to easily determine the reliability of information and websites on the Internet, and to adjust the results of the determination based on the user's feelings and display them more appropriately, thereby enabling users to use the Internet with peace of mind without being misled by fraud or false information.

[1393] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1394] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the external API result, means for transmitting the generated trustworthiness evaluation result to the user's terminal, means for recognizing the user's emotion and adjusting the display method of the trustworthiness evaluation result based on the recognized emotion, thereby enabling appropriate feedback according to the user's emotion.

[1395] A "user's terminal" is a device that a user uses to input information and perform operations, and specifically refers to a smartphone, tablet, PC, etc.

[1396] "Input information or URL" refers to the address or text data of the website that the user wishes to check or evaluate.

[1397] "Means for receiving" refers to a module or interface that has the function of importing information or URLs sent from the user's terminal into the server.

[1398] The "means for querying a database" is a module that has the function of checking the received information or URL against a database to see if there is a corresponding entry.

[1399] An "external trustworthiness assessment API" is an external service for assessing trustworthiness, and refers to an API provided by a public institution or a reliable data source.

[1400] The "means for sending a request and receiving the result" is a module that enables the server to send a request to an external trustworthiness evaluation API and receive the evaluation result.

[1401] The "means for generating a reliability evaluation result" is a module that has the function of generating a final reliability evaluation based on the database query result and the evaluation result of the external API.

[1402] The "means for transmitting the reliability evaluation result to the user's terminal" is a module having a function for transmitting the reliability evaluation result generated by the server to the user's terminal.

[1403] The "means for displaying the reliability evaluation result" is a module or interface for visually displaying the reliability evaluation result received on the user's terminal in an easy-to-read manner.

[1404] The "means for recognizing the user's emotions" is a module that has the function of analyzing the user's facial expressions, voice, operation methods, etc. to identify the emotions at that time.

[1405] The "means for adjusting the display method" is a module that has the function of appropriately changing the content and method of display based on the recognized user emotion.

[1406] This invention relates to a system that recognizes user emotions and evaluates the reliability of information and websites on the Internet. Specifically, it realizes an application in the advertising field where a user evaluates the reliability of advertisements displayed to them, adjusts the results according to the user's emotions, and provides feedback.

[1407] System configuration

[1408] The system consists of the following main elements:

[1409] 1. User device: This is the device where the user enters information and checks the results, and includes smartphones, tablets, etc. It also has an emotion engine that recognizes the user's emotions.

[1410] 2. Server: A central server receives information from users' devices, communicates with a database and an external trust evaluation API, generates trust evaluation results, and adjusts the results based on user sentiment.

[1411] 3. Database: A database containing information on false information and fraudulent websites on the Internet, which serves as a primary source of information for assessing credibility.

[1412] 4. External Trust Assessment API: An external service that assesses trust, using APIs provided by public institutions or trusted data sources.

[1413] 5. Emotion engine: A module that has the function of identifying emotions by analyzing the user's facial expressions, voice, and operation methods.

[1414] Program processing flow

[1415] 1. Entering and receiving information: The user enters the URL of the advertisement into the device and presses the "Check" button. The device then sends the entered information to the server.

[1416] 2. Emotion Recognition: While the user is inputting or interacting with the device, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion, for example, identifying emotions such as anxiety or anger.

[1417] 3. Database query: The server queries the database based on the received information to search for the corresponding entry. If the corresponding data is found, it retrieves the information.

[1418] 4. Use of external API: If there is no corresponding data in the database, the server sends a request to an external trust evaluation API to obtain the evaluation results.

[1419] 5. Generating the trust evaluation results: The server generates the trust evaluation results based on the results from the database and the evaluation results from the external API.

[1420] 6. Adjustment and transmission of results: Based on the user's emotional information recognized by the emotion engine, the server adjusts the trust assessment results. For example, if anxiety is recognized, the server adds a detailed explanation to make the results easier to understand. The adjusted results are then sent to the user's device.

[1421] 7. Displaying the results: The user's device displays the results of the trust assessment. For example, it may display a message saying "This advertising site is untrustworthy," along with detailed risk information and warnings.

[1422] Hardware and software used

[1423] Hardware: Smartphone

[1424] Software: Flask (web framework), EmotionEngine (emotion recognition library), requests (external API requests)

[1425] Specific examples

[1426] Example 1

[1427] If a user enters an ad URL (e.g., https: / / fakeads.com) into the app and displays anxiety when viewing the ad:

[1428] 1. The user enters the ad URL into the app.

[1429] 2. The emotion engine recognizes anxiety from the user's facial expression.

[1430] 3. The URL is sent to the server and a database check is performed.

[1431] 4. A rating is received from the database saying "This advertising site has been reported in the past."

[1432] 5. Based on the results of the sentiment engine, a message is added saying "More information follows."

[1433] 6. Final message: "This advertising site has been reported in the past. More information below."

[1434] Example 2

[1435] If a user enters the ad URL (e.g., https: / / legitads.com) into the app and displays an angry expression when viewing the ad:

[1436] 1. The user enters the ad URL into the app.

[1437] 2. The emotion engine recognizes anger from the user's facial expression.

[1438] 3. The URL is sent to the server and a database check is performed.

[1439] 4. A rating is received from the database saying "This advertising site is trustworthy."

[1440] 5. Based on the results of the emotion engine, a message is added saying "Caution required."

[1441] 6. The final message appears: "This advertising site is trustworthy, but be careful."

[1442] Prompt Sentence Examples

[1443] Below is an example of a prompt used to generate a program for this system for the generative AI model:

[1444] A user enters an ad URL into the app. Write a program that recognizes the emotion of the user's facial expression when viewing the ad, and adjusts the display of the trust rating message based on that emotion. Specifically, this is a Python program that checks the URL against a database and an external API, and adjusts the display result according to the user's emotion.

[1445] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1446] Step 1:

[1447] The user enters the URL of the advertisement into the device and presses the "Check" button.

[1448] The entered URL is acquired by the terminal and sent to the server.

[1449] Step 2:

[1450] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotions.

[1451] Input data: User's facial expressions and tone of voice

[1452] Output data: Recognized emotion (e.g., anxiety, anger)

[1453] Specific operation: Facial expression and voice data is acquired using the built-in camera and microphone, and analyzed by the emotion engine.

[1454] Step 3:

[1455] The server checks the URL received from the terminal against the database.

[1456] Input data: Ad URL

[1457] Output data: Reliability information retrieved from the database (if available)

[1458] Specific operation: The received URL is queried against an existing database to find the corresponding entry.

[1459] Step 4:

[1460] If there is no corresponding data in the database, the server sends a request to an external trust evaluation API.

[1461] Input data: Ad URL

[1462] Output data: Reliability evaluation results obtained from external API

[1463] Specific operation: Sends an HTTP request to an external API, parses the response from the API, and obtains the evaluation result.

[1464] Step 5:

[1465] The server generates a reliability evaluation result based on the database query result and the evaluation result of the external API.

[1466] Input data: Results from databases, results from external APIs

[1467] Output data: Reliability assessment result (e.g., reliable, unreliable)

[1468] Specific operation: Run an algorithm to integrate the results of each evaluation and generate a final reliability evaluation.

[1469] Step 6:

[1470] Based on the user's emotional information recognized by the emotion engine, the server adjusts the display method of the reliability evaluation result.

[1471] Input data: Emotion recognition results, reliability evaluation results

[1472] Output data: Adjusted reliability evaluation results

[1473] Specific actions: Change the message content and display method of the trust evaluation results in response to the user's emotions (e.g., add a detailed explanation if the user is anxious).

[1474] Step 7:

[1475] The server sends the adjusted results to the user's terminal.

[1476] Input data: Adjusted reliability assessment results

[1477] Output data: Evaluation results sent to the user's device

[1478] Specific operation: A communication protocol (such as HTTP) is used to transmit the generated evaluation results to the user's terminal.

[1479] Step 8:

[1480] The received reliability evaluation result is displayed on the user's terminal.

[1481] Input data: Adjusted reliability assessment results

[1482] Output data: Display of evaluation results (e.g., messages on the screen)

[1483] Specific actions: The evaluation results are displayed in an appropriate format using the user interface. The user confirms the results.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] [Fourth embodiment]

[1488] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1489] 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.

[1490] 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).

[1491] 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.

[1492] 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.

[1493] 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).

[1494] 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. 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] 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."

[1501] This invention relates to a system for verifying the reliability of information and websites on the Internet. Specifically, this system checks information and URLs entered by users through an app using a database and an external reliability evaluation API, and provides the results to the user.

[1502] System configuration

[1503] 1. On the user's device:

[1504] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications and provide an interface where users can enter information and URLs.

[1505] 2. Server:

[1506] A central server receives information from users' devices, queries the database for that information, and, if necessary, sends requests to external trust assessment APIs, receiving and analyzing the results.

[1507] 3. Database:

[1508] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[1509] 4. External Trust Assessment API:

[1510] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[1511] Program implementation example

[1512] 1. Launch the app and enter your information

[1513] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[1514] 2. Sending and Receiving Information

[1515] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[1516] 3. Querying the database

[1517] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[1518] 4. Use of external APIs

[1519] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[1520] 5. Generating reliability evaluation results

[1521] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[1522] 6. Sending and displaying results

[1523] The generated credibility evaluation results are sent from the server to the user's device. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the credibility of the information or site.

[1524] Specific examples

[1525] Example 1: Checking news articles

[1526] 1. The user launches the app and enters the URL of a news article.

[1527] 2. The device sends the input information to the server.

[1528] 3. The server queries the database and, if there is no matching entry, sends a request to an external API.

[1529] 4. The server receives the results of the external API and generates a trust rating and sends it to the device.

[1530] 5. The device will display "This news is trustworthy."

[1531] Example 2: Checking the safety of a shopping site

[1532] 1. The user launches the app and enters the URL of a shopping site.

[1533] 2. The device sends the input information to the server.

[1534] 3. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[1535] 4. The server sends the evaluation results to the device, which then displays the message "This shopping site is not trustworthy."

[1536] Error Handling

[1537] The system also has the ability to display an error message to the user if a database query or external API request fails, such as "Evaluation failed. Please try again."

[1538] In this way, this system allows users to easily check the reliability of information and sites on the Internet, reducing user risks and providing support that leads users to more reliable information.

[1539] The processing flow will be explained below.

[1540] Step 1:

[1541] The user launches the application. The user enters the information or URL they want to check into an input field. For example, they enter the URL of a news article.

[1542] Step 2:

[1543] The user presses the "Check" button. The device retrieves the entered information and URL.

[1544] Step 3:

[1545] The device sends the acquired information and URL to the server using a secure communication protocol such as HTTPS.

[1546] Step 4:

[1547] The server receives the input information, connects to the database, and searches the database based on the received information and URL.

[1548] Step 5:

[1549] The server queries the database to see if there is a matching entry, and if there is a matching entry in the database, retrieves its claims.

[1550] Step 6:

[1551] If there is no matching entry in the database, the server sends a request to an external trust assessment API, including the input information and URL.

[1552] Step 7:

[1553] The server receives a response from the external trust evaluation API, analyzes the received result, and obtains the trust information.

[1554] Step 8:

[1555] The server generates a final trust rating based on the results from the database and external APIs, which can be "trusted," "untrusted," or "unknown."

[1556] Step 9:

[1557] The server sends the generated trust evaluation results to the user's device using a secure communication protocol.

[1558] Step 10:

[1559] The device displays the trust evaluation results it received. The evaluation results are displayed in the user interface (UI) so that the user can confirm the results. For example, a message such as "This news is trustworthy" is displayed.

[1560] Step 11:

[1561] If the database query or external API request fails, the server generates an error message, which is sent to the user's device and displays "Evaluation failed. Please try again."

[1562] Example 1

[1563] 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."

[1564] Rapid and accurate evaluation of the reliability of information and websites on the Internet is an important issue in modern society. However, previous systems have been inadequate in detecting fake information and fraudulent websites, making it difficult for users to easily access reliable information. Furthermore, because systems rely solely on databases, they have had the problem of being slow to respond to newly emerging fraudulent information and hoaxes.

[1565] 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.

[1566] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for sending the generated trustworthiness evaluation result to the user's terminal, means for displaying the trustworthiness evaluation result on the user's terminal, means for sending an HTTP POST request from the user's terminal to the server, means for the server to execute an SQL query on the database and search for information, means for receiving the result returned from the external API via an HTTP request, means for the server to generate a trustworthiness evaluation in JSON format based on the received result, and means for displaying the JSON data received by the terminal on a user interface. This allows users to access highly reliable information quickly and accurately.

[1567] A "user's terminal" is a computing device used by a user, such as a smartphone, tablet, or PC.

[1568] "Means for receiving" refers to functions or programs that enable receiving data via a communications network.

[1569] "Means for querying a database" refers to a program or function that searches for entries in a database based on received information and retrieves matching data.

[1570] The "external trustworthiness evaluation API" is an interface for accessing external services to perform trustworthiness evaluation on the Internet and obtaining the necessary evaluation information.

[1571] "Reliability evaluation result" is the evaluation result regarding the reliability of specific information or URL, calculated based on the database query results and results from external APIs.

[1572] An "HTTP POST request" is a type of HTTP protocol used by a client to send data to a server.

[1573] An "SQL query" is a structured query language used to retrieve or manipulate specific data from a relational database.

[1574] "JSON format" stands for JavaScript Object Notation and is a standard format for representing data in a concise, easy-to-read text format.

[1575] "User interface" refers to the screen and operating means by which a user interacts with a computer system.

[1576] This invention relates to a system for evaluating the reliability of information and websites on the Internet. Specifically, the system is a system in which a server queries information and URLs entered from a user's terminal using a database and an external reliability evaluation API, and provides the results to the user.

[1577] System configuration

[1578] 1. User's device

[1579] This includes smartphones, tablets, and PCs used by users. These devices run dedicated applications and provide an interface for users to enter information and URLs.

[1580] 2. Server

[1581] The server has the function of receiving information and URLs sent from the user's device. It also executes SQL queries on the database to search for information. If necessary, it also sends requests to an external trust evaluation API and receives the results. These processes are performed to generate trust evaluation results and send them to the user's device in JSON format.

[1582] 3. Database

[1583] The database contains information about online hoaxes and fraudulent websites, and the server queries the database to find entries that match the information or URLs it receives.

[1584] 4. External Trust Assessment API

[1585] The external API provides a data source for trust assessment, including certificate information from public institutions, etc. The server uses this external API if the corresponding information does not exist in the database.

[1586] Specific examples of programs

[1587] Launching the app and entering information

[1588] A user launches a smartphone app and enters the information or URL they want to check in the input field displayed on the screen. For example, they enter the URL of a news article, "https: / / example.com / news123."

[1589] Sending and Receiving Information

[1590] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request, and the server receives the data encoded in JSON format.

[1591] Querying the database

[1592] The server uses the received information to query its internal database with an SQL query, for example "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[1593] Using external APIs

[1594] If there is no corresponding information in the database, the server will send an HTTP request to an external trust evaluation API. For example, it will send the following data: { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"}.

[1595] Generating reliability evaluation results

[1596] The server generates a trust evaluation result based on the database query results and the results of the external API. For example, if the database records it as "fraud," it will be evaluated as "untrustworthy," but if the external API returns "verified," it will be evaluated as "trustworthy."

[1597] Sending and displaying results

[1598] The generated trust evaluation results are sent from the server to the device in JSON format. The device receives the results and displays them on the user interface. The user can check the displayed results and determine the trustworthiness of the information or site.

[1599] Specific prompt examples

[1600] The specific prompt text is shown below.

[1601] 1. "Confirm the trustworthiness of this news article (URL: https: / / example.com / news123)"

[1602] 2. "Evaluate the security of the following shopping site (URL: https: / / example-shop.com)"

[1603] In this way, this system helps users access highly reliable information by quickly and accurately evaluating the reliability of information and sites on the Internet.

[1604] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1605] Step 1:

[1606] A user launches a smartphone app. They enter the information or URL they want to check into the input field displayed on the app screen. For example, the user enters the URL of a news article, "https: / / example.com / news123." As input, the user provides the URL, and as output, the device stores the URL in the input form. Specifically, the user enters the URL in the text field and presses the "Check" button.

[1607] Step 2:

[1608] When the user presses the "Check" button, the device sends the entered information and URL to the server via an HTTP POST request. As input, the user provides a URL, and as output, the device sends data encoded in JSON format to the server. Specifically, the device generates JSON data {"url": "https: / / example.com / news123"} and sends this data to the server via an HTTP POST request.

[1609] Step 3:

[1610] The server queries its internal database with an SQL query based on the received information. As input, it receives JSON data from the device, and as output, it executes an SQL query to retrieve matching entries in the database. Specifically, the server executes the query "SELECT FROM trust_data WHERE url='https: / / example.com / news123'".

[1611] Step 4:

[1612] If the server does not find the corresponding data in its database, it sends an HTTP request to an external trust evaluation API. As input, it checks whether there are any database query results, and as output, it generates and sends a request to the external API. Specifically, the server sends the data { "apikey": "YOUR_API_KEY", "url": "https: / / example.com / news123"} to the external API.

[1613] Step 5:

[1614] The server receives the results returned from the external API via an HTTP request. It receives the response from the external API as input and parses the results as output. Specifically, the server receives the response data from the external API and parses it as JSON format data.

[1615] Step 6:

[1616] The server generates a trust evaluation result based on the database query results and external API results. It takes the database query results and external API results as input and generates a trust evaluation as output. Specifically, the server analyzes the database and external API results and creates a trust evaluation result in JSON format (e.g., "trusted" or "not trustworthy").

[1617] Step 7:

[1618] The server sends the generated trust evaluation result to the user's device. It uses the trust evaluation result as input and sends JSON data to the device as output. Specifically, the server sends JSON data {"trustResult": "trusted"} to the device.

[1619] Step 8:

[1620] The terminal displays the reliability evaluation results it receives on the user interface. It uses the JSON data received from the server as input and displays the evaluation results to the user as output. Specifically, the terminal displays the message "This news is reliable" on the screen.

[1621] (Application example 1)

[1622] 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."

[1623] The Internet is plagued by a wealth of false information and fraudulent websites. Users lack the means to quickly assess the reliability of such information, making it difficult to verify its authenticity. Manually checking the reliability of URLs is time-consuming and laborious, placing a heavy burden on users. Furthermore, there is a lack of functionality for saving and reusing the reliability evaluation results of previously checked URLs, forcing users to repeatedly evaluate the same sites. The purpose of this invention is to solve these problems, efficiently evaluate the reliability of information on the Internet, and support users' safe access to information.

[1624] 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.

[1625] In this invention, the server includes: means for receiving information and URLs entered from a user's mobile device; means for querying a data storage for the received information and URLs; means for sending a request to an external trust evaluation API and receiving the result if the corresponding data is not found in the data storage; means for generating a trust evaluation result based on the data storage query result and the external API result; means for transmitting the generated trust evaluation result to the user's mobile device; means for displaying the trust evaluation result on the user's mobile device; means for automatically checking URLs from the clipboard; means for saving and reviewing the history; and means for setting a custom alert that warns the user about access to unsafe sites. This allows the user to automatically check URLs from the clipboard, quickly and efficiently receive and display the results, and reuse past history to avoid duplicate checks. The custom alert setting also makes it possible to prevent access to unsafe sites.

[1626] "User's Mobile Device" refers to a smartphone, tablet, or other portable device used by a User.

[1627] "Means for receiving information or URLs" refers to the function for sending information or URLs entered by the user to the server and receiving them on the server side.

[1628] "Data storage" refers to a storage device for managing and querying data, including information about false information and fraudulent websites on the Internet.

[1629] "Means for querying data storage" refers to the function for searching for received information or URLs in data storage and confirming their existence.

[1630] "Means for sending requests to an external trust assessment API and receiving the results" refers to the function for sending requests to an API that uses public institutions or other reliable information sources to perform assessments when there is no relevant data in the data storage, and receiving the results.

[1631] "Means for generating trustworthiness assessment results" refers to the function of making decisions to assess the trustworthiness of information or URLs based on results from data storage and external APIs.

[1632] "Means for transmitting to the user's mobile device" refers to a function for transmitting the generated reliability evaluation results to the user's smartphone or tablet.

[1633] The "means for displaying the reliability evaluation result" refers to a function for visually displaying the reliability evaluation result to the user on the user's mobile device.

[1634] "Means for automatically checking URLs from the clipboard" refers to a function that automatically detects URLs that a user has copied to the clipboard and evaluates the trustworthiness of those URLs.

[1635] "A means to save and review history" refers to a function that allows you to save the results of the reliability evaluation of URLs and information that you have checked in the past and review them later.

[1636] "Custom alert setting means" refers to a function for setting a custom alert when a user accesses an unstable site and providing that alert.

[1637] System Overview:

[1638] This invention is a system for verifying the reliability of information and websites on the Internet, checking information and URLs entered by users using data storage and an external reliability evaluation API, and providing the results to the users. Specific embodiments of the system are described below.

[1639] Hardware and software used:

[1640] Hardware: User devices such as smartphones, tablets, and PCs.

[1641] software:

[1642] SQLite: A local database for storing the reliability evaluation results.

[1643] requests module: A software component for handling HTTP requests to external APIs.

[1644] Python: The programming language used to implement the server and applications.

[1645] System configuration:

[1646] 1. On the user's device:

[1647] The user's device is a mobile device such as a smartphone, where the user runs the application and inputs information or URLs. For example, if the user copies the URL of a news article or a shopping site to the clipboard, the application automatically detects the URL and begins rating it.

[1648] 2. Server:

[1649] The server queries the data storage for the received information and URL, and if there is no corresponding data, it sends a request to an external trust evaluation API. It also generates a trust evaluation result based on the results of the data storage query and the results from the external API.

[1650] 3. Data Storage:

[1651] Data storage manages data, including information about false and fraudulent websites on the Internet, using database management systems such as SQLite.

[1652] 4. External Trust Assessment API:

[1653] External APIs are APIs based on public or other trusted data sources, for example, providing certification information.

[1654] Processing Details:

[1655] 1. Enter and submit your information:

[1656] When a user types a URL into their mobile device or copies it to their clipboard, the application automatically reads the URL and sends it to the server.

[1657] 2. Data storage query:

[1658] The server checks the received URL in the data storage to see if the corresponding information exists. If a matching entry is found in the data storage, it evaluates its credibility based on the results and notifies the user.

[1659] 3. Use of external APIs:

[1660] If there is no corresponding information in the data storage, the server sends a request to an external trust evaluation API and receives the response. It then obtains the trust evaluation information from the API and generates a new evaluation result based on this information.

[1661] 4. Submit and view the evaluation results:

[1662] The server generates the final trust evaluation result and sends it to the user's mobile device, which receives the evaluation result and displays it on the application screen.

[1663] Examples and prompts:

[1664] Example: When a user launches an application and copies the URL "https: / / example-news.com / article123" to the clipboard, the application automatically starts a process to evaluate the trustworthiness of the URL. The result of the evaluation is displayed on the device screen, informing the user that "This site is not trustworthy."

[1665] Example prompt sentence:

[1666] When a user copies the URL "https: / / example-news.com / article123" to their clipboard, they should rate its trustworthiness. They should receive some kind of notification about the trustworthiness of this site, including details of whether it has been reported as a hoax in the past.

[1667] This allows users to easily access reliable information and reduces the risk of false information and fraudulent sites on the Internet.

[1668] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1669] Step 1:

[1670] A user launches an application on a mobile device and inputs or copies a URL to the clipboard. The application then automatically detects the contents of the clipboard and prepares to parse the URL. Specifically, the application performs an input process that reads the contents of the clipboard and interprets the data as a URL.

[1671] Input: The URL that the user copied to the clipboard

[1672] Output: The URL is recognized in the application

[1673] Step 2:

[1674] The device sends the recognized URL to the server, the application sends the URL as an HTTP request to the server, and the server receives the request. This process initiates the evaluation of the trustworthiness of the data based on the URL.

[1675] Input: URL sent from the device

[1676] Output: URL sent to server

[1677] Step 3:

[1678] The server queries the data storage for the received URL to find the trust information for that URL. The server accesses the SQLite database and finds an entry that matches the received URL.

[1679] Input: URL received by the server

[1680] Output: Whether or not there is a matching entry in the data storage

[1681] Step 4:

[1682] If the server does not find a corresponding entry in its data storage, it sends a request to an external trust evaluation API. It sends a URL as a request to the external API and waits for the trust evaluation result. During this time, the server monitors the response from the API.

[1683] Input: URL where no corresponding data is found after querying the data storage

[1684] Output: Trust evaluation result from external API

[1685] Step 5:

[1686] The server receives the evaluation results from the external API and analyzes them. The server analyzes the data received from the external API and extracts the relevant evaluation information. This data includes the credibility evaluation results and related evidence information.

[1687] Input: Evaluation result from external API

[1688] Output: Analyze the evaluation results and extract the evaluation information

[1689] Step 6:

[1690] The server generates a final trust evaluation result based on the data storage query results and external API results. Based on the analyzed data, it generates an evaluation result such as "trusted," "untrusted," or "unknown."

[1691] Input: Data storage query results and external API evaluation results

[1692] Output: Final reliability evaluation result

[1693] Step 7:

[1694] The generated trust evaluation results are sent to the user's mobile device and notified to the user. The server sends the evaluation results to the user's terminal as an HTTP response, and the user's terminal displays the received results within the application.

[1695] Input: Final reliability evaluation result

[1696] Output: The evaluation result is displayed on the user's terminal.

[1697] Step 8:

[1698] Users can check the evaluation results on their mobile devices and judge the reliability of the information or site. Based on the displayed results, users can decide whether to continue using the information or browsing the site.

[1699] Input: Evaluation result displayed on the user's terminal

[1700] Output: User reviews the evaluation results and makes a decision

[1701] This allows users to efficiently obtain reliable information and avoid accessing suspicious sites.

[1702] 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.

[1703] This invention relates to a system that recognizes user emotions and verifies the reliability of information and websites on the Internet. Specifically, the system checks information and URLs entered by users through apps using a database and an external reliability evaluation API, and displays information appropriately based on the results, taking the user's emotions into consideration.

[1704] System configuration

[1705] 1. On the user's device:

[1706] This includes smartphones, tablets, PCs, etc. used by users. These devices run dedicated applications, provide an interface for users to input information and URLs, and an emotion engine that recognizes users' emotions.

[1707] 2. Server:

[1708] A central server receives information from users' devices, queries the database, and optionally sends requests to external trust assessment APIs, receives and analyzes the results, and adjusts the received assessment results based on the user's sentiment.

[1709] 3. Database:

[1710] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant data exists.

[1711] 4. External Trust Assessment API:

[1712] It is an external service for assessing trustworthiness, and uses data sources including, for example, certificate information from public institutions.

[1713] 5. Emotion Engine:

[1714] The emotion recognition function installed in the user's device analyzes the user's facial expressions, voice, input operations, etc. to identify the user's emotions.

[1715] Program implementation example

[1716] 1. Launch the app and enter your information

[1717] A user launches a smartphone app and enters the information or URL they want to check into the input field displayed on the app screen. For example, consider entering the URL of a news article.

[1718] 2. Emotional Recognition

[1719] When a user is entering information or pressing the "check" button, the device's built-in emotion engine analyzes the user's facial expressions, voice, and input operations to recognize their current emotion. For example, if the user looks anxious, the emotion will be recognized as "anxiety."

[1720] 3. Sending and Receiving Information

[1721] When the user presses the "Check" button, the device sends the entered information and URL to the server, which receives this information and first checks the database.

[1722] 4. Querying the Database

[1723] The server connects to its database and searches for an entry that matches the information or URL received. If the information is in the database, it retrieves information about its trustworthiness, such as "this site has been reported as a scam in the past."

[1724] 5. Use of external APIs

[1725] If the database does not contain the relevant information, the server sends a request to an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources and returns the results to the server.

[1726] 6. Generating reliability evaluation results

[1727] The server generates a final trust rating based on the results from the database and the evaluation results from the external API, such as "trusted," "untrusted," or "unknown."

[1728] 7. Adjustment and submission of results

[1729] Based on the user's emotional information recognized by the emotion engine, the server adjusts the way it displays the trust assessment results. For example, if the user is anxious, it will display a more understandable and polite message. The adjusted results are then sent from the server to the user's device.

[1730] 8. Displaying the results

[1731] The user's device displays the received reliability evaluation results. For example, if the user looks anxious, the device displays the message "This news is reliable" along with detailed reasons and an explanation of the evaluation process.

[1732] Specific examples

[1733] Example 1: Checking news articles

[1734] 1. The user launches the app and enters the URL of a news article.

[1735] 2. While typing, the emotion engine analyzes the user's facial expressions to recognize emotions (e.g., surprise).

[1736] 3. The device sends the input information to the server.

[1737] 4. The server queries the database and, if there is no matching entry, sends a request to an external API.

[1738] 5. The server that receives the results of the external API generates a trust rating.

[1739] 6. Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[1740] 7. Your device will display the message "This news is trustworthy" along with a detailed explanation.

[1741] Example 2: Checking the safety of a shopping site

[1742] 1. The user launches the app and enters the URL of a shopping site.

[1743] 2. As you type, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[1744] 3. The device sends the input information to the server.

[1745] 4. The server queries the database and, if a matching entry is found, retrieves the fraud information.

[1746] 5. The server generates the evaluation results, adjusts them based on the results of the emotion engine, and sends them to the device.

[1747] 6. Your device will display a message saying "This shopping site is untrustworthy" along with details about the specific risks.

[1748] Error Handling

[1749] In the system, if a database query or external API request fails, the server generates an error message, which is adjusted based on the results of the emotion engine, and the user's device displays "Evaluation failed. Please try again."

[1750] In this way, this system takes into account the user's feelings and allows them to easily check the reliability of information and sites on the Internet, thereby reducing user risks and providing support that leads them to more reliable information.

[1751] The processing flow will be explained below.

[1752] Step 1:

[1753] A user launches the app on their smartphone. The app screen displays fields for entering information and URLs. The user enters the URL of the news article they want to check.

[1754] Step 2:

[1755] While the user is entering information, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion. For example, if the user is frowning, the emotion engine will detect anxiety.

[1756] Step 3:

[1757] The user presses the "Check" button. The device retrieves the entered information and URL and sends them to the server. A secure communication protocol such as HTTPS is used for transmission.

[1758] Step 4:

[1759] The server receives the input information and first queries the database. The server connects to the database and searches for entries that match the received information and URL. At the same time, it also processes the user's emotional information.

[1760] Step 5:

[1761] If there is a matching entry in the database, the server retrieves its credibility information, for example, "this site has been reported as a scam in the past."

[1762] Step 6:

[1763] If there is no matching entry in the database, the server sends a request to an external trust assessment API, which includes the user-entered information and a URL.

[1764] Step 7:

[1765] The server receives a response from an external trust evaluation API, which evaluates the information based on official certificate information and other trusted data sources, and returns the result.

[1766] Step 8:

[1767] The server generates a final trust rating based on the results from the database and the external API, which may include ratings such as "trusted," "untrusted," or "unknown."

[1768] Step 9:

[1769] Based on the emotion engine's recognition results, the server adjusts the way it displays the trust assessment results. For example, if the user expresses anxiety, it adds detailed reasons and instructions on what to do next in addition to the assessment result.

[1770] Step 10:

[1771] The server then sends the adjusted trust evaluation results to the user's device using a secure communication protocol.

[1772] Step 11:

[1773] The device displays the results of the trust assessment it receives. For example, if the user looks anxious, it displays the message "This news is trustworthy" along with a detailed explanation of why it is trustworthy.

[1774] Step 12:

[1775] If the database query or external API request fails, the server generates an error message. Based on the result of the emotion engine, the message "Evaluation failed. Please try again" is displayed on the user's device.

[1776] Specific examples

[1777] Example 1: Checking news articles

[1778] 1. Step 1 - User launches the app and enters the URL of a news article.

[1779] 2. Step 2 - While the user is typing, the emotion engine analyzes the user's facial expressions and recognizes the emotion (e.g. surprise).

[1780] 3. Step 3 - The device sends the input information to the server.

[1781] 4. Step 4 - The server queries the database and if there is no matching entry, it sends a request to an external API.

[1782] 5. Step 7 - The server receives the results of the external API and generates a trust rating.

[1783] 6. Step 9 - Based on the results of the emotion engine, the server adjusts the evaluation results and sends them to the device.

[1784] 7. Step 11 - Your device will display the message "This news is trustworthy" along with a detailed explanation.

[1785] Example 2: Checking the safety of a shopping site

[1786] 1. Step 1 - User launches the app and enters the URL of a shopping site.

[1787] 2. Step 2 - While typing, the emotion engine analyzes the user's tone of voice to recognize emotions (e.g., anxiety).

[1788] 3. Step 3 - The device sends the input information to the server.

[1789] 4. Step 4 - The server queries the database and if a matching entry is found, it retrieves the fraud information.

[1790] 5. Step 7 - The server generates the evaluation result, adjusts it based on the emotion engine results, and sends it to the device.

[1791] 6. Step 11 - Your device will display a message saying "This shopping site is not trusted" along with details about the specific risks.

[1792] In this way, this system takes into account the user's feelings and displays the results of credibility evaluation appropriately, allowing users to use information on the Internet with peace of mind.

[1793] Example 2

[1794] 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."

[1795] Conventional information reliability evaluation systems were unable to consider the user's emotions when determining the reliability of information or URLs entered by the user. As a result, users may receive the results with anxiety or doubt, and even reliable information cannot be conveyed appropriately in accordance with the user's feelings. Furthermore, when there is no relevant data in the database, the evaluation method is uniform, making it difficult to provide users with an appropriate sense of security.

[1796] 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.

[1797] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the result of the external API, means for recognizing the user's emotion and transmitting the result to the server, means for adjusting the trustworthiness evaluation result based on the user's emotion information, means for transmitting the generated trustworthiness evaluation result to the user's terminal, and means for displaying the trustworthiness evaluation result on the user's terminal. This makes it possible to provide a trustworthiness evaluation result that reflects the user's emotion, thereby creating an environment in which users can check information with peace of mind.

[1798] "User device" refers to the device used by the user to enter information and check results, including smartphones, tablets, PCs, etc.

[1799] "Means for receiving" refers to a method or device that allows the server to obtain information or a URL sent from the user's terminal.

[1800] "Means for querying a database" refers to a method or device that allows the server to query an existing database for input information and confirm the presence or absence of the information and its contents.

[1801] "External Trust Assessment API" refers to an application programming interface that utilizes external data sources for trust assessment, including certificate information from public organizations.

[1802] "Means for generating reliability evaluation results" refers to a method or device for evaluating reliability and generating results based on information in a database or data from an external API.

[1803] "Means for recognizing emotions" refers to a function that analyzes the user's facial expressions, tone of voice, input operations, etc. to identify the user's current emotions.

[1804] The "means for adjusting the trustworthiness evaluation result" refers to a function for appropriately changing the display method and content of the trustworthiness evaluation result based on the recognized emotional information of the user.

[1805] The "means for transmitting" refers to a method or device for transmitting the generated reliability evaluation result or adjusted information to the user's terminal.

[1806] The "display means" refers to a method or device for visually displaying the reliability evaluation result on the user's terminal.

[1807] The system of this invention recognizes user emotions and evaluates the reliability of information and websites on the Internet based on the emotions. The system consists of the following main components:

[1808] 1. User's device

[1809] A device used by users to input information and check the results. It includes smartphones, tablets, PCs, etc. It runs a dedicated application and provides an interface for inputting information and URLs, as well as an emotion engine for recognizing the user's emotions. The emotion engine uses facial recognition and voice recognition technology to analyze the user's emotions. Specific software used includes a facial recognition API and a voice analysis API.

[1810] 2. Server

[1811] It is centrally located and receives information sent from user devices. It queries the received information against a database, sends requests to an external trust evaluation API as needed, and receives the results. It then generates trust evaluation results based on the database query results and external API results, and adjusts them based on user sentiment information. To perform these tasks, the server requires a database management system (DBMS) and software to process API requests.

[1812] 3. Database

[1813] This is a database containing information about online hoaxes and fraudulent websites. This database is queried by the server to check whether or not the relevant information exists. RDBMS such as MySQL or PostgreSQL is often used as the database software.

[1814] 4. External Trust Assessment API

[1815] It is an external service for evaluating the reliability of information, using data sources such as certificate information from public institutions. This allows for reliable evaluation results even when the relevant data is not available in the database. Specific APIs may use generative AI models such as those from OpenAI.

[1816] 5. Emotion Engine

[1817] This function is installed on the user's device and identifies the user's emotions by analyzing their facial expressions, voice, input operations, etc. It applies computer vision and natural language processing technology to analyze emotions in real time.

[1818] Specific examples

[1819] Example 1: Checking news articles

[1820] The user launches a dedicated app on their smartphone and enters the URL of a news article. As they type, the emotion engine analyzes their facial expressions and recognizes the emotion of surprise. When the user presses the "Check" button, the input information is sent to the server. The server queries the database and, if no matching entry is found, sends a request to an external credibility assessment API. After receiving the result from the external API, the server generates a credibility assessment, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This news is trustworthy" along with a detailed explanation.

[1821] Example 2: Checking the safety of a shopping site

[1822] A user launches a dedicated app on a tablet and enters the URL of a shopping site. As they type, the emotion engine analyzes the user's tone of voice to recognize the emotion of anxiety. When the user presses the "Check" button, the URL is sent to the server. The server queries the database and, if it finds a matching entry, retrieves the information reported as fraud. The server generates an evaluation result, adjusts it based on the emotion information, and sends it to the user's device. The user's device then displays the message "This shopping site is untrustworthy" along with details about the specific risks.

[1823] Prompt Sentence Examples

[1824] "I want to enter the URL of a news article to check its authenticity. I'm a little unsure."

[1825] In this way, the system of the present invention allows users to easily check the reliability of information and websites on the Internet while taking into account their feelings, thereby reducing user risks and providing support that leads users to more reliable information.

[1826] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1827] Step 1:

[1828] The user launches a dedicated app on a device such as a smartphone or PC, and the app screen displays fields for entering information and URLs.

[1829] Input: Information or URL the user wants to check (e.g., URL of a news article)

[1830] What happens: A user taps or clicks an app icon to launch the app and enters information or a URL into an on-screen input field.

[1831] Output: Information entered into input fields within the app and URLs

[1832] Step 2:

[1833] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and typing speed while they are typing or when they press the "check" button, and recognizes the user's emotions.

[1834] Input: User facial expressions, tone of voice, typing speed, etc.

[1835] How it works: Your device uses the camera to capture your facial expressions and the microphone to analyze the tone of your voice and record the speed and strength of your typing.

[1836] Output: Recognized user emotion (e.g., anxiety, surprise)

[1837] Step 3:

[1838] When the user presses the "Check" button, the device sends the entered information and URL to the server.

[1839] Input: User-entered information, URLs, and recognized emotions

[1840] How it works: The user presses the "Check" button, and the device generates and sends a request to send information and a URL to the server.

[1841] Output: Information sent to the server, URL, and recognized emotion

[1842] Step 4:

[1843] The server queries the database based on the received information to find a matching entry.

[1844] Input: Information or URL sent from the device

[1845] How it works: The server sends a query to the database, receives a response from the database, and checks whether the information is available.

[1846] Output: Database query results (e.g., information on reported fraudulent sites)

[1847] Step 5:

[1848] If the server does not have the relevant information in its database, it sends a request to an external trust evaluation API.

[1849] Input: Information or URL if the corresponding information does not exist in the database

[1850] How it works: The server generates a request for an external API and sends the request over the internet to the external API.

[1851] Output: Trust evaluation result from external API

[1852] Step 6:

[1853] The server generates a trust evaluation result based on the results from the database and external APIs.

[1854] Input: Database query results, trust evaluation results from external API

[1855] How it works: The server combines the responses from the database and the external API, analyzes key elements, and generates a final rating.

[1856] Output: Generated reliability evaluation result (e.g., "reliable", "unreliable", "unknown")

[1857] Step 7:

[1858] The server adjusts the display method of the reliability evaluation result based on the user's emotion information recognized by the emotion engine.

[1859] Input: Generated trust rating results, perceived user sentiment

[1860] How it works: The server formats the evaluation results based on emotional information to create a clear and polite message.

[1861] Output: Emotion-adjusted trustworthiness assessment results

[1862] Step 8:

[1863] The server transmits the adjusted trustworthiness evaluation result to the user's terminal.

[1864] Input: Emotion-adjusted trustworthiness assessment results

[1865] Action: The server sends the formatted evaluation results to the user's device.

[1866] Output: The trust evaluation result sent to the user's device

[1867] Step 9:

[1868] The user's terminal displays the received reliability evaluation result on the screen.

[1869] Input: Trustworthiness evaluation result sent from the server

[1870] How it works: The device displays the evaluation results received from the server on the screen, along with additional information and explanations based on the emotion.

[1871] Output: The credibility assessment result displayed to the user (e.g., "This news is trustworthy")

[1872] Error handling (if necessary)

[1873] If the server fails a database query or external API request, it generates an error message.

[1874] Input: Database query or external API request failure

[1875] How it works: The server generates error messages and adjusts them based on emotion information from the emotion engine.

[1876] Output: Tailored error message (e.g. "Evaluation failed. Please try again.")

[1877] In this way, the system takes into account the user's feelings and makes it easy to check the reliability of information and websites on the Internet, allowing users to check the information with peace of mind.

[1878] (Application example 2)

[1879] 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."

[1880] To enable users to easily determine the reliability of information and websites on the Internet, and to adjust the results of the determination based on the user's feelings and display them more appropriately, thereby enabling users to use the Internet with peace of mind without being misled by fraud or false information.

[1881] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1882] In this invention, the server includes means for receiving information or a URL entered from a user's terminal, means for querying a database for the received information or URL, means for sending a request to an external trustworthiness evaluation API and receiving the result if the database does not contain the relevant data, means for generating a trustworthiness evaluation result based on the database query result and the external API result, means for transmitting the generated trustworthiness evaluation result to the user's terminal, means for recognizing the user's emotion and adjusting the display method of the trustworthiness evaluation result based on the recognized emotion, thereby enabling appropriate feedback according to the user's emotion.

[1883] A "user's terminal" is a device that a user uses to input information and perform operations, and specifically refers to a smartphone, tablet, PC, etc.

[1884] "Input information or URL" refers to the address or text data of the website that the user wishes to check or evaluate.

[1885] "Means for receiving" refers to a module or interface that has the function of importing information or URLs sent from the user's terminal into the server.

[1886] The "means for querying a database" is a module that has the function of checking the received information or URL against a database to see if there is a corresponding entry.

[1887] An "external trustworthiness assessment API" is an external service for assessing trustworthiness, and refers to an API provided by a public institution or a reliable data source.

[1888] The "means for sending a request and receiving the result" is a module that enables the server to send a request to an external trustworthiness evaluation API and receive the evaluation result.

[1889] The "means for generating a reliability evaluation result" is a module that has the function of generating a final reliability evaluation based on the database query result and the evaluation result of the external API.

[1890] The "means for transmitting the reliability evaluation result to the user's terminal" is a module having a function for transmitting the reliability evaluation result generated by the server to the user's terminal.

[1891] The "means for displaying the reliability evaluation result" is a module or interface for visually displaying the reliability evaluation result received on the user's terminal in an easy-to-read manner.

[1892] The "means for recognizing the user's emotions" is a module that has the function of analyzing the user's facial expressions, voice, operation methods, etc. to identify the emotions at that time.

[1893] The "means for adjusting the display method" is a module that has the function of appropriately changing the content and method of display based on the recognized user emotion.

[1894] This invention relates to a system that recognizes user emotions and evaluates the reliability of information and websites on the Internet. Specifically, it realizes an application in the advertising field where a user evaluates the reliability of advertisements displayed to them, adjusts the results according to the user's emotions, and provides feedback.

[1895] System configuration

[1896] The system consists of the following main elements:

[1897] 1. User device: This is the device where the user enters information and checks the results, and includes smartphones, tablets, etc. It also has an emotion engine that recognizes the user's emotions.

[1898] 2. Server: A central server receives information from users' devices, communicates with a database and an external trust evaluation API, generates trust evaluation results, and adjusts the results based on user sentiment.

[1899] 3. Database: A database containing information on false information and fraudulent websites on the Internet, which serves as a primary source of information for assessing credibility.

[1900] 4. External Trust Assessment API: An external service that assesses trust, using APIs provided by public institutions or trusted data sources.

[1901] 5. Emotion engine: A module that has the function of identifying emotions by analyzing the user's facial expressions, voice, and operation methods.

[1902] Program processing flow

[1903] 1. Entering and receiving information: The user enters the URL of the advertisement into the device and presses the "Check" button. The device then sends the entered information to the server.

[1904] 2. Emotion Recognition: While the user is inputting or interacting with the device, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotion, for example, identifying emotions such as anxiety or anger.

[1905] 3. Database query: The server queries the database based on the received information to search for the corresponding entry. If the corresponding data is found, it retrieves the information.

[1906] 4. Use of external API: If there is no corresponding data in the database, the server sends a request to an external trust evaluation API to obtain the evaluation results.

[1907] 5. Generating the trust evaluation results: The server generates the trust evaluation results based on the results from the database and the evaluation results from the external API.

[1908] 6. Adjustment and transmission of results: Based on the user's emotional information recognized by the emotion engine, the server adjusts the trust assessment results. For example, if anxiety is recognized, the server adds a detailed explanation to make the results easier to understand. The adjusted results are then sent to the user's device.

[1909] 7. Displaying the results: The user's device displays the results of the trust assessment. For example, it may display a message saying "This advertising site is untrustworthy," along with detailed risk information and warnings.

[1910] Hardware and software used

[1911] Hardware: Smartphone

[1912] Software: Flask (web framework), EmotionEngine (emotion recognition library), requests (external API requests)

[1913] Specific examples

[1914] Example 1

[1915] If a user enters an ad URL (e.g., https: / / fakeads.com) into the app and displays anxiety when viewing the ad:

[1916] 1. The user enters the ad URL into the app.

[1917] 2. The emotion engine recognizes anxiety from the user's facial expression.

[1918] 3. The URL is sent to the server and a database check is performed.

[1919] 4. A rating is received from the database saying "This advertising site has been reported in the past."

[1920] 5. Based on the results of the sentiment engine, a message is added saying "More information follows."

[1921] 6. Final message: "This advertising site has been reported in the past. More information below."

[1922] Example 2

[1923] If a user enters the ad URL (e.g., https: / / legitads.com) into the app and displays an angry expression when viewing the ad:

[1924] 1. The user enters the ad URL into the app.

[1925] 2. The emotion engine recognizes anger from the user's facial expression.

[1926] 3. The URL is sent to the server and a database check is performed.

[1927] 4. A rating is received from the database saying "This advertising site is trustworthy."

[1928] 5. Based on the results of the emotion engine, a message is added saying "Caution required."

[1929] 6. The final message appears: "This advertising site is trustworthy, but be careful."

[1930] Prompt Sentence Examples

[1931] Below is an example of a prompt used to generate a program for this system for the generative AI model:

[1932] A user enters an ad URL into the app. Write a program that recognizes the emotion of the user's facial expression when viewing the ad, and adjusts the display of the trust rating message based on that emotion. Specifically, this is a Python program that checks the URL against a database and an external API, and adjusts the display result according to the user's emotion.

[1933] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1934] Step 1:

[1935] The user enters the URL of the advertisement into the device and presses the "Check" button.

[1936] The entered URL is acquired by the terminal and sent to the server.

[1937] Step 2:

[1938] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotions.

[1939] Input data: User's facial expressions and tone of voice

[1940] Output data: Recognized emotion (e.g., anxiety, anger)

[1941] Specific operation: Facial expression and voice data is acquired using the built-in camera and microphone, and analyzed by the emotion engine.

[1942] Step 3:

[1943] The server checks the URL received from the terminal against the database.

[1944] Input data: Ad URL

[1945] Output data: Reliability information retrieved from the database (if available)

[1946] Specific operation: The received URL is queried against an existing database to find the corresponding entry.

[1947] Step 4:

[1948] If there is no corresponding data in the database, the server sends a request to an external trust evaluation API.

[1949] Input data: Ad URL

[1950] Output data: Reliability evaluation results obtained from external API

[1951] Specific operation: Sends an HTTP request to an external API, parses the response from the API, and obtains the evaluation result.

[1952] Step 5:

[1953] The server generates a reliability evaluation result based on the database query result and the evaluation result of the external API.

[1954] Input data: Results from databases, results from external APIs

[1955] Output data: Reliability assessment result (e.g., reliable, unreliable)

[1956] Specific operation: Run an algorithm to integrate the results of each evaluation and generate a final reliability evaluation.

[1957] Step 6:

[1958] Based on the user's emotional information recognized by the emotion engine, the server adjusts the display method of the reliability evaluation result.

[1959] Input data: Emotion recognition results, reliability evaluation results

[1960] Output data: Adjusted reliability evaluation results

[1961] Specific actions: Change the message content and display method of the trust evaluation results in response to the user's emotions (e.g., add a detailed explanation if the user is anxious).

[1962] Step 7:

[1963] The server sends the adjusted results to the user's terminal.

[1964] Input data: Adjusted reliability assessment results

[1965] Output data: Evaluation results sent to the user's device

[1966] Specific operation: A communication protocol (such as HTTP) is used to transmit the generated evaluation results to the user's terminal.

[1967] Step 8:

[1968] The received reliability evaluation result is displayed on the user's terminal.

[1969] Input data: Adjusted reliability assessment results

[1970] Output data: Display of evaluation results (e.g., messages on the screen)

[1971] Specific actions: The evaluation results are displayed in an appropriate format using the user interface. The user confirms the results.

[1972] 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.

[1973] 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.

[1974] 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.

[1975] 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.

[1976] 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.

[1977] 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.

[1978] 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).

[1979] 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.

[1980] 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."

[1981] 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...

Claims

1. A means for receiving information and URLs input from a user's device; A means of querying the database for received information and URLs; If there is no corresponding data in the database, a means for sending a request to an external reliability evaluation API and receiving the result; A means for generating a reliability evaluation result based on the database query result and the external API result; means for transmitting the generated reliability evaluation result to a user terminal; A means for displaying the reliability evaluation results on the user's terminal A system including:

2. 2. The system according to claim 1, wherein the database contains information about hoaxes and fraudulent websites on the Internet.

3. 2. The system of claim 1, wherein the external trust assessment API is an API based on a data source including certificate information of a public institution.

Images