system

Abstract

Provide a system. The present invention provides a method for evaluating and displaying the reliability of information on the Internet, means for receiving a URL or text input from a user; A means for analyzing the content of received URLs or text and assessing their trustworthiness; a means for displaying a reliability score of the analysis result; 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] The spread of the Internet has made it possible to obtain information quickly and widely, but at the same time, the spread of fake news and misinformation has become a social problem. This has led to the spread of unreliable information, increasing the risk that many users will make incorrect decisions. Effective measures to solve this problem are needed. [Means for solving the problem]

[0005] The present invention provides a system for evaluating and displaying the reliability of information on the Internet. Specifically, the system includes a means for receiving a URL or text entered by a user, a means for analyzing the content of the received URL or text to evaluate its reliability, and a means for displaying a reliability score based on the analysis result. The system also includes a means for using a generative AI model to evaluate the reliability score and a means for using reliable and unreliable sources as the basis for the reliability evaluation. This allows users to easily determine the reliability of information, making it possible to curb the spread of misinformation and fake news.

[0006] The "Internet" is a huge network system that interconnects computers and other devices around the world, enabling data transmission and information acquisition.

[0007] "Reliability" refers to the extent to which information is accurate and free from errors or misinformation.

[0008] "Fake news" refers to false information disguised as fact, created and widely spread with the intent to mislead people.

[0009] "User" refers to any individual or entity that uses the System or Services.

[0010] "URL" is a unique address that indicates the location of a resource on the Internet, and is an abbreviation for Uniform Resource Locator.

[0011] "Text" refers to written characters or sentence data, and is primarily character information handled by computers.

[0012] A "generative AI model" is a model that has the algorithms and data structures used by artificial intelligence, and demonstrates high accuracy in generating and analyzing data.

[0013] A "credibility score" is a numerical value that represents the accuracy or reliability of information, and is usually expressed as a percentage.

[0014] "Source" refers to the place, person, organization, etc. from which information is disseminated. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[0037] Server-side behavior

[0038] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following actions based on the entered information:

[0039] Information analysis and reliability assessment

[0040] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[0041] Returning the results

[0042] After the analysis results are obtained, the server returns them to the user with a reliability score, expressed as a percentage. The higher the score, the more reliable the information is.

[0043] Operation on the terminal side

[0044] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[0045] Providing a user interface

[0046] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[0047] Sending information

[0048] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0049] Displaying the results

[0050] After the server returns the results of the trust assessment, the device displays the results on the user interface. The trust scores are displayed in a visually easy-to-understand format (e.g., a bar chart or a colored bar).

[0051] User operation

[0052] The user performs direct operations to use the system, including the following:

[0053] Entering information

[0054] Users enter the URL or text they want to rate on the system's input screen, and when they're done, they press the "Rate" button to submit the information.

[0055] Checking the results

[0056] The user checks the credibility evaluation results returned from the server on the screen and uses the displayed credibility score to determine the accuracy of the information.

[0057] Specific examples

[0058] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Evaluate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score. The user can use this result to determine whether the news article is reliable or not.

[0059] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and check its reliability score, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[0060] The processing flow will be explained below.

[0061] Step 1: Input from the user

[0062] The user enters the URL or text (such as a social media post) of the news article they want to rate into the system's input screen and presses the "Rate" button. In the example where a user enters the URL of a news article, they copy the URL of the news article they found in their browser, paste it into the system's input box, and press the submit button.

[0063] Step 2: Submit your information

[0064] The terminal receives the URL or text entered by the user, then packages the received information in JSON format or similar and sends it to the server using an HTTP POST request. In this example, a JSON object containing the entered URL is created and sent to the server.

[0065] Step 3: Receiving the request on the server

[0066] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL to be evaluated.

[0067] Step 4: Gather information

[0068] The server then performs web scraping or API requests to retrieve information from the extracted URLs, which is the step of retrieving the content of the specified news article from the internet.

[0069] Step 5: Pre-analysis processing using generative AI

[0070] The server preprocesses the retrieved news article content, which includes text normalization, removal of unnecessary data, language identification, etc. For example, HTML tags are removed from the news article text and language filters are applied.

[0071] Step 6: Reliability assessment

[0072] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and returns a rating of "80% reliability."

[0073] Step 7: Packaging the evaluation results

[0074] The server packages the generated reliability score in JSON format, etc. It generates a JSON object containing a reliability score of 80% as the evaluation result.

[0075] Step 8: Sending the results

[0076] The server returns a JSON object containing the evaluation results to the terminal as an HTTP response.

[0077] Step 9: Receiving the results

[0078] The device receives the HTTP response from the server and analyzes the response content. Specifically, it parses the received JSON data and extracts the reliability score.

[0079] Step 10: View the results

[0080] The device displays the extracted reliability score on the user interface, using a text representation of a reliability score of 80% or a visually easy-to-understand bar chart.

[0081] Step 11: Check the evaluation results

[0082] The user checks the results of the reliability assessment displayed on the device. The user uses the displayed reliability score to determine whether the news article is trustworthy. In a specific example, the user sees a message saying "The reliability of this news article is 80%" and evaluates the accuracy of the information.

[0083] These are the specific processing steps from user input to display of the reliability score. This system provides users with an effective means to easily evaluate the reliability of information on websites and social media sites and obtain accurate information.

[0084] Example 1

[0085] 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."

[0086] The Internet is overflowing with a wide variety of information, including unreliable information and fake news. This makes it difficult for users to determine which information is accurate and reliable. In particular, there is a need for a method to quickly evaluate and present the reliability of important news and information that requires fact-checking.

[0087] 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.

[0088] In this invention, the server includes a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and using a generative AI model to evaluate reliability, a means for calculating a reliability score, and a means for displaying the calculated reliability score, thereby enabling a user to easily and quickly evaluate the reliability of a URL or text and visually confirm the result.

[0089] "User" is the subject who uses the system to evaluate the reliability of URLs and text.

[0090] A "URL" is a uniform resource locator for specifying resources on the Internet.

[0091] "Text" is character string data to be evaluated.

[0092] A "server" is a central computing unit that analyzes URLs and text received from users and evaluates their trustworthiness.

[0093] "Means of receiving" refers to the method by which the server obtains the URL or text sent by the user.

[0094] A "generative AI model" is a computational model that uses artificial intelligence to analyze incoming URLs and text. For example, it is an AI that performs natural language processing.

[0095] "Analysis" refers to the act of using a generative AI model to examine the content of received URLs and text and assess their reliability.

[0096] A "means for assessing trustworthiness" is a method for determining the trustworthiness of a URL or text using a generative AI model.

[0097] A "reliability score" is a numerical expression of an evaluation based on the analysis results, and is an index showing the reliability of information.

[0098] The "means for calculating" is a method for deriving a reliability score based on the analysis results.

[0099] The "means for displaying" is a method for presenting the reliability score in a format that is easy for the user to understand.

[0100] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[0101] Server-side behavior

[0102] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following operations:

[0103] Information analysis and reliability assessment

[0104] The server analyzes the URLs and text received from users using a generative AI model (e.g., a generative AI model). This model performs detailed data analysis to assess trustworthiness. The analysis process generates a trustworthiness score based on highly reliable sources (such as official announcements from public institutions and major media outlets) and less reliable sources (such as anonymous blogs and social media posts).

[0105] For example, the prompt sentence is "Please rate the credibility of this news article. Link: https: / / example.com / news-article" and the generative AI model uses the analysis results to calculate a credibility score.

[0106] Returning the results

[0107] The server returns a credibility score based on the analysis to the user, expressed as a percentage, with higher scores indicating greater credibility.

[0108] Operation on the terminal side

[0109] The terminal is a device that provides an interface for the user to operate the system, and performs the following operations.

[0110] Providing a user interface

[0111] The terminal provides a text box and a submit button for users to enter the URL or text they want to rate, allowing them to easily enter the information they want to rate.

[0112] Sending information

[0113] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0114] Displaying the results

[0115] After receiving the result of the trustworthiness evaluation returned from the server, the terminal visually displays the result on the user interface in a visually easy-to-understand format such as a bar chart or a colored bar graph.

[0116] User operation

[0117] The user uses the system to perform the following operations:

[0118] Entering information

[0119] Users enter the URL or text they want to evaluate for trustworthiness into the input screen. This can be done using a browser or a dedicated application.

[0120] Checking the results

[0121] The user checks the reliability evaluation results returned from the server on the screen and uses the displayed reliability score to determine the accuracy of the information being evaluated.

[0122] Specific examples

[0123] For example, consider the case where a user wants to check the reliability of a news article. The user copies the URL of the news article and pastes it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score as a bar chart. The user can use this result to determine whether the news article is reliable or not.

[0124] In this way, the system of the present invention allows users to easily evaluate and confirm the reliability of information on the Internet, thereby improving the accuracy of information and preventing the spread of misinformation.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] The user enters the URL or text for which they want to rate the trustworthiness into the input screen. They do this by cutting and pasting the URL or text into the text box and pressing the "Rate" button. The input can be a URL or text. This provides the system with specific information on which the user wants to make a judgment.

[0128] Step 2:

[0129] The terminal receives the URL or text entered by the user and prepares it to be sent to the server. This is done using an HTTP POST request. The input is the URL or text entered by the user, and the R output is a well-formed HTTP request. Along the way, it checks for errors and formats the request.

[0130] Step 3:

[0131] The server receives the HTTP request sent from the device. It extracts the URL or text information in the request and prepares it to be passed to the generative AI model. The input is the HTTP request received from the device, and the output is the prompt text required for analysis. In this step, the URL is combined with the prompt text "Please rate the credibility of this news article. Link:".

[0132] Step 4:

[0133] The server passes the prompt to a generative AI model, which analyzes the URL or text content. The analysis is performed by the AI ​​and a reliability score is calculated. The input is the generated prompt, and the output is the reliability score as the analysis result. During this process, the AI ​​model performs calculations such as evaluating and comparing the content of the text.

[0134] Step 5:

[0135] The server receives the analysis results obtained by the generative AI model and calculates the reliability score. The input is the analysis data from the AI ​​model, and the output is a reliability score (%). Here, the level of reliability is quantified and expressed as a unified score.

[0136] Step 6:

[0137] The server returns the calculated reliability score in JSON format to the terminal. The input is the reliability score, and the output is the response data in JSON format. In this step, the returned data is sent to the terminal.

[0138] Step 7:

[0139] The terminal analyzes the reliability scores received from the server and displays them on the user interface. The reliability scores are visually displayed using bar charts, colored bars, etc. The input is the JSON response data from the server, and the output is a visual representation of the reliability score. During this process, the display format is adjusted to make the results easy for users to intuitively understand.

[0140] Step 8:

[0141] The user checks the displayed reliability score and evaluates the reliability of the information. The input is the displayed reliability score, and the final output is the user's information evaluation result. The user uses the reliability score to determine whether the input URL or text is trustworthy.

[0142] In this way, the data input and output are clearly defined at each processing step, and specific operations are performed, allowing users to easily and quickly evaluate the reliability of information on the Internet.

[0143] (Application example 1)

[0144] 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."

[0145] Systems for evaluating the reliability of information on the Internet allow users to easily verify the reliability of information, but until now they have been limited to devices such as PCs and smartphones. This has made it difficult to visually verify the reliability of information in real time. In addition, there are limited ways for users to verify the reliability of product reviews and descriptions in a virtual environment, which has resulted in low user convenience.

[0146] 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.

[0147] In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text entered by a user, a means for analyzing the content of the received URL or text and evaluating its reliability, a means for displaying a reliability score of the analysis result, a means for receiving information in real time through the user's visual device, a means for transmitting information captured on the visual device to the server, and a means for displaying the reliability score returned from the server on the visual device, thereby enabling users to visually check the reliability of product reviews and descriptions in real time in a virtual store.

[0148] The "Internet" is an information and communications network that interconnects computer networks around the world.

[0149] "Reliability of information" refers to assessing whether the information is accurate and factual.

[0150] A "URL" is a uniform resource locator used to identify a particular resource or page on the Internet.

[0151] "Text" means information expressed as a string of characters.

[0152] A "visual device" is a device that allows a user to visually check information, and in the present invention, this mainly refers to smart glasses and head-mounted displays.

[0153] A "generative AI model" refers to a model that uses artificial intelligence to analyze information and evaluate the reliability of its content.

[0154] "Analysis" refers to the process of deciphering and understanding the content of information.

[0155] A "reliability score" is a numerical representation of the reliability of specific information, with a higher score indicating higher reliability.

[0156] "Virtual store" refers to a shopping environment that exists in a virtual space rather than an actual physical store.

[0157] System Program Overview

[0158] In this invention, a system for evaluating the reliability of information and displaying it in real time is constructed using the following hardware and software.

[0159] Server: Analyzes information, evaluates reliability, and returns results

[0160] Visual devices: smart glasses and head-mounted displays

[0161] Generative AI models: used for information analysis and reliability assessment

[0162] Hardware and software usage

[0163] 1. Camera input: A camera mounted on the vision device captures the information the user sees (e.g., product reviews and descriptions in a virtual store).

[0164] 2. Information analysis: The captured text information is sent to the server as an HTTP request.

[0165] 3. Trustworthiness assessment: The text is analyzed using a generative AI model on the server side to calculate a trust score.

[0166] 4. Displaying the results: The returned reliability score is displayed on the visual device's display, allowing the user to check the reliability of the information in real time.

[0167] Specific examples

[0168] Scenario 1: Product evaluation in a virtual store

[0169] When a user visits the virtual shopping mall, the camera on the vision device captures the product page and automatically extracts reviews and descriptions. The information sent to the server is analyzed using a generative AI model to calculate a reliability score. For example, if the review "This smartphone has great features" is rated as 85% reliable, the vision device's display will show "Review reliability: 85%."

[0170] Example prompts for generative AI models

[0171] Prompt: "Rate the credibility of the following text: 'This smartphone has great features.'"

[0172] Implementation flow

[0173] The server plays a central role in the reliability evaluation, and users can check the reliability score of information in real time through visual devices, allowing them to make decisions based on reliable information.

[0174] In this way, by using the system of the present invention, users can evaluate the reliability of information in real time even in a virtual environment, and enjoy shopping with peace of mind based on reliable information.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] A user browses products in a virtual store.

[0178] Input: The user wears a visual device (smart glasses or a head-mounted display) and selects and browses products in the virtual environment.

[0179] Action: The vision device takes a camera capture of the product page.

[0180] Step 2:

[0181] The visual device extracts the captured text information.

[0182] Input: Camera captured image of product page.

[0183] Data processing: Uses OCR (Optical Character Recognition) technology to extract text from images.

[0184] Output: Extracted text information (e.g. product reviews and descriptions).

[0185] Step 3:

[0186] The terminal (visual device) transmits the extracted text information to the server.

[0187] Input: The extracted text information.

[0188] Data operation: Construct an HTTP request and send it including the text information.

[0189] Output: Text information sent to the server.

[0190] Step 4:

[0191] The server analyzes the received text information and calculates a reliability score.

[0192] Input: Text information sent from the device.

[0193] Data Computing: Analyzes text using a generative AI model to generate prompts.

[0194] Example prompt: "Please rate the credibility of the following text: 'This smartphone has great features.'"

[0195] Data processing: A generative AI model analyzes the text and generates a reliability score.

[0196] Output: A confidence score (e.g. 85%).

[0197] Step 5:

[0198] The server returns a reliability score of the analysis result to the terminal (visual device).

[0199] Input: Confidence score.

[0200] Data calculation: Construct a confidence score as an HTTP response.

[0201] Output: A response containing the confidence score.

[0202] Step 6:

[0203] The reliability score obtained by the terminal (visual device) is displayed to the user.

[0204] Input: The confidence score returned by the server.

[0205] Data Calculation: Converting confidence scores into a visually understandable format (e.g., colored bar graphs).

[0206] Output: The visual device display shows "Review Confidence: 85%."

[0207] This allows users to visually check the reliability of product reviews and descriptions in real time through visual devices, enabling them to make decisions based on highly reliable information.

[0208] 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.

[0209] The present invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state. Specific embodiments of this system are described below.

[0210] Server-side behavior

[0211] The server receives the URL or text entered by the user, analyzes it, and plays a central role in assessing its trustworthiness. It also uses an emotion engine to recognize the user's emotions and reflect them in the assessment results.

[0212] Information analysis and reliability assessment

[0213] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[0214] Emotion recognition by emotion engine

[0215] The server uses an emotion engine to recognize the user's emotions based on the user's input, past behavioral data, and reactions. This emotion recognition grasps emotions that change in real time depending on the user's text input and the information they come into contact with.

[0216] Returning the results

[0217] After obtaining the analysis and emotion recognition results, the server returns the results to the user, along with a confidence score and an appropriate response message based on the result.

[0218] Operation on the terminal side

[0219] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[0220] Providing a user interface

[0221] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[0222] Sending information

[0223] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0224] Displaying the results

[0225] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[0226] User operation

[0227] The user performs direct operations to use the system, including the following:

[0228] Entering information

[0229] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[0230] Checking the results

[0231] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[0232] Specific examples

[0233] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, "80% reliability," and a message corresponding to the emotion are displayed on the user's device. For example, the message may read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[0234] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and provides appropriate feedback according to the user's emotional state, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[0235] The processing flow will be explained below.

[0236] Step 1: Enter your information

[0237] The user enters the URL or text of an online news article or social media post, accesses the system's input screen, pastes the URL or text into the text box, and presses the "Rate" button.

[0238] Step 2: Submit your information

[0239] The device receives the URL or text entered by the user, packages the received information in JSON format or similar, and sends it to the server using an HTTP POST request.

[0240] Step 3: Receiving the request

[0241] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL or text to be evaluated.

[0242] Step 4: Gather information

[0243] The server then performs web scraping or API requests to gather information from the extracted URLs, specifically the content of news articles retrieved from the internet.

[0244] Step 5: Pre-analysis processing using generative AI

[0245] The server preprocesses the retrieved news articles and text content, including text normalization, removal of unnecessary data, and language identification. For example, HTML tags are removed from news article text.

[0246] Step 6: Reliability assessment

[0247] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and generates a score of "80% reliability."

[0248] Step 7: Emotion Recognition with the Emotion Engine

[0249] The server uses an emotion engine to recognize the user's emotions based on their past behavioral data and real-time reactions, including micro-facial expressions when users enter text or browse information.

[0250] Step 8: Packaging the evaluation results

[0251] The server packages the generated confidence score and the emotion recognition result from the emotion engine in JSON format. For example, it generates a JSON object containing a confidence score of 80% and an emotional state of "user is worried."

[0252] Step 9: Sending the results

[0253] The server then returns the packaged evaluation results and emotion recognition results to the device as an HTTP response.

[0254] Step 10: Receiving the results

[0255] The device receives the HTTP response sent back from the server, analyzes the response content, and parses the JSON data to extract the confidence score and emotion recognition results.

[0256] Step 11: View the results

[0257] The device displays the reliability score and emotion recognition results in the user interface, including text indicating a reliability score of 80% and a message corresponding to the emotion (e.g., "The reliability of this news article is 80%. If you are concerned, please check other reliable sources.").

[0258] Step 12: Check the evaluation results

[0259] The user can then review the results of the trust assessment and receive appropriate feedback based on their emotions, and can take action such as rechecking or finding another source of information.

[0260] These are the specific processing steps from user input to display of the reliability score and emotion recognition results. This system provides an effective means for users to easily evaluate the reliability of information on websites and social networking sites and receive appropriate feedback based on their emotions.

[0261] Example 2

[0262] 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."

[0263] It is difficult to distinguish reliable information from the vast amount of information on the Internet, and especially in today's world where fake news and misinformation are on the rise, a system that allows users to easily evaluate information that is reliable is needed. In addition, it is necessary to provide feedback according to the user's emotional state so that appropriate responses can be made that take into account how the information is received.

[0264] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and evaluating the reliability, a means for displaying a reliability score of the analysis result, a means for recognizing emotions based on the user's input information and past behavioral data, and a means for generating and displaying a feedback message based on the recognized emotions. This allows the user to easily evaluate the reliability of information on the Internet and receive appropriate feedback according to their emotional state.

[0265] The "Internet" is a communications network that uses standard protocols to connect computer networks worldwide.

[0266] "Information" is data accessible on the Internet, such as text, images, and video.

[0267] "Credibility" is the measure of whether information is accurate or whether its source is trustworthy.

[0268] "User" means a person who uses this system to evaluate the reliability of information on the Internet.

[0269] A "URL" is a Uniform Resource Locator that identifies the location of information on the Internet.

[0270] "Text" refers to data consisting of a string of characters, and is generally expressed as a sentence.

[0271] "Means of receiving" refers to the method by which the server obtains the URL or text entered by the user.

[0272] "Analysis" is the process of evaluating the content of input information and determining its reliability.

[0273] "Generation" refers to creating new data, such as reliability scores or messages, based on the analysis results.

[0274] "Display means" refers to a method for providing an interface for showing analysis results and feedback messages to the user.

[0275] A "generative artificial intelligence model," also known as a generative AI model, is a machine learning model that analyzes text and data to generate new data.

[0276] "Emotion recognition" is a technology that detects a user's current emotional state by analyzing the user's input and behavioral data.

[0277] A "feedback message" is advice or information provided to the user based on the analysis results or emotion recognition results.

[0278] This invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state.

[0279] System configuration

[0280] This system mainly consists of three main components: a server, a terminal, and a user.

[0281] Server Configuration

[0282] The server consists of hardware and software that provides the following functions:

[0283] 1. Information receiving function: A function to receive URL or text information entered by the user.

[0284] 2. Information analysis function: A function that analyzes received URLs and text information and evaluates their reliability. This analysis uses a generative AI model (for example, a general generative AI model or natural language processing technology).

[0285] 3. Emotion recognition function: A function that recognizes the user's emotions using an emotion engine (e.g., a general emotion recognition API) based on the user's input information and past behavioral data.

[0286] 4. Result generation function: A function that generates evaluation results and appropriate feedback messages based on the reliability score and emotion recognition results.

[0287] 5. Result return function: A function that returns analysis results and emotion recognition results to the user.

[0288] Device configuration

[0289] A terminal is a device that a user uses to operate the system and provides the following functions:

[0290] 1. User interface: Provide an interface that includes a text box for users to enter the URL or text they want to rate, and a submit button.

[0291] 2. Information transmission function: A function that sends the URL or text entered by the user to the server using an HTTP request.

[0292] 3. Result display function: A function that displays the reliability evaluation results and emotion recognition results returned from the server on the user interface.

[0293] User operations

[0294] The user operates the system using a terminal and evaluates the reliability of information using the following procedure.

[0295] 1. Entering information: The user enters the URL or text for which they want to rate the trustworthiness into the system's input screen and presses the "Rate" button.

[0296] 2. Check the results: Check the reliability evaluation results and emotion recognition results returned from the server on the screen. Based on the displayed reliability score and emotion-based feedback, you can decide whether the information is trustworthy or not.

[0297] Hardware and software used

[0298] Server: A cloud server or dedicated server for running high-performance analysis capabilities and multi-function APIs.

[0299] Generative AI model: A general generative AI model, specifically a model based on natural language processing technology (e.g., OpenAI (registered trademark) model).

[0300] Emotion recognition engine: A common emotion recognition API (e.g., Microsoft® Azure® Emotion API).

[0301] Device: Any device that can connect to the internet, such as a PC, tablet, or smartphone.

[0302] Specific examples

[0303] For example, if a user wants to check the reliability of a news article, they paste the URL of the news article into the system's input screen and press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, a message corresponding to the emotion, such as "80% reliability," is displayed on the user's device. For example, the message might read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources." In this way, users can easily evaluate the reliability of information on the Internet and receive appropriate feedback based on their emotional state.

[0304] This system can curb the spread of fake news and misinformation and disseminate reliable information.

[0305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0306] Program processing flow

[0307] Step 1: Accept information input

[0308] User behavior

[0309] The user enters the URL or text for which they want to rate trustworthiness into the device's input screen and presses the "Rate" button. This input screen has a text box where the user can enter the information to be rated. For example, they enter the URL of a news article, "https: / / example.com / news-article".

[0310] Input: URL or text

[0311] Output: Input completion status to terminal

[0312] Step 2: Submit your input

[0313] Operation on the terminal side

[0314] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user. For example, the URL of a news article is sent to the server in an HTTP POST request.

[0315] Input: URL or text entered by the user

[0316] Output: HTTP request to the server

[0317] Step 3: Analyze input information and assess its reliability

[0318] Server-side behavior

[0319] The server analyzes the received information and evaluates its reliability. This analysis is performed using a generative AI model (e.g., a general generative AI model). Specifically, the server inputs the received URL or text as a prompt into the generative AI model, which then analyzes the content and calculates a reliability score. For example, official announcements from public institutions and reports from major media outlets are rated as highly reliable, while anonymous blogs and social media posts are rated as less reliable.

[0320] Input: URL or text received from an HTTP request

[0321] Output: Confidence score

[0322] Step 4: Recognize emotions

[0323] Server-side behavior

[0324] The server uses an emotion engine (for example, a general emotion recognition API) to recognize the user's emotions based on the user's input information and past behavioral data. Specifically, the server passes the user's input text and past behavioral data to the emotion recognition API, which detects emotions in real time. For example, if the user uses emotional words, the emotion is recognized as "anger" or "anxiety."

[0325] Input: User input information, past behavior data

[0326] Output: Emotion recognition result

[0327] Step 5: Generating evaluation and emotion recognition results

[0328] Server-side behavior

[0329] The server integrates the reliability score and the emotion recognition results to generate an evaluation result and an appropriate feedback message, such as "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[0330] Input: Confidence score, emotion recognition result

[0331] Output: Evaluation results, feedback messages

[0332] Step 6: Returning the results

[0333] Server-side behavior

[0334] The server returns the generated evaluation results and emotion recognition results to the user. The returned information includes a confidence score and a feedback message based on the emotion. For example, a confidence score of "80%" and a feedback message are returned as an HTTP response.

[0335] Input: Evaluation results, feedback message

[0336] Output: HTTP response to the user

[0337] Step 7: View the results

[0338] Operation on the terminal side

[0339] The device displays the reliability evaluation results and emotion recognition results received from the server on the user interface. Specifically, the reliability score is displayed in a visually easy-to-understand format, along with an appropriate message according to the user's emotion. For example, "80% reliability" is displayed in large letters, with a message below it saying, "If you are concerned, please check other reliable sources of information."

[0340] Input: HTTP response from the server

[0341] Output: Confidence score and feedback message in the user interface

[0342] (Application example 2)

[0343] 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."

[0344] In recent years, the Internet has become overflowing with a wide variety of information, and product reviews, especially on online shopping sites, have a significant influence on product purchasing decisions. However, not all reviews are necessarily reliable, making it difficult for users to discern their authenticity. Furthermore, users are easily influenced by their own emotions and may make inappropriate decisions based on unreliable information. Therefore, there is a need for a system that allows users to accurately evaluate the reliability of information and receive appropriate feedback based on their own emotions.

[0345] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for evaluating and displaying the reliability of information on the Internet, means for receiving a URL or text entered by a user, means for analyzing the content of the received URL or text and evaluating the reliability, means for displaying a reliability score of the analysis result, means for recognizing the user's emotions, and means for providing feedback according to the recognized user emotions. This allows the user to easily evaluate the reliability of information and further to receive appropriate feedback according to their own emotions.

[0346] "Means for evaluating and displaying the reliability of information on the Internet" is a function that analyzes the reliability of information present on the Internet and visually presents the results to the user.

[0347] The "means for receiving a URL or text input by a user" is a function that allows a user to input a URL or text to be evaluated into the system and send it to the server.

[0348] "Means for analyzing the content of received URLs or text and evaluating its reliability" refers to a function that analyzes the content of URLs or text received by the server and evaluates the reliability of that information.

[0349] The "means for displaying the reliability score of the analysis result" is a function for displaying the score calculated as a result of the reliability evaluation on the user interface.

[0350] "Means for recognizing user emotions" refers to a function that analyzes emotions based on user input and behavioral data.

[0351] The "means for providing feedback according to the recognized user emotions" is a function for displaying appropriate messages or recommendations based on the user's emotions.

[0352] "Means using generative AI models" refers to functions that use machine learning algorithms to analyze information and evaluate its reliability.

[0353] "Means of using reliable and unreliable sources" refers to a function that refers to predefined reliable and unreliable sources as evaluation criteria.

[0354] To implement this invention, it is necessary to build a system in which the server, terminal, and user operate in cooperation with each other. To understand the operation of this system, the roles and processes of each will be explained.

[0355] Server Operation

[0356] The server is responsible for the following main functions:

[0357] 1. Information reliability assessment

[0358] The server receives the URL or text entered by the user, analyzes its content, and evaluates its trustworthiness. To evaluate trustworthiness, it uses a generative AI model. Specifically, it analyzes the text using a Python natural language processing library (e.g., spaCy or NLTK) and calculates a trustworthiness score based on the analysis.

[0359] 2. Emotion recognition

[0360] The server is equipped with an emotion engine that analyzes emotions based on user input and behavioral data. For example, it analyzes the types of reviews that users frequently read, their completion rate, and the length of time they spend on the site. This is done using machine learning models (such as TENSORFLOW (registered trademark) and PyTorch).

[0361] 3. Providing Feedback

[0362] The server generates appropriate feedback for the user based on the reliability evaluation result and emotion recognition result. This feedback message is customized according to the emotion.

[0363] Device behavior

[0364] The terminal provides an interface for the user to interact with the system. The specific operation is as follows:

[0365] 1. Providing a user interface

[0366] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[0367] 2. Transmission of information

[0368] The terminal sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0369] 3. Displaying the results

[0370] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[0371] User operations

[0372] The user performs direct operations to use the system, including the following:

[0373] 1. Enter your information

[0374] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[0375] 2. Check the results

[0376] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[0377] Specific examples

[0378] For example, if a user wants to check the reliability of reviews on a product page, they copy the product's URL, paste it into the system's input screen, and press the "Rate" button. The server retrieves the product's review information from the URL, analyzes its content using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message.

[0379] The evaluation result, "75% reliability," and a message based on the user's emotion are displayed on the user's device. For example, the message might read, "The reliability of the reviews for this product is 75%. You may be optimistic about purchasing it, but please also check other reviews."

[0380] Prompt Sentence Examples

[0381] An example of a prompt sentence to be input to a generative AI model is as follows:

[0382] While a user is browsing a product page, analyze all reviews on that page, calculate the review credibility score, analyze user sentiment, and generate appropriate feedback messages based on that sentiment.

[0383] This system allows users to easily evaluate the reliability of information and receive appropriate feedback based on their personal feelings.

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

[0385] Step 1:

[0386] The user enters the URL or text they want to rate on the system's input screen and presses the "Rate" button. The entered information is sent to the terminal and then sent to the server as an HTTP request.

[0387] (Input) User URL or text

[0388] (Output) HTTP request

[0389] Step 2:

[0390] The server analyzes the HTTP request received from the device and extracts the URL or text data, then inputs the obtained data into a generative AI model to analyze the text content.

[0391] (Input) URL or text data in the HTTP request

[0392] (Output) Intermediate dataset of analysis results

[0393] Step 3:

[0394] The server evaluates the reliability of the received information based on the results of analysis using the generative AI model and calculates a reliability score.

[0395] (Input) Intermediate dataset of analysis results

[0396] (Output) Confidence score

[0397] Step 4:

[0398] The server uses an emotion engine to recognize the user's emotions based on the user's past behavioral data and current input data.

[0399] (Input) User's past behavior data and current input data

[0400] (Output) User emotion recognition results

[0401] Step 5:

[0402] The server integrates the confidence score with the emotion recognition result to generate a feedback message, which is customized according to the user's emotional state.

[0403] (Input) Reliability score, emotion recognition result

[0404] (Output) Feedback message

[0405] Step 6:

[0406] The server sends the reliability score and the feedback message together to the terminal.

[0407] (Input) Feedback message

[0408] (Output) HTTP response

[0409] Step 7:

[0410] The terminal receives the HTTP response from the server and displays the reliability score and feedback message on the user interface. The user can check the reliability of the information by referring to the reliability score and feedback message.

[0411] (Input) Confidence score and feedback message in the HTTP response

[0412] (Output) The confidence score and feedback message displayed in the user interface

[0413] 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.

[0414] 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.

[0415] 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.

[0416] [Second embodiment]

[0417] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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).

[0423] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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."

[0429] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[0430] Server-side behavior

[0431] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following actions based on the entered information:

[0432] Information analysis and reliability assessment

[0433] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[0434] Returning the results

[0435] After the analysis results are obtained, the server returns them to the user with a reliability score, expressed as a percentage. The higher the score, the more reliable the information is.

[0436] Operation on the terminal side

[0437] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[0438] Providing a user interface

[0439] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[0440] Sending information

[0441] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0442] Displaying the results

[0443] After the server returns the results of the trust assessment, the device displays the results on the user interface. The trust scores are displayed in a visually easy-to-understand format (e.g., a bar chart or a colored bar).

[0444] User operation

[0445] The user performs direct operations to use the system, including the following:

[0446] Entering information

[0447] Users enter the URL or text they want to rate on the system's input screen, and when they're done, they press the "Rate" button to submit the information.

[0448] Checking the results

[0449] The user checks the credibility evaluation results returned from the server on the screen and uses the displayed credibility score to determine the accuracy of the information.

[0450] Specific examples

[0451] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Evaluate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score. The user can use this result to determine whether the news article is reliable or not.

[0452] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and check its reliability score, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[0453] The processing flow will be explained below.

[0454] Step 1: Input from the user

[0455] The user enters the URL or text (such as a social media post) of the news article they want to rate into the system's input screen and presses the "Rate" button. In the example where a user enters the URL of a news article, they copy the URL of the news article they found in their browser, paste it into the system's input box, and press the submit button.

[0456] Step 2: Submit your information

[0457] The terminal receives the URL or text entered by the user, then packages the received information in JSON format or similar and sends it to the server using an HTTP POST request. In this example, a JSON object containing the entered URL is created and sent to the server.

[0458] Step 3: Receiving the request on the server

[0459] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL to be evaluated.

[0460] Step 4: Gather information

[0461] The server then performs web scraping or API requests to retrieve information from the extracted URLs, which is the step of retrieving the content of the specified news article from the internet.

[0462] Step 5: Pre-analysis processing using generative AI

[0463] The server preprocesses the retrieved news article content, which includes text normalization, removal of unnecessary data, language identification, etc. For example, HTML tags are removed from the news article text and language filters are applied.

[0464] Step 6: Reliability assessment

[0465] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and returns a rating of "80% reliability."

[0466] Step 7: Packaging the evaluation results

[0467] The server packages the generated reliability score in JSON format, etc. It generates a JSON object containing a reliability score of 80% as the evaluation result.

[0468] Step 8: Sending the results

[0469] The server returns a JSON object containing the evaluation results to the terminal as an HTTP response.

[0470] Step 9: Receiving the results

[0471] The device receives the HTTP response from the server and analyzes the response content. Specifically, it parses the received JSON data and extracts the reliability score.

[0472] Step 10: View the results

[0473] The device displays the extracted reliability score on the user interface, using a text representation of a reliability score of 80% or a visually easy-to-understand bar chart.

[0474] Step 11: Check the evaluation results

[0475] The user checks the results of the reliability assessment displayed on the device. The user uses the displayed reliability score to determine whether the news article is trustworthy. In a specific example, the user sees a message saying "The reliability of this news article is 80%" and evaluates the accuracy of the information.

[0476] These are the specific processing steps from user input to display of the reliability score. This system provides users with an effective means to easily evaluate the reliability of information on websites and social media sites and obtain accurate information.

[0477] Example 1

[0478] 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."

[0479] The Internet is overflowing with a wide variety of information, including unreliable information and fake news. This makes it difficult for users to determine which information is accurate and reliable. In particular, there is a need for a method to quickly evaluate and present the reliability of important news and information that requires fact-checking.

[0480] 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.

[0481] In this invention, the server includes a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and using a generative AI model to evaluate reliability, a means for calculating a reliability score, and a means for displaying the calculated reliability score, thereby enabling a user to easily and quickly evaluate the reliability of a URL or text and visually confirm the result.

[0482] "User" is the subject who uses the system to evaluate the reliability of URLs and text.

[0483] A "URL" is a uniform resource locator for specifying resources on the Internet.

[0484] "Text" is character string data to be evaluated.

[0485] A "server" is a central computing unit that analyzes URLs and text received from users and evaluates their trustworthiness.

[0486] "Means of receiving" refers to the method by which the server obtains the URL or text sent by the user.

[0487] A "generative AI model" is a computational model that uses artificial intelligence to analyze incoming URLs and text. For example, it is an AI that performs natural language processing.

[0488] "Analysis" refers to the act of using a generative AI model to examine the content of received URLs and text and assess their reliability.

[0489] A "means for assessing trustworthiness" is a method for determining the trustworthiness of a URL or text using a generative AI model.

[0490] A "reliability score" is a numerical expression of an evaluation based on the analysis results, and is an index showing the reliability of information.

[0491] The "means for calculating" is a method for deriving a reliability score based on the analysis results.

[0492] The "means for displaying" is a method for presenting the reliability score in a format that is easy for the user to understand.

[0493] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[0494] Server-side behavior

[0495] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following operations:

[0496] Information analysis and reliability assessment

[0497] The server analyzes the URLs and text received from users using a generative AI model (e.g., a generative AI model). This model performs detailed data analysis to assess trustworthiness. The analysis process generates a trustworthiness score based on highly reliable sources (such as official announcements from public institutions and major media outlets) and less reliable sources (such as anonymous blogs and social media posts).

[0498] For example, the prompt sentence is "Please rate the credibility of this news article. Link: https: / / example.com / news-article" and the generative AI model uses the analysis results to calculate a credibility score.

[0499] Returning the results

[0500] The server returns a credibility score based on the analysis to the user, expressed as a percentage, with higher scores indicating greater credibility.

[0501] Operation on the terminal side

[0502] The terminal is a device that provides an interface for the user to operate the system, and performs the following operations.

[0503] Providing a user interface

[0504] The terminal provides a text box and a submit button for users to enter the URL or text they want to rate, allowing them to easily enter the information they want to rate.

[0505] Sending information

[0506] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0507] Displaying the results

[0508] After receiving the result of the trustworthiness evaluation returned from the server, the terminal visually displays the result on the user interface in a visually easy-to-understand format such as a bar chart or a colored bar graph.

[0509] User operation

[0510] The user uses the system to perform the following operations:

[0511] Entering information

[0512] Users enter the URL or text they want to evaluate for trustworthiness into the input screen. This can be done using a browser or a dedicated application.

[0513] Checking the results

[0514] The user checks the reliability evaluation results returned from the server on the screen and uses the displayed reliability score to determine the accuracy of the information being evaluated.

[0515] Specific examples

[0516] For example, consider the case where a user wants to check the reliability of a news article. The user copies the URL of the news article and pastes it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score as a bar chart. The user can use this result to determine whether the news article is reliable or not.

[0517] In this way, the system of the present invention allows users to easily evaluate and confirm the reliability of information on the Internet, thereby improving the accuracy of information and preventing the spread of misinformation.

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

[0519] Step 1:

[0520] The user enters the URL or text for which they want to rate the trustworthiness into the input screen. They do this by cutting and pasting the URL or text into the text box and pressing the "Rate" button. The input can be a URL or text. This provides the system with specific information on which the user wants to make a judgment.

[0521] Step 2:

[0522] The terminal receives the URL or text entered by the user and prepares it to be sent to the server. This is done using an HTTP POST request. The input is the URL or text entered by the user, and the R output is a well-formed HTTP request. Along the way, it checks for errors and formats the request.

[0523] Step 3:

[0524] The server receives the HTTP request sent from the device. It extracts the URL or text information in the request and prepares it to be passed to the generative AI model. The input is the HTTP request received from the device, and the output is the prompt text required for analysis. In this step, the URL is combined with the prompt text "Please rate the credibility of this news article. Link:".

[0525] Step 4:

[0526] The server passes the prompt to a generative AI model, which analyzes the URL or text content. The analysis is performed by the AI ​​and a reliability score is calculated. The input is the generated prompt, and the output is the reliability score as the analysis result. During this process, the AI ​​model performs calculations such as evaluating and comparing the content of the text.

[0527] Step 5:

[0528] The server receives the analysis results obtained by the generative AI model and calculates the reliability score. The input is the analysis data from the AI ​​model, and the output is a reliability score (%). Here, the level of reliability is quantified and expressed as a unified score.

[0529] Step 6:

[0530] The server returns the calculated reliability score in JSON format to the terminal. The input is the reliability score, and the output is the response data in JSON format. In this step, the returned data is sent to the terminal.

[0531] Step 7:

[0532] The terminal analyzes the reliability scores received from the server and displays them on the user interface. The reliability scores are visually displayed using bar charts, colored bars, etc. The input is the JSON response data from the server, and the output is a visual representation of the reliability score. During this process, the display format is adjusted to make the results easy for users to intuitively understand.

[0533] Step 8:

[0534] The user checks the displayed reliability score and evaluates the reliability of the information. The input is the displayed reliability score, and the final output is the user's information evaluation result. The user uses the reliability score to determine whether the input URL or text is trustworthy.

[0535] In this way, the data input and output are clearly defined at each processing step, and specific operations are performed, allowing users to easily and quickly evaluate the reliability of information on the Internet.

[0536] (Application example 1)

[0537] 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."

[0538] Systems for evaluating the reliability of information on the Internet allow users to easily verify the reliability of information, but until now they have been limited to devices such as PCs and smartphones. This has made it difficult to visually verify the reliability of information in real time. In addition, there are limited ways for users to verify the reliability of product reviews and descriptions in a virtual environment, which has resulted in low user convenience.

[0539] 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.

[0540] In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text entered by a user, a means for analyzing the content of the received URL or text and evaluating its reliability, a means for displaying a reliability score of the analysis result, a means for receiving information in real time through the user's visual device, a means for transmitting information captured on the visual device to the server, and a means for displaying the reliability score returned from the server on the visual device, thereby enabling users to visually check the reliability of product reviews and descriptions in real time in a virtual store.

[0541] The "Internet" is an information and communications network that interconnects computer networks around the world.

[0542] "Reliability of information" refers to assessing whether the information is accurate and factual.

[0543] A "URL" is a uniform resource locator used to identify a particular resource or page on the Internet.

[0544] "Text" means information expressed as a string of characters.

[0545] A "visual device" is a device that allows a user to visually check information, and in the present invention, this mainly refers to smart glasses and head-mounted displays.

[0546] A "generative AI model" refers to a model that uses artificial intelligence to analyze information and evaluate the reliability of its content.

[0547] "Analysis" refers to the process of deciphering and understanding the content of information.

[0548] A "reliability score" is a numerical representation of the reliability of specific information, with a higher score indicating higher reliability.

[0549] "Virtual store" refers to a shopping environment that exists in a virtual space rather than an actual physical store.

[0550] System Program Overview

[0551] In this invention, a system for evaluating the reliability of information and displaying it in real time is constructed using the following hardware and software.

[0552] Server: Analyzes information, evaluates reliability, and returns results

[0553] Visual devices: smart glasses and head-mounted displays

[0554] Generative AI models: used for information analysis and reliability assessment

[0555] Hardware and software usage

[0556] 1. Camera input: A camera mounted on the vision device captures the information the user sees (e.g., product reviews and descriptions in a virtual store).

[0557] 2. Information analysis: The captured text information is sent to the server as an HTTP request.

[0558] 3. Trustworthiness assessment: The text is analyzed using a generative AI model on the server side to calculate a trust score.

[0559] 4. Displaying the results: The returned reliability score is displayed on the visual device's display, allowing the user to check the reliability of the information in real time.

[0560] Specific examples

[0561] Scenario 1: Product evaluation in a virtual store

[0562] When a user visits the virtual shopping mall, the camera on the vision device captures the product page and automatically extracts reviews and descriptions. The information sent to the server is analyzed using a generative AI model to calculate a reliability score. For example, if the review "This smartphone has great features" is rated as 85% reliable, the vision device's display will show "Review reliability: 85%."

[0563] Example prompts for generative AI models

[0564] Prompt: "Rate the credibility of the following text: 'This smartphone has great features.'"

[0565] Implementation flow

[0566] The server plays a central role in the reliability evaluation, and users can check the reliability score of information in real time through visual devices, allowing them to make decisions based on reliable information.

[0567] In this way, by using the system of the present invention, users can evaluate the reliability of information in real time even in a virtual environment, and enjoy shopping with peace of mind based on reliable information.

[0568] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0569] Step 1:

[0570] A user browses products in a virtual store.

[0571] Input: The user wears a visual device (smart glasses or a head-mounted display) and selects and browses products in the virtual environment.

[0572] Action: The vision device takes a camera capture of the product page.

[0573] Step 2:

[0574] The visual device extracts the captured text information.

[0575] Input: Camera captured image of product page.

[0576] Data processing: Uses OCR (Optical Character Recognition) technology to extract text from images.

[0577] Output: Extracted text information (e.g. product reviews and descriptions).

[0578] Step 3:

[0579] The terminal (visual device) transmits the extracted text information to the server.

[0580] Input: The extracted text information.

[0581] Data operation: Construct an HTTP request and send it including the text information.

[0582] Output: Text information sent to the server.

[0583] Step 4:

[0584] The server analyzes the received text information and calculates a reliability score.

[0585] Input: Text information sent from the device.

[0586] Data Computing: Analyzes text using a generative AI model to generate prompts.

[0587] Example prompt: "Please rate the credibility of the following text: 'This smartphone has great features.'"

[0588] Data processing: A generative AI model analyzes the text and generates a reliability score.

[0589] Output: A confidence score (e.g. 85%).

[0590] Step 5:

[0591] The server returns a reliability score of the analysis result to the terminal (visual device).

[0592] Input: Confidence score.

[0593] Data calculation: Construct a confidence score as an HTTP response.

[0594] Output: A response containing the confidence score.

[0595] Step 6:

[0596] The reliability score obtained by the terminal (visual device) is displayed to the user.

[0597] Input: The confidence score returned by the server.

[0598] Data Calculation: Converting confidence scores into a visually understandable format (e.g., colored bar graphs).

[0599] Output: The visual device display shows "Review Confidence: 85%."

[0600] This allows users to visually check the reliability of product reviews and descriptions in real time through visual devices, enabling them to make decisions based on highly reliable information.

[0601] 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.

[0602] The present invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state. Specific embodiments of this system are described below.

[0603] Server-side behavior

[0604] The server receives the URL or text entered by the user, analyzes it, and plays a central role in assessing its trustworthiness. It also uses an emotion engine to recognize the user's emotions and reflect them in the assessment results.

[0605] Information analysis and reliability assessment

[0606] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[0607] Emotion recognition by emotion engine

[0608] The server uses an emotion engine to recognize the user's emotions based on the user's input, past behavioral data, and reactions. This emotion recognition grasps emotions that change in real time depending on the user's text input and the information they come into contact with.

[0609] Returning the results

[0610] After obtaining the analysis and emotion recognition results, the server returns the results to the user, along with a confidence score and an appropriate response message based on the result.

[0611] Operation on the terminal side

[0612] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[0613] Providing a user interface

[0614] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[0615] Sending information

[0616] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0617] Displaying the results

[0618] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[0619] User operation

[0620] The user performs direct operations to use the system, including the following:

[0621] Entering information

[0622] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[0623] Checking the results

[0624] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[0625] Specific examples

[0626] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, "80% reliability," and a message corresponding to the emotion are displayed on the user's device. For example, the message may read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[0627] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and provides appropriate feedback according to the user's emotional state, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[0628] The processing flow will be explained below.

[0629] Step 1: Enter your information

[0630] The user enters the URL or text of an online news article or social media post, accesses the system's input screen, pastes the URL or text into the text box, and presses the "Rate" button.

[0631] Step 2: Submit your information

[0632] The device receives the URL or text entered by the user, packages the received information in JSON format or similar, and sends it to the server using an HTTP POST request.

[0633] Step 3: Receiving the request

[0634] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL or text to be evaluated.

[0635] Step 4: Gather information

[0636] The server then performs web scraping or API requests to gather information from the extracted URLs, specifically the content of news articles retrieved from the internet.

[0637] Step 5: Pre-analysis processing using generative AI

[0638] The server preprocesses the retrieved news articles and text content, including text normalization, removal of unnecessary data, and language identification. For example, HTML tags are removed from news article text.

[0639] Step 6: Reliability assessment

[0640] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and generates a score of "80% reliability."

[0641] Step 7: Emotion Recognition with the Emotion Engine

[0642] The server uses an emotion engine to recognize the user's emotions based on their past behavioral data and real-time reactions, including micro-facial expressions when users enter text or browse information.

[0643] Step 8: Packaging the evaluation results

[0644] The server packages the generated confidence score and the emotion recognition result from the emotion engine in JSON format. For example, it generates a JSON object containing a confidence score of 80% and an emotional state of "user is worried."

[0645] Step 9: Sending the results

[0646] The server then returns the packaged evaluation results and emotion recognition results to the device as an HTTP response.

[0647] Step 10: Receiving the results

[0648] The device receives the HTTP response sent back from the server, analyzes the response content, and parses the JSON data to extract the confidence score and emotion recognition results.

[0649] Step 11: View the results

[0650] The device displays the reliability score and emotion recognition results in the user interface, including text indicating a reliability score of 80% and a message corresponding to the emotion (e.g., "The reliability of this news article is 80%. If you are concerned, please check other reliable sources.").

[0651] Step 12: Check the evaluation results

[0652] The user can then review the results of the trust assessment and receive appropriate feedback based on their emotions, and can take action such as rechecking or finding another source of information.

[0653] These are the specific processing steps from user input to display of the reliability score and emotion recognition results. This system provides an effective means for users to easily evaluate the reliability of information on websites and social networking sites and receive appropriate feedback based on their emotions.

[0654] Example 2

[0655] 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."

[0656] It is difficult to distinguish reliable information from the vast amount of information on the Internet, and especially in today's world where fake news and misinformation are on the rise, a system that allows users to easily evaluate information that is reliable is needed. In addition, it is necessary to provide feedback according to the user's emotional state so that appropriate responses can be made that take into account how the information is received.

[0657] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and evaluating the reliability, a means for displaying a reliability score of the analysis result, a means for recognizing emotions based on the user's input information and past behavioral data, and a means for generating and displaying a feedback message based on the recognized emotions. This allows the user to easily evaluate the reliability of information on the Internet and receive appropriate feedback according to their emotional state.

[0658] The "Internet" is a communications network that uses standard protocols to connect computer networks worldwide.

[0659] "Information" is data accessible on the Internet, such as text, images, and video.

[0660] "Credibility" is the measure of whether information is accurate or whether its source is trustworthy.

[0661] "User" means a person who uses this system to evaluate the reliability of information on the Internet.

[0662] A "URL" is a Uniform Resource Locator that identifies the location of information on the Internet.

[0663] "Text" refers to data consisting of a string of characters, and is generally expressed as a sentence.

[0664] "Means of receiving" refers to the method by which the server obtains the URL or text entered by the user.

[0665] "Analysis" is the process of evaluating the content of input information and determining its reliability.

[0666] "Generation" refers to creating new data, such as reliability scores or messages, based on the analysis results.

[0667] "Display means" refers to a method for providing an interface for showing analysis results and feedback messages to the user.

[0668] A "generative artificial intelligence model," also known as a generative AI model, is a machine learning model that analyzes text and data to generate new data.

[0669] "Emotion recognition" is a technology that detects a user's current emotional state by analyzing the user's input and behavioral data.

[0670] A "feedback message" is advice or information provided to the user based on the analysis results or emotion recognition results.

[0671] This invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state.

[0672] System configuration

[0673] This system mainly consists of three main components: a server, a terminal, and a user.

[0674] Server Configuration

[0675] The server consists of hardware and software that provides the following functions:

[0676] 1. Information receiving function: A function to receive URL or text information entered by the user.

[0677] 2. Information analysis function: A function that analyzes received URLs and text information and evaluates their reliability. This analysis uses a generative AI model (for example, a general generative AI model or natural language processing technology).

[0678] 3. Emotion recognition function: A function that recognizes the user's emotions using an emotion engine (e.g., a general emotion recognition API) based on the user's input information and past behavioral data.

[0679] 4. Result generation function: A function that generates evaluation results and appropriate feedback messages based on the reliability score and emotion recognition results.

[0680] 5. Result return function: A function that returns analysis results and emotion recognition results to the user.

[0681] Device configuration

[0682] A terminal is a device that a user uses to operate the system and provides the following functions:

[0683] 1. User interface: Provide an interface that includes a text box for users to enter the URL or text they want to rate, and a submit button.

[0684] 2. Information transmission function: A function that sends the URL or text entered by the user to the server using an HTTP request.

[0685] 3. Result display function: A function that displays the reliability evaluation results and emotion recognition results returned from the server on the user interface.

[0686] User operations

[0687] The user operates the system using a terminal and evaluates the reliability of information using the following procedure.

[0688] 1. Entering information: The user enters the URL or text for which they want to rate the trustworthiness into the system's input screen and presses the "Rate" button.

[0689] 2. Check the results: Check the reliability evaluation results and emotion recognition results returned from the server on the screen. Based on the displayed reliability score and emotion-based feedback, you can decide whether the information is trustworthy or not.

[0690] Hardware and software used

[0691] Server: A cloud server or dedicated server for running high-performance analysis capabilities and multi-function APIs.

[0692] Generative AI models: Generative AI models in general, specifically models based on natural language processing techniques (e.g., OpenAI's models).

[0693] Emotion recognition engine: A common emotion recognition API (e.g., Microsoft Azure's Emotion API).

[0694] Device: Any device that can connect to the internet, such as a PC, tablet, or smartphone.

[0695] Specific examples

[0696] For example, if a user wants to check the reliability of a news article, they paste the URL of the news article into the system's input screen and press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, a message corresponding to the emotion, such as "80% reliability," is displayed on the user's device. For example, the message might read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources." In this way, users can easily evaluate the reliability of information on the Internet and receive appropriate feedback based on their emotional state.

[0697] This system can curb the spread of fake news and misinformation and disseminate reliable information.

[0698] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0699] Program processing flow

[0700] Step 1: Accept information input

[0701] User behavior

[0702] The user enters the URL or text for which they want to rate trustworthiness into the device's input screen and presses the "Rate" button. This input screen has a text box where the user can enter the information to be rated. For example, they enter the URL of a news article, "https: / / example.com / news-article".

[0703] Input: URL or text

[0704] Output: Input completion status to terminal

[0705] Step 2: Submit your input

[0706] Operation on the terminal side

[0707] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user. For example, the URL of a news article is sent to the server in an HTTP POST request.

[0708] Input: URL or text entered by the user

[0709] Output: HTTP request to the server

[0710] Step 3: Analyze input information and assess its reliability

[0711] Server-side behavior

[0712] The server analyzes the received information and evaluates its reliability. This analysis is performed using a generative AI model (e.g., a general generative AI model). Specifically, the server inputs the received URL or text as a prompt into the generative AI model, which then analyzes the content and calculates a reliability score. For example, official announcements from public institutions and reports from major media outlets are rated as highly reliable, while anonymous blogs and social media posts are rated as less reliable.

[0713] Input: URL or text received from an HTTP request

[0714] Output: Confidence score

[0715] Step 4: Recognize emotions

[0716] Server-side behavior

[0717] The server uses an emotion engine (for example, a general emotion recognition API) to recognize the user's emotions based on the user's input information and past behavioral data. Specifically, the server passes the user's input text and past behavioral data to the emotion recognition API, which detects emotions in real time. For example, if the user uses emotional words, the emotion is recognized as "anger" or "anxiety."

[0718] Input: User input information, past behavior data

[0719] Output: Emotion recognition result

[0720] Step 5: Generating evaluation and emotion recognition results

[0721] Server-side behavior

[0722] The server integrates the reliability score and the emotion recognition results to generate an evaluation result and an appropriate feedback message, such as "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[0723] Input: Confidence score, emotion recognition result

[0724] Output: Evaluation results, feedback messages

[0725] Step 6: Returning the results

[0726] Server-side behavior

[0727] The server returns the generated evaluation results and emotion recognition results to the user. The returned information includes a confidence score and a feedback message based on the emotion. For example, a confidence score of "80%" and a feedback message are returned as an HTTP response.

[0728] Input: Evaluation results, feedback message

[0729] Output: HTTP response to the user

[0730] Step 7: View the results

[0731] Operation on the terminal side

[0732] The device displays the reliability evaluation results and emotion recognition results received from the server on the user interface. Specifically, the reliability score is displayed in a visually easy-to-understand format, along with an appropriate message according to the user's emotion. For example, "80% reliability" is displayed in large letters, with a message below it saying, "If you are concerned, please check other reliable sources of information."

[0733] Input: HTTP response from the server

[0734] Output: Confidence score and feedback message in the user interface

[0735] (Application example 2)

[0736] 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."

[0737] In recent years, the Internet has become overflowing with a wide variety of information, and product reviews, especially on online shopping sites, have a significant influence on product purchasing decisions. However, not all reviews are necessarily reliable, making it difficult for users to discern their authenticity. Furthermore, users are easily influenced by their own emotions and may make inappropriate decisions based on unreliable information. Therefore, there is a need for a system that allows users to accurately evaluate the reliability of information and receive appropriate feedback based on their own emotions.

[0738] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for evaluating and displaying the reliability of information on the Internet, means for receiving a URL or text entered by a user, means for analyzing the content of the received URL or text and evaluating the reliability, means for displaying a reliability score of the analysis result, means for recognizing the user's emotions, and means for providing feedback according to the recognized user emotions. This allows the user to easily evaluate the reliability of information and further to receive appropriate feedback according to their own emotions.

[0739] "Means for evaluating and displaying the reliability of information on the Internet" is a function that analyzes the reliability of information present on the Internet and visually presents the results to the user.

[0740] The "means for receiving a URL or text input by a user" is a function that allows a user to input a URL or text to be evaluated into the system and send it to the server.

[0741] "Means for analyzing the content of received URLs or text and evaluating its reliability" refers to a function that analyzes the content of URLs or text received by the server and evaluates the reliability of that information.

[0742] The "means for displaying the reliability score of the analysis result" is a function for displaying the score calculated as a result of the reliability evaluation on the user interface.

[0743] "Means for recognizing user emotions" refers to a function that analyzes emotions based on user input and behavioral data.

[0744] The "means for providing feedback according to the recognized user emotions" is a function for displaying appropriate messages or recommendations based on the user's emotions.

[0745] "Means using generative AI models" refers to functions that use machine learning algorithms to analyze information and evaluate its reliability.

[0746] "Means of using reliable and unreliable sources" refers to a function that refers to predefined reliable and unreliable sources as evaluation criteria.

[0747] To implement this invention, it is necessary to build a system in which the server, terminal, and user operate in cooperation with each other. To understand the operation of this system, the roles and processes of each will be explained.

[0748] Server Operation

[0749] The server is responsible for the following main functions:

[0750] 1. Information reliability assessment

[0751] The server receives the URL or text entered by the user, analyzes its content, and evaluates its trustworthiness. To evaluate trustworthiness, it uses a generative AI model. Specifically, it analyzes the text using a Python natural language processing library (e.g., spaCy or NLTK) and calculates a trustworthiness score based on the analysis.

[0752] 2. Emotion recognition

[0753] The server is equipped with an emotion engine that analyzes emotions based on user input and behavioral data. For example, it analyzes the types of reviews users frequently read, their completion rate, and the duration of their stay. This is done using machine learning models (e.g., TensorFlow and PyTorch).

[0754] 3. Providing Feedback

[0755] The server generates appropriate feedback for the user based on the reliability evaluation result and emotion recognition result. This feedback message is customized according to the emotion.

[0756] Device behavior

[0757] The terminal provides an interface for the user to interact with the system. The specific operation is as follows:

[0758] 1. Providing a user interface

[0759] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[0760] 2. Transmission of information

[0761] The terminal sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0762] 3. Displaying the results

[0763] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[0764] User operations

[0765] The user performs direct operations to use the system, including the following:

[0766] 1. Enter your information

[0767] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[0768] 2. Check the results

[0769] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[0770] Specific examples

[0771] For example, if a user wants to check the reliability of reviews on a product page, they copy the product's URL, paste it into the system's input screen, and press the "Rate" button. The server retrieves the product's review information from the URL, analyzes its content using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message.

[0772] The evaluation result, "75% reliability," and a message based on the user's emotion are displayed on the user's device. For example, the message might read, "The reliability of the reviews for this product is 75%. You may be optimistic about purchasing it, but please also check other reviews."

[0773] Prompt Sentence Examples

[0774] An example of a prompt sentence to be input to a generative AI model is as follows:

[0775] While a user is browsing a product page, analyze all reviews on that page, calculate the review credibility score, analyze user sentiment, and generate appropriate feedback messages based on that sentiment.

[0776] This system allows users to easily evaluate the reliability of information and receive appropriate feedback based on their personal feelings.

[0777] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0778] Step 1:

[0779] The user enters the URL or text they want to rate on the system's input screen and presses the "Rate" button. The entered information is sent to the terminal and then sent to the server as an HTTP request.

[0780] (Input) User URL or text

[0781] (Output) HTTP request

[0782] Step 2:

[0783] The server analyzes the HTTP request received from the device and extracts the URL or text data, then inputs the obtained data into a generative AI model to analyze the text content.

[0784] (Input) URL or text data in the HTTP request

[0785] (Output) Intermediate dataset of analysis results

[0786] Step 3:

[0787] The server evaluates the reliability of the received information based on the results of analysis using the generative AI model and calculates a reliability score.

[0788] (Input) Intermediate dataset of analysis results

[0789] (Output) Confidence score

[0790] Step 4:

[0791] The server uses an emotion engine to recognize the user's emotions based on the user's past behavioral data and current input data.

[0792] (Input) User's past behavior data and current input data

[0793] (Output) User emotion recognition results

[0794] Step 5:

[0795] The server integrates the confidence score with the emotion recognition result to generate a feedback message, which is customized according to the user's emotional state.

[0796] (Input) Reliability score, emotion recognition result

[0797] (Output) Feedback message

[0798] Step 6:

[0799] The server sends the reliability score and the feedback message together to the terminal.

[0800] (Input) Feedback message

[0801] (Output) HTTP response

[0802] Step 7:

[0803] The terminal receives the HTTP response from the server and displays the reliability score and feedback message on the user interface. The user can check the reliability of the information by referring to the reliability score and feedback message.

[0804] (Input) Confidence score and feedback message in the HTTP response

[0805] (Output) The confidence score and feedback message displayed in the user interface

[0806] 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.

[0807] 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.

[0808] 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.

[0809] [Third embodiment]

[0810] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0811] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0812] 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).

[0813] 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.

[0814] 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.

[0815] 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).

[0816] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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."

[0822] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[0823] Server-side behavior

[0824] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following actions based on the entered information:

[0825] Information analysis and reliability assessment

[0826] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[0827] Returning the results

[0828] After the analysis results are obtained, the server returns them to the user with a reliability score, expressed as a percentage. The higher the score, the more reliable the information is.

[0829] Operation on the terminal side

[0830] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[0831] Providing a user interface

[0832] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[0833] Sending information

[0834] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0835] Displaying the results

[0836] After the server returns the results of the trust assessment, the device displays the results on the user interface. The trust scores are displayed in a visually easy-to-understand format (e.g., a bar chart or a colored bar).

[0837] User operation

[0838] The user performs direct operations to use the system, including the following:

[0839] Entering information

[0840] Users enter the URL or text they want to rate on the system's input screen, and when they're done, they press the "Rate" button to submit the information.

[0841] Checking the results

[0842] The user checks the credibility evaluation results returned from the server on the screen and uses the displayed credibility score to determine the accuracy of the information.

[0843] Specific examples

[0844] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Evaluate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score. The user can use this result to determine whether the news article is reliable or not.

[0845] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and check its reliability score, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[0846] The processing flow will be explained below.

[0847] Step 1: Input from the user

[0848] The user enters the URL or text (such as a social media post) of the news article they want to rate into the system's input screen and presses the "Rate" button. In the example where a user enters the URL of a news article, they copy the URL of the news article they found in their browser, paste it into the system's input box, and press the submit button.

[0849] Step 2: Submit your information

[0850] The terminal receives the URL or text entered by the user, then packages the received information in JSON format or similar and sends it to the server using an HTTP POST request. In this example, a JSON object containing the entered URL is created and sent to the server.

[0851] Step 3: Receiving the request on the server

[0852] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL to be evaluated.

[0853] Step 4: Gather information

[0854] The server then performs web scraping or API requests to retrieve information from the extracted URLs, which is the step of retrieving the content of the specified news article from the internet.

[0855] Step 5: Pre-analysis processing using generative AI

[0856] The server preprocesses the retrieved news article content, which includes text normalization, removal of unnecessary data, language identification, etc. For example, HTML tags are removed from the news article text and language filters are applied.

[0857] Step 6: Reliability assessment

[0858] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and returns a rating of "80% reliability."

[0859] Step 7: Packaging the evaluation results

[0860] The server packages the generated reliability score in JSON format, etc. It generates a JSON object containing a reliability score of 80% as the evaluation result.

[0861] Step 8: Sending the results

[0862] The server returns a JSON object containing the evaluation results to the terminal as an HTTP response.

[0863] Step 9: Receiving the results

[0864] The device receives the HTTP response from the server and analyzes the response content. Specifically, it parses the received JSON data and extracts the reliability score.

[0865] Step 10: View the results

[0866] The device displays the extracted reliability score on the user interface, using a text representation of a reliability score of 80% or a visually easy-to-understand bar chart.

[0867] Step 11: Check the evaluation results

[0868] The user checks the results of the reliability assessment displayed on the device. The user uses the displayed reliability score to determine whether the news article is trustworthy. In a specific example, the user sees a message saying "The reliability of this news article is 80%" and evaluates the accuracy of the information.

[0869] These are the specific processing steps from user input to display of the reliability score. This system provides users with an effective means to easily evaluate the reliability of information on websites and social media sites and obtain accurate information.

[0870] Example 1

[0871] 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."

[0872] The Internet is overflowing with a wide variety of information, including unreliable information and fake news. This makes it difficult for users to determine which information is accurate and reliable. In particular, there is a need for a method to quickly evaluate and present the reliability of important news and information that requires fact-checking.

[0873] 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.

[0874] In this invention, the server includes a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and using a generative AI model to evaluate reliability, a means for calculating a reliability score, and a means for displaying the calculated reliability score, thereby enabling a user to easily and quickly evaluate the reliability of a URL or text and visually confirm the result.

[0875] "User" is the subject who uses the system to evaluate the reliability of URLs and text.

[0876] A "URL" is a uniform resource locator for specifying resources on the Internet.

[0877] "Text" is character string data to be evaluated.

[0878] A "server" is a central computing unit that analyzes URLs and text received from users and evaluates their trustworthiness.

[0879] "Means of receiving" refers to the method by which the server obtains the URL or text sent by the user.

[0880] A "generative AI model" is a computational model that uses artificial intelligence to analyze incoming URLs and text. For example, it is an AI that performs natural language processing.

[0881] "Analysis" refers to the act of using a generative AI model to examine the content of received URLs and text and assess their reliability.

[0882] A "means for assessing trustworthiness" is a method for determining the trustworthiness of a URL or text using a generative AI model.

[0883] A "reliability score" is a numerical expression of an evaluation based on the analysis results, and is an index showing the reliability of information.

[0884] The "means for calculating" is a method for deriving a reliability score based on the analysis results.

[0885] The "means for displaying" is a method for presenting the reliability score in a format that is easy for the user to understand.

[0886] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[0887] Server-side behavior

[0888] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following operations:

[0889] Information analysis and reliability assessment

[0890] The server analyzes the URLs and text received from users using a generative AI model (e.g., a generative AI model). This model performs detailed data analysis to assess trustworthiness. The analysis process generates a trustworthiness score based on highly reliable sources (such as official announcements from public institutions and major media outlets) and less reliable sources (such as anonymous blogs and social media posts).

[0891] For example, the prompt sentence is "Please rate the credibility of this news article. Link: https: / / example.com / news-article" and the generative AI model uses the analysis results to calculate a credibility score.

[0892] Returning the results

[0893] The server returns a credibility score based on the analysis to the user, expressed as a percentage, with higher scores indicating greater credibility.

[0894] Operation on the terminal side

[0895] The terminal is a device that provides an interface for the user to operate the system, and performs the following operations.

[0896] Providing a user interface

[0897] The terminal provides a text box and a submit button for users to enter the URL or text they want to rate, allowing them to easily enter the information they want to rate.

[0898] Sending information

[0899] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[0900] Displaying the results

[0901] After receiving the result of the trustworthiness evaluation returned from the server, the terminal visually displays the result on the user interface in a visually easy-to-understand format such as a bar chart or a colored bar graph.

[0902] User operation

[0903] The user uses the system to perform the following operations:

[0904] Entering information

[0905] Users enter the URL or text they want to evaluate for trustworthiness into the input screen. This can be done using a browser or a dedicated application.

[0906] Checking the results

[0907] The user checks the reliability evaluation results returned from the server on the screen and uses the displayed reliability score to determine the accuracy of the information being evaluated.

[0908] Specific examples

[0909] For example, consider the case where a user wants to check the reliability of a news article. The user copies the URL of the news article and pastes it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score as a bar chart. The user can use this result to determine whether the news article is reliable or not.

[0910] In this way, the system of the present invention allows users to easily evaluate and confirm the reliability of information on the Internet, thereby improving the accuracy of information and preventing the spread of misinformation.

[0911] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0912] Step 1:

[0913] The user enters the URL or text for which they want to rate the trustworthiness into the input screen. They do this by cutting and pasting the URL or text into the text box and pressing the "Rate" button. The input can be a URL or text. This provides the system with specific information on which the user wants to make a judgment.

[0914] Step 2:

[0915] The terminal receives the URL or text entered by the user and prepares it to be sent to the server. This is done using an HTTP POST request. The input is the URL or text entered by the user, and the R output is a well-formed HTTP request. Along the way, it checks for errors and formats the request.

[0916] Step 3:

[0917] The server receives the HTTP request sent from the device. It extracts the URL or text information in the request and prepares it to be passed to the generative AI model. The input is the HTTP request received from the device, and the output is the prompt text required for analysis. In this step, the URL is combined with the prompt text "Please rate the credibility of this news article. Link:".

[0918] Step 4:

[0919] The server passes the prompt to a generative AI model, which analyzes the URL or text content. The analysis is performed by the AI ​​and a reliability score is calculated. The input is the generated prompt, and the output is the reliability score as the analysis result. During this process, the AI ​​model performs calculations such as evaluating and comparing the content of the text.

[0920] Step 5:

[0921] The server receives the analysis results obtained by the generative AI model and calculates the reliability score. The input is the analysis data from the AI ​​model, and the output is a reliability score (%). Here, the level of reliability is quantified and expressed as a unified score.

[0922] Step 6:

[0923] The server returns the calculated reliability score in JSON format to the terminal. The input is the reliability score, and the output is the response data in JSON format. In this step, the returned data is sent to the terminal.

[0924] Step 7:

[0925] The terminal analyzes the reliability scores received from the server and displays them on the user interface. The reliability scores are visually displayed using bar charts, colored bars, etc. The input is the JSON response data from the server, and the output is a visual representation of the reliability score. During this process, the display format is adjusted to make the results easy for users to intuitively understand.

[0926] Step 8:

[0927] The user checks the displayed reliability score and evaluates the reliability of the information. The input is the displayed reliability score, and the final output is the user's information evaluation result. The user uses the reliability score to determine whether the input URL or text is trustworthy.

[0928] In this way, the data input and output are clearly defined at each processing step, and specific operations are performed, allowing users to easily and quickly evaluate the reliability of information on the Internet.

[0929] (Application example 1)

[0930] 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."

[0931] Systems for evaluating the reliability of information on the Internet allow users to easily verify the reliability of information, but until now they have been limited to devices such as PCs and smartphones. This has made it difficult to visually verify the reliability of information in real time. In addition, there are limited ways for users to verify the reliability of product reviews and descriptions in a virtual environment, which has resulted in low user convenience.

[0932] 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.

[0933] In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text entered by a user, a means for analyzing the content of the received URL or text and evaluating its reliability, a means for displaying a reliability score of the analysis result, a means for receiving information in real time through the user's visual device, a means for transmitting information captured on the visual device to the server, and a means for displaying the reliability score returned from the server on the visual device, thereby enabling users to visually check the reliability of product reviews and descriptions in real time in a virtual store.

[0934] The "Internet" is an information and communications network that interconnects computer networks around the world.

[0935] "Reliability of information" refers to assessing whether the information is accurate and factual.

[0936] A "URL" is a uniform resource locator used to identify a particular resource or page on the Internet.

[0937] "Text" means information expressed as a string of characters.

[0938] A "visual device" is a device that allows a user to visually check information, and in the present invention, this mainly refers to smart glasses and head-mounted displays.

[0939] A "generative AI model" refers to a model that uses artificial intelligence to analyze information and evaluate the reliability of its content.

[0940] "Analysis" refers to the process of deciphering and understanding the content of information.

[0941] A "reliability score" is a numerical representation of the reliability of specific information, with a higher score indicating higher reliability.

[0942] "Virtual store" refers to a shopping environment that exists in a virtual space rather than an actual physical store.

[0943] System Program Overview

[0944] In this invention, a system for evaluating the reliability of information and displaying it in real time is constructed using the following hardware and software.

[0945] Server: Analyzes information, evaluates reliability, and returns results

[0946] Visual devices: smart glasses and head-mounted displays

[0947] Generative AI models: used for information analysis and reliability assessment

[0948] Hardware and software usage

[0949] 1. Camera input: A camera mounted on the vision device captures the information the user sees (e.g., product reviews and descriptions in a virtual store).

[0950] 2. Information analysis: The captured text information is sent to the server as an HTTP request.

[0951] 3. Trustworthiness assessment: The text is analyzed using a generative AI model on the server side to calculate a trust score.

[0952] 4. Displaying the results: The returned reliability score is displayed on the visual device's display, allowing the user to check the reliability of the information in real time.

[0953] Specific examples

[0954] Scenario 1: Product evaluation in a virtual store

[0955] When a user visits the virtual shopping mall, the camera on the vision device captures the product page and automatically extracts reviews and descriptions. The information sent to the server is analyzed using a generative AI model to calculate a reliability score. For example, if the review "This smartphone has great features" is rated as 85% reliable, the vision device's display will show "Review reliability: 85%."

[0956] Example prompts for generative AI models

[0957] Prompt: "Rate the credibility of the following text: 'This smartphone has great features.'"

[0958] Implementation flow

[0959] The server plays a central role in the reliability evaluation, and users can check the reliability score of information in real time through visual devices, allowing them to make decisions based on reliable information.

[0960] In this way, by using the system of the present invention, users can evaluate the reliability of information in real time even in a virtual environment, and enjoy shopping with peace of mind based on reliable information.

[0961] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0962] Step 1:

[0963] A user browses products in a virtual store.

[0964] Input: The user wears a visual device (smart glasses or a head-mounted display) and selects and browses products in the virtual environment.

[0965] Action: The vision device takes a camera capture of the product page.

[0966] Step 2:

[0967] The visual device extracts the captured text information.

[0968] Input: Camera captured image of product page.

[0969] Data processing: Uses OCR (Optical Character Recognition) technology to extract text from images.

[0970] Output: Extracted text information (e.g. product reviews and descriptions).

[0971] Step 3:

[0972] The terminal (visual device) transmits the extracted text information to the server.

[0973] Input: The extracted text information.

[0974] Data operation: Construct an HTTP request and send it including the text information.

[0975] Output: Text information sent to the server.

[0976] Step 4:

[0977] The server analyzes the received text information and calculates a reliability score.

[0978] Input: Text information sent from the device.

[0979] Data Computing: Analyzes text using a generative AI model to generate prompts.

[0980] Example prompt: "Please rate the credibility of the following text: 'This smartphone has great features.'"

[0981] Data processing: A generative AI model analyzes the text and generates a reliability score.

[0982] Output: A confidence score (e.g. 85%).

[0983] Step 5:

[0984] The server returns a reliability score of the analysis result to the terminal (visual device).

[0985] Input: Confidence score.

[0986] Data calculation: Construct a confidence score as an HTTP response.

[0987] Output: A response containing the confidence score.

[0988] Step 6:

[0989] The reliability score obtained by the terminal (visual device) is displayed to the user.

[0990] Input: The confidence score returned by the server.

[0991] Data Calculation: Converting confidence scores into a visually understandable format (e.g., colored bar graphs).

[0992] Output: The visual device display shows "Review Confidence: 85%."

[0993] This allows users to visually check the reliability of product reviews and descriptions in real time through visual devices, enabling them to make decisions based on highly reliable information.

[0994] 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.

[0995] The present invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state. Specific embodiments of this system are described below.

[0996] Server-side behavior

[0997] The server receives the URL or text entered by the user, analyzes it, and plays a central role in assessing its trustworthiness. It also uses an emotion engine to recognize the user's emotions and reflect them in the assessment results.

[0998] Information analysis and reliability assessment

[0999] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[1000] Emotion recognition by emotion engine

[1001] The server uses an emotion engine to recognize the user's emotions based on the user's input, past behavioral data, and reactions. This emotion recognition grasps emotions that change in real time depending on the user's text input and the information they come into contact with.

[1002] Returning the results

[1003] After obtaining the analysis and emotion recognition results, the server returns the results to the user, along with a confidence score and an appropriate response message based on the result.

[1004] Operation on the terminal side

[1005] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[1006] Providing a user interface

[1007] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[1008] Sending information

[1009] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[1010] Displaying the results

[1011] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[1012] User operation

[1013] The user performs direct operations to use the system, including the following:

[1014] Entering information

[1015] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[1016] Checking the results

[1017] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[1018] Specific examples

[1019] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, "80% reliability," and a message corresponding to the emotion are displayed on the user's device. For example, the message may read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[1020] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and provides appropriate feedback according to the user's emotional state, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[1021] The processing flow will be explained below.

[1022] Step 1: Enter your information

[1023] The user enters the URL or text of an online news article or social media post, accesses the system's input screen, pastes the URL or text into the text box, and presses the "Rate" button.

[1024] Step 2: Submit your information

[1025] The device receives the URL or text entered by the user, packages the received information in JSON format or similar, and sends it to the server using an HTTP POST request.

[1026] Step 3: Receiving the request

[1027] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL or text to be evaluated.

[1028] Step 4: Gather information

[1029] The server then performs web scraping or API requests to gather information from the extracted URLs, specifically the content of news articles retrieved from the internet.

[1030] Step 5: Pre-analysis processing using generative AI

[1031] The server preprocesses the retrieved news articles and text content, including text normalization, removal of unnecessary data, and language identification. For example, HTML tags are removed from news article text.

[1032] Step 6: Reliability assessment

[1033] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and generates a score of "80% reliability."

[1034] Step 7: Emotion Recognition with the Emotion Engine

[1035] The server uses an emotion engine to recognize the user's emotions based on their past behavioral data and real-time reactions, including micro-facial expressions when users enter text or browse information.

[1036] Step 8: Packaging the evaluation results

[1037] The server packages the generated confidence score and the emotion recognition result from the emotion engine in JSON format. For example, it generates a JSON object containing a confidence score of 80% and an emotional state of "user is worried."

[1038] Step 9: Sending the results

[1039] The server then returns the packaged evaluation results and emotion recognition results to the device as an HTTP response.

[1040] Step 10: Receiving the results

[1041] The device receives the HTTP response sent back from the server, analyzes the response content, and parses the JSON data to extract the confidence score and emotion recognition results.

[1042] Step 11: View the results

[1043] The device displays the reliability score and emotion recognition results in the user interface, including text indicating a reliability score of 80% and a message corresponding to the emotion (e.g., "The reliability of this news article is 80%. If you are concerned, please check other reliable sources.").

[1044] Step 12: Check the evaluation results

[1045] The user can then review the results of the trust assessment and receive appropriate feedback based on their emotions, and can take action such as rechecking or finding another source of information.

[1046] These are the specific processing steps from user input to display of the reliability score and emotion recognition results. This system provides an effective means for users to easily evaluate the reliability of information on websites and social networking sites and receive appropriate feedback based on their emotions.

[1047] Example 2

[1048] 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."

[1049] It is difficult to distinguish reliable information from the vast amount of information on the Internet, and especially in today's world where fake news and misinformation are on the rise, a system that allows users to easily evaluate information that is reliable is needed. In addition, it is necessary to provide feedback according to the user's emotional state so that appropriate responses can be made that take into account how the information is received.

[1050] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and evaluating the reliability, a means for displaying a reliability score of the analysis result, a means for recognizing emotions based on the user's input information and past behavioral data, and a means for generating and displaying a feedback message based on the recognized emotions. This allows the user to easily evaluate the reliability of information on the Internet and receive appropriate feedback according to their emotional state.

[1051] The "Internet" is a communications network that uses standard protocols to connect computer networks worldwide.

[1052] "Information" is data accessible on the Internet, such as text, images, and video.

[1053] "Credibility" is the measure of whether information is accurate or whether its source is trustworthy.

[1054] "User" means a person who uses this system to evaluate the reliability of information on the Internet.

[1055] A "URL" is a Uniform Resource Locator that identifies the location of information on the Internet.

[1056] "Text" refers to data consisting of a string of characters, and is generally expressed as a sentence.

[1057] "Means of receiving" refers to the method by which the server obtains the URL or text entered by the user.

[1058] "Analysis" is the process of evaluating the content of input information and determining its reliability.

[1059] "Generation" refers to creating new data, such as reliability scores or messages, based on the analysis results.

[1060] "Display means" refers to a method for providing an interface for showing analysis results and feedback messages to the user.

[1061] A "generative artificial intelligence model," also known as a generative AI model, is a machine learning model that analyzes text and data to generate new data.

[1062] "Emotion recognition" is a technology that detects a user's current emotional state by analyzing the user's input and behavioral data.

[1063] A "feedback message" is advice or information provided to the user based on the analysis results or emotion recognition results.

[1064] This invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state.

[1065] System configuration

[1066] This system mainly consists of three main components: a server, a terminal, and a user.

[1067] Server Configuration

[1068] The server consists of hardware and software that provides the following functions:

[1069] 1. Information receiving function: A function to receive URL or text information entered by the user.

[1070] 2. Information analysis function: A function that analyzes received URLs and text information and evaluates their reliability. This analysis uses a generative AI model (for example, a general generative AI model or natural language processing technology).

[1071] 3. Emotion recognition function: A function that recognizes the user's emotions using an emotion engine (e.g., a general emotion recognition API) based on the user's input information and past behavioral data.

[1072] 4. Result generation function: A function that generates evaluation results and appropriate feedback messages based on the reliability score and emotion recognition results.

[1073] 5. Result return function: A function that returns analysis results and emotion recognition results to the user.

[1074] Device configuration

[1075] A terminal is a device that a user uses to operate the system and provides the following functions:

[1076] 1. User interface: Provide an interface that includes a text box for users to enter the URL or text they want to rate, and a submit button.

[1077] 2. Information transmission function: A function that sends the URL or text entered by the user to the server using an HTTP request.

[1078] 3. Result display function: A function that displays the reliability evaluation results and emotion recognition results returned from the server on the user interface.

[1079] User operations

[1080] The user operates the system using a terminal and evaluates the reliability of information using the following procedure.

[1081] 1. Entering information: The user enters the URL or text for which they want to rate the trustworthiness into the system's input screen and presses the "Rate" button.

[1082] 2. Check the results: Check the reliability evaluation results and emotion recognition results returned from the server on the screen. Based on the displayed reliability score and emotion-based feedback, you can decide whether the information is trustworthy or not.

[1083] Hardware and software used

[1084] Server: A cloud server or dedicated server for running high-performance analysis capabilities and multi-function APIs.

[1085] Generative AI models: Generative AI models in general, specifically models based on natural language processing techniques (e.g., OpenAI's models).

[1086] Emotion recognition engine: A common emotion recognition API (e.g., Microsoft Azure's Emotion API).

[1087] Device: Any device that can connect to the internet, such as a PC, tablet, or smartphone.

[1088] Specific examples

[1089] For example, if a user wants to check the reliability of a news article, they paste the URL of the news article into the system's input screen and press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, a message corresponding to the emotion, such as "80% reliability," is displayed on the user's device. For example, the message might read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources." In this way, users can easily evaluate the reliability of information on the Internet and receive appropriate feedback based on their emotional state.

[1090] This system can curb the spread of fake news and misinformation and disseminate reliable information.

[1091] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1092] Program processing flow

[1093] Step 1: Accept information input

[1094] User behavior

[1095] The user enters the URL or text for which they want to rate trustworthiness into the device's input screen and presses the "Rate" button. This input screen has a text box where the user can enter the information to be rated. For example, they enter the URL of a news article, "https: / / example.com / news-article".

[1096] Input: URL or text

[1097] Output: Input completion status to terminal

[1098] Step 2: Submit your input

[1099] Operation on the terminal side

[1100] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user. For example, the URL of a news article is sent to the server in an HTTP POST request.

[1101] Input: URL or text entered by the user

[1102] Output: HTTP request to the server

[1103] Step 3: Analyze input information and assess its reliability

[1104] Server-side behavior

[1105] The server analyzes the received information and evaluates its reliability. This analysis is performed using a generative AI model (e.g., a general generative AI model). Specifically, the server inputs the received URL or text as a prompt into the generative AI model, which then analyzes the content and calculates a reliability score. For example, official announcements from public institutions and reports from major media outlets are rated as highly reliable, while anonymous blogs and social media posts are rated as less reliable.

[1106] Input: URL or text received from an HTTP request

[1107] Output: Confidence score

[1108] Step 4: Recognize emotions

[1109] Server-side behavior

[1110] The server uses an emotion engine (for example, a general emotion recognition API) to recognize the user's emotions based on the user's input information and past behavioral data. Specifically, the server passes the user's input text and past behavioral data to the emotion recognition API, which detects emotions in real time. For example, if the user uses emotional words, the emotion is recognized as "anger" or "anxiety."

[1111] Input: User input information, past behavior data

[1112] Output: Emotion recognition result

[1113] Step 5: Generating evaluation and emotion recognition results

[1114] Server-side behavior

[1115] The server integrates the reliability score and the emotion recognition results to generate an evaluation result and an appropriate feedback message, such as "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[1116] Input: Confidence score, emotion recognition result

[1117] Output: Evaluation results, feedback messages

[1118] Step 6: Returning the results

[1119] Server-side behavior

[1120] The server returns the generated evaluation results and emotion recognition results to the user. The returned information includes a confidence score and a feedback message based on the emotion. For example, a confidence score of "80%" and a feedback message are returned as an HTTP response.

[1121] Input: Evaluation results, feedback message

[1122] Output: HTTP response to the user

[1123] Step 7: View the results

[1124] Operation on the terminal side

[1125] The device displays the reliability evaluation results and emotion recognition results received from the server on the user interface. Specifically, the reliability score is displayed in a visually easy-to-understand format, along with an appropriate message according to the user's emotion. For example, "80% reliability" is displayed in large letters, with a message below it saying, "If you are concerned, please check other reliable sources of information."

[1126] Input: HTTP response from the server

[1127] Output: Confidence score and feedback message in the user interface

[1128] (Application example 2)

[1129] 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."

[1130] In recent years, the Internet has become overflowing with a wide variety of information, and product reviews, especially on online shopping sites, have a significant influence on product purchasing decisions. However, not all reviews are necessarily reliable, making it difficult for users to discern their authenticity. Furthermore, users are easily influenced by their own emotions and may make inappropriate decisions based on unreliable information. Therefore, there is a need for a system that allows users to accurately evaluate the reliability of information and receive appropriate feedback based on their own emotions.

[1131] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for evaluating and displaying the reliability of information on the Internet, means for receiving a URL or text entered by a user, means for analyzing the content of the received URL or text and evaluating the reliability, means for displaying a reliability score of the analysis result, means for recognizing the user's emotions, and means for providing feedback according to the recognized user emotions. This allows the user to easily evaluate the reliability of information and further to receive appropriate feedback according to their own emotions.

[1132] "Means for evaluating and displaying the reliability of information on the Internet" is a function that analyzes the reliability of information present on the Internet and visually presents the results to the user.

[1133] The "means for receiving a URL or text input by a user" is a function that allows a user to input a URL or text to be evaluated into the system and send it to the server.

[1134] "Means for analyzing the content of received URLs or text and evaluating its reliability" refers to a function that analyzes the content of URLs or text received by the server and evaluates the reliability of that information.

[1135] The "means for displaying the reliability score of the analysis result" is a function for displaying the score calculated as a result of the reliability evaluation on the user interface.

[1136] "Means for recognizing user emotions" refers to a function that analyzes emotions based on user input and behavioral data.

[1137] The "means for providing feedback according to the recognized user emotions" is a function for displaying appropriate messages or recommendations based on the user's emotions.

[1138] "Means using generative AI models" refers to functions that use machine learning algorithms to analyze information and evaluate its reliability.

[1139] "Means of using reliable and unreliable sources" refers to a function that refers to predefined reliable and unreliable sources as evaluation criteria.

[1140] To implement this invention, it is necessary to build a system in which the server, terminal, and user operate in cooperation with each other. To understand the operation of this system, the roles and processes of each will be explained.

[1141] Server Operation

[1142] The server is responsible for the following main functions:

[1143] 1. Information reliability assessment

[1144] The server receives the URL or text entered by the user, analyzes its content, and evaluates its trustworthiness. To evaluate trustworthiness, it uses a generative AI model. Specifically, it analyzes the text using a Python natural language processing library (e.g., spaCy or NLTK) and calculates a trustworthiness score based on the analysis.

[1145] 2. Emotion recognition

[1146] The server is equipped with an emotion engine that analyzes emotions based on user input and behavioral data. For example, it analyzes the types of reviews users frequently read, their completion rate, and the duration of their stay. This is done using machine learning models (e.g., TensorFlow and PyTorch).

[1147] 3. Providing Feedback

[1148] The server generates appropriate feedback for the user based on the reliability evaluation result and emotion recognition result. This feedback message is customized according to the emotion.

[1149] Device behavior

[1150] The terminal provides an interface for the user to interact with the system. The specific operation is as follows:

[1151] 1. Providing a user interface

[1152] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[1153] 2. Transmission of information

[1154] The terminal sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[1155] 3. Displaying the results

[1156] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[1157] User operations

[1158] The user performs direct operations to use the system, including the following:

[1159] 1. Enter your information

[1160] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[1161] 2. Check the results

[1162] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[1163] Specific examples

[1164] For example, if a user wants to check the reliability of reviews on a product page, they copy the product's URL, paste it into the system's input screen, and press the "Rate" button. The server retrieves the product's review information from the URL, analyzes its content using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message.

[1165] The evaluation result, "75% reliability," and a message based on the user's emotion are displayed on the user's device. For example, the message might read, "The reliability of the reviews for this product is 75%. You may be optimistic about purchasing it, but please also check other reviews."

[1166] Prompt Sentence Examples

[1167] An example of a prompt sentence to be input to a generative AI model is as follows:

[1168] While a user is browsing a product page, analyze all reviews on that page, calculate the review credibility score, analyze user sentiment, and generate appropriate feedback messages based on that sentiment.

[1169] This system allows users to easily evaluate the reliability of information and receive appropriate feedback based on their personal feelings.

[1170] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1171] Step 1:

[1172] The user enters the URL or text they want to rate on the system's input screen and presses the "Rate" button. The entered information is sent to the terminal and then sent to the server as an HTTP request.

[1173] (Input) User URL or text

[1174] (Output) HTTP request

[1175] Step 2:

[1176] The server analyzes the HTTP request received from the device and extracts the URL or text data, then inputs the obtained data into a generative AI model to analyze the text content.

[1177] (Input) URL or text data in the HTTP request

[1178] (Output) Intermediate dataset of analysis results

[1179] Step 3:

[1180] The server evaluates the reliability of the received information based on the results of analysis using the generative AI model and calculates a reliability score.

[1181] (Input) Intermediate dataset of analysis results

[1182] (Output) Confidence score

[1183] Step 4:

[1184] The server uses an emotion engine to recognize the user's emotions based on the user's past behavioral data and current input data.

[1185] (Input) User's past behavior data and current input data

[1186] (Output) User emotion recognition results

[1187] Step 5:

[1188] The server integrates the confidence score with the emotion recognition result to generate a feedback message, which is customized according to the user's emotional state.

[1189] (Input) Reliability score, emotion recognition result

[1190] (Output) Feedback message

[1191] Step 6:

[1192] The server sends the reliability score and the feedback message together to the terminal.

[1193] (Input) Feedback message

[1194] (Output) HTTP response

[1195] Step 7:

[1196] The terminal receives the HTTP response from the server and displays the reliability score and feedback message on the user interface. The user can check the reliability of the information by referring to the reliability score and feedback message.

[1197] (Input) Confidence score and feedback message in the HTTP response

[1198] (Output) The confidence score and feedback message displayed in the user interface

[1199] 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.

[1200] 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.

[1201] 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.

[1202] [Fourth embodiment]

[1203] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1204] 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.

[1205] 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).

[1206] 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.

[1207] 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.

[1208] 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).

[1209] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1210] 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.

[1211] 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.

[1212] 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.

[1213] 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.

[1214] 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.

[1215] 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."

[1216] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[1217] Server-side behavior

[1218] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following actions based on the entered information:

[1219] Information analysis and reliability assessment

[1220] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[1221] Returning the results

[1222] After the analysis results are obtained, the server returns them to the user with a reliability score, expressed as a percentage. The higher the score, the more reliable the information is.

[1223] Operation on the terminal side

[1224] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[1225] Providing a user interface

[1226] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[1227] Sending information

[1228] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[1229] Displaying the results

[1230] After the server returns the results of the trust assessment, the device displays the results on the user interface. The trust scores are displayed in a visually easy-to-understand format (e.g., a bar chart or a colored bar).

[1231] User operation

[1232] The user performs direct operations to use the system, including the following:

[1233] Entering information

[1234] Users enter the URL or text they want to rate on the system's input screen, and when they're done, they press the "Rate" button to submit the information.

[1235] Checking the results

[1236] The user checks the credibility evaluation results returned from the server on the screen and uses the displayed credibility score to determine the accuracy of the information.

[1237] Specific examples

[1238] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Evaluate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score. The user can use this result to determine whether the news article is reliable or not.

[1239] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and check its reliability score, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[1240] The processing flow will be explained below.

[1241] Step 1: Input from the user

[1242] The user enters the URL or text (such as a social media post) of the news article they want to rate into the system's input screen and presses the "Rate" button. In the example where a user enters the URL of a news article, they copy the URL of the news article they found in their browser, paste it into the system's input box, and press the submit button.

[1243] Step 2: Submit your information

[1244] The terminal receives the URL or text entered by the user, then packages the received information in JSON format or similar and sends it to the server using an HTTP POST request. In this example, a JSON object containing the entered URL is created and sent to the server.

[1245] Step 3: Receiving the request on the server

[1246] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL to be evaluated.

[1247] Step 4: Gather information

[1248] The server then performs web scraping or API requests to retrieve information from the extracted URLs, which is the step of retrieving the content of the specified news article from the internet.

[1249] Step 5: Pre-analysis processing using generative AI

[1250] The server preprocesses the retrieved news article content, which includes text normalization, removal of unnecessary data, language identification, etc. For example, HTML tags are removed from the news article text and language filters are applied.

[1251] Step 6: Reliability assessment

[1252] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and returns a rating of "80% reliability."

[1253] Step 7: Packaging the evaluation results

[1254] The server packages the generated reliability score in JSON format, etc. It generates a JSON object containing a reliability score of 80% as the evaluation result.

[1255] Step 8: Sending the results

[1256] The server returns a JSON object containing the evaluation results to the terminal as an HTTP response.

[1257] Step 9: Receiving the results

[1258] The device receives the HTTP response from the server and analyzes the response content. Specifically, it parses the received JSON data and extracts the reliability score.

[1259] Step 10: View the results

[1260] The device displays the extracted reliability score on the user interface, using a text representation of a reliability score of 80% or a visually easy-to-understand bar chart.

[1261] Step 11: Check the evaluation results

[1262] The user checks the results of the reliability assessment displayed on the device. The user uses the displayed reliability score to determine whether the news article is trustworthy. In a specific example, the user sees a message saying "The reliability of this news article is 80%" and evaluates the accuracy of the information.

[1263] These are the specific processing steps from user input to display of the reliability score. This system provides users with an effective means to easily evaluate the reliability of information on websites and social media sites and obtain accurate information.

[1264] Example 1

[1265] 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."

[1266] The Internet is overflowing with a wide variety of information, including unreliable information and fake news. This makes it difficult for users to determine which information is accurate and reliable. In particular, there is a need for a method to quickly evaluate and present the reliability of important news and information that requires fact-checking.

[1267] 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.

[1268] In this invention, the server includes a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and using a generative AI model to evaluate reliability, a means for calculating a reliability score, and a means for displaying the calculated reliability score, thereby enabling a user to easily and quickly evaluate the reliability of a URL or text and visually confirm the result.

[1269] "User" is the subject who uses the system to evaluate the reliability of URLs and text.

[1270] A "URL" is a uniform resource locator for specifying resources on the Internet.

[1271] "Text" is character string data to be evaluated.

[1272] A "server" is a central computing unit that analyzes URLs and text received from users and evaluates their trustworthiness.

[1273] "Means of receiving" refers to the method by which the server obtains the URL or text sent by the user.

[1274] A "generative AI model" is a computational model that uses artificial intelligence to analyze incoming URLs and text. For example, it is an AI that performs natural language processing.

[1275] "Analysis" refers to the act of using a generative AI model to examine the content of received URLs and text and assess their reliability.

[1276] A "means for assessing trustworthiness" is a method for determining the trustworthiness of a URL or text using a generative AI model.

[1277] A "reliability score" is a numerical expression of an evaluation based on the analysis results, and is an index showing the reliability of information.

[1278] The "means for calculating" is a method for deriving a reliability score based on the analysis results.

[1279] The "means for displaying" is a method for presenting the reliability score in a format that is easy for the user to understand.

[1280] The present invention provides a system that allows users to evaluate the reliability of information on the Internet and easily check the results. A specific embodiment of this system will be described below.

[1281] Server-side behavior

[1282] The server plays a central role in receiving the URL or text entered by the user, analyzing it, and assessing its trustworthiness. The server performs the following operations:

[1283] Information analysis and reliability assessment

[1284] The server analyzes the URLs and text received from users using a generative AI model (e.g., a generative AI model). This model performs detailed data analysis to assess trustworthiness. The analysis process generates a trustworthiness score based on highly reliable sources (such as official announcements from public institutions and major media outlets) and less reliable sources (such as anonymous blogs and social media posts).

[1285] For example, the prompt sentence is "Please rate the credibility of this news article. Link: https: / / example.com / news-article" and the generative AI model uses the analysis results to calculate a credibility score.

[1286] Returning the results

[1287] The server returns a credibility score based on the analysis to the user, expressed as a percentage, with higher scores indicating greater credibility.

[1288] Operation on the terminal side

[1289] The terminal is a device that provides an interface for the user to operate the system, and performs the following operations.

[1290] Providing a user interface

[1291] The terminal provides a text box and a submit button for users to enter the URL or text they want to rate, allowing them to easily enter the information they want to rate.

[1292] Sending information

[1293] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[1294] Displaying the results

[1295] After receiving the result of the trustworthiness evaluation returned from the server, the terminal visually displays the result on the user interface in a visually easy-to-understand format such as a bar chart or a colored bar graph.

[1296] User operation

[1297] The user uses the system to perform the following operations:

[1298] Entering information

[1299] Users enter the URL or text they want to evaluate for trustworthiness into the input screen. This can be done using a browser or a dedicated application.

[1300] Checking the results

[1301] The user checks the reliability evaluation results returned from the server on the screen and uses the displayed reliability score to determine the accuracy of the information being evaluated.

[1302] Specific examples

[1303] For example, consider the case where a user wants to check the reliability of a news article. The user copies the URL of the news article and pastes it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. The evaluation result is returned to the user's device as "80% reliability," and the device visually displays this score as a bar chart. The user can use this result to determine whether the news article is reliable or not.

[1304] In this way, the system of the present invention allows users to easily evaluate and confirm the reliability of information on the Internet, thereby improving the accuracy of information and preventing the spread of misinformation.

[1305] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1306] Step 1:

[1307] The user enters the URL or text for which they want to rate the trustworthiness into the input screen. They do this by cutting and pasting the URL or text into the text box and pressing the "Rate" button. The input can be a URL or text. This provides the system with specific information on which the user wants to make a judgment.

[1308] Step 2:

[1309] The terminal receives the URL or text entered by the user and prepares it to be sent to the server. This is done using an HTTP POST request. The input is the URL or text entered by the user, and the R output is a well-formed HTTP request. Along the way, it checks for errors and formats the request.

[1310] Step 3:

[1311] The server receives the HTTP request sent from the device. It extracts the URL or text information in the request and prepares it to be passed to the generative AI model. The input is the HTTP request received from the device, and the output is the prompt text required for analysis. In this step, the URL is combined with the prompt text "Please rate the credibility of this news article. Link:".

[1312] Step 4:

[1313] The server passes the prompt to a generative AI model, which analyzes the URL or text content. The analysis is performed by the AI ​​and a reliability score is calculated. The input is the generated prompt, and the output is the reliability score as the analysis result. During this process, the AI ​​model performs calculations such as evaluating and comparing the content of the text.

[1314] Step 5:

[1315] The server receives the analysis results obtained by the generative AI model and calculates the reliability score. The input is the analysis data from the AI ​​model, and the output is a reliability score (%). Here, the level of reliability is quantified and expressed as a unified score.

[1316] Step 6:

[1317] The server returns the calculated reliability score in JSON format to the terminal. The input is the reliability score, and the output is the response data in JSON format. In this step, the returned data is sent to the terminal.

[1318] Step 7:

[1319] The terminal analyzes the reliability scores received from the server and displays them on the user interface. The reliability scores are visually displayed using bar charts, colored bars, etc. The input is the JSON response data from the server, and the output is a visual representation of the reliability score. During this process, the display format is adjusted to make the results easy for users to intuitively understand.

[1320] Step 8:

[1321] The user checks the displayed reliability score and evaluates the reliability of the information. The input is the displayed reliability score, and the final output is the user's information evaluation result. The user uses the reliability score to determine whether the input URL or text is trustworthy.

[1322] In this way, the data input and output are clearly defined at each processing step, and specific operations are performed, allowing users to easily and quickly evaluate the reliability of information on the Internet.

[1323] (Application example 1)

[1324] 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."

[1325] Systems for evaluating the reliability of information on the Internet allow users to easily verify the reliability of information, but until now they have been limited to devices such as PCs and smartphones. This has made it difficult to visually verify the reliability of information in real time. In addition, there are limited ways for users to verify the reliability of product reviews and descriptions in a virtual environment, which has resulted in low user convenience.

[1326] 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.

[1327] In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text entered by a user, a means for analyzing the content of the received URL or text and evaluating its reliability, a means for displaying a reliability score of the analysis result, a means for receiving information in real time through the user's visual device, a means for transmitting information captured on the visual device to the server, and a means for displaying the reliability score returned from the server on the visual device, thereby enabling users to visually check the reliability of product reviews and descriptions in real time in a virtual store.

[1328] The "Internet" is an information and communications network that interconnects computer networks around the world.

[1329] "Reliability of information" refers to assessing whether the information is accurate and factual.

[1330] A "URL" is a uniform resource locator used to identify a particular resource or page on the Internet.

[1331] "Text" means information expressed as a string of characters.

[1332] A "visual device" is a device that allows a user to visually check information, and in the present invention, this mainly refers to smart glasses and head-mounted displays.

[1333] A "generative AI model" refers to a model that uses artificial intelligence to analyze information and evaluate the reliability of its content.

[1334] "Analysis" refers to the process of deciphering and understanding the content of information.

[1335] A "reliability score" is a numerical representation of the reliability of specific information, with a higher score indicating higher reliability.

[1336] "Virtual store" refers to a shopping environment that exists in a virtual space rather than an actual physical store.

[1337] System Program Overview

[1338] In this invention, a system for evaluating the reliability of information and displaying it in real time is constructed using the following hardware and software.

[1339] Server: Analyzes information, evaluates reliability, and returns results

[1340] Visual devices: smart glasses and head-mounted displays

[1341] Generative AI models: used for information analysis and reliability assessment

[1342] Hardware and software usage

[1343] 1. Camera input: A camera mounted on the vision device captures the information the user sees (e.g., product reviews and descriptions in a virtual store).

[1344] 2. Information analysis: The captured text information is sent to the server as an HTTP request.

[1345] 3. Trustworthiness assessment: The text is analyzed using a generative AI model on the server side to calculate a trust score.

[1346] 4. Displaying the results: The returned reliability score is displayed on the visual device's display, allowing the user to check the reliability of the information in real time.

[1347] Specific examples

[1348] Scenario 1: Product evaluation in a virtual store

[1349] When a user visits the virtual shopping mall, the camera on the vision device captures the product page and automatically extracts reviews and descriptions. The information sent to the server is analyzed using a generative AI model to calculate a reliability score. For example, if the review "This smartphone has great features" is rated as 85% reliable, the vision device's display will show "Review reliability: 85%."

[1350] Example prompts for generative AI models

[1351] Prompt: "Rate the credibility of the following text: 'This smartphone has great features.'"

[1352] Implementation flow

[1353] The server plays a central role in the reliability evaluation, and users can check the reliability score of information in real time through visual devices, allowing them to make decisions based on reliable information.

[1354] In this way, by using the system of the present invention, users can evaluate the reliability of information in real time even in a virtual environment, and enjoy shopping with peace of mind based on reliable information.

[1355] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1356] Step 1:

[1357] A user browses products in a virtual store.

[1358] Input: The user wears a visual device (smart glasses or a head-mounted display) and selects and browses products in the virtual environment.

[1359] Action: The vision device takes a camera capture of the product page.

[1360] Step 2:

[1361] The visual device extracts the captured text information.

[1362] Input: Camera captured image of product page.

[1363] Data processing: Uses OCR (Optical Character Recognition) technology to extract text from images.

[1364] Output: Extracted text information (e.g. product reviews and descriptions).

[1365] Step 3:

[1366] The terminal (visual device) transmits the extracted text information to the server.

[1367] Input: The extracted text information.

[1368] Data operation: Construct an HTTP request and send it including the text information.

[1369] Output: Text information sent to the server.

[1370] Step 4:

[1371] The server analyzes the received text information and calculates a reliability score.

[1372] Input: Text information sent from the device.

[1373] Data Computing: Analyzes text using a generative AI model to generate prompts.

[1374] Example prompt: "Please rate the credibility of the following text: 'This smartphone has great features.'"

[1375] Data processing: A generative AI model analyzes the text and generates a reliability score.

[1376] Output: A confidence score (e.g. 85%).

[1377] Step 5:

[1378] The server returns a reliability score of the analysis result to the terminal (visual device).

[1379] Input: Confidence score.

[1380] Data calculation: Construct a confidence score as an HTTP response.

[1381] Output: A response containing the confidence score.

[1382] Step 6:

[1383] The reliability score obtained by the terminal (visual device) is displayed to the user.

[1384] Input: The confidence score returned by the server.

[1385] Data Calculation: Converting confidence scores into a visually understandable format (e.g., colored bar graphs).

[1386] Output: The visual device display shows "Review Confidence: 85%."

[1387] This allows users to visually check the reliability of product reviews and descriptions in real time through visual devices, enabling them to make decisions based on highly reliable information.

[1388] 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.

[1389] The present invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state. Specific embodiments of this system are described below.

[1390] Server-side behavior

[1391] The server receives the URL or text entered by the user, analyzes it, and plays a central role in assessing its trustworthiness. It also uses an emotion engine to recognize the user's emotions and reflect them in the assessment results.

[1392] Information analysis and reliability assessment

[1393] The server analyzes the URLs and text received from users. This analysis uses a generative AI model to analyze the content of the information and generate a reliability score. The analysis results are evaluated based on reliable and less reliable sources. For example, official announcements from public institutions and reports from major media outlets are considered highly reliable, while anonymous personal blogs and social media posts are considered less reliable.

[1394] Emotion recognition by emotion engine

[1395] The server uses an emotion engine to recognize the user's emotions based on the user's input, past behavioral data, and reactions. This emotion recognition grasps emotions that change in real time depending on the user's text input and the information they come into contact with.

[1396] Returning the results

[1397] After obtaining the analysis and emotion recognition results, the server returns the results to the user, along with a confidence score and an appropriate response message based on the result.

[1398] Operation on the terminal side

[1399] The terminal provides an interface for the user to operate the system. The following operations are performed on the terminal:

[1400] Providing a user interface

[1401] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[1402] Sending information

[1403] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[1404] Displaying the results

[1405] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[1406] User operation

[1407] The user performs direct operations to use the system, including the following:

[1408] Entering information

[1409] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[1410] Checking the results

[1411] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[1412] Specific examples

[1413] For example, if a user wants to check the reliability of a news article, they copy the URL of the news article and paste it into the system's input screen. Then, they press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, "80% reliability," and a message corresponding to the emotion are displayed on the user's device. For example, the message may read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[1414] In this way, the system of the present invention allows users to easily evaluate the reliability of information on the Internet and provides appropriate feedback according to the user's emotional state, thereby making it possible to curb the spread of fake news and misinformation and to disseminate reliable information.

[1415] The processing flow will be explained below.

[1416] Step 1: Enter your information

[1417] The user enters the URL or text of an online news article or social media post, accesses the system's input screen, pastes the URL or text into the text box, and presses the "Rate" button.

[1418] Step 2: Submit your information

[1419] The device receives the URL or text entered by the user, packages the received information in JSON format or similar, and sends it to the server using an HTTP POST request.

[1420] Step 3: Receiving the request

[1421] The server receives the HTTP request sent from the device, analyzes the request content, and extracts the URL or text. Specifically, it analyzes the received JSON data and extracts the URL or text to be evaluated.

[1422] Step 4: Gather information

[1423] The server then performs web scraping or API requests to gather information from the extracted URLs, specifically the content of news articles retrieved from the internet.

[1424] Step 5: Pre-analysis processing using generative AI

[1425] The server preprocesses the retrieved news articles and text content, including text normalization, removal of unnecessary data, and language identification. For example, HTML tags are removed from news article text.

[1426] Step 6: Reliability assessment

[1427] The server inputs the preprocessed text into a generative AI model to evaluate the reliability of the content. The AI ​​model generates a reliability score (0-100%). For example, the generative AI model analyzes a news article and generates a score of "80% reliability."

[1428] Step 7: Emotion Recognition with the Emotion Engine

[1429] The server uses an emotion engine to recognize the user's emotions based on their past behavioral data and real-time reactions, including micro-facial expressions when users enter text or browse information.

[1430] Step 8: Packaging the evaluation results

[1431] The server packages the generated confidence score and the emotion recognition result from the emotion engine in JSON format. For example, it generates a JSON object containing a confidence score of 80% and an emotional state of "user is worried."

[1432] Step 9: Sending the results

[1433] The server then returns the packaged evaluation results and emotion recognition results to the device as an HTTP response.

[1434] Step 10: Receiving the results

[1435] The device receives the HTTP response sent back from the server, analyzes the response content, and parses the JSON data to extract the confidence score and emotion recognition results.

[1436] Step 11: View the results

[1437] The device displays the reliability score and emotion recognition results in the user interface, including text indicating a reliability score of 80% and a message corresponding to the emotion (e.g., "The reliability of this news article is 80%. If you are concerned, please check other reliable sources.").

[1438] Step 12: Check the evaluation results

[1439] The user can then review the results of the trust assessment and receive appropriate feedback based on their emotions, and can take action such as rechecking or finding another source of information.

[1440] These are the specific processing steps from user input to display of the reliability score and emotion recognition results. This system provides an effective means for users to easily evaluate the reliability of information on websites and social networking sites and receive appropriate feedback based on their emotions.

[1441] Example 2

[1442] 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."

[1443] It is difficult to distinguish reliable information from the vast amount of information on the Internet, and especially in today's world where fake news and misinformation are on the rise, a system that allows users to easily evaluate information that is reliable is needed. In addition, it is necessary to provide feedback according to the user's emotional state so that appropriate responses can be made that take into account how the information is received.

[1444] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for evaluating and displaying the reliability of information on the Internet, a means for receiving a URL or text input by a user, a means for analyzing the content of the received URL or text and evaluating the reliability, a means for displaying a reliability score of the analysis result, a means for recognizing emotions based on the user's input information and past behavioral data, and a means for generating and displaying a feedback message based on the recognized emotions. This allows the user to easily evaluate the reliability of information on the Internet and receive appropriate feedback according to their emotional state.

[1445] The "Internet" is a communications network that uses standard protocols to connect computer networks worldwide.

[1446] "Information" is data accessible on the Internet, such as text, images, and video.

[1447] "Credibility" is the measure of whether information is accurate or whether its source is trustworthy.

[1448] "User" means a person who uses this system to evaluate the reliability of information on the Internet.

[1449] A "URL" is a Uniform Resource Locator that identifies the location of information on the Internet.

[1450] "Text" refers to data consisting of a string of characters, and is generally expressed as a sentence.

[1451] "Means of receiving" refers to the method by which the server obtains the URL or text entered by the user.

[1452] "Analysis" is the process of evaluating the content of input information and determining its reliability.

[1453] "Generation" refers to creating new data, such as reliability scores or messages, based on the analysis results.

[1454] "Display means" refers to a method for providing an interface for showing analysis results and feedback messages to the user.

[1455] A "generative artificial intelligence model," also known as a generative AI model, is a machine learning model that analyzes text and data to generate new data.

[1456] "Emotion recognition" is a technology that detects a user's current emotional state by analyzing the user's input and behavioral data.

[1457] A "feedback message" is advice or information provided to the user based on the analysis results or emotion recognition results.

[1458] This invention combines a system that allows users to evaluate the reliability of information on the Internet and easily check the results with an emotion engine that recognizes the user's emotions. This combination not only evaluates the reliability of information, but also makes it possible to provide appropriate feedback according to the user's emotional state.

[1459] System configuration

[1460] This system mainly consists of three main components: a server, a terminal, and a user.

[1461] Server Configuration

[1462] The server consists of hardware and software that provides the following functions:

[1463] 1. Information receiving function: A function to receive URL or text information entered by the user.

[1464] 2. Information analysis function: A function that analyzes received URLs and text information and evaluates their reliability. This analysis uses a generative AI model (for example, a general generative AI model or natural language processing technology).

[1465] 3. Emotion recognition function: A function that recognizes the user's emotions using an emotion engine (e.g., a general emotion recognition API) based on the user's input information and past behavioral data.

[1466] 4. Result generation function: A function that generates evaluation results and appropriate feedback messages based on the reliability score and emotion recognition results.

[1467] 5. Result return function: A function that returns analysis results and emotion recognition results to the user.

[1468] Device configuration

[1469] A terminal is a device that a user uses to operate the system and provides the following functions:

[1470] 1. User interface: Provide an interface that includes a text box for users to enter the URL or text they want to rate, and a submit button.

[1471] 2. Information transmission function: A function that sends the URL or text entered by the user to the server using an HTTP request.

[1472] 3. Result display function: A function that displays the reliability evaluation results and emotion recognition results returned from the server on the user interface.

[1473] User operations

[1474] The user operates the system using a terminal and evaluates the reliability of information using the following procedure.

[1475] 1. Entering information: The user enters the URL or text for which they want to rate the trustworthiness into the system's input screen and presses the "Rate" button.

[1476] 2. Check the results: Check the reliability evaluation results and emotion recognition results returned from the server on the screen. Based on the displayed reliability score and emotion-based feedback, you can decide whether the information is trustworthy or not.

[1477] Hardware and software used

[1478] Server: A cloud server or dedicated server for running high-performance analysis capabilities and multi-function APIs.

[1479] Generative AI models: Generative AI models in general, specifically models based on natural language processing techniques (e.g., OpenAI's models).

[1480] Emotion recognition engine: A common emotion recognition API (e.g., Microsoft Azure's Emotion API).

[1481] Device: Any device that can connect to the internet, such as a PC, tablet, or smartphone.

[1482] Specific examples

[1483] For example, if a user wants to check the reliability of a news article, they paste the URL of the news article into the system's input screen and press the "Rate" button. The server retrieves the content of the news article from this URL, analyzes it using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message. The evaluation result, a message corresponding to the emotion, such as "80% reliability," is displayed on the user's device. For example, the message might read, "The reliability of this news article is 80%. If you are concerned, please check other reliable sources." In this way, users can easily evaluate the reliability of information on the Internet and receive appropriate feedback based on their emotional state.

[1484] This system can curb the spread of fake news and misinformation and disseminate reliable information.

[1485] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1486] Program processing flow

[1487] Step 1: Accept information input

[1488] User behavior

[1489] The user enters the URL or text for which they want to rate trustworthiness into the device's input screen and presses the "Rate" button. This input screen has a text box where the user can enter the information to be rated. For example, they enter the URL of a news article, "https: / / example.com / news-article".

[1490] Input: URL or text

[1491] Output: Input completion status to terminal

[1492] Step 2: Submit your input

[1493] Operation on the terminal side

[1494] The device sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user. For example, the URL of a news article is sent to the server in an HTTP POST request.

[1495] Input: URL or text entered by the user

[1496] Output: HTTP request to the server

[1497] Step 3: Analyze input information and assess its reliability

[1498] Server-side behavior

[1499] The server analyzes the received information and evaluates its reliability. This analysis is performed using a generative AI model (e.g., a general generative AI model). Specifically, the server inputs the received URL or text as a prompt into the generative AI model, which then analyzes the content and calculates a reliability score. For example, official announcements from public institutions and reports from major media outlets are rated as highly reliable, while anonymous blogs and social media posts are rated as less reliable.

[1500] Input: URL or text received from an HTTP request

[1501] Output: Confidence score

[1502] Step 4: Recognize emotions

[1503] Server-side behavior

[1504] The server uses an emotion engine (for example, a general emotion recognition API) to recognize the user's emotions based on the user's input information and past behavioral data. Specifically, the server passes the user's input text and past behavioral data to the emotion recognition API, which detects emotions in real time. For example, if the user uses emotional words, the emotion is recognized as "anger" or "anxiety."

[1505] Input: User input information, past behavior data

[1506] Output: Emotion recognition result

[1507] Step 5: Generating evaluation and emotion recognition results

[1508] Server-side behavior

[1509] The server integrates the reliability score and the emotion recognition results to generate an evaluation result and an appropriate feedback message, such as "The reliability of this news article is 80%. If you are concerned, please check other reliable sources."

[1510] Input: Confidence score, emotion recognition result

[1511] Output: Evaluation results, feedback messages

[1512] Step 6: Returning the results

[1513] Server-side behavior

[1514] The server returns the generated evaluation results and emotion recognition results to the user. The returned information includes a confidence score and a feedback message based on the emotion. For example, a confidence score of "80%" and a feedback message are returned as an HTTP response.

[1515] Input: Evaluation results, feedback message

[1516] Output: HTTP response to the user

[1517] Step 7: View the results

[1518] Operation on the terminal side

[1519] The device displays the reliability evaluation results and emotion recognition results received from the server on the user interface. Specifically, the reliability score is displayed in a visually easy-to-understand format, along with an appropriate message according to the user's emotion. For example, "80% reliability" is displayed in large letters, with a message below it saying, "If you are concerned, please check other reliable sources of information."

[1520] Input: HTTP response from the server

[1521] Output: Confidence score and feedback message in the user interface

[1522] (Application example 2)

[1523] 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."

[1524] In recent years, the Internet has become overflowing with a wide variety of information, and product reviews, especially on online shopping sites, have a significant influence on product purchasing decisions. However, not all reviews are necessarily reliable, making it difficult for users to discern their authenticity. Furthermore, users are easily influenced by their own emotions and may make inappropriate decisions based on unreliable information. Therefore, there is a need for a system that allows users to accurately evaluate the reliability of information and receive appropriate feedback based on their own emotions.

[1525] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for evaluating and displaying the reliability of information on the Internet, means for receiving a URL or text entered by a user, means for analyzing the content of the received URL or text and evaluating the reliability, means for displaying a reliability score of the analysis result, means for recognizing the user's emotions, and means for providing feedback according to the recognized user emotions. This allows the user to easily evaluate the reliability of information and further to receive appropriate feedback according to their own emotions.

[1526] "Means for evaluating and displaying the reliability of information on the Internet" is a function that analyzes the reliability of information present on the Internet and visually presents the results to the user.

[1527] The "means for receiving a URL or text input by a user" is a function that allows a user to input a URL or text to be evaluated into the system and send it to the server.

[1528] "Means for analyzing the content of received URLs or text and evaluating its reliability" refers to a function that analyzes the content of URLs or text received by the server and evaluates the reliability of that information.

[1529] The "means for displaying the reliability score of the analysis result" is a function for displaying the score calculated as a result of the reliability evaluation on the user interface.

[1530] "Means for recognizing user emotions" refers to a function that analyzes emotions based on user input and behavioral data.

[1531] The "means for providing feedback according to the recognized user emotions" is a function for displaying appropriate messages or recommendations based on the user's emotions.

[1532] "Means using generative AI models" refers to functions that use machine learning algorithms to analyze information and evaluate its reliability.

[1533] "Means of using reliable and unreliable sources" refers to a function that refers to predefined reliable and unreliable sources as evaluation criteria.

[1534] To implement this invention, it is necessary to build a system in which the server, terminal, and user operate in cooperation with each other. To understand the operation of this system, the roles and processes of each will be explained.

[1535] Server Operation

[1536] The server is responsible for the following main functions:

[1537] 1. Information reliability assessment

[1538] The server receives the URL or text entered by the user, analyzes its content, and evaluates its trustworthiness. To evaluate trustworthiness, it uses a generative AI model. Specifically, it analyzes the text using a Python natural language processing library (e.g., spaCy or NLTK) and calculates a trustworthiness score based on the analysis.

[1539] 2. Emotion recognition

[1540] The server is equipped with an emotion engine that analyzes emotions based on user input and behavioral data. For example, it analyzes the types of reviews users frequently read, their completion rate, and the duration of their stay. This is done using machine learning models (e.g., TensorFlow and PyTorch).

[1541] 3. Providing Feedback

[1542] The server generates appropriate feedback for the user based on the reliability evaluation result and emotion recognition result. This feedback message is customized according to the emotion.

[1543] Device behavior

[1544] The terminal provides an interface for the user to interact with the system. The specific operation is as follows:

[1545] 1. Providing a user interface

[1546] The terminal provides a text box for the user to enter the URL or text they want to rate, and a submit button, where the information entered by the user is accepted.

[1547] 2. Transmission of information

[1548] The terminal sends the URL or text entered by the user to the server using an HTTP request, which includes the information entered by the user.

[1549] 3. Displaying the results

[1550] After receiving the reliability evaluation results and emotion recognition results from the server, the device displays them on the user interface. The reliability score is displayed in a visually easy-to-understand format, along with an appropriate message based on the user's emotion.

[1551] User operations

[1552] The user performs direct operations to use the system, including the following:

[1553] 1. Enter your information

[1554] The user enters the URL or text for which they want to rate its trustworthiness into the system's input screen and presses the "Rate" button. Once the input is complete, the information is sent to the server.

[1555] 2. Check the results

[1556] The user checks the reliability evaluation results and emotion recognition results returned from the server on the screen. The user can then use the displayed reliability score and emotion-based feedback to determine whether the information is trustworthy.

[1557] Specific examples

[1558] For example, if a user wants to check the reliability of reviews on a product page, they copy the product's URL, paste it into the system's input screen, and press the "Rate" button. The server retrieves the product's review information from the URL, analyzes its content using a generative AI model, and calculates a reliability score. At the same time, the emotion engine recognizes the user's emotions and generates an appropriate feedback message.

[1559] The evaluation result, "75% reliability," and a message based on the user's emotion are displayed on the user's device. For example, the message might read, "The reliability of the reviews for this product is 75%. You may be optimistic about purchasing it, but please also check other reviews."

[1560] Prompt Sentence Examples

[1561] An example of a prompt sentence to be input to a generative AI model is as follows:

[1562] While a user is browsing a product page, analyze all reviews on that page, calculate the review credibility score, analyze user sentiment, and generate appropriate feedback messages based on that sentiment.

[1563] This system allows users to easily evaluate the reliability of information and receive appropriate feedback based on their personal feelings.

[1564] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1565] Step 1:

[1566] The user enters the URL or text they want to rate on the system's input screen and presses the "Rate" button. The entered information is sent to the terminal and then sent to the server as an HTTP request.

[1567] (Input) User URL or text

[1568] (Output) HTTP request

[1569] Step 2:

[1570] The server analyzes the HTTP request received from the device and extracts the URL or text data, then inputs the obtained data into a generative AI model to analyze the text content.

[1571] (Input) URL or text data in the HTTP request

[1572] (Output) Intermediate dataset of analysis results

[1573] Step 3:

[1574] The server evaluates the reliability of the received information based on the results of analysis using the generative AI model and calculates a reliability score.

[1575] (Input) Intermediate dataset of analysis results

[1576] (Output) Confidence score

[1577] Step 4:

[1578] The server uses an emotion engine to recognize the user's emotions based on the user's past behavioral data and current input data.

[1579] (Input) User's past behavior data and current input data

[1580] (Output) User emotion recognition results

[1581] Step 5:

[1582] The server integrates the confidence score with the emotion recognition result to generate a feedback message, which is customized according to the user's emotional state.

[1583] (Input) Reliability score, emotion recognition result

[1584] (Output) Feedback message

[1585] Step 6:

[1586] The server sends the reliability score and the feedback message together to the terminal.

[1587] (Input) Feedback message

[1588] (Output) HTTP response

[1589] Step 7:

[1590] The terminal receives the HTTP response from the server and displays the reliability score and feedback message on the user interface. The user can check the reliability of the information by referring to the reliability score and feedback message.

[1591] (Input) Confidence score and feedback message in the HTTP response

[1592] (Output) The confidence score and feedback message displayed in the user interface

[1593] 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.

[1594] 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.

[1595] 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 robot 414.

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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).

[1600] 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.

[1601] 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."

[1602] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1603] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1604] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1605] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1606] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1607] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1608] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1609] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1610] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1611] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1612] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1613] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1614] The following is further disclosed regarding the above embodiment.

[1615] (Claim 1)

[1616] A means for assessing and displaying the reliability of information on the Internet;

[1617] means for receiving a URL or text input from a user;

[1618] A means for analyzing the content of received URLs or text and assessing their trustworthiness;

[1619] a means for displaying a reliability score of the analysis result;

[1620] A system including:

[1621] (Claim 2)

[1622] 10. The system of claim 1, further comprising means for using a generative AI model to assess the reliability score.

[1623] (Claim 3)

[1624] 10. The system of claim 1, further comprising means for using reliable and unreliable sources as criteria for reliability assessment.

[1625] "Example 1"

[1626] (Claim 1)

[1627] means for receiving a URL or text input from a user;

[1628] using a generative AI model to analyze content from received URLs or text and assess trustworthiness;

[1629] a means for calculating a reliability score;

[1630] a means for displaying the calculated reliability score;

[1631] A system including:

[1632] (Claim 2)

[1633] 2. The system according to claim 1, further comprising means for calculating a reliability score based on the analysis result and returning the reliability score to the user.

[1634] (Claim 3)

[1635] 10. The system of claim 1, further comprising means for evaluating the reliability of the information source.

[1636] "Application Example 1"

[1637] (Claim 1)

[1638] A means for assessing and displaying the reliability of information on the Internet;

[1639] means for receiving a URL or text input from a user;

[1640] A means for analyzing the content of received URLs or text to assess their trustworthiness;

[1641] a means for displaying a reliability score of the analysis result;

[1642] a means for receiving information in real time through a user's visual device;

[1643] means for transmitting information captured on the visual device to a server;

[1644] means for displaying the confidence scores returned from the server on a visual device;

[1645] A system including:

[1646] (Claim 2)

[1647] 10. The system of claim 1, further comprising means for using a generative AI model to assess the reliability score.

[1648] (Claim 3)

[1649] 10. The system of claim 1, further comprising means for using reliable and unreliable sources as criteria for reliability assessment.

[1650] "Example 2: Combining Emotion Engines"

[1651] (Claim 1)

[1652] A means for assessing and displaying the reliability of information on the Internet;

[1653] means for receiving a URL or text input from a user;

[1654] A means for analyzing the content of received URLs or text and assessing their trustworthiness;

[1655] a means for displaying a reliability score of the analysis result;

[1656] A means of recognizing emotions based on user input information and past behavioral data,

[1657] means for generating and displaying a feedback message based on the recognized emotion;

[1658] A system including:

[1659] (Claim 2)

[1660] 10. The system of claim 1, further comprising means for using a generative artificial intelligence model to assess the reliability score.

[1661] (Claim 3)

[1662] 10. The system of claim 1, further comprising means for using reliable and unreliable sources as criteria for reliability assessment.

[1663] "Application example 2 when combining emotion engines"

[1664] (Claim 1)

[1665] A means for assessing and displaying the reliability of information on the Internet;

[1666] means for receiving a URL or text input from a user;

[1667] A means for analyzing the content of received URLs or text and assessing their trustworthiness;

[1668] a means for displaying a reliability score of the analysis result;

[1669] means for recognizing a user's emotion;

[1670] means for providing feedback in response to the recognized user emotion;

[1671] A system including:

[1672] (Claim 2)

[1673] a means for using a generative AI model to assess the trustworthiness score;

[1674] A means of analyzing user emotions and reflecting the results in feedback;

[1675] 10. The system of claim 1, comprising:

[1676] (Claim 3)

[1677] A method that uses reliable and unreliable sources as criteria for assessing trustworthiness;

[1678] a means for displaying appropriate feedback based on the user's emotions;

[1679] 10. The system of claim 1, comprising: [Explanation of symbols]

[1680] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for assessing and displaying the reliability of information on the Internet; means for receiving a URL or text input from a user; A means for analyzing the content of received URLs or text and assessing their trustworthiness; a means for displaying a reliability score of the analysis result; A system including:

2. 10. The system of claim 1, further comprising means for using a generative AI model to assess the reliability score.

3. 2. The system of claim 1, further comprising means for using reliable and unreliable sources as criteria for reliability evaluation.

Images