System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information from diverse information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for factually verifying the authenticity of the information analyzed using the generative artificial intelligence model and evaluating the authenticity as a percentage; means for visually displaying the evaluation results; and means for providing an interactive interface for a user to ask additional questions about the evaluation results and answer the questions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, as information dissemination via the internet has increased, the spread of false and inaccurate information has become a problem. In particular, the credibility of news obtained from various platforms such as social media and messaging applications is often questioned. At the same time, users want to obtain accurate information quickly from a variety of sources, and there is a demand to meet this demand. Therefore, there is a need for technology that can appropriately evaluate the credibility of news and provide it to users in a visually understandable manner. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system that collects news from various information sources and analyzes its content using a generative artificial intelligence model. The system analyzes the collected news data and extracts key information elements. The system then uses the generative artificial intelligence model to fact-check the credibility of the analyzed information and evaluate its credibility as a percentage. The evaluation results are displayed in a visually easy-to-understand format and also provide an interactive interface for users to ask additional questions. In this way, users can quickly and easily determine the credibility of various news sources.

[0006] "Diverse information sources" refers to different types of information sources, such as social media, messaging applications and online news platforms.

[0007] "Generative artificial intelligence model" refers to artificial intelligence technology that includes advanced machine learning algorithms that can analyze and generate text data.

[0008] "Credibility" refers to a measure of the reliability of a particular piece of information or news based on facts.

[0009] "Rating as a percentage" refers to expressing the credibility of information numerically as a percentage.

[0010] "Visual display" refers to presenting data and evaluation results to users in an easy-to-read format such as graphs or charts.

[0011] An "interactive interface" is an interface that allows a user to enter questions or requests into a system and the system to provide appropriate responses. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results, allowing users to quickly and easily determine the credibility of information collected from a variety of news sources.

[0034] News Gathering Phase

[0035] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[0036] example:

[0037] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[0038] The server retrieves news messages from the official account of the messaging application.

[0039] The server collects top news stories using the API of an online news platform.

[0040] News Analysis Phase

[0041] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[0042] example:

[0043] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[0044] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[0045] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[0046] Credibility assessment phase

[0047] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[0048] example:

[0049] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[0050] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[0051] Data Display and User Interaction Phase

[0052] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[0053] example:

[0054] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[0055] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[0056] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[0057] In this way, this system can quickly and accurately evaluate the credibility of information collected from various news sources and provide the results to users. Furthermore, through user interaction, users can obtain more detailed information, making this a very easy-to-use service.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[0061] Step 2:

[0062] The server uses the LINE API to collect news messages from LINE official accounts.

[0063] Step 3:

[0064] The server retrieves the latest top news stories through the Yahoo! News API.

[0065] Step 4:

[0066] The server inputs the collected tweet data into a generative AI model to extract key information elements (e.g., people, places, events).

[0067] Step 5:

[0068] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[0069] Step 6:

[0070] The server inputs the text of Yahoo! News articles into a generative AI model, analyzes the content, and extracts key points.

[0071] Step 7:

[0072] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[0073] Step 8:

[0074] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[0075] Step 9:

[0076] The server stores the results of the credibility assessment in a database for later viewing.

[0077] Step 10:

[0078] A user logs into the web application using a terminal and views the parsed news list.

[0079] Step 11:

[0080] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[0081] Step 12:

[0082] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[0083] Step 13:

[0084] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[0085] Step 14:

[0086] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[0087] Step 15:

[0088] The user reviews the answers provided and asks the chatbot further questions if necessary.

[0089] Example 1

[0090] 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."

[0091] In today's world, it is extremely important to quickly and accurately evaluate the credibility of news collected from a variety of sources. However, conventional systems collect information, analyze it, evaluate its credibility, and visually display the results separately, making the overall process complex and time-consuming. This also makes it difficult for users to ask detailed questions about the evaluation results. This increases the burden on users when judging the credibility of news, which has been an issue.

[0092] 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.

[0093] In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for users to ask and answer follow-up questions about the evaluation results; means for preprocessing the collected information; and means for displaying the evaluation results in chart or graph format. This enables the credibility of news to be evaluated quickly and accurately and the results to be visually confirmed. Furthermore, users can easily ask detailed questions about the evaluation results, thereby reducing the burden on users.

[0094] "Information sources" refers to various information sources, such as social media, messaging applications, and online news platforms.

[0095] "Generative artificial intelligence models" refer to advanced algorithms and software systems that can understand and generate natural language, such as GPT-4.

[0096] "Analysis" refers to the process of inputting collected news data into a generative artificial intelligence model to extract key information elements (e.g., people, places, events).

[0097] "Credibility assessment" refers to the process of fact-checking analyzed news information and then quantifying its credibility in the form of a percentage.

[0098] "Preprocessing" refers to the process of cleaning collected news data and filtering out irrelevant information before analysis.

[0099] "Dialogue interface" means an interface that allows a user to ask follow-up questions and receive answers to those questions through natural language interaction with the system.

[0100] "Charts and graph formats" refers to figures and diagrams that display evaluation results in a visually easy-to-understand manner.

[0101] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results. This system is mainly composed of a server, terminals, and users.

[0102] First, in the news gathering phase, the server collects news data using the APIs of various information sources (e.g., social media, messaging applications, online news platforms). Specifically, it uses social media APIs to collect posts containing specific hashtags, obtains news messages from official messaging app accounts, and uses online news platform APIs to obtain the latest news. This gathering process allows for the rapid and efficient accumulation of diverse news data.

[0103] Next, in the news analysis phase, the server inputs the collected news data into a generative AI model (e.g., GPT-4) to extract key information elements (e.g., people, places, and events). After preprocessing the collected news data and removing unnecessary information, the generative AI model is given prompts such as the following to analyze it. This analysis organizes the main points of each news item and extracts important information.

[0104] Example prompt sentence:

[0105] "Extract the main topics and related keywords of tweets about the latest news."

[0106] "Please summarize the main points of this news text."

[0107] In the credibility evaluation phase, the server compares the analyzed news information with other reliable sources and evaluates its credibility as a percentage using a generative artificial intelligence model. For example, the content of a specific news article is compared and collated with other major news sites and databases to quantify its credibility. This allows the credibility of each news item to be clearly displayed, supporting user decision-making.

[0108] Finally, in the data display and user interaction phase, the user accesses the system using a device (e.g., a smartphone or PC) to view the credibility assessment results. The server visually displays the assessment results in the form of charts and graphs, along with details of each news item and the reasons for its assessment. The user can also ask additional questions through a dialogue interface, and the answers to those questions are also provided using the generative AI model. For example, if the user asks, "Tell me why the credibility of this news is 70%," the server inputs this prompt into the generative AI model and returns an appropriate answer.

[0109] The present invention enables the rapid and accurate evaluation and visual display of the credibility of information collected from multiple news sources, and also allows users to ask detailed questions in an interactive format, providing a highly user-friendly service.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1:

[0112] The server collects news data from a variety of sources.

[0113] Specific behavior:

[0114] The server uses a social media API endpoint and an access token to collect posts containing a specific hashtag (e.g., "breaking news"), taking the posts containing the hashtag as input and obtaining the metadata, text, and related information for the posts as output.

[0115] The server uses the messaging application's API to retrieve news messages from official accounts, using the official account's authentication information as input and collecting the news messages and their metadata as output.

[0116] The server retrieves the latest top news stories using the API of an online news platform (e.g., Google News API), using the API key and endpoint as input, and gets the list of latest news articles along with their metadata and article text as output.

[0117] Step 2:

[0118] The server preprocesses the collected news data.

[0119] Specific behavior:

[0120] The server cleans irrelevant elements such as hashtags, links, and user mentions from the collected tweet text. At this time, the tweet text is used as input, and the clean text with unnecessary elements removed is obtained as output.

[0121] The server filters news text obtained from a messaging application to remove unnecessary parts, giving message text as input and obtaining the news text with unnecessary parts removed as output.

[0122] The server filters advertisements and noise data from article texts of online news platforms, using the collected article texts as input and obtaining the filtered clean article texts as output.

[0123] Step 3:

[0124] The server inputs the preprocessed news data into the generative AI model for analysis.

[0125] Specific behavior:

[0126] The server inputs the preprocessed tweet data into a generative AI model (e.g., GPT-4) and analyzes it using the prompt, "Please extract the main topic and related keywords of this tweet." At this time, the clean tweet data is given as input, and the main topic and related keywords are obtained as output.

[0127] The server inputs the preprocessed news text obtained from the messaging application into a generative AI model to extract gist points, using the clean news text as input and obtaining gist points as output.

[0128] The server inputs the preprocessed article text obtained from the online news platform into a generative AI model to analyze and summarize the main points of the content, using the clean article text as input and obtaining the summarized information as output.

[0129] Step 4:

[0130] The server evaluates the credibility of the news based on the analysis results.

[0131] Specific behavior:

[0132] The server compares the analyzed news information with other reliable sources (e.g., major news sites or databases), using the analysis results and data from reliable sources as inputs and obtaining the comparison results as output.

[0133] The server evaluates the credibility of the news in percentage format based on the matching result, using the matching result as input and obtaining a percentage value indicating the credibility of the news as output.

[0134] Step 5:

[0135] The server creates data for visually displaying the credibility evaluation results.

[0136] Specific behavior:

[0137] The server converts the credibility assessment results into charts and graphs, using the credibility assessment results as input and obtaining data converted into a visually displayable format as output.

[0138] Step 6:

[0139] The user accesses the system using a terminal and checks the credibility evaluation results.

[0140] Specific behavior:

[0141] A user logs in to a web application from a terminal and accesses a homepage. At this time, a username and password are used as input, and the homepage screen after successful authentication is obtained as output.

[0142] The user opens a screen to display the news credibility list. At this time, data for visually displaying the credibility evaluation results is used as input, and the results displayed in chart and graph format are obtained as output.

[0143] Step 7:

[0144] The user uses the interactive interface to ask follow-up questions.

[0145] Specific behavior:

[0146] A user uses the interactive interface to type, "Tell me why this news story is 70% reliable," and the user's question is used as input.

[0147] The server uses a generative AI model to generate an answer to the question and respond to the user, taking the user's question as input and obtaining an appropriate answer as output.

[0148] By going through the above steps, the system can perform consistent processing from news collection to credibility assessment, visual display, and user interaction.

[0149] (Application example 1)

[0150] 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."

[0151] In modern society, it is difficult to determine the credibility of news and information provided by a variety of sources, and especially on digital platforms such as virtual stores, users lack the means to immediately determine the credibility of news related to products. For this reason, there is a need to provide users with the information they need to make decisions quickly and reliably when purchasing products.

[0152] 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.

[0153] In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and rating the credibility as a percentage; means for visually displaying the rating results; means for providing an interactive interface for users to ask and answer follow-up questions about the rating results; and display means for viewers to check related news and credibility ratings of products in real time while viewing products in a virtual store. This allows users to quickly evaluate the credibility of news information related to a product when selecting a product in the virtual store, which can help them make a purchasing decision.

[0154] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[0155] A "generative artificial intelligence model" refers to a learning system that uses natural language processing techniques to analyze text data and extract and generate specific information.

[0156] "Key information elements" refer to people, places, events, and other elements that are deemed important in news or information.

[0157] "Credibility" refers to the reliability of information based on facts and is evaluated as a percentage based on specific criteria.

[0158] "Visual display means" refers to a method of displaying the results of the credibility assessment of collected and analyzed information in a visual format such as a graph or chart so that users can easily understand it.

[0159] "Interactive interface" refers to an interactive user interface that allows a user to ask a system additional questions and for the system to respond to those questions.

[0160] A "virtual store" refers to a virtual shopping environment created using the Internet and VR technology.

[0161] "Display means" refers to the method by which information is displayed to the user via a device such as smart glasses or a head-mounted display.

[0162] The present invention relates to a system for gathering, analyzing, and evaluating the credibility of news, and visually displaying the results. This system is particularly designed to allow users to check related news and credibility ratings of products in real time within a virtual store.

[0163] News Gathering Phase

[0164] The server collects news data from various information sources, such as social media, messaging applications, and online news platforms. To achieve this, it uses the APIs of each platform. For example, it uses the APIs of social media to collect tweets containing a specific hashtag. It also obtains news messages from official accounts on messaging applications and uses the APIs of online news platforms to collect top news stories.

[0165] News Analysis Phase

[0166] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements from the news (e.g., people, places, and events). For example, acquired tweet data is input into the generative AI model to extract key topics and related keywords. It also analyzes and extracts key elements from news text obtained from messaging applications.

[0167] Credibility assessment phase

[0168] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., reliable news sites and databases). The credibility is expressed as a percentage. For example, the content of a particular news article is compared with other reliable sources to assess its credibility. The server also checks tweet content against multiple news sites to determine its credibility.

[0169] Data Display and User Interaction Phase

[0170] Users can access the system using a device (smart glasses or head-mounted display) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use a dialogue interface to ask additional questions, and the server will provide answers using a generative AI model. For example, they can ask, "Tell me why the credibility of this news is 70%," and receive a detailed answer from the server.

[0171] The specific hardware and software you will use

[0172] Hardware: Smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest 2)

[0173] Software: Python, OpenAI GPT-4 API, News API, Matplotlib

[0174] Case studies

[0175] For example, imagine a user is browsing a new smartphone in a virtual store. The smart glasses display a news item about the release of a new smartphone, along with a news description that reads, "The latest model is equipped with new AI features and is attracting a lot of attention." The generative AI model then displays a credibility rating for this news item, visually indicating a result of, say, 85%.

[0176] The prompt for the generative AI model is:

[0177] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] The server collects news data using APIs from various sources, such as social media, messaging applications, and online news platforms, and retrieves tweets containing specific hashtags (e.g., breaking news), news messages from official accounts, and top news stories.

[0181] Input: API of each platform, hashtag

[0182] Output: A list of news data retrieved from each platform

[0183] Step 2:

[0184] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content, which extracts key information elements (people, places, events) from the news.

[0185] Input: List of news data

[0186] Output: Analysis results for each news article (text structure including key information elements)

[0187] Step 3:

[0188] The server compares the analyzed news information with other reliable sources to assess its credibility, and calculates a percentage based on the credibility rating to filter out less reliable information.

[0189] Input: Parsed news data, list of reliable sources

[0190] Output: The credibility rating (percentage) of each news article

[0191] Step 4:

[0192] The server generates data to visually display the evaluation results, including graphs and charts, and uses libraries such as Matplotlib to convert the data into a format that is easy for users to understand.

[0193] Input: Credibility assessment result

[0194] Output: Visual display data (in the form of graphs and charts)

[0195] Step 5:

[0196] The user accesses the system using a device (smart glasses or a head-mounted display) and visually checks the credibility evaluation results. Information is sent so that the results are displayed on the smart glasses or head-mounted display.

[0197] Input: Visual display data

[0198] Output: The credibility assessment result displayed on the user's device.

[0199] Step 6:

[0200] The user uses a conversational interface to ask follow-up questions about the results. These questions are sent to the generative AI model, and the server generates an appropriate answer to the question. For example, "Tell me why this news story is 70% reliable."

[0201] Input: User question

[0202] Output: Answer from the generative AI model (detailed explanation)

[0203] Example prompt sentence:

[0204] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[0205] 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.

[0206] This invention is a system that collects, analyzes, and evaluates the credibility of news, and visually displays the results, and also combines it with an emotion engine that recognizes the user's emotions. This system allows users to quickly and easily judge the credibility of information collected from various news sources, and receive appropriate information displayed based on their emotions.

[0207] News Gathering Phase

[0208] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[0209] example:

[0210] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[0211] The server retrieves news messages from the official account of the messaging application.

[0212] The server collects top news stories using the API of an online news platform.

[0213] News Analysis Phase

[0214] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[0215] example:

[0216] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[0217] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[0218] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[0219] Credibility assessment phase

[0220] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[0221] example:

[0222] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[0223] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[0224] Data Display and User Interaction Phase

[0225] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[0226] example:

[0227] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[0228] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[0229] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[0230] Emotion Recognition Phase

[0231] The server analyzes the user's input information (e.g., text input, voice input, facial recognition, etc.) and recognizes the user's emotions using an emotion engine. The emotion engine changes the way the credibility evaluation results are displayed based on the user's emotions.

[0232] example:

[0233] When a user checks the news evaluation results, they input information into the system indicating "anxiety" or "doubt."

[0234] The server uses an emotion engine to recognize the user's emotion as "anxiety" and displays the credibility evaluation results in more detail according to the emotion.

[0235] When the user inputs something that indicates "relief" or "understanding," the server uses an emotion engine to recognize the user's emotion and selects an appropriate information display format.

[0236] In this way, the system not only quickly and accurately evaluates the credibility of information collected from a variety of news sources and provides the results to users, but also optimizes the way information is displayed according to the user's emotions, thereby realizing an extremely user-friendly service.

[0237] The processing flow will be explained below.

[0238] Step 1:

[0239] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[0240] Step 2:

[0241] The server uses the LINE API to collect news messages from LINE official accounts.

[0242] Step 3:

[0243] The server retrieves the latest top news stories through the Yahoo! News API.

[0244] Step 4:

[0245] The tweet data collected by the server is input into a generative AI model to extract key information elements (people, places, events).

[0246] Step 5:

[0247] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[0248] Step 6:

[0249] The server inputs the text of Yahoo! News articles into a generative AI model, which analyzes the content and extracts key information elements.

[0250] Step 7:

[0251] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[0252] Step 8:

[0253] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[0254] Step 9:

[0255] The server stores the results of the credibility assessment in a database for later viewing.

[0256] Step 10:

[0257] The server uses an emotion engine to analyze the user's input information (e.g., text input, voice input, facial recognition) and recognize the user's emotions.

[0258] Step 11:

[0259] A user logs into the web application using a terminal and views the parsed news list.

[0260] Step 12:

[0261] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[0262] Step 13:

[0263] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[0264] Step 14:

[0265] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[0266] Step 15:

[0267] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[0268] Step 16:

[0269] The server uses an emotion engine to generate a customized response based on the user's emotion. For example, if the user indicates "anxiety," the server provides additional detailed fact-checking information.

[0270] Step 17:

[0271] The user reviews the answers provided and asks the chatbot further questions if necessary.

[0272] Step 18:

[0273] The server adjusts the way news is displayed according to the user's emotions and provides information in a format more suited to the user.

[0274] Example 2

[0275] 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."

[0276] In today's world, advanced analysis and credibility assessment are required to quickly and accurately evaluate the credibility of news and information obtained from diverse sources and provide it visually to users. However, conventional systems only evaluate credibility centrally, making it difficult to optimize the way information is displayed in response to the user's emotions. Furthermore, they lack an interactive interface that can answer users' follow-up questions in real time. Therefore, there is a need for a system that is easy for users to use.

[0277] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask follow-up questions about the evaluation results and answer those questions; means for analyzing information input by the user and recognizing the user's emotions using an emotion engine; and means for changing the display method of the credibility evaluation results based on the user's emotions. This makes it possible not only to quickly and accurately evaluate the credibility of collected information and provide the results to the user, but also to optimize the information display method according to the user's emotions.

[0278] "Diverse information sources" refers to multiple sources that provide different types of information, such as social media, messaging applications, and online news platforms.

[0279] A "generative artificial intelligence model" is an advanced AI model for natural language processing and machine learning, used to analyze data and make generation and predictions according to specific tasks.

[0280] "Key information elements" refer to entities such as people, places, and events that are of particular importance in the collected information.

[0281] "Fact-checking for authenticity" refers to the process of verifying whether the collected and analyzed information is consistent with other reliable sources and databases.

[0282] "Interactive interface" refers to a user interface that allows a user to ask questions and receive answers in real time.

[0283] "User input information" refers to various data provided by a user to the system, such as text input, voice input, or facial recognition.

[0284] An "emotion engine" refers to an algorithm or software that analyzes a user's input information to recognize their emotional state (e.g., anxiety, relief, understanding, etc.) and optimizes the system's response and display content.

[0285] "Changing the display method of the credibility assessment results" refers to the process of dynamically adjusting the presentation format of the credibility assessment results (e.g., graphs, detailed reports, etc.) according to the user's emotional state.

[0286] The present invention is a system that collects information from various information sources, analyzes it, evaluates its credibility, and then visually presents it to the user. Furthermore, it has the feature of recognizing the user's emotions and optimizing the way information is presented accordingly. Below, we will explain the mode for implementing the invention by following a specific flow.

[0287] First, the server collects news data from multiple information sources, including social media, messaging applications, and online news platforms. For example, from social media, the server uses the Twitter API to retrieve tweets containing a specific hashtag (e.g., breaking news). From messaging applications, the server uses the LINE API to retrieve news messages from official accounts. Finally, from online news platforms, the server uses the Google News API to collect top news stories.

[0288] The server uses a generative AI model (e.g., GPT-4) to analyze the collected news data. For example, the following prompt sentences can be used when analyzing news text:

[0289] "Please extract the key information elements from this news article."

[0290] "What are the main events and related keywords in this tweet?"

[0291] Based on these prompts, the generative AI model analyzes the news data and extracts key information elements (people, places, events, etc.).

[0292] Next, the server evaluates the credibility of the analyzed news information by checking it against other reliable sources (e.g., reliable news sites or databases). The credibility is expressed as a percentage, for example:

[0293] "We compare the content of a particular article with other reliable sources and rate its credibility at 85%."

[0294] "The tweet content was checked against multiple news sites and its credibility was determined to be 70%."

[0295] The server provides a means to visually display the credibility evaluation results. When a user accesses the system on a device (smartphone or PC), the evaluation results are provided in a visually easy-to-understand format, such as a graph or chart. For example, when a user logs into a web application and opens a screen displaying a list of news credibility, the server presents the credibility evaluation results in the form of a chart, along with details of each news item and the reasons for its evaluation.

[0296] Furthermore, the server uses an emotion engine to recognize the user's emotions. It analyzes the text, voice, or facial recognition information entered by the user and recognizes the user's emotions as "anxiety," "relief," "understanding," etc. For example, if a user inputs "anxiety" or "doubt" when checking the news evaluation results, the server will recognize this as "anxiety" using the emotion engine and display more detailed credibility evaluation results according to that emotion.

[0297] This system allows users to quickly and accurately evaluate the credibility of information collected from various news sources and visually understand the results.In addition, the way information is displayed is optimized according to the user's emotions, making it an extremely user-friendly service.

[0298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0299] Step 1: Gathering news

[0300] A server collects news data from social media, messaging applications, and online news platforms.

[0301] Input: hashtags on social media, news messages on messaging applications, news articles on online news platforms.

[0302] Processing: Use APIs to retrieve information from each platform: from social media, retrieve tweets containing specific hashtags; from messaging applications, collect news messages from official accounts; and from online news platforms, collect top stories.

[0303] Output: News data in JSON format.

[0304] Specific operation: Sends API requests and receives news data from each information source.

[0305] Step 2: News Preprocessing

[0306] The server standardizes the collected news data and converts it into text format.

[0307] Input: Collected news data in JSON format.

[0308] Processing: Data cleaning, removing unnecessary HTML tags and special characters, formatting the text, converting the news data into text format.

[0309] Output: Preprocessed news data in text format.

[0310] Specific behavior: Runs data cleaning scripts and performs text formatting.

[0311] Step 3: News analysis

[0312] The server uses a generative AI model (GPT-4) to analyze the preprocessed news data.

[0313] Input: Preprocessed news data in text format.

[0314] Processing: Generative AI models analyze news data and extract key information elements (people, places, events).

[0315] Prompts: "Please extract the main information elements from this news article.", "What are the keywords related to the main events in this tweet?"

[0316] Output: Extracted key information elements.

[0317] Specific operation: News text is input into the generative AI model and analysis results are obtained.

[0318] Step 4: Credibility assessment

[0319] The server uses the generated AI model to evaluate the credibility of the analyzed news information.

[0320] Input: Key information elements of the parsed news.

[0321] Processing: Check against trusted sources and rate the credibility as a percentage, e.g., compare with trusted news sites or databases.

[0322] Output: Belief assessment result (e.g., 85% Belief).

[0323] Specific operation: Compare the analyzed information with a reliability database and calculate a credibility score.

[0324] Step 5: Data display

[0325] The server visually displays the credibility evaluation results.

[0326] Input: The credibility assessment result.

[0327] Processing: Rendering the evaluation results in a visually understandable format such as graphs or charts.

[0328] Output: Visually displayed credibility assessment results.

[0329] What it does: Renders the evaluation results in a graph format in a web browser and provides detailed information.

[0330] Step 6: User Interaction

[0331] The user accesses the system at a terminal and asks additional questions about the evaluation results.

[0332] Input: The user's question.

[0333] Processing: Uses generative AI models to generate answers to user questions and provide a conversational interface.

[0334] Output: The answer to the question asked by the user.

[0335] Specific operation: The user's question is input into the generative AI model, an appropriate answer is generated, and it is presented to the user through the interface.

[0336] Step 7: Emotion Recognition

[0337] The server analyzes the user's input information and recognizes the user's emotions using an emotion engine.

[0338] Input: User input (text, voice, facial recognition).

[0339] Processing: Uses an emotion engine to recognize the user's emotions as "anxiety," "relief," "understanding," etc.

[0340] Output: Perceived user emotion.

[0341] What it does: It uses text analysis, speech analysis, and facial recognition models to determine the user's emotions.

[0342] Step 8: Adjust the display

[0343] The server changes the display method of the credibility evaluation result based on the user's emotions recognized by the server.

[0344] Input: Perceived user emotion.

[0345] Processing: Select an appropriate information display format according to the user's emotion and re-render.

[0346] Output: Credibility assessment results visually presented in a tailored presentation format.

[0347] Specific behavior: Dynamically change the display format based on the user's sentiment, such as displaying detailed information or a concise summary.

[0348] (Application example 2)

[0349] 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."

[0350] Current news gathering systems quickly evaluate the credibility of news information collected from various information sources and provide it to users, but they lack the ability to present information that takes user emotions into consideration. As a result, appropriate information display methods are not applied to users who feel anxious or suspicious, making it difficult to improve the user experience. Furthermore, the lack of a system specialized in providing news information in autonomous vehicles limits the means of providing reliable news information in real time.

[0351] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask and answer follow-up questions about the evaluation results; means for analyzing user input information and recognizing the user's emotions using an emotion engine; and means for dynamically changing the information display format in accordance with the user's emotions. This makes it possible to provide reliable news information in real time within an autonomous vehicle while taking user emotions into consideration.

[0352] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[0353] A "generative artificial intelligence model" is a deep learning model that uses artificial intelligence, and refers to a system that can analyze, generate, and evaluate information based on large amounts of data.

[0354] "Credibility" indicates the likelihood that collected information is factual, and refers to the degree to which it is evaluated as a percentage.

[0355] An "emotion engine" refers to an algorithm or system that analyzes user input (e.g., language, voice, facial expressions) and identifies their emotional state.

[0356] "Information presentation" refers to the way in which information is visually or interactively presented to a user, and includes different presentation formats such as graphical formats, detailed views, etc.

[0357] An "autonomous vehicle" refers to a vehicle that uses artificial intelligence and sensor technology to drive autonomously.

[0358] "Conversational interface" refers to an interface that allows a user to interact with a system using natural language, including interactions such as question-answering and information search.

[0359] "Real-time" refers to the temporal characteristic that enables a system to process information almost instantly and provide it to the user.

[0360] In order to implement the present invention, a system is constructed in which the elements of the server, the terminal, and the user function in cooperation with each other. A specific embodiment of this system is shown below.

[0361] First, the server collects information from various information sources, including social media, messaging applications, online news platforms, etc. The server uses the API of each platform to collect information. For example, the server may use the API of a social media platform to collect posts containing a specific hashtag.

[0362] Next, the collected information is analyzed using a generative AI model, such as GPT-4. Through this analysis, key information elements are extracted from the news content. Specifically, the server inputs the tweet data it has acquired into the generative AI model, which then extracts topics and related keywords.

[0363] The server then evaluates the credibility of the analyzed information. This evaluation is also performed using a generative AI model, which compares the information with other reliable sources and displays the credibility as a percentage. For example, the server compares the content of a particular news article with other reliable sources and rates its credibility as 85%.

[0364] The evaluation results are displayed visually. Users access the system through a terminal (such as the dashboard or head-up display of an autonomous vehicle) and check the information. The evaluation results are displayed in easy-to-understand visual formats such as graphs and charts.

[0365] Furthermore, when a user asks additional questions about the evaluation results, a dialogue-based interface is used. When the user inputs information from the device, the server uses the generative AI model to provide an appropriate answer to the question. For example, if a user asks, "Please tell me why the credibility of this news is 70%," the server uses the generative AI model to provide an answer.

[0366] The server also analyzes the user's input (e.g., text input or voice input) and uses an emotion engine to recognize the user's emotions. Based on this, the way information is displayed is dynamically changed depending on the user's emotions. For example, if the user inputs an expression indicating "anxiety" or "doubt," the server will use the emotion engine to recognize the user's emotion as "anxiety" and display a detailed evaluation result.

[0367] For example, if a user feels uneasy about recent news, the server will provide a detailed assessment of the news' credibility based on this input. An example of a prompt would be "Evaluate the credibility of the following news: [news content]," and the AI ​​model will analyze its credibility.

[0368] As described above, the present invention realizes a system that responds to the user's emotions while providing reliable news information in real time within an autonomous vehicle.

[0369] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0370] Step 1:

[0371] The server collects information from various information sources (social media, messaging applications, online news platforms) and uses the API of each platform to retrieve posts containing a specific hashtag, for example, from the social media API.

[0372] Input: Data from each platform's API

[0373] Output: Raw collected news data

[0374] Step 2:

[0375] The server analyzes the collected news data using a generative artificial intelligence model (such as GPT-4), which extracts key information elements from the news content.

[0376] Input: Collected news data

[0377] Data processing: News data is input into a generative AI model to analyze and extract key topics and keywords.

[0378] Output: The main information elements parsed

[0379] Step 3:

[0380] The server evaluates the veracity of the analyzed information, again using a generative AI model and comparing it with other reliable sources, and the evaluation result is expressed as a percentage.

[0381] Input: Parsed key information elements

[0382] Data calculation: Compare with other reliable sources and calculate the credibility as a percentage

[0383] Output: Credibility evaluation result (e.g., 85%)

[0384] Step 4:

[0385] The server converts the credibility assessment results into a visually displayed data format, which the user can view on their device (dashboard or head-up display).

[0386] Input: Credibility evaluation result

[0387] Data processing: Converting data into graphs and charts

[0388] Output: Visually displayable data

[0389] Step 5:

[0390] The user uses a terminal to access an interactive interface to ask follow-up questions about the assessment results, and the server uses a generative AI model to provide appropriate answers to these questions.

[0391] Input: User question

[0392] Data Computation: Using generative AI models to analyze questions and generate answers

[0393] Output: The answer that is presented to the user

[0394] Step 6:

[0395] The user inputs their emotions (for example, "I'm worried about the recent news") into the device. The server analyzes this using an emotion engine and recognizes the user's emotions.

[0396] Input: User emotion input

[0397] Data Computation: Uses an emotion engine to analyze input text and voice to identify user emotions

[0398] Output: Parsed user's emotional state (e.g., "anxiety")

[0399] Step 7:

[0400] The server dynamically changes the way information is displayed depending on the user's emotional state. For example, if the user expresses "anxiety," the server displays the credibility evaluation results in detail.

[0401] Input: User's emotional state and credibility evaluation results

[0402] Data processing: Display method adjusted according to emotional state

[0403] Output: Dynamically changed display format (e.g., detailed view)

[0404] These steps enable the system to respond to user sentiment and provide reliable news information in real time within self-driving vehicles.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] [Second embodiment]

[0409] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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."

[0421] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results, allowing users to quickly and easily determine the credibility of information collected from a variety of news sources.

[0422] News Gathering Phase

[0423] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[0424] example:

[0425] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[0426] The server retrieves news messages from the official account of the messaging application.

[0427] The server collects top news stories using the API of an online news platform.

[0428] News Analysis Phase

[0429] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[0430] example:

[0431] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[0432] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[0433] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[0434] Credibility assessment phase

[0435] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[0436] example:

[0437] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[0438] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[0439] Data Display and User Interaction Phase

[0440] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[0441] example:

[0442] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[0443] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[0444] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[0445] In this way, this system can quickly and accurately evaluate the credibility of information collected from various news sources and provide the results to users. Furthermore, through user interaction, users can obtain more detailed information, making this a very easy-to-use service.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[0449] Step 2:

[0450] The server uses the LINE API to collect news messages from LINE official accounts.

[0451] Step 3:

[0452] The server retrieves the latest top news stories through the Yahoo! News API.

[0453] Step 4:

[0454] The server inputs the collected tweet data into a generative AI model to extract key information elements (e.g., people, places, events).

[0455] Step 5:

[0456] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[0457] Step 6:

[0458] The server inputs the text of Yahoo! News articles into a generative AI model, analyzes the content, and extracts key points.

[0459] Step 7:

[0460] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[0461] Step 8:

[0462] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[0463] Step 9:

[0464] The server stores the results of the credibility assessment in a database for later viewing.

[0465] Step 10:

[0466] A user logs into the web application using a terminal and views the parsed news list.

[0467] Step 11:

[0468] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[0469] Step 12:

[0470] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[0471] Step 13:

[0472] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[0473] Step 14:

[0474] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[0475] Step 15:

[0476] The user reviews the answers provided and asks the chatbot further questions if necessary.

[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] In today's world, it is extremely important to quickly and accurately evaluate the credibility of news collected from a variety of sources. However, conventional systems collect information, analyze it, evaluate its credibility, and visually display the results separately, making the overall process complex and time-consuming. This also makes it difficult for users to ask detailed questions about the evaluation results. This increases the burden on users when judging the credibility of news, which has been an issue.

[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: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for users to ask and answer follow-up questions about the evaluation results; means for preprocessing the collected information; and means for displaying the evaluation results in chart or graph format. This enables the credibility of news to be evaluated quickly and accurately and the results to be visually confirmed. Furthermore, users can easily ask detailed questions about the evaluation results, thereby reducing the burden on users.

[0482] "Information sources" refers to various information sources, such as social media, messaging applications, and online news platforms.

[0483] "Generative artificial intelligence models" refer to advanced algorithms and software systems that can understand and generate natural language, such as GPT-4.

[0484] "Analysis" refers to the process of inputting collected news data into a generative artificial intelligence model to extract key information elements (e.g., people, places, events).

[0485] "Credibility assessment" refers to the process of fact-checking analyzed news information and then quantifying its credibility in the form of a percentage.

[0486] "Preprocessing" refers to the process of cleaning collected news data and filtering out irrelevant information before analysis.

[0487] "Dialogue interface" means an interface that allows a user to ask follow-up questions and receive answers to those questions through natural language interaction with the system.

[0488] "Charts and graph formats" refers to figures and diagrams that display evaluation results in a visually easy-to-understand manner.

[0489] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results. This system is mainly composed of a server, terminals, and users.

[0490] First, in the news gathering phase, the server collects news data using the APIs of various information sources (e.g., social media, messaging applications, online news platforms). Specifically, it uses social media APIs to collect posts containing specific hashtags, obtains news messages from official messaging app accounts, and uses online news platform APIs to obtain the latest news. This gathering process allows for the rapid and efficient accumulation of diverse news data.

[0491] Next, in the news analysis phase, the server inputs the collected news data into a generative AI model (e.g., GPT-4) to extract key information elements (e.g., people, places, and events). After preprocessing the collected news data and removing unnecessary information, the generative AI model is given prompts such as the following to analyze it. This analysis organizes the main points of each news item and extracts important information.

[0492] Example prompt sentence:

[0493] "Extract the main topics and related keywords of tweets about the latest news."

[0494] "Please summarize the main points of this news text."

[0495] In the credibility evaluation phase, the server compares the analyzed news information with other reliable sources and evaluates its credibility as a percentage using a generative artificial intelligence model. For example, the content of a specific news article is compared and collated with other major news sites and databases to quantify its credibility. This allows the credibility of each news item to be clearly displayed, supporting user decision-making.

[0496] Finally, in the data display and user interaction phase, the user accesses the system using a device (e.g., a smartphone or PC) to view the credibility assessment results. The server visually displays the assessment results in the form of charts and graphs, along with details of each news item and the reasons for its assessment. The user can also ask additional questions through a dialogue interface, and the answers to those questions are also provided using the generative AI model. For example, if the user asks, "Tell me why the credibility of this news is 70%," the server inputs this prompt into the generative AI model and returns an appropriate answer.

[0497] The present invention enables the rapid and accurate evaluation and visual display of the credibility of information collected from multiple news sources, and also allows users to ask detailed questions in an interactive format, providing a highly user-friendly service.

[0498] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0499] Step 1:

[0500] The server collects news data from a variety of sources.

[0501] Specific behavior:

[0502] The server uses a social media API endpoint and an access token to collect posts containing a specific hashtag (e.g., "breaking news"), taking the posts containing the hashtag as input and obtaining the metadata, text, and related information for the posts as output.

[0503] The server uses the messaging application's API to retrieve news messages from official accounts, using the official account's authentication information as input and collecting the news messages and their metadata as output.

[0504] The server retrieves the latest top news stories using the API of an online news platform (e.g., Google News API), using the API key and endpoint as input, and gets the list of latest news articles along with their metadata and article text as output.

[0505] Step 2:

[0506] The server preprocesses the collected news data.

[0507] Specific behavior:

[0508] The server cleans irrelevant elements such as hashtags, links, and user mentions from the collected tweet text. At this time, the tweet text is used as input, and the clean text with unnecessary elements removed is obtained as output.

[0509] The server filters news text obtained from a messaging application to remove unnecessary parts, giving message text as input and obtaining the news text with unnecessary parts removed as output.

[0510] The server filters advertisements and noise data from article texts of online news platforms, using the collected article texts as input and obtaining the filtered clean article texts as output.

[0511] Step 3:

[0512] The server inputs the preprocessed news data into the generative AI model for analysis.

[0513] Specific behavior:

[0514] The server inputs the preprocessed tweet data into a generative AI model (e.g., GPT-4) and analyzes it using the prompt, "Please extract the main topic and related keywords of this tweet." At this time, the clean tweet data is given as input, and the main topic and related keywords are obtained as output.

[0515] The server inputs the preprocessed news text obtained from the messaging application into a generative AI model to extract gist points, using the clean news text as input and obtaining gist points as output.

[0516] The server inputs the preprocessed article text obtained from the online news platform into a generative AI model to analyze and summarize the main points of the content, using the clean article text as input and obtaining the summarized information as output.

[0517] Step 4:

[0518] The server evaluates the credibility of the news based on the analysis results.

[0519] Specific behavior:

[0520] The server compares the analyzed news information with other reliable sources (e.g., major news sites or databases), using the analysis results and data from reliable sources as inputs and obtaining the comparison results as output.

[0521] The server evaluates the credibility of the news in percentage format based on the matching result, using the matching result as input and obtaining a percentage value indicating the credibility of the news as output.

[0522] Step 5:

[0523] The server creates data for visually displaying the credibility evaluation results.

[0524] Specific behavior:

[0525] The server converts the credibility assessment results into charts and graphs, using the credibility assessment results as input and obtaining data converted into a visually displayable format as output.

[0526] Step 6:

[0527] The user accesses the system using a terminal and checks the credibility evaluation results.

[0528] Specific behavior:

[0529] A user logs in to a web application from a terminal and accesses a homepage. At this time, a username and password are used as input, and the homepage screen after successful authentication is obtained as output.

[0530] The user opens a screen to display the news credibility list. At this time, data for visually displaying the credibility evaluation results is used as input, and the results displayed in chart and graph format are obtained as output.

[0531] Step 7:

[0532] The user uses the interactive interface to ask follow-up questions.

[0533] Specific behavior:

[0534] A user uses the interactive interface to type, "Tell me why this news story is 70% reliable," and the user's question is used as input.

[0535] The server uses a generative AI model to generate an answer to the question and respond to the user, taking the user's question as input and obtaining an appropriate answer as output.

[0536] By going through the above steps, the system can perform consistent processing from news collection to credibility assessment, visual display, and user interaction.

[0537] (Application example 1)

[0538] 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."

[0539] In modern society, it is difficult to determine the credibility of news and information provided by a variety of sources, and especially on digital platforms such as virtual stores, users lack the means to immediately determine the credibility of news related to products. For this reason, there is a need to provide users with the information they need to make decisions quickly and reliably when purchasing products.

[0540] 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.

[0541] In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and rating the credibility as a percentage; means for visually displaying the rating results; means for providing an interactive interface for users to ask and answer follow-up questions about the rating results; and display means for viewers to check related news and credibility ratings of products in real time while viewing products in a virtual store. This allows users to quickly evaluate the credibility of news information related to a product when selecting a product in the virtual store, which can help them make a purchasing decision.

[0542] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[0543] A "generative artificial intelligence model" refers to a learning system that uses natural language processing techniques to analyze text data and extract and generate specific information.

[0544] "Key information elements" refer to people, places, events, and other elements that are deemed important in news or information.

[0545] "Credibility" refers to the reliability of information based on facts and is evaluated as a percentage based on specific criteria.

[0546] "Visual display means" refers to a method of displaying the results of the credibility assessment of collected and analyzed information in a visual format such as a graph or chart so that users can easily understand it.

[0547] "Interactive interface" refers to an interactive user interface that allows a user to ask a system additional questions and for the system to respond to those questions.

[0548] A "virtual store" refers to a virtual shopping environment created using the Internet and VR technology.

[0549] "Display means" refers to the method by which information is displayed to the user via a device such as smart glasses or a head-mounted display.

[0550] The present invention relates to a system for gathering, analyzing, and evaluating the credibility of news, and visually displaying the results. This system is particularly designed to allow users to check related news and credibility ratings of products in real time within a virtual store.

[0551] News Gathering Phase

[0552] The server collects news data from various information sources, such as social media, messaging applications, and online news platforms. To achieve this, it uses the APIs of each platform. For example, it uses the APIs of social media to collect tweets containing a specific hashtag. It also obtains news messages from official accounts on messaging applications and uses the APIs of online news platforms to collect top news stories.

[0553] News Analysis Phase

[0554] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements from the news (e.g., people, places, and events). For example, acquired tweet data is input into the generative AI model to extract key topics and related keywords. It also analyzes and extracts key elements from news text obtained from messaging applications.

[0555] Credibility assessment phase

[0556] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., reliable news sites and databases). The credibility is expressed as a percentage. For example, the content of a particular news article is compared with other reliable sources to assess its credibility. The server also checks tweet content against multiple news sites to determine its credibility.

[0557] Data Display and User Interaction Phase

[0558] Users can access the system using a device (smart glasses or head-mounted display) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use a dialogue interface to ask additional questions, and the server will provide answers using a generative AI model. For example, they can ask, "Tell me why the credibility of this news is 70%," and receive a detailed answer from the server.

[0559] The specific hardware and software you will use

[0560] Hardware: Smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest 2)

[0561] Software: Python, OpenAI GPT-4 API, News API, Matplotlib

[0562] Case studies

[0563] For example, imagine a user is browsing a new smartphone in a virtual store. The smart glasses display a news item about the release of a new smartphone, along with a news description that reads, "The latest model is equipped with new AI features and is attracting a lot of attention." The generative AI model then displays a credibility rating for this news item, visually indicating a result of, say, 85%.

[0564] The prompt for the generative AI model is:

[0565] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[0566] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0567] Step 1:

[0568] The server collects news data using APIs from various sources, such as social media, messaging applications, and online news platforms, and retrieves tweets containing specific hashtags (e.g., breaking news), news messages from official accounts, and top news stories.

[0569] Input: API of each platform, hashtag

[0570] Output: A list of news data retrieved from each platform

[0571] Step 2:

[0572] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content, which extracts key information elements (people, places, events) from the news.

[0573] Input: List of news data

[0574] Output: Analysis results for each news article (text structure including key information elements)

[0575] Step 3:

[0576] The server compares the analyzed news information with other reliable sources to assess its credibility, and calculates a percentage based on the credibility rating to filter out less reliable information.

[0577] Input: Parsed news data, list of reliable sources

[0578] Output: The credibility rating (percentage) of each news article

[0579] Step 4:

[0580] The server generates data to visually display the evaluation results, including graphs and charts, and uses libraries such as Matplotlib to convert the data into a format that is easy for users to understand.

[0581] Input: Credibility assessment result

[0582] Output: Visual display data (in the form of graphs and charts)

[0583] Step 5:

[0584] The user accesses the system using a device (smart glasses or a head-mounted display) and visually checks the credibility evaluation results. Information is sent so that the results are displayed on the smart glasses or head-mounted display.

[0585] Input: Visual display data

[0586] Output: The credibility assessment result displayed on the user's device.

[0587] Step 6:

[0588] The user uses a conversational interface to ask follow-up questions about the results. These questions are sent to the generative AI model, and the server generates an appropriate answer to the question. For example, "Tell me why this news story is 70% reliable."

[0589] Input: User question

[0590] Output: Answer from the generative AI model (detailed explanation)

[0591] Example prompt sentence:

[0592] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[0593] 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.

[0594] This invention is a system that collects, analyzes, and evaluates the credibility of news, and visually displays the results, and also combines it with an emotion engine that recognizes the user's emotions. This system allows users to quickly and easily judge the credibility of information collected from various news sources, and receive appropriate information displayed based on their emotions.

[0595] News Gathering Phase

[0596] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[0597] example:

[0598] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[0599] The server retrieves news messages from the official account of the messaging application.

[0600] The server collects top news stories using the API of an online news platform.

[0601] News Analysis Phase

[0602] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[0603] example:

[0604] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[0605] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[0606] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[0607] Credibility assessment phase

[0608] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[0609] example:

[0610] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[0611] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[0612] Data Display and User Interaction Phase

[0613] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[0614] example:

[0615] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[0616] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[0617] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[0618] Emotion Recognition Phase

[0619] The server analyzes the user's input information (e.g., text input, voice input, facial recognition, etc.) and recognizes the user's emotions using an emotion engine. The emotion engine changes the way the credibility evaluation results are displayed based on the user's emotions.

[0620] example:

[0621] When a user checks the news evaluation results, they input information into the system indicating "anxiety" or "doubt."

[0622] The server uses an emotion engine to recognize the user's emotion as "anxiety" and displays the credibility evaluation results in more detail according to the emotion.

[0623] When the user inputs something that indicates "relief" or "understanding," the server uses an emotion engine to recognize the user's emotion and selects an appropriate information display format.

[0624] In this way, the system not only quickly and accurately evaluates the credibility of information collected from a variety of news sources and provides the results to users, but also optimizes the way information is displayed according to the user's emotions, thereby realizing an extremely user-friendly service.

[0625] The processing flow will be explained below.

[0626] Step 1:

[0627] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[0628] Step 2:

[0629] The server uses the LINE API to collect news messages from LINE official accounts.

[0630] Step 3:

[0631] The server retrieves the latest top news stories through the Yahoo! News API.

[0632] Step 4:

[0633] The tweet data collected by the server is input into a generative AI model to extract key information elements (people, places, events).

[0634] Step 5:

[0635] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[0636] Step 6:

[0637] The server inputs the text of Yahoo! News articles into a generative AI model, which analyzes the content and extracts key information elements.

[0638] Step 7:

[0639] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[0640] Step 8:

[0641] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[0642] Step 9:

[0643] The server stores the results of the credibility assessment in a database for later viewing.

[0644] Step 10:

[0645] The server uses an emotion engine to analyze the user's input information (e.g., text input, voice input, facial recognition) and recognize the user's emotions.

[0646] Step 11:

[0647] A user logs into the web application using a terminal and views the parsed news list.

[0648] Step 12:

[0649] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[0650] Step 13:

[0651] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[0652] Step 14:

[0653] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[0654] Step 15:

[0655] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[0656] Step 16:

[0657] The server uses an emotion engine to generate a customized response based on the user's emotion. For example, if the user indicates "anxiety," the server provides additional detailed fact-checking information.

[0658] Step 17:

[0659] The user reviews the answers provided and asks the chatbot further questions if necessary.

[0660] Step 18:

[0661] The server adjusts the way news is displayed according to the user's emotions and provides information in a format more suited to the user.

[0662] Example 2

[0663] 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."

[0664] In today's world, advanced analysis and credibility assessment are required to quickly and accurately evaluate the credibility of news and information obtained from diverse sources and provide it visually to users. However, conventional systems only evaluate credibility centrally, making it difficult to optimize the way information is displayed in response to the user's emotions. Furthermore, they lack an interactive interface that can answer users' follow-up questions in real time. Therefore, there is a need for a system that is easy for users to use.

[0665] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask follow-up questions about the evaluation results and answer those questions; means for analyzing information input by the user and recognizing the user's emotions using an emotion engine; and means for changing the display method of the credibility evaluation results based on the user's emotions. This makes it possible not only to quickly and accurately evaluate the credibility of collected information and provide the results to the user, but also to optimize the information display method according to the user's emotions.

[0666] "Diverse information sources" refers to multiple sources that provide different types of information, such as social media, messaging applications, and online news platforms.

[0667] A "generative artificial intelligence model" is an advanced AI model for natural language processing and machine learning, used to analyze data and make generation and predictions according to specific tasks.

[0668] "Key information elements" refer to entities such as people, places, and events that are of particular importance in the collected information.

[0669] "Fact-checking for authenticity" refers to the process of verifying whether the collected and analyzed information is consistent with other reliable sources and databases.

[0670] "Interactive interface" refers to a user interface that allows a user to ask questions and receive answers in real time.

[0671] "User input information" refers to various data provided by a user to the system, such as text input, voice input, or facial recognition.

[0672] An "emotion engine" refers to an algorithm or software that analyzes a user's input information to recognize their emotional state (e.g., anxiety, relief, understanding, etc.) and optimizes the system's response and display content.

[0673] "Changing the display method of the credibility assessment results" refers to the process of dynamically adjusting the presentation format of the credibility assessment results (e.g., graphs, detailed reports, etc.) according to the user's emotional state.

[0674] The present invention is a system that collects information from various information sources, analyzes it, evaluates its credibility, and then visually presents it to the user. Furthermore, it has the feature of recognizing the user's emotions and optimizing the way information is presented accordingly. Below, we will explain the mode for implementing the invention by following a specific flow.

[0675] First, the server collects news data from multiple information sources, including social media, messaging applications, and online news platforms. For example, from social media, the server uses the Twitter API to retrieve tweets containing a specific hashtag (e.g., breaking news). From messaging applications, the server uses the LINE API to retrieve news messages from official accounts. Finally, from online news platforms, the server uses the Google News API to collect top news stories.

[0676] The server uses a generative AI model (e.g., GPT-4) to analyze the collected news data. For example, the following prompt sentences can be used when analyzing news text:

[0677] "Please extract the key information elements from this news article."

[0678] "What are the main events and related keywords in this tweet?"

[0679] Based on these prompts, the generative AI model analyzes the news data and extracts key information elements (people, places, events, etc.).

[0680] Next, the server evaluates the credibility of the analyzed news information by checking it against other reliable sources (e.g., reliable news sites or databases). The credibility is expressed as a percentage, for example:

[0681] "We compare the content of a particular article with other reliable sources and rate its credibility at 85%."

[0682] "The tweet content was checked against multiple news sites and its credibility was determined to be 70%."

[0683] The server provides a means to visually display the credibility evaluation results. When a user accesses the system on a device (smartphone or PC), the evaluation results are provided in a visually easy-to-understand format, such as a graph or chart. For example, when a user logs into a web application and opens a screen displaying a list of news credibility, the server presents the credibility evaluation results in the form of a chart, along with details of each news item and the reasons for its evaluation.

[0684] Furthermore, the server uses an emotion engine to recognize the user's emotions. It analyzes the text, voice, or facial recognition information entered by the user and recognizes the user's emotions as "anxiety," "relief," "understanding," etc. For example, if a user inputs "anxiety" or "doubt" when checking the news evaluation results, the server will recognize this as "anxiety" using the emotion engine and display more detailed credibility evaluation results according to that emotion.

[0685] This system allows users to quickly and accurately evaluate the credibility of information collected from various news sources and visually understand the results.In addition, the way information is displayed is optimized according to the user's emotions, making it an extremely user-friendly service.

[0686] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0687] Step 1: Gathering news

[0688] A server collects news data from social media, messaging applications, and online news platforms.

[0689] Input: hashtags on social media, news messages on messaging applications, news articles on online news platforms.

[0690] Processing: Use APIs to retrieve information from each platform: from social media, retrieve tweets containing specific hashtags; from messaging applications, collect news messages from official accounts; and from online news platforms, collect top stories.

[0691] Output: News data in JSON format.

[0692] Specific operation: Sends API requests and receives news data from each information source.

[0693] Step 2: News Preprocessing

[0694] The server standardizes the collected news data and converts it into text format.

[0695] Input: Collected news data in JSON format.

[0696] Processing: Data cleaning, removing unnecessary HTML tags and special characters, formatting the text, converting the news data into text format.

[0697] Output: Preprocessed news data in text format.

[0698] Specific behavior: Runs data cleaning scripts and performs text formatting.

[0699] Step 3: News analysis

[0700] The server uses a generative AI model (GPT-4) to analyze the preprocessed news data.

[0701] Input: Preprocessed news data in text format.

[0702] Processing: Generative AI models analyze news data and extract key information elements (people, places, events).

[0703] Prompts: "Please extract the main information elements from this news article.", "What are the keywords related to the main events in this tweet?"

[0704] Output: Extracted key information elements.

[0705] Specific operation: News text is input into the generative AI model and analysis results are obtained.

[0706] Step 4: Credibility assessment

[0707] The server uses the generated AI model to evaluate the credibility of the analyzed news information.

[0708] Input: Key information elements of the parsed news.

[0709] Processing: Check against trusted sources and rate the credibility as a percentage, e.g., compare with trusted news sites or databases.

[0710] Output: Belief assessment result (e.g., 85% Belief).

[0711] Specific operation: Compare the analyzed information with a reliability database and calculate a credibility score.

[0712] Step 5: Data display

[0713] The server visually displays the credibility evaluation results.

[0714] Input: The credibility assessment result.

[0715] Processing: Rendering the evaluation results in a visually understandable format such as graphs or charts.

[0716] Output: Visually displayed credibility assessment results.

[0717] What it does: Renders the evaluation results in a graph format in a web browser and provides detailed information.

[0718] Step 6: User Interaction

[0719] The user accesses the system at a terminal and asks additional questions about the evaluation results.

[0720] Input: The user's question.

[0721] Processing: Uses generative AI models to generate answers to user questions and provide a conversational interface.

[0722] Output: The answer to the question asked by the user.

[0723] Specific operation: The user's question is input into the generative AI model, an appropriate answer is generated, and it is presented to the user through the interface.

[0724] Step 7: Emotion Recognition

[0725] The server analyzes the user's input information and recognizes the user's emotions using an emotion engine.

[0726] Input: User input (text, voice, facial recognition).

[0727] Processing: Uses an emotion engine to recognize the user's emotions as "anxiety," "relief," "understanding," etc.

[0728] Output: Perceived user emotion.

[0729] What it does: It uses text analysis, speech analysis, and facial recognition models to determine the user's emotions.

[0730] Step 8: Adjust the display

[0731] The server changes the display method of the credibility evaluation result based on the user's emotions recognized by the server.

[0732] Input: Perceived user emotion.

[0733] Processing: Select an appropriate information display format according to the user's emotion and re-render.

[0734] Output: Credibility assessment results visually presented in a tailored presentation format.

[0735] Specific behavior: Dynamically change the display format based on the user's sentiment, such as displaying detailed information or a concise summary.

[0736] (Application example 2)

[0737] 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."

[0738] Current news gathering systems quickly evaluate the credibility of news information collected from various information sources and provide it to users, but they lack the ability to present information that takes user emotions into consideration. As a result, appropriate information display methods are not applied to users who feel anxious or suspicious, making it difficult to improve the user experience. Furthermore, the lack of a system specialized in providing news information in autonomous vehicles limits the means of providing reliable news information in real time.

[0739] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask and answer follow-up questions about the evaluation results; means for analyzing user input information and recognizing the user's emotions using an emotion engine; and means for dynamically changing the information display format in accordance with the user's emotions. This makes it possible to provide reliable news information in real time within an autonomous vehicle while taking user emotions into consideration.

[0740] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[0741] A "generative artificial intelligence model" is a deep learning model that uses artificial intelligence, and refers to a system that can analyze, generate, and evaluate information based on large amounts of data.

[0742] "Credibility" indicates the likelihood that collected information is factual, and refers to the degree to which it is evaluated as a percentage.

[0743] An "emotion engine" refers to an algorithm or system that analyzes user input (e.g., language, voice, facial expressions) and identifies their emotional state.

[0744] "Information presentation" refers to the way in which information is visually or interactively presented to a user, and includes different presentation formats such as graphical formats, detailed views, etc.

[0745] An "autonomous vehicle" refers to a vehicle that uses artificial intelligence and sensor technology to drive autonomously.

[0746] "Conversational interface" refers to an interface that allows a user to interact with a system using natural language, including interactions such as question-answering and information search.

[0747] "Real-time" refers to the temporal characteristic that enables a system to process information almost instantly and provide it to the user.

[0748] In order to implement the present invention, a system is constructed in which the elements of the server, the terminal, and the user function in cooperation with each other. A specific embodiment of this system is shown below.

[0749] First, the server collects information from various information sources, including social media, messaging applications, online news platforms, etc. The server uses the API of each platform to collect information. For example, the server may use the API of a social media platform to collect posts containing a specific hashtag.

[0750] Next, the collected information is analyzed using a generative AI model, such as GPT-4. Through this analysis, key information elements are extracted from the news content. Specifically, the server inputs the tweet data it has acquired into the generative AI model, which then extracts topics and related keywords.

[0751] The server then evaluates the credibility of the analyzed information. This evaluation is also performed using a generative AI model, which compares the information with other reliable sources and displays the credibility as a percentage. For example, the server compares the content of a particular news article with other reliable sources and rates its credibility as 85%.

[0752] The evaluation results are displayed visually. Users access the system through a terminal (such as the dashboard or head-up display of an autonomous vehicle) and check the information. The evaluation results are displayed in easy-to-understand visual formats such as graphs and charts.

[0753] Furthermore, when a user asks additional questions about the evaluation results, a dialogue-based interface is used. When the user inputs information from the device, the server uses the generative AI model to provide an appropriate answer to the question. For example, if a user asks, "Please tell me why the credibility of this news is 70%," the server uses the generative AI model to provide an answer.

[0754] The server also analyzes the user's input (e.g., text input or voice input) and uses an emotion engine to recognize the user's emotions. Based on this, the way information is displayed is dynamically changed depending on the user's emotions. For example, if the user inputs an expression indicating "anxiety" or "doubt," the server will use the emotion engine to recognize the user's emotion as "anxiety" and display a detailed evaluation result.

[0755] For example, if a user feels uneasy about recent news, the server will provide a detailed assessment of the news' credibility based on this input. An example of a prompt would be "Evaluate the credibility of the following news: [news content]," and the AI ​​model will analyze its credibility.

[0756] As described above, the present invention realizes a system that responds to the user's emotions while providing reliable news information in real time within an autonomous vehicle.

[0757] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0758] Step 1:

[0759] The server collects information from various information sources (social media, messaging applications, online news platforms) and uses the API of each platform to retrieve posts containing a specific hashtag, for example, from the social media API.

[0760] Input: Data from each platform's API

[0761] Output: Raw collected news data

[0762] Step 2:

[0763] The server analyzes the collected news data using a generative artificial intelligence model (such as GPT-4), which extracts key information elements from the news content.

[0764] Input: Collected news data

[0765] Data processing: News data is input into a generative AI model to analyze and extract key topics and keywords.

[0766] Output: The main information elements parsed

[0767] Step 3:

[0768] The server evaluates the veracity of the analyzed information, again using a generative AI model and comparing it with other reliable sources, and the evaluation result is expressed as a percentage.

[0769] Input: Parsed key information elements

[0770] Data calculation: Compare with other reliable sources and calculate the credibility as a percentage

[0771] Output: Credibility evaluation result (e.g., 85%)

[0772] Step 4:

[0773] The server converts the credibility assessment results into a visually displayed data format, which the user can view on their device (dashboard or head-up display).

[0774] Input: Credibility evaluation result

[0775] Data processing: Converting data into graphs and charts

[0776] Output: Visually displayable data

[0777] Step 5:

[0778] The user uses a terminal to access an interactive interface to ask follow-up questions about the assessment results, and the server uses a generative AI model to provide appropriate answers to these questions.

[0779] Input: User question

[0780] Data Computation: Using generative AI models to analyze questions and generate answers

[0781] Output: The answer that is presented to the user

[0782] Step 6:

[0783] The user inputs their emotions (for example, "I'm worried about the recent news") into the device. The server analyzes this using an emotion engine and recognizes the user's emotions.

[0784] Input: User emotion input

[0785] Data Computation: Uses an emotion engine to analyze input text and voice to identify user emotions

[0786] Output: Parsed user's emotional state (e.g., "anxiety")

[0787] Step 7:

[0788] The server dynamically changes the way information is displayed depending on the user's emotional state. For example, if the user expresses "anxiety," the server displays the credibility evaluation results in detail.

[0789] Input: User's emotional state and credibility evaluation results

[0790] Data processing: Display method adjusted according to emotional state

[0791] Output: Dynamically changed display format (e.g., detailed view)

[0792] These steps enable the system to respond to user sentiment and provide reliable news information in real time within self-driving vehicles.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] [Third embodiment]

[0797] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0798] 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.

[0799] 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).

[0800] 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.

[0801] 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.

[0802] 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).

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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."

[0809] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results, allowing users to quickly and easily determine the credibility of information collected from a variety of news sources.

[0810] News Gathering Phase

[0811] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[0812] example:

[0813] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[0814] The server retrieves news messages from the official account of the messaging application.

[0815] The server collects top news stories using the API of an online news platform.

[0816] News Analysis Phase

[0817] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[0818] example:

[0819] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[0820] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[0821] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[0822] Credibility assessment phase

[0823] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[0824] example:

[0825] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[0826] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[0827] Data Display and User Interaction Phase

[0828] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[0829] example:

[0830] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[0831] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[0832] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[0833] In this way, this system can quickly and accurately evaluate the credibility of information collected from various news sources and provide the results to users. Furthermore, through user interaction, users can obtain more detailed information, making this a very easy-to-use service.

[0834] The processing flow will be explained below.

[0835] Step 1:

[0836] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[0837] Step 2:

[0838] The server uses the LINE API to collect news messages from LINE official accounts.

[0839] Step 3:

[0840] The server retrieves the latest top news stories through the Yahoo! News API.

[0841] Step 4:

[0842] The server inputs the collected tweet data into a generative AI model to extract key information elements (e.g., people, places, events).

[0843] Step 5:

[0844] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[0845] Step 6:

[0846] The server inputs the text of Yahoo! News articles into a generative AI model, analyzes the content, and extracts key points.

[0847] Step 7:

[0848] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[0849] Step 8:

[0850] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[0851] Step 9:

[0852] The server stores the results of the credibility assessment in a database for later viewing.

[0853] Step 10:

[0854] A user logs into the web application using a terminal and views the parsed news list.

[0855] Step 11:

[0856] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[0857] Step 12:

[0858] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[0859] Step 13:

[0860] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[0861] Step 14:

[0862] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[0863] Step 15:

[0864] The user reviews the answers provided and asks the chatbot further questions if necessary.

[0865] Example 1

[0866] 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."

[0867] In today's world, it is extremely important to quickly and accurately evaluate the credibility of news collected from a variety of sources. However, conventional systems collect information, analyze it, evaluate its credibility, and visually display the results separately, making the overall process complex and time-consuming. This also makes it difficult for users to ask detailed questions about the evaluation results. This increases the burden on users when judging the credibility of news, which has been an issue.

[0868] 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.

[0869] In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for users to ask and answer follow-up questions about the evaluation results; means for preprocessing the collected information; and means for displaying the evaluation results in chart or graph format. This enables the credibility of news to be evaluated quickly and accurately and the results to be visually confirmed. Furthermore, users can easily ask detailed questions about the evaluation results, thereby reducing the burden on users.

[0870] "Information sources" refers to various information sources, such as social media, messaging applications, and online news platforms.

[0871] "Generative artificial intelligence models" refer to advanced algorithms and software systems that can understand and generate natural language, such as GPT-4.

[0872] "Analysis" refers to the process of inputting collected news data into a generative artificial intelligence model to extract key information elements (e.g., people, places, events).

[0873] "Credibility assessment" refers to the process of fact-checking analyzed news information and then quantifying its credibility in the form of a percentage.

[0874] "Preprocessing" refers to the process of cleaning collected news data and filtering out irrelevant information before analysis.

[0875] "Dialogue interface" means an interface that allows a user to ask follow-up questions and receive answers to those questions through natural language interaction with the system.

[0876] "Charts and graph formats" refers to figures and diagrams that display evaluation results in a visually easy-to-understand manner.

[0877] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results. This system is mainly composed of a server, terminals, and users.

[0878] First, in the news gathering phase, the server collects news data using the APIs of various information sources (e.g., social media, messaging applications, online news platforms). Specifically, it uses social media APIs to collect posts containing specific hashtags, obtains news messages from official messaging app accounts, and uses online news platform APIs to obtain the latest news. This gathering process allows for the rapid and efficient accumulation of diverse news data.

[0879] Next, in the news analysis phase, the server inputs the collected news data into a generative AI model (e.g., GPT-4) to extract key information elements (e.g., people, places, and events). After preprocessing the collected news data and removing unnecessary information, the generative AI model is given prompts such as the following to analyze it. This analysis organizes the main points of each news item and extracts important information.

[0880] Example prompt sentence:

[0881] "Extract the main topics and related keywords of tweets about the latest news."

[0882] "Please summarize the main points of this news text."

[0883] In the credibility evaluation phase, the server compares the analyzed news information with other reliable sources and evaluates its credibility as a percentage using a generative artificial intelligence model. For example, the content of a specific news article is compared and collated with other major news sites and databases to quantify its credibility. This allows the credibility of each news item to be clearly displayed, supporting user decision-making.

[0884] Finally, in the data display and user interaction phase, the user accesses the system using a device (e.g., a smartphone or PC) to view the credibility assessment results. The server visually displays the assessment results in the form of charts and graphs, along with details of each news item and the reasons for its assessment. The user can also ask additional questions through a dialogue interface, and the answers to those questions are also provided using the generative AI model. For example, if the user asks, "Tell me why the credibility of this news is 70%," the server inputs this prompt into the generative AI model and returns an appropriate answer.

[0885] The present invention enables the rapid and accurate evaluation and visual display of the credibility of information collected from multiple news sources, and also allows users to ask detailed questions in an interactive format, providing a highly user-friendly service.

[0886] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0887] Step 1:

[0888] The server collects news data from a variety of sources.

[0889] Specific behavior:

[0890] The server uses a social media API endpoint and an access token to collect posts containing a specific hashtag (e.g., "breaking news"), taking the posts containing the hashtag as input and obtaining the metadata, text, and related information for the posts as output.

[0891] The server uses the messaging application's API to retrieve news messages from official accounts, using the official account's authentication information as input and collecting the news messages and their metadata as output.

[0892] The server retrieves the latest top news stories using the API of an online news platform (e.g., Google News API), using the API key and endpoint as input, and gets the list of latest news articles along with their metadata and article text as output.

[0893] Step 2:

[0894] The server preprocesses the collected news data.

[0895] Specific behavior:

[0896] The server cleans irrelevant elements such as hashtags, links, and user mentions from the collected tweet text. At this time, the tweet text is used as input, and the clean text with unnecessary elements removed is obtained as output.

[0897] The server filters news text obtained from a messaging application to remove unnecessary parts, giving message text as input and obtaining the news text with unnecessary parts removed as output.

[0898] The server filters advertisements and noise data from article texts of online news platforms, using the collected article texts as input and obtaining the filtered clean article texts as output.

[0899] Step 3:

[0900] The server inputs the preprocessed news data into the generative AI model for analysis.

[0901] Specific behavior:

[0902] The server inputs the preprocessed tweet data into a generative AI model (e.g., GPT-4) and analyzes it using the prompt, "Please extract the main topic and related keywords of this tweet." At this time, the clean tweet data is given as input, and the main topic and related keywords are obtained as output.

[0903] The server inputs the preprocessed news text obtained from the messaging application into a generative AI model to extract gist points, using the clean news text as input and obtaining gist points as output.

[0904] The server inputs the preprocessed article text obtained from the online news platform into a generative AI model to analyze and summarize the main points of the content, using the clean article text as input and obtaining the summarized information as output.

[0905] Step 4:

[0906] The server evaluates the credibility of the news based on the analysis results.

[0907] Specific behavior:

[0908] The server compares the analyzed news information with other reliable sources (e.g., major news sites or databases), using the analysis results and data from reliable sources as inputs and obtaining the comparison results as output.

[0909] The server evaluates the credibility of the news in percentage format based on the matching result, using the matching result as input and obtaining a percentage value indicating the credibility of the news as output.

[0910] Step 5:

[0911] The server creates data for visually displaying the credibility evaluation results.

[0912] Specific behavior:

[0913] The server converts the credibility assessment results into charts and graphs, using the credibility assessment results as input and obtaining data converted into a visually displayable format as output.

[0914] Step 6:

[0915] The user accesses the system using a terminal and checks the credibility evaluation results.

[0916] Specific behavior:

[0917] A user logs in to a web application from a terminal and accesses a homepage. At this time, a username and password are used as input, and the homepage screen after successful authentication is obtained as output.

[0918] The user opens a screen to display the news credibility list. At this time, data for visually displaying the credibility evaluation results is used as input, and the results displayed in chart and graph format are obtained as output.

[0919] Step 7:

[0920] The user uses the interactive interface to ask follow-up questions.

[0921] Specific behavior:

[0922] A user uses the interactive interface to type, "Tell me why this news story is 70% reliable," and the user's question is used as input.

[0923] The server uses a generative AI model to generate an answer to the question and respond to the user, taking the user's question as input and obtaining an appropriate answer as output.

[0924] By going through the above steps, the system can perform consistent processing from news collection to credibility assessment, visual display, and user interaction.

[0925] (Application example 1)

[0926] 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."

[0927] In modern society, it is difficult to determine the credibility of news and information provided by a variety of sources, and especially on digital platforms such as virtual stores, users lack the means to immediately determine the credibility of news related to products. For this reason, there is a need to provide users with the information they need to make decisions quickly and reliably when purchasing products.

[0928] 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.

[0929] In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and rating the credibility as a percentage; means for visually displaying the rating results; means for providing an interactive interface for users to ask and answer follow-up questions about the rating results; and display means for viewers to check related news and credibility ratings of products in real time while viewing products in a virtual store. This allows users to quickly evaluate the credibility of news information related to a product when selecting a product in the virtual store, which can help them make a purchasing decision.

[0930] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[0931] A "generative artificial intelligence model" refers to a learning system that uses natural language processing techniques to analyze text data and extract and generate specific information.

[0932] "Key information elements" refer to people, places, events, and other elements that are deemed important in news or information.

[0933] "Credibility" refers to the reliability of information based on facts and is evaluated as a percentage based on specific criteria.

[0934] "Visual display means" refers to a method of displaying the results of the credibility assessment of collected and analyzed information in a visual format such as a graph or chart so that users can easily understand it.

[0935] "Interactive interface" refers to an interactive user interface that allows a user to ask a system additional questions and for the system to respond to those questions.

[0936] A "virtual store" refers to a virtual shopping environment created using the Internet and VR technology.

[0937] "Display means" refers to the method by which information is displayed to the user via a device such as smart glasses or a head-mounted display.

[0938] The present invention relates to a system for gathering, analyzing, and evaluating the credibility of news, and visually displaying the results. This system is particularly designed to allow users to check related news and credibility ratings of products in real time within a virtual store.

[0939] News Gathering Phase

[0940] The server collects news data from various information sources, such as social media, messaging applications, and online news platforms. To achieve this, it uses the APIs of each platform. For example, it uses the APIs of social media to collect tweets containing a specific hashtag. It also obtains news messages from official accounts on messaging applications and uses the APIs of online news platforms to collect top news stories.

[0941] News Analysis Phase

[0942] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements from the news (e.g., people, places, and events). For example, acquired tweet data is input into the generative AI model to extract key topics and related keywords. It also analyzes and extracts key elements from news text obtained from messaging applications.

[0943] Credibility assessment phase

[0944] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., reliable news sites and databases). The credibility is expressed as a percentage. For example, the content of a particular news article is compared with other reliable sources to assess its credibility. The server also checks tweet content against multiple news sites to determine its credibility.

[0945] Data Display and User Interaction Phase

[0946] Users can access the system using a device (smart glasses or head-mounted display) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use a dialogue interface to ask additional questions, and the server will provide answers using a generative AI model. For example, they can ask, "Tell me why the credibility of this news is 70%," and receive a detailed answer from the server.

[0947] The specific hardware and software you will use

[0948] Hardware: Smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest 2)

[0949] Software: Python, OpenAI GPT-4 API, News API, Matplotlib

[0950] Case studies

[0951] For example, imagine a user is browsing a new smartphone in a virtual store. The smart glasses display a news item about the release of a new smartphone, along with a news description that reads, "The latest model is equipped with new AI features and is attracting a lot of attention." The generative AI model then displays a credibility rating for this news item, visually indicating a result of, say, 85%.

[0952] The prompt for the generative AI model is:

[0953] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[0954] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0955] Step 1:

[0956] The server collects news data using APIs from various sources, such as social media, messaging applications, and online news platforms, and retrieves tweets containing specific hashtags (e.g., breaking news), news messages from official accounts, and top news stories.

[0957] Input: API of each platform, hashtag

[0958] Output: A list of news data retrieved from each platform

[0959] Step 2:

[0960] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content, which extracts key information elements (people, places, events) from the news.

[0961] Input: List of news data

[0962] Output: Analysis results for each news article (text structure including key information elements)

[0963] Step 3:

[0964] The server compares the analyzed news information with other reliable sources to assess its credibility, and calculates a percentage based on the credibility rating to filter out less reliable information.

[0965] Input: Parsed news data, list of reliable sources

[0966] Output: The credibility rating (percentage) of each news article

[0967] Step 4:

[0968] The server generates data to visually display the evaluation results, including graphs and charts, and uses libraries such as Matplotlib to convert the data into a format that is easy for users to understand.

[0969] Input: Credibility assessment result

[0970] Output: Visual display data (in the form of graphs and charts)

[0971] Step 5:

[0972] The user accesses the system using a device (smart glasses or a head-mounted display) and visually checks the credibility evaluation results. Information is sent so that the results are displayed on the smart glasses or head-mounted display.

[0973] Input: Visual display data

[0974] Output: The credibility assessment result displayed on the user's device.

[0975] Step 6:

[0976] The user uses a conversational interface to ask follow-up questions about the results. These questions are sent to the generative AI model, and the server generates an appropriate answer to the question. For example, "Tell me why this news story is 70% reliable."

[0977] Input: User question

[0978] Output: Answer from the generative AI model (detailed explanation)

[0979] Example prompt sentence:

[0980] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[0981] 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.

[0982] This invention is a system that collects, analyzes, and evaluates the credibility of news, and visually displays the results, and also combines it with an emotion engine that recognizes the user's emotions. This system allows users to quickly and easily judge the credibility of information collected from various news sources, and receive appropriate information displayed based on their emotions.

[0983] News Gathering Phase

[0984] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[0985] example:

[0986] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[0987] The server retrieves news messages from the official account of the messaging application.

[0988] The server collects top news stories using the API of an online news platform.

[0989] News Analysis Phase

[0990] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[0991] example:

[0992] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[0993] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[0994] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[0995] Credibility assessment phase

[0996] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[0997] example:

[0998] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[0999] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[1000] Data Display and User Interaction Phase

[1001] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[1002] example:

[1003] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[1004] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[1005] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[1006] Emotion Recognition Phase

[1007] The server analyzes the user's input information (e.g., text input, voice input, facial recognition, etc.) and recognizes the user's emotions using an emotion engine. The emotion engine changes the way the credibility evaluation results are displayed based on the user's emotions.

[1008] example:

[1009] When a user checks the news evaluation results, they input information into the system indicating "anxiety" or "doubt."

[1010] The server uses an emotion engine to recognize the user's emotion as "anxiety" and displays the credibility evaluation results in more detail according to the emotion.

[1011] When the user inputs something that indicates "relief" or "understanding," the server uses an emotion engine to recognize the user's emotion and selects an appropriate information display format.

[1012] In this way, the system not only quickly and accurately evaluates the credibility of information collected from a variety of news sources and provides the results to users, but also optimizes the way information is displayed according to the user's emotions, thereby realizing an extremely user-friendly service.

[1013] The processing flow will be explained below.

[1014] Step 1:

[1015] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[1016] Step 2:

[1017] The server uses the LINE API to collect news messages from LINE official accounts.

[1018] Step 3:

[1019] The server retrieves the latest top news stories through the Yahoo! News API.

[1020] Step 4:

[1021] The tweet data collected by the server is input into a generative AI model to extract key information elements (people, places, events).

[1022] Step 5:

[1023] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[1024] Step 6:

[1025] The server inputs the text of Yahoo! News articles into a generative AI model, which analyzes the content and extracts key information elements.

[1026] Step 7:

[1027] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[1028] Step 8:

[1029] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[1030] Step 9:

[1031] The server stores the results of the credibility assessment in a database for later viewing.

[1032] Step 10:

[1033] The server uses an emotion engine to analyze the user's input information (e.g., text input, voice input, facial recognition) and recognize the user's emotions.

[1034] Step 11:

[1035] A user logs into the web application using a terminal and views the parsed news list.

[1036] Step 12:

[1037] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[1038] Step 13:

[1039] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[1040] Step 14:

[1041] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[1042] Step 15:

[1043] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[1044] Step 16:

[1045] The server uses an emotion engine to generate a customized response based on the user's emotion. For example, if the user indicates "anxiety," the server provides additional detailed fact-checking information.

[1046] Step 17:

[1047] The user reviews the answers provided and asks the chatbot further questions if necessary.

[1048] Step 18:

[1049] The server adjusts the way news is displayed according to the user's emotions and provides information in a format more suited to the user.

[1050] Example 2

[1051] 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."

[1052] In today's world, advanced analysis and credibility assessment are required to quickly and accurately evaluate the credibility of news and information obtained from diverse sources and provide it visually to users. However, conventional systems only evaluate credibility centrally, making it difficult to optimize the way information is displayed in response to the user's emotions. Furthermore, they lack an interactive interface that can answer users' follow-up questions in real time. Therefore, there is a need for a system that is easy for users to use.

[1053] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask follow-up questions about the evaluation results and answer those questions; means for analyzing information input by the user and recognizing the user's emotions using an emotion engine; and means for changing the display method of the credibility evaluation results based on the user's emotions. This makes it possible not only to quickly and accurately evaluate the credibility of collected information and provide the results to the user, but also to optimize the information display method according to the user's emotions.

[1054] "Diverse information sources" refers to multiple sources that provide different types of information, such as social media, messaging applications, and online news platforms.

[1055] A "generative artificial intelligence model" is an advanced AI model for natural language processing and machine learning, used to analyze data and make generation and predictions according to specific tasks.

[1056] "Key information elements" refer to entities such as people, places, and events that are of particular importance in the collected information.

[1057] "Fact-checking for authenticity" refers to the process of verifying whether the collected and analyzed information is consistent with other reliable sources and databases.

[1058] "Interactive interface" refers to a user interface that allows a user to ask questions and receive answers in real time.

[1059] "User input information" refers to various data provided by a user to the system, such as text input, voice input, or facial recognition.

[1060] An "emotion engine" refers to an algorithm or software that analyzes a user's input information to recognize their emotional state (e.g., anxiety, relief, understanding, etc.) and optimizes the system's response and display content.

[1061] "Changing the display method of the credibility assessment results" refers to the process of dynamically adjusting the presentation format of the credibility assessment results (e.g., graphs, detailed reports, etc.) according to the user's emotional state.

[1062] The present invention is a system that collects information from various information sources, analyzes it, evaluates its credibility, and then visually presents it to the user. Furthermore, it has the feature of recognizing the user's emotions and optimizing the way information is presented accordingly. Below, we will explain the mode for implementing the invention by following a specific flow.

[1063] First, the server collects news data from multiple information sources, including social media, messaging applications, and online news platforms. For example, from social media, the server uses the Twitter API to retrieve tweets containing a specific hashtag (e.g., breaking news). From messaging applications, the server uses the LINE API to retrieve news messages from official accounts. Finally, from online news platforms, the server uses the Google News API to collect top news stories.

[1064] The server uses a generative AI model (e.g., GPT-4) to analyze the collected news data. For example, the following prompt sentences can be used when analyzing news text:

[1065] "Please extract the key information elements from this news article."

[1066] "What are the main events and related keywords in this tweet?"

[1067] Based on these prompts, the generative AI model analyzes the news data and extracts key information elements (people, places, events, etc.).

[1068] Next, the server evaluates the credibility of the analyzed news information by checking it against other reliable sources (e.g., reliable news sites or databases). The credibility is expressed as a percentage, for example:

[1069] "We compare the content of a particular article with other reliable sources and rate its credibility at 85%."

[1070] "The tweet content was checked against multiple news sites and its credibility was determined to be 70%."

[1071] The server provides a means to visually display the credibility evaluation results. When a user accesses the system on a device (smartphone or PC), the evaluation results are provided in a visually easy-to-understand format, such as a graph or chart. For example, when a user logs into a web application and opens a screen displaying a list of news credibility, the server presents the credibility evaluation results in the form of a chart, along with details of each news item and the reasons for its evaluation.

[1072] Furthermore, the server uses an emotion engine to recognize the user's emotions. It analyzes the text, voice, or facial recognition information entered by the user and recognizes the user's emotions as "anxiety," "relief," "understanding," etc. For example, if a user inputs "anxiety" or "doubt" when checking the news evaluation results, the server will recognize this as "anxiety" using the emotion engine and display more detailed credibility evaluation results according to that emotion.

[1073] This system allows users to quickly and accurately evaluate the credibility of information collected from various news sources and visually understand the results.In addition, the way information is displayed is optimized according to the user's emotions, making it an extremely user-friendly service.

[1074] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1075] Step 1: Gathering news

[1076] A server collects news data from social media, messaging applications, and online news platforms.

[1077] Input: hashtags on social media, news messages on messaging applications, news articles on online news platforms.

[1078] Processing: Use APIs to retrieve information from each platform: from social media, retrieve tweets containing specific hashtags; from messaging applications, collect news messages from official accounts; and from online news platforms, collect top stories.

[1079] Output: News data in JSON format.

[1080] Specific operation: Sends API requests and receives news data from each information source.

[1081] Step 2: News Preprocessing

[1082] The server standardizes the collected news data and converts it into text format.

[1083] Input: Collected news data in JSON format.

[1084] Processing: Data cleaning, removing unnecessary HTML tags and special characters, formatting the text, converting the news data into text format.

[1085] Output: Preprocessed news data in text format.

[1086] Specific behavior: Runs data cleaning scripts and performs text formatting.

[1087] Step 3: News analysis

[1088] The server uses a generative AI model (GPT-4) to analyze the preprocessed news data.

[1089] Input: Preprocessed news data in text format.

[1090] Processing: Generative AI models analyze news data and extract key information elements (people, places, events).

[1091] Prompts: "Please extract the main information elements from this news article.", "What are the keywords related to the main events in this tweet?"

[1092] Output: Extracted key information elements.

[1093] Specific operation: News text is input into the generative AI model and analysis results are obtained.

[1094] Step 4: Credibility assessment

[1095] The server uses the generated AI model to evaluate the credibility of the analyzed news information.

[1096] Input: Key information elements of the parsed news.

[1097] Processing: Check against trusted sources and rate the credibility as a percentage, e.g., compare with trusted news sites or databases.

[1098] Output: Belief assessment result (e.g., 85% Belief).

[1099] Specific operation: Compare the analyzed information with a reliability database and calculate a credibility score.

[1100] Step 5: Data display

[1101] The server visually displays the credibility evaluation results.

[1102] Input: The credibility assessment result.

[1103] Processing: Rendering the evaluation results in a visually understandable format such as graphs or charts.

[1104] Output: Visually displayed credibility assessment results.

[1105] What it does: Renders the evaluation results in a graph format in a web browser and provides detailed information.

[1106] Step 6: User Interaction

[1107] The user accesses the system at a terminal and asks additional questions about the evaluation results.

[1108] Input: The user's question.

[1109] Processing: Uses generative AI models to generate answers to user questions and provide a conversational interface.

[1110] Output: The answer to the question asked by the user.

[1111] Specific operation: The user's question is input into the generative AI model, an appropriate answer is generated, and it is presented to the user through the interface.

[1112] Step 7: Emotion Recognition

[1113] The server analyzes the user's input information and recognizes the user's emotions using an emotion engine.

[1114] Input: User input (text, voice, facial recognition).

[1115] Processing: Uses an emotion engine to recognize the user's emotions as "anxiety," "relief," "understanding," etc.

[1116] Output: Perceived user emotion.

[1117] What it does: It uses text analysis, speech analysis, and facial recognition models to determine the user's emotions.

[1118] Step 8: Adjust the display

[1119] The server changes the display method of the credibility evaluation result based on the user's emotions recognized by the server.

[1120] Input: Perceived user emotion.

[1121] Processing: Select an appropriate information display format according to the user's emotion and re-render.

[1122] Output: Credibility assessment results visually presented in a tailored presentation format.

[1123] Specific behavior: Dynamically change the display format based on the user's sentiment, such as displaying detailed information or a concise summary.

[1124] (Application example 2)

[1125] 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."

[1126] Current news gathering systems quickly evaluate the credibility of news information collected from various information sources and provide it to users, but they lack the ability to present information that takes user emotions into consideration. As a result, appropriate information display methods are not applied to users who feel anxious or suspicious, making it difficult to improve the user experience. Furthermore, the lack of a system specialized in providing news information in autonomous vehicles limits the means of providing reliable news information in real time.

[1127] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask and answer follow-up questions about the evaluation results; means for analyzing user input information and recognizing the user's emotions using an emotion engine; and means for dynamically changing the information display format in accordance with the user's emotions. This makes it possible to provide reliable news information in real time within an autonomous vehicle while taking user emotions into consideration.

[1128] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[1129] A "generative artificial intelligence model" is a deep learning model that uses artificial intelligence, and refers to a system that can analyze, generate, and evaluate information based on large amounts of data.

[1130] "Credibility" indicates the likelihood that collected information is factual, and refers to the degree to which it is evaluated as a percentage.

[1131] An "emotion engine" refers to an algorithm or system that analyzes user input (e.g., language, voice, facial expressions) and identifies their emotional state.

[1132] "Information presentation" refers to the way in which information is visually or interactively presented to a user, and includes different presentation formats such as graphical formats, detailed views, etc.

[1133] An "autonomous vehicle" refers to a vehicle that uses artificial intelligence and sensor technology to drive autonomously.

[1134] "Conversational interface" refers to an interface that allows a user to interact with a system using natural language, including interactions such as question-answering and information search.

[1135] "Real-time" refers to the temporal characteristic that enables a system to process information almost instantly and provide it to the user.

[1136] In order to implement the present invention, a system is constructed in which the elements of the server, the terminal, and the user function in cooperation with each other. A specific embodiment of this system is shown below.

[1137] First, the server collects information from various information sources, including social media, messaging applications, online news platforms, etc. The server uses the API of each platform to collect information. For example, the server may use the API of a social media platform to collect posts containing a specific hashtag.

[1138] Next, the collected information is analyzed using a generative AI model, such as GPT-4. Through this analysis, key information elements are extracted from the news content. Specifically, the server inputs the tweet data it has acquired into the generative AI model, which then extracts topics and related keywords.

[1139] The server then evaluates the credibility of the analyzed information. This evaluation is also performed using a generative AI model, which compares the information with other reliable sources and displays the credibility as a percentage. For example, the server compares the content of a particular news article with other reliable sources and rates its credibility as 85%.

[1140] The evaluation results are displayed visually. Users access the system through a terminal (such as the dashboard or head-up display of an autonomous vehicle) and check the information. The evaluation results are displayed in easy-to-understand visual formats such as graphs and charts.

[1141] Furthermore, when a user asks additional questions about the evaluation results, a dialogue-based interface is used. When the user inputs information from the device, the server uses the generative AI model to provide an appropriate answer to the question. For example, if a user asks, "Please tell me why the credibility of this news is 70%," the server uses the generative AI model to provide an answer.

[1142] The server also analyzes the user's input (e.g., text input or voice input) and uses an emotion engine to recognize the user's emotions. Based on this, the way information is displayed is dynamically changed depending on the user's emotions. For example, if the user inputs an expression indicating "anxiety" or "doubt," the server will use the emotion engine to recognize the user's emotion as "anxiety" and display a detailed evaluation result.

[1143] For example, if a user feels uneasy about recent news, the server will provide a detailed assessment of the news' credibility based on this input. An example of a prompt would be "Evaluate the credibility of the following news: [news content]," and the AI ​​model will analyze its credibility.

[1144] As described above, the present invention realizes a system that responds to the user's emotions while providing reliable news information in real time within an autonomous vehicle.

[1145] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1146] Step 1:

[1147] The server collects information from various information sources (social media, messaging applications, online news platforms) and uses the API of each platform to retrieve posts containing a specific hashtag, for example, from the social media API.

[1148] Input: Data from each platform's API

[1149] Output: Raw collected news data

[1150] Step 2:

[1151] The server analyzes the collected news data using a generative artificial intelligence model (such as GPT-4), which extracts key information elements from the news content.

[1152] Input: Collected news data

[1153] Data processing: News data is input into a generative AI model to analyze and extract key topics and keywords.

[1154] Output: The main information elements parsed

[1155] Step 3:

[1156] The server evaluates the veracity of the analyzed information, again using a generative AI model and comparing it with other reliable sources, and the evaluation result is expressed as a percentage.

[1157] Input: Parsed key information elements

[1158] Data calculation: Compare with other reliable sources and calculate the credibility as a percentage

[1159] Output: Credibility evaluation result (e.g., 85%)

[1160] Step 4:

[1161] The server converts the credibility assessment results into a visually displayed data format, which the user can view on their device (dashboard or head-up display).

[1162] Input: Credibility evaluation result

[1163] Data processing: Converting data into graphs and charts

[1164] Output: Visually displayable data

[1165] Step 5:

[1166] The user uses a terminal to access an interactive interface to ask follow-up questions about the assessment results, and the server uses a generative AI model to provide appropriate answers to these questions.

[1167] Input: User question

[1168] Data Computation: Using generative AI models to analyze questions and generate answers

[1169] Output: The answer that is presented to the user

[1170] Step 6:

[1171] The user inputs their emotions (for example, "I'm worried about the recent news") into the device. The server analyzes this using an emotion engine and recognizes the user's emotions.

[1172] Input: User emotion input

[1173] Data Computation: Uses an emotion engine to analyze input text and voice to identify user emotions

[1174] Output: Parsed user's emotional state (e.g., "anxiety")

[1175] Step 7:

[1176] The server dynamically changes the way information is displayed depending on the user's emotional state. For example, if the user expresses "anxiety," the server displays the credibility evaluation results in detail.

[1177] Input: User's emotional state and credibility evaluation results

[1178] Data processing: Display method adjusted according to emotional state

[1179] Output: Dynamically changed display format (e.g., detailed view)

[1180] These steps enable the system to respond to user sentiment and provide reliable news information in real time within self-driving vehicles.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] [Fourth embodiment]

[1185] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1186] 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.

[1187] 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).

[1188] 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.

[1189] 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.

[1190] 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).

[1191] 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.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] 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.

[1196] 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.

[1197] 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."

[1198] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results, allowing users to quickly and easily determine the credibility of information collected from a variety of news sources.

[1199] News Gathering Phase

[1200] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[1201] example:

[1202] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[1203] The server retrieves news messages from the official account of the messaging application.

[1204] The server collects top news stories using the API of an online news platform.

[1205] News Analysis Phase

[1206] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[1207] example:

[1208] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[1209] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[1210] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[1211] Credibility assessment phase

[1212] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[1213] example:

[1214] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[1215] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[1216] Data Display and User Interaction Phase

[1217] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[1218] example:

[1219] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[1220] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[1221] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[1222] In this way, this system can quickly and accurately evaluate the credibility of information collected from various news sources and provide the results to users. Furthermore, through user interaction, users can obtain more detailed information, making this a very easy-to-use service.

[1223] The processing flow will be explained below.

[1224] Step 1:

[1225] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[1226] Step 2:

[1227] The server uses the LINE API to collect news messages from LINE official accounts.

[1228] Step 3:

[1229] The server retrieves the latest top news stories through the Yahoo! News API.

[1230] Step 4:

[1231] The server inputs the collected tweet data into a generative AI model to extract key information elements (e.g., people, places, events).

[1232] Step 5:

[1233] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[1234] Step 6:

[1235] The server inputs the text of Yahoo! News articles into a generative AI model, analyzes the content, and extracts key points.

[1236] Step 7:

[1237] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[1238] Step 8:

[1239] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[1240] Step 9:

[1241] The server stores the results of the credibility assessment in a database for later viewing.

[1242] Step 10:

[1243] A user logs into the web application using a terminal and views the parsed news list.

[1244] Step 11:

[1245] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[1246] Step 12:

[1247] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[1248] Step 13:

[1249] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[1250] Step 14:

[1251] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[1252] Step 15:

[1253] The user reviews the answers provided and asks the chatbot further questions if necessary.

[1254] Example 1

[1255] 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."

[1256] In today's world, it is extremely important to quickly and accurately evaluate the credibility of news collected from a variety of sources. However, conventional systems collect information, analyze it, evaluate its credibility, and visually display the results separately, making the overall process complex and time-consuming. This also makes it difficult for users to ask detailed questions about the evaluation results. This increases the burden on users when judging the credibility of news, which has been an issue.

[1257] 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.

[1258] In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for users to ask and answer follow-up questions about the evaluation results; means for preprocessing the collected information; and means for displaying the evaluation results in chart or graph format. This enables the credibility of news to be evaluated quickly and accurately and the results to be visually confirmed. Furthermore, users can easily ask detailed questions about the evaluation results, thereby reducing the burden on users.

[1259] "Information sources" refers to various information sources, such as social media, messaging applications, and online news platforms.

[1260] "Generative artificial intelligence models" refer to advanced algorithms and software systems that can understand and generate natural language, such as GPT-4.

[1261] "Analysis" refers to the process of inputting collected news data into a generative artificial intelligence model to extract key information elements (e.g., people, places, events).

[1262] "Credibility assessment" refers to the process of fact-checking analyzed news information and then quantifying its credibility in the form of a percentage.

[1263] "Preprocessing" refers to the process of cleaning collected news data and filtering out irrelevant information before analysis.

[1264] "Dialogue interface" means an interface that allows a user to ask follow-up questions and receive answers to those questions through natural language interaction with the system.

[1265] "Charts and graph formats" refers to figures and diagrams that display evaluation results in a visually easy-to-understand manner.

[1266] The present invention is a system that collects, analyzes, and evaluates the credibility of news and visually displays the results. This system is mainly composed of a server, terminals, and users.

[1267] First, in the news gathering phase, the server collects news data using the APIs of various information sources (e.g., social media, messaging applications, online news platforms). Specifically, it uses social media APIs to collect posts containing specific hashtags, obtains news messages from official messaging app accounts, and uses online news platform APIs to obtain the latest news. This gathering process allows for the rapid and efficient accumulation of diverse news data.

[1268] Next, in the news analysis phase, the server inputs the collected news data into a generative AI model (e.g., GPT-4) to extract key information elements (e.g., people, places, and events). After preprocessing the collected news data and removing unnecessary information, the generative AI model is given prompts such as the following to analyze it. This analysis organizes the main points of each news item and extracts important information.

[1269] Example prompt sentence:

[1270] "Extract the main topics and related keywords of tweets about the latest news."

[1271] "Please summarize the main points of this news text."

[1272] In the credibility evaluation phase, the server compares the analyzed news information with other reliable sources and evaluates its credibility as a percentage using a generative artificial intelligence model. For example, the content of a specific news article is compared and collated with other major news sites and databases to quantify its credibility. This allows the credibility of each news item to be clearly displayed, supporting user decision-making.

[1273] Finally, in the data display and user interaction phase, the user accesses the system using a device (e.g., a smartphone or PC) to view the credibility assessment results. The server visually displays the assessment results in the form of charts and graphs, along with details of each news item and the reasons for its assessment. The user can also ask additional questions through a dialogue interface, and the answers to those questions are also provided using the generative AI model. For example, if the user asks, "Tell me why the credibility of this news is 70%," the server inputs this prompt into the generative AI model and returns an appropriate answer.

[1274] The present invention enables the rapid and accurate evaluation and visual display of the credibility of information collected from multiple news sources, and also allows users to ask detailed questions in an interactive format, providing a highly user-friendly service.

[1275] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1276] Step 1:

[1277] The server collects news data from a variety of sources.

[1278] Specific behavior:

[1279] The server uses a social media API endpoint and an access token to collect posts containing a specific hashtag (e.g., "breaking news"), taking the posts containing the hashtag as input and obtaining the metadata, text, and related information for the posts as output.

[1280] The server uses the messaging application's API to retrieve news messages from official accounts, using the official account's authentication information as input and collecting the news messages and their metadata as output.

[1281] The server retrieves the latest top news stories using the API of an online news platform (e.g., Google News API), using the API key and endpoint as input, and gets the list of latest news articles along with their metadata and article text as output.

[1282] Step 2:

[1283] The server preprocesses the collected news data.

[1284] Specific behavior:

[1285] The server cleans irrelevant elements such as hashtags, links, and user mentions from the collected tweet text. At this time, the tweet text is used as input, and the clean text with unnecessary elements removed is obtained as output.

[1286] The server filters news text obtained from a messaging application to remove unnecessary parts, giving message text as input and obtaining the news text with unnecessary parts removed as output.

[1287] The server filters advertisements and noise data from article texts of online news platforms, using the collected article texts as input and obtaining the filtered clean article texts as output.

[1288] Step 3:

[1289] The server inputs the preprocessed news data into the generative AI model for analysis.

[1290] Specific behavior:

[1291] The server inputs the preprocessed tweet data into a generative AI model (e.g., GPT-4) and analyzes it using the prompt, "Please extract the main topic and related keywords of this tweet." At this time, the clean tweet data is given as input, and the main topic and related keywords are obtained as output.

[1292] The server inputs the preprocessed news text obtained from the messaging application into a generative AI model to extract gist points, using the clean news text as input and obtaining gist points as output.

[1293] The server inputs the preprocessed article text obtained from the online news platform into a generative AI model to analyze and summarize the main points of the content, using the clean article text as input and obtaining the summarized information as output.

[1294] Step 4:

[1295] The server evaluates the credibility of the news based on the analysis results.

[1296] Specific behavior:

[1297] The server compares the analyzed news information with other reliable sources (e.g., major news sites or databases), using the analysis results and data from reliable sources as inputs and obtaining the comparison results as output.

[1298] The server evaluates the credibility of the news in percentage format based on the matching result, using the matching result as input and obtaining a percentage value indicating the credibility of the news as output.

[1299] Step 5:

[1300] The server creates data for visually displaying the credibility evaluation results.

[1301] Specific behavior:

[1302] The server converts the credibility assessment results into charts and graphs, using the credibility assessment results as input and obtaining data converted into a visually displayable format as output.

[1303] Step 6:

[1304] The user accesses the system using a terminal and checks the credibility evaluation results.

[1305] Specific behavior:

[1306] A user logs in to a web application from a terminal and accesses a homepage. At this time, a username and password are used as input, and the homepage screen after successful authentication is obtained as output.

[1307] The user opens a screen to display the news credibility list. At this time, data for visually displaying the credibility evaluation results is used as input, and the results displayed in chart and graph format are obtained as output.

[1308] Step 7:

[1309] The user uses the interactive interface to ask follow-up questions.

[1310] Specific behavior:

[1311] A user uses the interactive interface to type, "Tell me why this news story is 70% reliable," and the user's question is used as input.

[1312] The server uses a generative AI model to generate an answer to the question and respond to the user, taking the user's question as input and obtaining an appropriate answer as output.

[1313] By going through the above steps, the system can perform consistent processing from news collection to credibility assessment, visual display, and user interaction.

[1314] (Application example 1)

[1315] 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."

[1316] In modern society, it is difficult to determine the credibility of news and information provided by a variety of sources, and especially on digital platforms such as virtual stores, users lack the means to immediately determine the credibility of news related to products. For this reason, there is a need to provide users with the information they need to make decisions quickly and reliably when purchasing products.

[1317] 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.

[1318] In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and rating the credibility as a percentage; means for visually displaying the rating results; means for providing an interactive interface for users to ask and answer follow-up questions about the rating results; and display means for viewers to check related news and credibility ratings of products in real time while viewing products in a virtual store. This allows users to quickly evaluate the credibility of news information related to a product when selecting a product in the virtual store, which can help them make a purchasing decision.

[1319] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[1320] A "generative artificial intelligence model" refers to a learning system that uses natural language processing techniques to analyze text data and extract and generate specific information.

[1321] "Key information elements" refer to people, places, events, and other elements that are deemed important in news or information.

[1322] "Credibility" refers to the reliability of information based on facts and is evaluated as a percentage based on specific criteria.

[1323] "Visual display means" refers to a method of displaying the results of the credibility assessment of collected and analyzed information in a visual format such as a graph or chart so that users can easily understand it.

[1324] "Interactive interface" refers to an interactive user interface that allows a user to ask a system additional questions and for the system to respond to those questions.

[1325] A "virtual store" refers to a virtual shopping environment created using the Internet and VR technology.

[1326] "Display means" refers to the method by which information is displayed to the user via a device such as smart glasses or a head-mounted display.

[1327] The present invention relates to a system for gathering, analyzing, and evaluating the credibility of news, and visually displaying the results. This system is particularly designed to allow users to check related news and credibility ratings of products in real time within a virtual store.

[1328] News Gathering Phase

[1329] The server collects news data from various information sources, such as social media, messaging applications, and online news platforms. To achieve this, it uses the APIs of each platform. For example, it uses the APIs of social media to collect tweets containing a specific hashtag. It also obtains news messages from official accounts on messaging applications and uses the APIs of online news platforms to collect top news stories.

[1330] News Analysis Phase

[1331] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements from the news (e.g., people, places, and events). For example, acquired tweet data is input into the generative AI model to extract key topics and related keywords. It also analyzes and extracts key elements from news text obtained from messaging applications.

[1332] Credibility assessment phase

[1333] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., reliable news sites and databases). The credibility is expressed as a percentage. For example, the content of a particular news article is compared with other reliable sources to assess its credibility. The server also checks tweet content against multiple news sites to determine its credibility.

[1334] Data Display and User Interaction Phase

[1335] Users can access the system using a device (smart glasses or head-mounted display) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use a dialogue interface to ask additional questions, and the server will provide answers using a generative AI model. For example, they can ask, "Tell me why the credibility of this news is 70%," and receive a detailed answer from the server.

[1336] The specific hardware and software you will use

[1337] Hardware: Smart glasses (e.g., Google Glass), head-mounted displays (e.g., Oculus Quest 2)

[1338] Software: Python, OpenAI GPT-4 API, News API, Matplotlib

[1339] Case studies

[1340] For example, imagine a user is browsing a new smartphone in a virtual store. The smart glasses display a news item about the release of a new smartphone, along with a news description that reads, "The latest model is equipped with new AI features and is attracting a lot of attention." The generative AI model then displays a credibility rating for this news item, visually indicating a result of, say, 85%.

[1341] The prompt for the generative AI model is:

[1342] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[1343] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1344] Step 1:

[1345] The server collects news data using APIs from various sources, such as social media, messaging applications, and online news platforms, and retrieves tweets containing specific hashtags (e.g., breaking news), news messages from official accounts, and top news stories.

[1346] Input: API of each platform, hashtag

[1347] Output: A list of news data retrieved from each platform

[1348] Step 2:

[1349] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content, which extracts key information elements (people, places, events) from the news.

[1350] Input: List of news data

[1351] Output: Analysis results for each news article (text structure including key information elements)

[1352] Step 3:

[1353] The server compares the analyzed news information with other reliable sources to assess its credibility, and calculates a percentage based on the credibility rating to filter out less reliable information.

[1354] Input: Parsed news data, list of reliable sources

[1355] Output: The credibility rating (percentage) of each news article

[1356] Step 4:

[1357] The server generates data to visually display the evaluation results, including graphs and charts, and uses libraries such as Matplotlib to convert the data into a format that is easy for users to understand.

[1358] Input: Credibility assessment result

[1359] Output: Visual display data (in the form of graphs and charts)

[1360] Step 5:

[1361] The user accesses the system using a device (smart glasses or a head-mounted display) and visually checks the credibility evaluation results. Information is sent so that the results are displayed on the smart glasses or head-mounted display.

[1362] Input: Visual display data

[1363] Output: The credibility assessment result displayed on the user's device.

[1364] Step 6:

[1365] The user uses a conversational interface to ask follow-up questions about the results. These questions are sent to the generative AI model, and the server generates an appropriate answer to the question. For example, "Tell me why this news story is 70% reliable."

[1366] Input: User question

[1367] Output: Answer from the generative AI model (detailed explanation)

[1368] Example prompt sentence:

[1369] "News: New smartphones released. The latest models are equipped with new AI functions and are attracting a lot of attention. What are the main details?"

[1370] 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.

[1371] This invention is a system that collects, analyzes, and evaluates the credibility of news, and visually displays the results, and also combines it with an emotion engine that recognizes the user's emotions. This system allows users to quickly and easily judge the credibility of information collected from various news sources, and receive appropriate information displayed based on their emotions.

[1372] News Gathering Phase

[1373] The server collects news data from sources such as social media, messaging applications, and online news platforms, which involves using each platform's API to retrieve the information.

[1374] example:

[1375] The server uses social media APIs to collect tweets containing a specific hashtag (e.g., breaking news).

[1376] The server retrieves news messages from the official account of the messaging application.

[1377] The server collects top news stories using the API of an online news platform.

[1378] News Analysis Phase

[1379] The server inputs the collected news data into a generative AI model (e.g., GPT-4) to analyze the news content. This analysis extracts key information elements (e.g., people, places, and events).

[1380] example:

[1381] The server inputs the acquired tweet data into a generative AI model to extract key topics and related keywords.

[1382] The server inputs news text obtained from messaging applications into a generative AI model, which analyzes and extracts key points.

[1383] The server inputs article text from an online news platform into a generative AI model, which analyzes the content and summarizes the main points.

[1384] Credibility assessment phase

[1385] The server evaluates the credibility of the analyzed news information using a generative AI model. The evaluation includes cross-referencing with other reliable sources (e.g., trusted news sites and databases). The credibility is expressed as a percentage.

[1386] example:

[1387] The server compares the content of a particular news article with other reliable sources and rates its credibility at 85%.

[1388] The server checks the tweet content against multiple news sites and determines its credibility as 70%.

[1389] Data Display and User Interaction Phase

[1390] Users can access the system using a device (smartphone or PC) and check the credibility assessment results. The assessment results are presented in a visually easy-to-understand format, such as graphs and charts. Users can also use the dialogue interface to ask additional questions.

[1391] example:

[1392] A user logs into a web application and opens a screen displaying a list of news credibility ratings.

[1393] The server presents the credibility ratings in a chart format, along with details of each news item and the reasons for its rating.

[1394] Using a conversational interface, a user asks, "Tell me why this news story is 70% reliable," and the server uses a generative AI model to provide the answer.

[1395] Emotion Recognition Phase

[1396] The server analyzes the user's input information (e.g., text input, voice input, facial recognition, etc.) and recognizes the user's emotions using an emotion engine. The emotion engine changes the way the credibility evaluation results are displayed based on the user's emotions.

[1397] example:

[1398] When a user checks the news evaluation results, they input information into the system indicating "anxiety" or "doubt."

[1399] The server uses an emotion engine to recognize the user's emotion as "anxiety" and displays the credibility evaluation results in more detail according to the emotion.

[1400] When the user inputs something that indicates "relief" or "understanding," the server uses an emotion engine to recognize the user's emotion and selects an appropriate information display format.

[1401] In this way, the system not only quickly and accurately evaluates the credibility of information collected from a variety of news sources and provides the results to users, but also optimizes the way information is displayed according to the user's emotions, thereby realizing an extremely user-friendly service.

[1402] The processing flow will be explained below.

[1403] Step 1:

[1404] The server accesses the Twitter API and sends a request to gather tweets containing a specific hashtag (e.g., breaking news).

[1405] Step 2:

[1406] The server uses the LINE API to collect news messages from LINE official accounts.

[1407] Step 3:

[1408] The server retrieves the latest top news stories through the Yahoo! News API.

[1409] Step 4:

[1410] The tweet data collected by the server is input into a generative AI model to extract key information elements (people, places, events).

[1411] Step 5:

[1412] The server passes news messages collected from LINE to a generative AI model, which extracts key points and relevant facts.

[1413] Step 6:

[1414] The server inputs the text of Yahoo! News articles into a generative AI model, which analyzes the content and extracts key information elements.

[1415] Step 7:

[1416] The server then refers the generative AI model to reliable sources (e.g., Wikipedia or other news sites) related to the extracted information.

[1417] Step 8:

[1418] The server evaluates the credibility of each news item based on the analysis results of the generated AI model and expresses it as a percentage.

[1419] Step 9:

[1420] The server stores the results of the credibility assessment in a database for later viewing.

[1421] Step 10:

[1422] The server uses an emotion engine to analyze the user's input information (e.g., text input, voice input, facial recognition) and recognize the user's emotions.

[1423] Step 11:

[1424] A user logs into the web application using a terminal and views the parsed news list.

[1425] Step 12:

[1426] The server displays the credibility of the news along with the percentage in a visually easy-to-understand graph format.

[1427] Step 13:

[1428] Users can click on the details of the news that interests them to view the reasons for the credibility rating and related fact-checking information.

[1429] Step 14:

[1430] A user asks the chatbot, "Please tell me why this news story is rated 70% credible."

[1431] Step 15:

[1432] The server uses a generative AI model to answer questions and generate answers such as "This is because the information obtained from certain trusted sources did not match."

[1433] Step 16:

[1434] The server uses an emotion engine to generate a customized response based on the user's emotion. For example, if the user indicates "anxiety," the server provides additional detailed fact-checking information.

[1435] Step 17:

[1436] The user reviews the answers provided and asks the chatbot further questions if necessary.

[1437] Step 18:

[1438] The server adjusts the way news is displayed according to the user's emotions and provides information in a format more suited to the user.

[1439] Example 2

[1440] 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."

[1441] In today's world, advanced analysis and credibility assessment are required to quickly and accurately evaluate the credibility of news and information obtained from diverse sources and provide it visually to users. However, conventional systems only evaluate credibility centrally, making it difficult to optimize the way information is displayed in response to the user's emotions. Furthermore, they lack an interactive interface that can answer users' follow-up questions in real time. Therefore, there is a need for a system that is easy for users to use.

[1442] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask follow-up questions about the evaluation results and answer those questions; means for analyzing information input by the user and recognizing the user's emotions using an emotion engine; and means for changing the display method of the credibility evaluation results based on the user's emotions. This makes it possible not only to quickly and accurately evaluate the credibility of collected information and provide the results to the user, but also to optimize the information display method according to the user's emotions.

[1443] "Diverse information sources" refers to multiple sources that provide different types of information, such as social media, messaging applications, and online news platforms.

[1444] A "generative artificial intelligence model" is an advanced AI model for natural language processing and machine learning, used to analyze data and make generation and predictions according to specific tasks.

[1445] "Key information elements" refer to entities such as people, places, and events that are of particular importance in the collected information.

[1446] "Fact-checking for authenticity" refers to the process of verifying whether the collected and analyzed information is consistent with other reliable sources and databases.

[1447] "Interactive interface" refers to a user interface that allows a user to ask questions and receive answers in real time.

[1448] "User input information" refers to various data provided by a user to the system, such as text input, voice input, or facial recognition.

[1449] An "emotion engine" refers to an algorithm or software that analyzes a user's input information to recognize their emotional state (e.g., anxiety, relief, understanding, etc.) and optimizes the system's response and display content.

[1450] "Changing the display method of the credibility assessment results" refers to the process of dynamically adjusting the presentation format of the credibility assessment results (e.g., graphs, detailed reports, etc.) according to the user's emotional state.

[1451] The present invention is a system that collects information from various information sources, analyzes it, evaluates its credibility, and then visually presents it to the user. Furthermore, it has the feature of recognizing the user's emotions and optimizing the way information is presented accordingly. Below, we will explain the mode for implementing the invention by following a specific flow.

[1452] First, the server collects news data from multiple information sources, including social media, messaging applications, and online news platforms. For example, from social media, the server uses the Twitter API to retrieve tweets containing a specific hashtag (e.g., breaking news). From messaging applications, the server uses the LINE API to retrieve news messages from official accounts. Finally, from online news platforms, the server uses the Google News API to collect top news stories.

[1453] The server uses a generative AI model (e.g., GPT-4) to analyze the collected news data. For example, the following prompt sentences can be used when analyzing news text:

[1454] "Please extract the key information elements from this news article."

[1455] "What are the main events and related keywords in this tweet?"

[1456] Based on these prompts, the generative AI model analyzes the news data and extracts key information elements (people, places, events, etc.).

[1457] Next, the server evaluates the credibility of the analyzed news information by checking it against other reliable sources (e.g., reliable news sites or databases). The credibility is expressed as a percentage, for example:

[1458] "We compare the content of a particular article with other reliable sources and rate its credibility at 85%."

[1459] "The tweet content was checked against multiple news sites and its credibility was determined to be 70%."

[1460] The server provides a means to visually display the credibility evaluation results. When a user accesses the system on a device (smartphone or PC), the evaluation results are provided in a visually easy-to-understand format, such as a graph or chart. For example, when a user logs into a web application and opens a screen displaying a list of news credibility, the server presents the credibility evaluation results in the form of a chart, along with details of each news item and the reasons for its evaluation.

[1461] Furthermore, the server uses an emotion engine to recognize the user's emotions. It analyzes the text, voice, or facial recognition information entered by the user and recognizes the user's emotions as "anxiety," "relief," "understanding," etc. For example, if a user inputs "anxiety" or "doubt" when checking the news evaluation results, the server will recognize this as "anxiety" using the emotion engine and display more detailed credibility evaluation results according to that emotion.

[1462] This system allows users to quickly and accurately evaluate the credibility of information collected from various news sources and visually understand the results.In addition, the way information is displayed is optimized according to the user's emotions, making it an extremely user-friendly service.

[1463] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1464] Step 1: Gathering news

[1465] A server collects news data from social media, messaging applications, and online news platforms.

[1466] Input: hashtags on social media, news messages on messaging applications, news articles on online news platforms.

[1467] Processing: Use APIs to retrieve information from each platform: from social media, retrieve tweets containing specific hashtags; from messaging applications, collect news messages from official accounts; and from online news platforms, collect top stories.

[1468] Output: News data in JSON format.

[1469] Specific operation: Sends API requests and receives news data from each information source.

[1470] Step 2: News Preprocessing

[1471] The server standardizes the collected news data and converts it into text format.

[1472] Input: Collected news data in JSON format.

[1473] Processing: Data cleaning, removing unnecessary HTML tags and special characters, formatting the text, converting the news data into text format.

[1474] Output: Preprocessed news data in text format.

[1475] Specific behavior: Runs data cleaning scripts and performs text formatting.

[1476] Step 3: News analysis

[1477] The server uses a generative AI model (GPT-4) to analyze the preprocessed news data.

[1478] Input: Preprocessed news data in text format.

[1479] Processing: Generative AI models analyze news data and extract key information elements (people, places, events).

[1480] Prompts: "Please extract the main information elements from this news article.", "What are the keywords related to the main events in this tweet?"

[1481] Output: Extracted key information elements.

[1482] Specific operation: News text is input into the generative AI model and analysis results are obtained.

[1483] Step 4: Credibility assessment

[1484] The server uses the generated AI model to evaluate the credibility of the analyzed news information.

[1485] Input: Key information elements of the parsed news.

[1486] Processing: Check against trusted sources and rate the credibility as a percentage, e.g., compare with trusted news sites or databases.

[1487] Output: Belief assessment result (e.g., 85% Belief).

[1488] Specific operation: Compare the analyzed information with a reliability database and calculate a credibility score.

[1489] Step 5: Data display

[1490] The server visually displays the credibility evaluation results.

[1491] Input: The credibility assessment result.

[1492] Processing: Rendering the evaluation results in a visually understandable format such as graphs or charts.

[1493] Output: Visually displayed credibility assessment results.

[1494] What it does: Renders the evaluation results in a graph format in a web browser and provides detailed information.

[1495] Step 6: User Interaction

[1496] The user accesses the system at a terminal and asks additional questions about the evaluation results.

[1497] Input: The user's question.

[1498] Processing: Uses generative AI models to generate answers to user questions and provide a conversational interface.

[1499] Output: The answer to the question asked by the user.

[1500] Specific operation: The user's question is input into the generative AI model, an appropriate answer is generated, and it is presented to the user through the interface.

[1501] Step 7: Emotion Recognition

[1502] The server analyzes the user's input information and recognizes the user's emotions using an emotion engine.

[1503] Input: User input (text, voice, facial recognition).

[1504] Processing: Uses an emotion engine to recognize the user's emotions as "anxiety," "relief," "understanding," etc.

[1505] Output: Perceived user emotion.

[1506] What it does: It uses text analysis, speech analysis, and facial recognition models to determine the user's emotions.

[1507] Step 8: Adjust the display

[1508] The server changes the display method of the credibility evaluation result based on the user's emotions recognized by the server.

[1509] Input: Perceived user emotion.

[1510] Processing: Select an appropriate information display format according to the user's emotion and re-render.

[1511] Output: Credibility assessment results visually presented in a tailored presentation format.

[1512] Specific behavior: Dynamically change the display format based on the user's sentiment, such as displaying detailed information or a concise summary.

[1513] (Application example 2)

[1514] 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."

[1515] Current news gathering systems quickly evaluate the credibility of news information collected from various information sources and provide it to users, but they lack the ability to present information that takes user emotions into consideration. As a result, appropriate information display methods are not applied to users who feel anxious or suspicious, making it difficult to improve the user experience. Furthermore, the lack of a system specialized in providing news information in autonomous vehicles limits the means of providing reliable news information in real time.

[1516] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information from various information sources; means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; means for visually displaying the evaluation results; means for providing an interactive interface for the user to ask and answer follow-up questions about the evaluation results; means for analyzing user input information and recognizing the user's emotions using an emotion engine; and means for dynamically changing the information display format in accordance with the user's emotions. This makes it possible to provide reliable news information in real time within an autonomous vehicle while taking user emotions into consideration.

[1517] "Diverse information sources" refers to multiple different information sources, such as social media, messaging applications, and online news platforms.

[1518] A "generative artificial intelligence model" is a deep learning model that uses artificial intelligence, and refers to a system that can analyze, generate, and evaluate information based on large amounts of data.

[1519] "Credibility" indicates the likelihood that collected information is factual, and refers to the degree to which it is evaluated as a percentage.

[1520] An "emotion engine" refers to an algorithm or system that analyzes user input (e.g., language, voice, facial expressions) and identifies their emotional state.

[1521] "Information presentation" refers to the way in which information is visually or interactively presented to a user, and includes different presentation formats such as graphical formats, detailed views, etc.

[1522] An "autonomous vehicle" refers to a vehicle that uses artificial intelligence and sensor technology to drive autonomously.

[1523] "Conversational interface" refers to an interface that allows a user to interact with a system using natural language, including interactions such as question-answering and information search.

[1524] "Real-time" refers to the temporal characteristic that enables a system to process information almost instantly and provide it to the user.

[1525] In order to implement the present invention, a system is constructed in which the elements of the server, the terminal, and the user function in cooperation with each other. A specific embodiment of this system is shown below.

[1526] First, the server collects information from various information sources, including social media, messaging applications, online news platforms, etc. The server uses the API of each platform to collect information. For example, the server may use the API of a social media platform to collect posts containing a specific hashtag.

[1527] Next, the collected information is analyzed using a generative AI model, such as GPT-4. Through this analysis, key information elements are extracted from the news content. Specifically, the server inputs the tweet data it has acquired into the generative AI model, which then extracts topics and related keywords.

[1528] The server then evaluates the credibility of the analyzed information. This evaluation is also performed using a generative AI model, which compares the information with other reliable sources and displays the credibility as a percentage. For example, the server compares the content of a particular news article with other reliable sources and rates its credibility as 85%.

[1529] The evaluation results are displayed visually. Users access the system through a terminal (such as the dashboard or head-up display of an autonomous vehicle) and check the information. The evaluation results are displayed in easy-to-understand visual formats such as graphs and charts.

[1530] Furthermore, when a user asks additional questions about the evaluation results, a dialogue-based interface is used. When the user inputs information from the device, the server uses the generative AI model to provide an appropriate answer to the question. For example, if a user asks, "Please tell me why the credibility of this news is 70%," the server uses the generative AI model to provide an answer.

[1531] The server also analyzes the user's input (e.g., text input or voice input) and uses an emotion engine to recognize the user's emotions. Based on this, the way information is displayed is dynamically changed depending on the user's emotions. For example, if the user inputs an expression indicating "anxiety" or "doubt," the server will use the emotion engine to recognize the user's emotion as "anxiety" and display a detailed evaluation result.

[1532] For example, if a user feels uneasy about recent news, the server will provide a detailed assessment of the news' credibility based on this input. An example of a prompt would be "Evaluate the credibility of the following news: [news content]," and the AI ​​model will analyze its credibility.

[1533] As described above, the present invention realizes a system that responds to the user's emotions while providing reliable news information in real time within an autonomous vehicle.

[1534] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1535] Step 1:

[1536] The server collects information from various information sources (social media, messaging applications, online news platforms) and uses the API of each platform to retrieve posts containing a specific hashtag, for example, from the social media API.

[1537] Input: Data from each platform's API

[1538] Output: Raw collected news data

[1539] Step 2:

[1540] The server analyzes the collected news data using a generative artificial intelligence model (such as GPT-4), which extracts key information elements from the news content.

[1541] Input: Collected news data

[1542] Data processing: News data is input into a generative AI model to analyze and extract key topics and keywords.

[1543] Output: The main information elements parsed

[1544] Step 3:

[1545] The server evaluates the veracity of the analyzed information, again using a generative AI model and comparing it with other reliable sources, and the evaluation result is expressed as a percentage.

[1546] Input: Parsed key information elements

[1547] Data calculation: Compare with other reliable sources and calculate the credibility as a percentage

[1548] Output: Credibility evaluation result (e.g., 85%)

[1549] Step 4:

[1550] The server converts the credibility assessment results into a visually displayed data format, which the user can view on their device (dashboard or head-up display).

[1551] Input: Credibility evaluation result

[1552] Data processing: Converting data into graphs and charts

[1553] Output: Visually displayable data

[1554] Step 5:

[1555] The user uses a terminal to access an interactive interface to ask follow-up questions about the assessment results, and the server uses a generative AI model to provide appropriate answers to these questions.

[1556] Input: User question

[1557] Data Computation: Using generative AI models to analyze questions and generate answers

[1558] Output: The answer that is presented to the user

[1559] Step 6:

[1560] The user inputs their emotions (for example, "I'm worried about the recent news") into the device. The server analyzes this using an emotion engine and recognizes the user's emotions.

[1561] Input: User emotion input

[1562] Data Computation: Uses an emotion engine to analyze input text and voice to identify user emotions

[1563] Output: Parsed user's emotional state (e.g., "anxiety")

[1564] Step 7:

[1565] The server dynamically changes the way information is displayed depending on the user's emotional state. For example, if the user expresses "anxiety," the server displays the credibility evaluation results in detail.

[1566] Input: User's emotional state and credibility evaluation results

[1567] Data processing: Display method adjusted according to emotional state

[1568] Output: Dynamically changed display format (e.g., detailed view)

[1569] These steps enable the system to respond to user sentiment and provide reliable news information in real time within self-driving vehicles.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] 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.

[1576] 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).

[1577] 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.

[1578] 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."

[1579] 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.

[1580] 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).

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] The following is further disclosed regarding the above embodiment.

[1592] (Claim 1)

[1593] A means of collecting information from a variety of sources;

[1594] A means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements;

[1595] A means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage;

[1596] a means for visually displaying the evaluation results;

[1597] a means for providing an interactive interface for users to ask and answer follow-up questions about the assessment results;

[1598] A system including:

[1599] (Claim 2)

[1600] 10. The system of claim 1, wherein the diverse information sources include social media, messaging applications, and online news platforms.

[1601] (Claim 3)

[1602] 10. The system of claim 1, further comprising means for visually displaying the evaluation results in a graphical format.

[1603] "Example 1"

[1604] (Claim 1)

[1605] A means of collecting information from a variety of sources;

[1606] A means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements;

[1607] A means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage;

[1608] a means for visually displaying the evaluation results;

[1609] a means for providing an interactive interface for users to ask and answer follow-up questions about the assessment results;

[1610] means for pre-processing the collected information;

[1611] A means of displaying the evaluation results in charts and graphs;

[1612] A system including:

[1613] (Claim 2)

[1614] 10. The system of claim 1, wherein the diverse information sources include social media, messaging applications, and online news platforms.

[1615] (Claim 3)

[1616] 10. The system of claim 1, further comprising means for visually displaying the evaluation results in the form of a chart.

[1617] "Application Example 1"

[1618] (Claim 1)

[1619] A means of collecting information from a variety of sources;

[1620] A means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements;

[1621] A means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage;

[1622] a means for visually displaying the evaluation results;

[1623] a means for providing an interactive interface for users to ask and answer follow-up questions about the assessment results;

[1624] A display means for viewers to check related news and credibility ratings of products in real time while viewing the products in the virtual store;

[1625] A system including:

[1626] (Claim 2)

[1627] 10. The system of claim 1, wherein the diverse information sources include social media, messaging applications, and online news platforms.

[1628] (Claim 3)

[1629] 10. The system of claim 1, further comprising means for visually displaying the evaluation results in a graphical format.

[1630] "Example 2: Combining Emotion Engines"

[1631] (Claim 1)

[1632] A means of collecting information from a variety of sources;

[1633] A means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements;

[1634] A means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage;

[1635] a means for visually displaying the evaluation results;

[1636] a means for providing an interactive interface for users to ask and answer follow-up questions about the assessment results;

[1637] means for analyzing user input information and recognizing user emotions using an emotion engine;

[1638] a means for changing a display method of the credibility evaluation result based on the user's emotion;

[1639] A system including:

[1640] (Claim 2)

[1641] 10. The system of claim 1, wherein the diverse information sources include social media, messaging applications, and online news platforms.

[1642] (Claim 3)

[1643] 10. The system of claim 1, further comprising means for visually displaying the evaluation results in a graphical format.

[1644] "Application example 2 when combining emotion engines"

[1645] (Claim 1)

[1646] A means of collecting information from a variety of sources;

[1647] A means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements;

[1648] A means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage;

[1649] a means for visually displaying the evaluation results;

[1650] a means for providing an interactive interface for users to ask and answer follow-up questions about the assessment results;

[1651] means for analyzing user input information and recognizing user emotions using an emotion engine;

[1652] means for dynamically changing the information display format in response to the user's emotions;

[1653] A system including:

[1654] (Claim 2)

[1655] 10. The system of claim 1, wherein the diverse information sources include social media, messaging applications, and online news platforms.

[1656] (Claim 3)

[1657] 10. The system of claim 1, further comprising means for visually displaying the evaluation results in a graphical format. [Explanation of symbols]

[1658] 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 of collecting information from a variety of sources; A means for analyzing the collected information using a generative artificial intelligence model and extracting key information elements; A means for fact-checking the credibility of the information analyzed using the generative artificial intelligence model and evaluating the credibility as a percentage; a means for visually displaying the evaluation results; a means for providing an interactive interface for users to ask and answer follow-up questions about the assessment results; A system including:

2. 10. The system of claim 1, wherein the diverse information sources include social media, messaging applications, and online news platforms.

3. 10. The system of claim 1, further comprising means for visually displaying the evaluation results in a graphical format.

Images