system

Abstract

We provide the system. [Solution] The information obtained from the user is used as an input method, Information gathering means that automatically collects relevant data from external information sources based on the information obtained from the input means, An evaluation means that compares external information collected by the information collection means with information from the user and evaluates the reliability of the information, A display means that presents to the user the reliability of the information evaluated by the evaluation means, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a problem that misinformation floods the Internet and its spread causes confusion in society. In particular, social media and articles on the Internet are easily spread, but there is a lack of means to quickly and accurately judge their reliability. As a result, there is a risk that individuals and the media may believe or spread false information. The present invention aims to solve the problem of the lack of reliability evaluation of such information and provide support for accurate information judgment.

Means for Solving the Problems

[0005] This invention provides a system for evaluating the reliability of information. Specifically, it includes an information gathering means that takes user-provided information as input and automatically collects related data from external sources. This information gathering means obtains related data using scraping technology. Furthermore, it includes an evaluation means that compares the acquired data with the user-provided information and evaluates its reliability using AI and machine learning technology. The evaluation results are provided by an efficient display means that is easy for the user to understand. In this way, this invention prevents the spread of misinformation and enables rapid checking of information reliability.

[0006] "User" refers to the entity that inputs information into the system and receives the results.

[0007] "Information" refers to data that users input into the system for the purpose of reliability evaluation, such as text, images, and videos.

[0008] "Input means" refers to a mechanism that provides an interface for receiving information from the user.

[0009] "Information gathering means" refers to the function of acquiring relevant data from external sources based on information obtained through input means.

[0010] "External information sources" refer to websites and databases on the internet that provide data necessary for reliability assessment.

[0011] "Automated scraping methods" refer to the process of automatically collecting information from the web using a program.

[0012] "Evaluation means" refers to a mechanism that uses data collected by information gathering means to evaluate the reliability of input information in numerical or other forms.

[0013] "Machine learning technology" refers to algorithms and methods that allow computers to learn patterns from data and use them for subsequent data evaluation.

[0014] "Display means" refers to an interface that presents the reliability evaluation results generated by the evaluation means to the user in an easily understandable manner. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

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

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

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

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

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

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

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0036] This invention is a system for quickly and accurately evaluating the reliability of information existing on the internet. This system receives information in various forms provided by users, automatically collects related data from external sources, and evaluates its reliability using machine learning techniques. The evaluation results are provided to the user through an intuitive interface.

[0037] First, the user accesses the system and inputs information they want to evaluate for reliability in the form of text, images, videos, etc. This information is sent to the system via the terminal. The terminal then constructs a request to send the input information to the server.

[0038] Next, based on the information received by the server, relevant data is automatically collected from external sources on the internet using scraping techniques. For example, relevant information is obtained from news sites, public databases, and fact-checking sites.

[0039] The collected external information is compared with the user-provided information by an evaluation tool on the server. Machine learning techniques are used to analyze the degree of agreement and inconsistencies between the information, and a reliability score is calculated. This score is an important indicator for evaluating the reliability of the information provided by the user.

[0040] Finally, the server formats the reliability score and related information calculated by the evaluation method and sends it back to the terminal as displayable data. The terminal presents this information to the user through a universal interface. The user can see the evaluation results at a glance and determine whether appropriate action or further investigation is needed based on the reliability level.

[0041] This configuration enables rapid verification of misinformation, supporting users in making reliable decisions. The system flexibly accepts various information formats, allowing for rapid data acquisition and accurate evaluation, thereby addressing the challenges of today's information society.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user opens an application or website and enters information they want to evaluate for reliability. The input format can be text, images, or videos, and the user places the information in an input form on the provided interface.

[0045] Step 2:

[0046] The terminal receives information entered by the user and constructs an HTTP request to send to the backend server. This request may include the content of the information and the user's identification information.

[0047] Step 3:

[0048] The server processes requests received from the terminal and performs scraping to collect relevant external information based on the input. The server accesses trusted news sites, databases, and fact-checking sites to retrieve the necessary data.

[0049] Step 4:

[0050] The information gathering mechanism on the server stores the data collected through scraping and passes it to the evaluation mechanism. This data is structured and converted into a format suitable for analysis.

[0051] Step 5:

[0052] The server evaluation method uses machine learning techniques to compare input user information with external information and perform reliability assessments. The evaluation includes the degree of information consistency, detection of inconsistencies, and calculation of a reliability score based on an AI model.

[0053] Step 6:

[0054] The server formats the evaluation results and generates response data to be sent to the terminal in a user-friendly format. This data includes a list of reliability scores and related information.

[0055] Step 7:

[0056] The terminal displays the evaluation results received from the server and presents them to the user. Based on these results, the user can judge the reliability of the information and refer to other sources of information as needed.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In today's information society, it is crucial to quickly and accurately assess the reliability of information circulating on the internet. However, it is difficult for users to judge the reliability of information in various forms on their own, potentially contributing to the spread of misinformation. Methods are needed to prevent the spread of such misinformation and enable users to make decisions based on accurate information.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes an input means for receiving information provided by a user, an information gathering means for automatically collecting relevant data from external information sources on the Internet based on the information received from the input means, an evaluation means for comparing the external information obtained by the information gathering means with the information provided by the user and evaluating the reliability of the information using a generating AI model, and a display means for providing the user with the evaluation results, including the reliability score obtained by the evaluation means. This enables the reliability of information to be determined quickly and accurately, prevents the spread of misinformation, and allows users to make decisions based on correct information.

[0062] An "input mechanism" is a system for receiving information provided by the user.

[0063] An "information gathering means" is a system that automatically collects relevant data from external information sources on the internet based on information received from an input means.

[0064] An "evaluation method" is a system that compares external information obtained through information gathering methods with information provided by users and evaluates the reliability of the information using a generative AI model.

[0065] A "display means" is a mechanism for providing users with evaluation results, including the reliability score obtained by the evaluation means.

[0066] A "generative AI model" refers to an algorithm or model that uses machine learning techniques to analyze information and evaluate its reliability.

[0067] "Data acquisition means" refers to technologies and methods used to acquire data from external information sources on the internet as part of information gathering means.

[0068] A "reliability score" is an indicator of the reliability of information, calculated using an evaluation method.

[0069] This invention provides a system for efficiently evaluating the reliability of information on the internet. Specifically, it takes the form of a system in which a user provides information as input, a server automatically collects related data from external sources, and evaluates it using a generated AI model.

[0070] First, the user can input information they want to evaluate the reliability of via their device. For example, they can provide information in the form of a news article's URL, its text, or images and videos. The device then creates a request to send this information to the server.

[0071] The server automatically collects data from relevant external sources on the internet using scraping techniques based on the input information. Specifically, it obtains information from news sites, public databases, and fact-checking sites. Common open-source scraping tools and dedicated APIs can be used for scraping techniques.

[0072] Subsequently, the server compares the collected external information with the input information and evaluates its reliability using a generative AI model. By utilizing machine learning techniques and natural language processing to analyze the degree of consistency and inconsistencies in the information, a reliability score is calculated. This evaluation process enables accurate analysis of the information and allows for highly accurate calculation of reliability.

[0073] The evaluation results are sent from the server to the terminal, which then presents them to the user via a universal interface. This interface is designed to visualize the reliability score in an intuitively understandable way, allowing users to quickly verify the reliability of the information.

[0074] (As a specific example) If a user wants to check the reliability of a health-related article they saw on social media, they enter the URL of the article into the system from their device. The system collects information from relevant public medical databases and reliable medical article websites, compares the content, and provides a reliability score. The user can then use this score to determine the veracity of the information in the article.

[0075] (Example of a prompt message)

[0076] "I want to verify the credibility of this article I found on social media: {article URL}. Please provide the credibility score and related information."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The user inputs information they want to evaluate the reliability of into the system. Specifically, they provide information in the form of text, images, videos, or URLs. The input data is collected on the user's device and formatted according to its content. The output is a request to be sent to the server.

[0080] Step 2:

[0081] The terminal receives information entered by the user and creates a request to send it to the server. During this process, the data format is standardized and processed into a format easily interpreted by the server. The input is user-provided information, and the output is data including the HTTP request to the server.

[0082] Step 3:

[0083] The server receives requests from the terminal and collects relevant data from external sources on the internet based on the information provided by the user. The technology used is web scraping, which retrieves information from news sites and public databases. The input is the information request from the terminal, and the output is the external information obtained through web scraping.

[0084] Step 4:

[0085] The server uses collected external information and a generative AI model to compare it with user-provided information. Machine learning techniques are used to analyze the degree of agreement and inconsistencies in the information, and a reliability score is calculated. The input consists of external information on the server and user information, and the output is the calculated reliability score and related evaluation results.

[0086] Step 5:

[0087] The server formats the obtained reliability score and related information and returns it to the terminal as data for display. It arranges the data in a way that is easy to visualize and processes it into a format suitable for display in the user interface. The input is evaluated reliability data, and the output is a data package formatted for display.

[0088] Step 6:

[0089] The terminal presents reliability scores and related information received from the server through an intuitive interface that the user can easily understand. The information is organized by category, and visual highlighting and graphics are used. The input is formatted data provided by the server, and the output is visual information presented to the user.

[0090] Step 7:

[0091] Based on the presented reliability score and detailed information, users judge the veracity of the information and decide on further investigation or action as needed. The input is the evaluation result presented by the device, and the output is the user's judgment and next action.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] Much of the information circulating on the internet is of questionable reliability. Therefore, it is difficult for users to select reliable information. Furthermore, a system is needed to verify the reliability of information before it is disseminated. This is necessary to prevent the spread of misinformation and support users in making more appropriate judgments.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes a device for inputting information obtained from a user, an information collection device for automatically collecting relevant data from external information sources based on the information obtained from the input device, and an evaluation device for comparing the external information collected by the information collection device with the information from the user and evaluating the reliability of the information. This makes it possible for users to evaluate the reliability of the content they intend to post in advance and check the reliability score.

[0097] "User" refers to an individual or organization that inputs or verifies information.

[0098] "Device" refers to an instrument or system designed to perform a specific function.

[0099] An "information gathering device" refers to a device that has the function of automatically acquiring relevant data from external information sources.

[0100] An "evaluation device" refers to a device used to compare collected information and evaluate its reliability.

[0101] A "reliability score" is an index that numerically represents the reliability of information and is used by users to judge the accuracy of that information.

[0102] "External information sources" refer to information providers that are the target of information collection, such as publicly available databases and news sites on the internet.

[0103] The system of the present invention consists of multiple elements, including a user, a terminal, and a server. The user inputs content to be posted (e.g., text, images, videos, etc.) into the terminal via an input means. The terminal is responsible for transmitting this information to the server.

[0104] The server has information gathering devices, evaluation devices, and display devices, which are used to evaluate the reliability of the information. The information gathering device uses scraping technology to automatically acquire relevant data from external information sources on the internet. Specifically, for scraping, "BeautifulSoup" is used, and for data analysis, machine learning libraries such as "TENSORFLOW®" and "PyTorch" are used.

[0105] The evaluation device analyzes the collected data, uses a generative AI model to assess the consistency and inconsistencies of the information, and calculates a reliability score. This reliability score is an indicator of how trustworthy the information is and is used by users to make decisions about disclosing the information.

[0106] The server passes the evaluation results to a display device and sends them back to the user's terminal. The terminal presents the received reliability score and related information to the user through an intuitive interface. This allows the user to verify the reliability of the information in advance and publish content with confidence.

[0107] As a concrete example, when a user posts an article about a social issue, the server evaluates the reliability of the article and checks whether it has been cross-referenced with information from major news outlets and public databases. An example of a prompt message would be: "Please evaluate the reliability of the following news article. Article title: ''. Content: ''. What related information can be collected, and how is the reliability score calculated based on that information?"

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The terminal receives text, image, or video data entered by the user. The input data is processed into a format that is then constructed as a request to be sent to the server. This enables efficient data communication in the next step.

[0111] Step 2:

[0112] The server receives input data sent from the terminal. Based on the received data, the information gathering device prepares to automatically collect relevant data from external sources. At this stage, an appropriate scraping strategy is selected depending on the type of input information.

[0113] Step 3:

[0114] The information gathering device accesses external information sources on the internet and collects relevant information through available APIs or by utilizing scraping techniques. The collected data is stored on the server as primary data for reliability evaluation.

[0115] Step 4:

[0116] The evaluation system performs analysis using collected external data and original information provided by the user. It utilizes generative AI models and machine learning libraries to analyze the degree of consistency and inconsistencies in the information. The inputs are user information and external information, and the output is a reliability score.

[0117] Step 5:

[0118] The server formats the reliability score and related information obtained as a result of the evaluation, converting it into a user-friendly format. This allows the information to be presented on a visually intuitive user interface.

[0119] Step 6:

[0120] The terminal displays the reliability score and related information received from the server to the user using a display device. Based on the displayed data, the user checks the reliability of the content they intend to post and makes a decision on whether to publish the information as appropriate.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention relates to a system for evaluating the reliability of information on the Internet, which also takes into account the user's emotions. This system incorporates an emotion engine that recognizes the emotions expressed and selected by the user when they input information. This prevents the reliability evaluation from being excessively influenced by the user's emotional bias.

[0123] First, the user enters the information they want to evaluate for reliability via an application or website. The entered information is then sent from the device to the server. Next, the server automatically collects relevant data from external sources using information gathering tools. It obtains data from other news sites, databases, and fact-checking services to complete the information gathering process.

[0124] A further feature of this system is its emotion engine, which analyzes user emotions. It identifies the user's emotions from the input information through text and voice analysis, and incorporates the results into the reliability evaluation. This analysis allows for the assessment of how emotions might influence reliability judgments, for example, if the user is in a highly angered state.

[0125] The evaluation method utilizes machine learning techniques to scrutinize the degree of agreement and inconsistencies between user information and external data. Furthermore, it integrates the obtained sentiment data into the evaluation, allowing for correction of emotionally over-influenced ratings.

[0126] Ultimately, the server generates the reliability evaluation results and displays them to the user via the terminal. The display method presents the results in a way that suits the user's emotional state, supporting calmer and less biased decision-making. For example, users exhibiting positive emotions are shown results with a neutral color scheme, while users exhibiting negative emotions are visually highlighted with cautionary colors.

[0127] This allows users to receive accurate reliability assessments that go beyond simple information evaluation, taking emotional influences into account. By providing reliability judgments that combine emotion and information, this system is a valuable technology in today's complex information environment.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] Users enter the information they want to evaluate via an application or website. The input can be text, images, or audio, and users place it in a designated form.

[0131] Step 2:

[0132] The terminal receives user input information and constructs an HTTP request to send it to the server. The request includes the content of the information and the user's identification information.

[0133] Step 3:

[0134] The server receives a request and uses information gathering tools to collect relevant data from external sources through scraping. This is the process of obtaining data from trusted news sites and public databases.

[0135] Step 4:

[0136] The server uses an emotion engine to recognize emotions from the information entered by the user. It uses text and voice sentiment analysis techniques to identify the emotional state the user is experiencing.

[0137] Step 5:

[0138] The server uses evaluation tools to compare user information with external information. During this process, machine learning models are used to analyze the degree of agreement and inconsistencies, and a reliability score is calculated by taking into account perceived emotions. Emotional bias is corrected by the system.

[0139] Step 6:

[0140] The server formats the evaluation results and generates response data to send back to the terminal. This data includes a reliability score, an assessment of significant sentiment, and related information.

[0141] Step 7:

[0142] The terminal displays the evaluation results received from the server and presents them to the user. The display uses appropriate formats and colors that take into account the influence of emotions, allowing the user to verify the reliability of the information from a more balanced perspective.

[0143] (Example 2)

[0144] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0145] In today's information environment, evaluating the reliability of information on the internet is extremely important. However, conventional systems fail to take into account the emotional biases of users, and as a result, reliability evaluations can be excessively influenced by emotions. This leads to the problem that the evaluation results provided are not always objective or accurate.

[0146] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0147] In this invention, the server includes means for analyzing the user's emotions and performing a reliability evaluation that takes emotional bias into account, means for automatically collecting relevant data from external sources, and means for comparing user information with external information and evaluating reliability. This makes it possible to perform a more accurate and objective reliability evaluation while taking into account the user's emotional state.

[0148] A "user" is an individual or group that uses the system to evaluate the reliability of information.

[0149] An "input means" is a device or interface used by a user to provide information they wish to evaluate to the system.

[0150] "Information gathering means" refers to a function or process that automatically acquires relevant data from external sources based on the input information.

[0151] "Evaluation means" refers to a device or program for comparing and analyzing collected external information with information from users to evaluate the reliability of the information.

[0152] "Emotion analysis means" refers to a technology or module for identifying emotional states from user input information and analyzing the impact of those emotions on trust assessment.

[0153] "Display means" refers to an interface or device that presents the reliability of the information derived by the evaluation means to the user in an easily understandable manner.

[0154] This invention aims to incorporate user emotions into a system for evaluating the reliability of information. This reduces emotional bias and provides a more accurate and objective reliability assessment.

[0155] Users first input the information they want to evaluate for reliability via a dedicated application or website. The device used is designed to transmit the information to a server over a network. Common web browsers and mobile applications are used on these devices.

[0156] The server automatically collects relevant external data based on the input information. This process utilizes news sites, databases, and fact-checking services on the internet. The collected data is used to build the information base necessary for reliability assessment. The server incorporates a high-performance data collection engine and a database management system.

[0157] Next, the server uses an emotion engine to analyze the user's emotions. By performing text and voice analysis, it identifies the emotional state from the information the user has entered. This emotion data plays a crucial role in reliability evaluation. Natural language processing and voice analysis technologies are employed for the analysis.

[0158] In the evaluation process, the server utilizes machine learning algorithms to closely compare collected external information with user input. This identifies points of agreement and disagreement in the information, and further corrects for the influence of emotions to perform an accurate reliability assessment.

[0159] Ultimately, the server presents the evaluation results to the user. During this process, customization is applied based on the user's emotional state; for example, the interface becomes neutral for users exhibiting positive emotions. This allows users to make calm and rational decisions.

[0160] An example of a prompt is, "Evaluate the reliability of this information. Generate a reliability score, taking into account the content of the information, relevant external data, and the user's emotional state." Using this prompt, the generative AI model can assist in the evaluation process.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The user inputs information they want to evaluate for reliability using their device. Specifically, they copy and paste the URL of a news article into a dedicated input field. The input information is then sent from the device to the server via the internet. The input is the information to be evaluated provided by the user, and the output is digital information sent from the device to the server.

[0164] Step 2:

[0165] The server automatically collects relevant data from external sources using information gathering tools. Specifically, the server accesses news APIs and databases to retrieve the corresponding information. In this step, user-provided information is passed as input, and supplemented external data is generated as output.

[0166] Step 3:

[0167] The server uses an emotion engine to analyze the user's emotions. The server performs text analysis on the input information using natural language processing techniques to determine the user's emotional state. The input is the user's text information, and the output is data indicating the user's emotional state.

[0168] Step 4:

[0169] The server uses evaluation tools to compare collected external information with user information and perform a reliability assessment. The server applies machine learning algorithms to identify similarities and inconsistencies and calculates a reliability score. The input is the collected external data and user input data, and the output is the evaluation result, including the reliability score.

[0170] Step 5:

[0171] The server transmits and displays the reliability evaluation results to the terminal in a format that reflects the user's emotional state. The server adjusts the color scheme and messages to accommodate the user's emotions when displaying the results. The input consists of the reliability evaluation results and the user's emotional state, while the output is customized display information.

[0172] (Application Example 2)

[0173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0174] In modern content distribution services, user reviews have a significant impact on content selection. Therefore, ensuring the reliability of reviews and mitigating excessive emotional bias is crucial. However, traditional systems often fail to consider user emotions and lack sufficient means to ensure the objectivity of review content, making it difficult to provide reliable information.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0176] In this invention, the server includes an input means for information obtained from the user, an information gathering means for automatically collecting relevant data from external information sources, and an evaluation means for evaluating reliability based on the collected information and sentiment. This enables accurate content evaluation that takes sentiment into account.

[0177] "User" refers to a person who operates the system and inputs information.

[0178] An "input means" is a device or interface for taking information from a user into a system.

[0179] "Information gathering means" refers to processes or mechanisms for automatically acquiring relevant data from external information sources.

[0180] "Evaluation methods" refer to functions and mechanisms for comparing user information with external information and analyzing its reliability.

[0181] "Emotion analysis means" refers to a function that identifies emotions from information entered by the user and reflects that in the reliability evaluation.

[0182] "Display means" refers to a device or interface for showing the reliability of evaluated information in a format appropriate to the user's emotional state.

[0183] "Learning model technology" is a technique that uses machine learning to analyze the degree of consistency and inconsistencies in information and determine its reliability.

[0184] "Collection method" refers to the mechanism or method for automatically collecting data from information sources.

[0185] The system that realizes this invention consists of an internet-connected server and a terminal used by the user. The server provides an interface for inputting information obtained from the user. This interface is typically implemented as an application that runs on a smartphone or computer, and enables text input and voice input.

[0186] When a user submits a review or rating, the server receives that information. The input information is then analyzed using a natural language processing engine to scan the user's sentiment from the text data. Python libraries such as NLTK and SpaCy are often used for this analysis.

[0187] The server then accesses external information sources and retrieves relevant data through collection methods. Generally, this process utilizes scraping techniques, where automated programs gather relevant information from news and review sites on the internet. The collected data is managed on a database built using learning model techniques and prepared for comparison.

[0188] To evaluate the consistency and inconsistencies of the data, the server utilizes evaluation tools based on machine learning libraries such as TensorFlow and PyTorch. During this process, user sentiment data is also incorporated into the evaluation, allowing for a multifaceted analysis of the review's reliability. The evaluation results are ultimately displayed on the device through a visual interface tailored to the user's emotional state. The interface features an adapted design and color scheme to enable users to make calm and rational judgments.

[0189] As a concrete example, suppose a user writes a review of a movie. Suppose the review includes the phrase, "It was very moving, but it's easy to get carried away by emotions." The system receives this input, detects the emotional state of "being moved" through text analysis, and evaluates its reliability while considering its influence.

[0190] An example of a prompt would be, "As a review of the movie XYZ, please assess the emotions contained in the text and calculate the degree to which they influence the rating." Through this prompt, the user's subjective opinion will be appropriately reflected in the rating system.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The device provides an interface for users to enter reviews and ratings. When users input information via text or voice, it is captured by the device. The entered information is then sent to the server as text data.

[0194] Step 2:

[0195] The server sends the received text data to a natural language processing engine for analysis. During this process, the server extracts sentiment from the input information. The text analysis is performed using Python libraries such as NLTK and SpaCy. The input is user reviews, and the output is sentiment information.

[0196] Step 3:

[0197] Based on the sentiment analysis results, the server initiates access to external information sources. The data to be evaluated is automatically scraped from internet news sites and review sites using various collection methods. The input is analyzed sentiment data, and the output is external information data.

[0198] Step 4:

[0199] The server uses learning model techniques to perform reliability assessments by comparing collected external information with user input data. It analyzes data consistency and inconsistencies using TensorFlow or PyTorch. In this step, sentiment data and external information are used as input, and the output is the evaluation result.

[0200] Step 5:

[0201] The server prepares to display the results in a format adapted to the user's emotional state, based on the evaluation results. It generates an interface design tailored to the user's emotions and sends it to the terminal. In this case, the input is the evaluation results, and the output is the adaptive interface.

[0202] Step 6:

[0203] The terminal displays the evaluation results to the user using an interface received from the server. Appropriate colors and designs are used to allow the user to make a calm and rational judgment. The final output is the evaluation results that the user sees on the screen. In this step, the role of the terminal is to display the evaluation results.

[0204] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0205] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0206] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0210] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0211] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0212] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0214] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0215] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0216] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0217] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0218] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0219] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0220] This invention is a system for quickly and accurately evaluating the reliability of information existing on the internet. This system receives information in various forms provided by users, automatically collects related data from external sources, and evaluates its reliability using machine learning techniques. The evaluation results are provided to the user through an intuitive interface.

[0221] First, the user accesses the system and inputs information they want to evaluate the reliability of, in the form of text, images, videos, etc. This information is sent to the system via the terminal. The terminal then constructs a request to send the input information to the server.

[0222] Next, based on the information received by the server, relevant data is automatically collected from external sources on the internet using scraping techniques. For example, relevant information is obtained from news sites, public databases, and fact-checking sites.

[0223] The collected external information is compared with the user-provided information by an evaluation tool on the server. Machine learning techniques are used to analyze the degree of agreement and inconsistencies between the information, and a reliability score is calculated. This score is an important indicator for evaluating the reliability of the information provided by the user.

[0224] Finally, the server formats the reliability score and related information calculated by the evaluation method and sends it back to the terminal as displayable data. The terminal presents this information to the user through a universal interface. The user can see the evaluation results at a glance and determine whether appropriate action or further investigation is needed based on the reliability level.

[0225] This configuration enables rapid verification of misinformation, supporting users in making reliable decisions. The system flexibly accepts various information formats, allowing for rapid data acquisition and accurate evaluation, thereby addressing the challenges of today's information society.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The user opens an application or website and enters information they want to evaluate for reliability. The input format can be text, images, or videos, and the user places the information in an input form on the provided interface.

[0229] Step 2:

[0230] The terminal receives information entered by the user and constructs an HTTP request to send to the backend server. This request may include the content of the information and the user's identification information.

[0231] Step 3:

[0232] The server processes requests received from the terminal and performs scraping to collect relevant external information based on the input. The server accesses trusted news sites, databases, and fact-checking sites to retrieve the necessary data.

[0233] Step 4:

[0234] The information gathering mechanism on the server stores the data collected through scraping and passes it to the evaluation mechanism. This data is structured and converted into a format suitable for analysis.

[0235] Step 5:

[0236] The server evaluation method uses machine learning techniques to compare input user information with external information and perform reliability assessments. The evaluation includes the degree of information consistency, detection of inconsistencies, and calculation of a reliability score based on an AI model.

[0237] Step 6:

[0238] The server formats the evaluation results and generates response data to be sent to the terminal in a user-friendly format. This data includes a list of reliability scores and related information.

[0239] Step 7:

[0240] The terminal displays the evaluation results received from the server and presents them to the user. Based on these results, the user can judge the reliability of the information and refer to other sources of information as needed.

[0241] (Example 1)

[0242] Next, we will describe Example 1. 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."

[0243] In today's information society, it is crucial to quickly and accurately assess the reliability of information circulating on the internet. However, it is difficult for users to judge the reliability of information in various forms on their own, potentially contributing to the spread of misinformation. Methods are needed to prevent the spread of such misinformation and enable users to make decisions based on accurate information.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes an input means for receiving information provided by a user, an information gathering means for automatically collecting relevant data from external information sources on the Internet based on the information received from the input means, an evaluation means for comparing the external information obtained by the information gathering means with the information provided by the user and evaluating the reliability of the information using a generating AI model, and a display means for providing the user with the evaluation results, including the reliability score obtained by the evaluation means. This enables the reliability of information to be determined quickly and accurately, prevents the spread of misinformation, and allows users to make decisions based on correct information.

[0246] An "input mechanism" is a system for receiving information provided by the user.

[0247] An "information gathering means" is a system that automatically collects relevant data from external information sources on the internet based on information received from an input means.

[0248] An "evaluation method" is a system that compares external information obtained through information gathering methods with information provided by users and evaluates the reliability of the information using a generative AI model.

[0249] A "display means" is a mechanism for providing users with evaluation results, including the reliability score obtained by the evaluation means.

[0250] A "generative AI model" refers to an algorithm or model that uses machine learning techniques to analyze information and evaluate its reliability.

[0251] "Data acquisition means" refers to technologies and methods used to acquire data from external information sources on the internet as part of information gathering means.

[0252] A "reliability score" is an indicator of the reliability of information, calculated using an evaluation method.

[0253] This invention provides a system for efficiently evaluating the reliability of information on the Internet. Specifically, it takes the form of a system in which a user provides information as input, a server automatically collects related data from external sources, and evaluates it using a generated AI model.

[0254] First, the user can input information they want to evaluate the reliability of via their device. For example, they can provide information in the form of a news article's URL, its text, or images and videos. The device then creates a request to send this information to the server.

[0255] The server automatically collects data from relevant external sources on the internet using scraping techniques based on the input information. Specifically, it obtains information from news sites, public databases, and fact-checking sites. Common open-source scraping tools and dedicated APIs can be used for scraping techniques.

[0256] Subsequently, the server compares the collected external information with the input information and evaluates its reliability using a generative AI model. By utilizing machine learning techniques and natural language processing to analyze the degree of consistency and inconsistencies in the information, a reliability score is calculated. This evaluation process enables accurate analysis of the information and allows for highly accurate calculation of reliability.

[0257] The evaluation results are sent from the server to the terminal, which then presents them to the user via a universal interface. This interface is designed to visualize the reliability score in an intuitively understandable way, allowing users to quickly verify the reliability of the information.

[0258] (As a specific example) If a user wants to check the reliability of a health-related article they saw on social media, they enter the URL of the article into the system from their device. The system collects information from relevant public medical databases and trusted medical article websites, compares the content, and provides a reliability score. The user can then use this score to determine the veracity of the information in the article.

[0259] (Example of a prompt message)

[0260] "I want to verify the credibility of this article I found on social media: {article URL}. Please provide the credibility score and related information."

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] The user inputs information they want to evaluate the reliability of into the system. Specifically, they provide information in the form of text, images, videos, or URLs. The input data is collected on the user's device and formatted according to its content. The output is a request to be sent to the server.

[0264] Step 2:

[0265] The terminal receives information entered by the user and creates a request to send it to the server. During this process, the data format is standardized and processed into a format easily interpreted by the server. The input is user-provided information, and the output is data including the HTTP request to the server.

[0266] Step 3:

[0267] The server receives requests from the terminal and collects relevant data from external sources on the internet based on the information provided by the user. The technology used is web scraping, which retrieves information from news sites and public databases. The input is the information request from the terminal, and the output is the external information obtained through web scraping.

[0268] Step 4:

[0269] The server uses collected external information and a generative AI model to compare it with user-provided information. Machine learning techniques are used to analyze the degree of agreement and inconsistencies in the information, and a reliability score is calculated. The input consists of external information on the server and user information, and the output is the calculated reliability score and related evaluation results.

[0270] Step 5:

[0271] The server formats the obtained reliability score and related information and returns it to the terminal as data for display. It arranges the data in a way that is easy to visualize and processes it into a format suitable for display on the user interface. The input is evaluated reliability data, and the output is a data package formatted for display.

[0272] Step 6:

[0273] The terminal presents reliability scores and related information received from the server through an intuitive interface that the user can easily understand. The information is organized by category, and visual highlighting and graphics are used. The input is formatted data provided by the server, and the output is visual information presented to the user.

[0274] Step 7:

[0275] Based on the presented reliability score and detailed information, users judge the veracity of the information and decide on further investigation or action as needed. The input is the evaluation result presented by the device, and the output is the user's judgment and next action.

[0276] (Application Example 1)

[0277] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] Much of the information circulating on the internet is of questionable reliability. Therefore, it is difficult for users to select reliable information. Furthermore, a system is needed to verify the reliability of information before it is disseminated. This is necessary to prevent the spread of misinformation and support users in making more appropriate judgments.

[0279] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0280] In this invention, the server includes a device for inputting information obtained from a user, an information collection device for automatically collecting relevant data from external information sources based on the information obtained from the input device, and an evaluation device for comparing the external information collected by the information collection device with the information from the user and evaluating the reliability of the information. This makes it possible for users to evaluate the reliability of the content they intend to post in advance and check the reliability score.

[0281] "User" refers to an individual or organization that inputs or checks information.

[0282] "Device" refers to a device or system designed to perform a specific function.

[0283] "Information collection device" refers to a device that has the function of automatically acquiring relevant data from external information sources.

[0284] "Evaluation device" refers to a device for comparing the collected information and evaluating its reliability.

[0285] "Reliability score" is an indicator that numerically represents the reliability of information and is used by users to judge the accuracy of information.

[0286] "External information source" refers to an information provider that is the target of information collection, such as a publicly available database or news site existing on the Internet.

[0287] The system of the present invention is composed of a plurality of elements including a user, a terminal, and a server. The user inputs content (such as text, image, video, etc.) to be posted through an input means into the terminal. The terminal plays the role of transmitting this information to the server.

[0288] The server has an information collection device, an evaluation device, and a display device, and uses these to evaluate the reliability of information. The information collection device uses scraping technology to automatically acquire relevant data from external information sources on the Internet. As specific technologies used, "BeautifulSoup" etc. are used for scraping, and machine learning libraries such as "TensorFlow" and "PyTorch" are used for data analysis.

[0289] The evaluation device analyzes the collected data, uses a generative AI model to assess the consistency and inconsistencies of the information, and calculates a reliability score. This reliability score is an indicator of how trustworthy the information is and is used by users to make decisions about disclosing the information.

[0290] The server passes the evaluation results to a display device and sends them back to the user's terminal. The terminal presents the received reliability score and related information to the user through an intuitive interface. This allows the user to verify the reliability of the information in advance and publish content with confidence.

[0291] As a concrete example, when a user posts an article about a social issue, the server evaluates the reliability of the article and checks whether it has been cross-referenced with information from major news outlets and public databases. An example of a prompt message would be: "Please evaluate the reliability of the following news article. Article title: ''. Content: ''. What related information can be collected, and how is the reliability score calculated based on that information?"

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The terminal receives text, image, or video data entered by the user. The input data is processed into a format that is then constructed as a request to be sent to the server. This enables efficient data communication in the next step.

[0295] Step 2:

[0296] The server receives input data sent from the terminal. Based on the received data, the information gathering device prepares to automatically collect relevant data from external sources. At this stage, an appropriate scraping strategy is selected depending on the type of input information.

[0297] Step 3:

[0298] The information gathering device accesses external information sources on the internet and collects relevant information through available APIs or by utilizing scraping techniques. The collected data is stored on the server as primary data for reliability evaluation.

[0299] Step 4:

[0300] The evaluation system performs analysis using collected external data and original information provided by the user. It utilizes generative AI models and machine learning libraries to analyze the degree of consistency and inconsistencies in the information. The inputs are user information and external information, and the output is a reliability score.

[0301] Step 5:

[0302] The server formats the reliability score and related information obtained as a result of the evaluation, converting it into a user-friendly format. This allows the information to be presented on a visually intuitive user interface.

[0303] Step 6:

[0304] The terminal displays the reliability score and related information received from the server to the user using a display device. Based on the displayed data, the user checks the reliability of the content they intend to post and makes a decision on whether to publish the information as appropriate.

[0305] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0306] The present invention performs reliability evaluation considering the emotions of users in a system for evaluating the reliability of information on the Internet. This system combines an emotion engine that recognizes the emotions manifested in the expression and selection when a user inputs information. Thereby, it is possible to avoid the reliability evaluation being overly influenced by the emotional bias of the user.

[0307] First, the user inputs the information for which reliability is to be evaluated via an application or a website. The input information is transmitted by the terminal to the server. Next, the server automatically collects relevant data from external information sources using information collection means. It obtains data from other news sites, databases, fact-checking services, and completes the information collection process.

[0308] As a further feature, this system has an emotion engine that analyzes the emotions of the user. The emotions of the user are identified from the input information by text analysis or voice analysis, and the results are incorporated into the reliability evaluation. Through this analysis, for example, when the user is in a very angry state, it is possible to evaluate the possibility of the emotion affecting the reliability judgment.

[0309] The evaluation means utilizes machine learning techniques to scrutinize the degree of consistency and contradictions between the information from the user and the external data. Also, it is possible to integrate the obtained emotion data into the evaluation and correct the evaluation that is overly influenced emotionally.

[0310] Finally, the server constructs the reliability evaluation result and displays it to the user via the terminal. The display means presents the result in a form corresponding to the emotional state of the user, supporting a more calm and less biased judgment. For example, for users showing positive emotions, the result is displayed with an interface of a neutral color tone, and for users showing negative emotions, it is visually emphasized with a color tone that prompts caution.

[0311] This allows users to receive accurate reliability assessments that go beyond simple information evaluation, taking emotional influences into account. By providing reliability judgments that combine emotion and information, this system is a valuable technology in today's complex information environment.

[0312] The following describes the processing flow.

[0313] Step 1:

[0314] Users enter the information they want to evaluate via an application or website. The input can be text, images, or audio, and users place it in a designated form.

[0315] Step 2:

[0316] The terminal receives user input information and constructs an HTTP request to send it to the server. The request includes the content of the information and the user's identification information.

[0317] Step 3:

[0318] The server receives a request and uses information gathering tools to collect relevant data from external sources through scraping. This is the process of obtaining data from trusted news sites and public databases.

[0319] Step 4:

[0320] The server uses an emotion engine to recognize emotions from the information entered by the user. It uses text and voice sentiment analysis techniques to identify the emotional state the user is experiencing.

[0321] Step 5:

[0322] The server uses evaluation tools to compare user information with external information. During this process, machine learning models are used to analyze the degree of agreement and inconsistencies, and a reliability score is calculated, taking into account perceived emotions. Emotional bias is corrected by the system.

[0323] Step 6:

[0324] The server formats the evaluation results and generates response data to send back to the terminal. This data includes a reliability score, an assessment of significant sentiment, and related information.

[0325] Step 7:

[0326] The terminal displays the evaluation results received from the server and presents them to the user. The display uses appropriate formats and colors that take into account the influence of emotions, allowing the user to verify the reliability of the information from a more balanced perspective.

[0327] (Example 2)

[0328] Next, we will describe Example 2. 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".

[0329] In today's information environment, evaluating the reliability of information on the internet is extremely important. However, conventional systems fail to take into account the emotional biases of users, and as a result, reliability evaluations can be excessively influenced by emotions. This leads to the problem that the evaluation results provided are not always objective or accurate.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes means for analyzing the user's emotions and performing a reliability evaluation that takes emotional bias into account, means for automatically collecting relevant data from external sources, and means for comparing user information with external information and evaluating reliability. This makes it possible to perform a more accurate and objective reliability evaluation while taking into account the user's emotional state.

[0332] A "user" is an individual or group that uses the system to evaluate the reliability of information.

[0333] An "input means" is a device or interface used by a user to provide information they wish to evaluate to the system.

[0334] "Information gathering means" refers to a function or process that automatically acquires relevant data from external sources based on the input information.

[0335] "Evaluation means" refers to a device or program for comparing and analyzing collected external information with information from users to evaluate the reliability of the information.

[0336] "Emotion analysis means" refers to a technology or module for identifying emotional states from user input information and analyzing the impact of those emotions on trust assessment.

[0337] "Display means" refers to an interface or device that presents the reliability of the information derived by the evaluation means to the user in an easily understandable manner.

[0338] This invention aims to incorporate user emotions into a system for evaluating the reliability of information. This reduces emotional bias and provides a more accurate and objective reliability assessment.

[0339] Users first input the information they want to evaluate for reliability via a dedicated application or website. The device used is designed to transmit the information to a server over a network. Common web browsers and mobile applications are used on these devices.

[0340] The server automatically collects relevant external data based on the input information. This process utilizes news sites, databases, and fact-checking services on the internet. The collected data is used to build the information base necessary for reliability assessment. The server incorporates a high-performance data collection engine and a database management system.

[0341] Next, the server uses an emotion engine to analyze the user's emotions. By performing text and voice analysis, it identifies the emotional state from the information the user has entered. This emotion data plays a crucial role in reliability evaluation. Natural language processing and voice analysis technologies are employed for the analysis.

[0342] In the evaluation process, the server utilizes machine learning algorithms to closely compare collected external information with user input. This identifies points of agreement and disagreement in the information, and further corrects for the influence of emotions to perform an accurate reliability assessment.

[0343] Ultimately, the server presents the evaluation results to the user. During this process, customization is applied based on the user's emotional state; for example, the interface becomes neutral for users exhibiting positive emotions. This allows users to make calm and rational decisions.

[0344] An example of a prompt is, "Evaluate the reliability of this information. Generate a reliability score, taking into account the content of the information, relevant external data, and the user's emotional state." Using this prompt, the generative AI model can assist in the evaluation process.

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The user inputs information they want to evaluate for reliability using their device. Specifically, they copy and paste the URL of a news article into a dedicated input field. The input information is then sent from the device to the server via the internet. The input is the information to be evaluated provided by the user, and the output is digital information sent from the device to the server.

[0348] Step 2:

[0349] The server automatically collects relevant data from external sources using information gathering tools. Specifically, the server accesses news APIs and databases to retrieve the corresponding information. In this step, user-provided information is passed as input, and supplemented external data is generated as output.

[0350] Step 3:

[0351] The server uses an emotion engine to analyze the user's emotions. The server performs text analysis on the input information using natural language processing techniques to determine the user's emotional state. The input is the user's text information, and the output is data indicating the user's emotional state.

[0352] Step 4:

[0353] The server uses evaluation tools to compare collected external information with user information and perform a reliability assessment. The server applies machine learning algorithms to identify similarities and inconsistencies and calculates a reliability score. The input is the collected external data and user input data, and the output is the evaluation result, including the reliability score.

[0354] Step 5:

[0355] The server transmits and displays the reliability evaluation results to the terminal in a format that reflects the user's emotional state. The server adjusts the color scheme and messages to accommodate the user's emotions when displaying the results. The input consists of the reliability evaluation results and the user's emotional state, while the output is customized display information.

[0356] (Application Example 2)

[0357] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0358] In modern content distribution services, user reviews have a significant impact on content selection. Therefore, ensuring the reliability of reviews and mitigating excessive emotional bias is crucial. However, traditional systems often fail to consider user emotions and lack sufficient means to ensure the objectivity of review content, making it difficult to provide reliable information.

[0359] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0360] In this invention, the server includes an input means for information obtained from users, an information gathering means for automatically collecting relevant data from external information sources, and an evaluation means for evaluating reliability based on the collected information and sentiment. This enables accurate content evaluation that takes sentiment into account.

[0361] "User" refers to a person who operates the system and inputs information.

[0362] An "input means" is a device or interface for taking information from a user into a system.

[0363] "Information gathering means" refers to processes or mechanisms for automatically acquiring relevant data from external information sources.

[0364] "Evaluation methods" refer to functions and mechanisms for comparing user information with external information and analyzing its reliability.

[0365] "Emotion analysis means" refers to a function that identifies emotions from information entered by the user and reflects that in the reliability evaluation.

[0366] "Display means" refers to a device or interface for showing the reliability of evaluated information in a format appropriate to the user's emotional state.

[0367] "Learning model technology" is a technique that uses machine learning to analyze the degree of consistency and inconsistencies in information and determine its reliability.

[0368] "Collection method" refers to the mechanism or method for automatically collecting data from information sources.

[0369] The system that realizes this invention consists of an internet-connected server and a terminal used by the user. The server provides an interface for inputting information obtained from the user. This interface is typically implemented as an application that runs on a smartphone or computer, and enables text input and voice input.

[0370] When a user submits a review or rating, the server receives that information. The server then uses a natural language processing engine to analyze the content and scan the user's sentiment from the text data. This analysis often utilizes Python libraries such as NLTK or SpaCy.

[0371] The server then accesses external information sources and retrieves relevant data through collection methods. Generally, this process utilizes scraping techniques, where automated programs gather relevant information from news and review sites on the internet. The collected data is managed on a database built using learning model techniques and prepared for comparison.

[0372] To evaluate the consistency and inconsistencies of the data, the server utilizes evaluation tools based on machine learning libraries such as TensorFlow and PyTorch. During this process, user sentiment data is also incorporated into the evaluation, allowing for a multifaceted analysis of the review's reliability. The evaluation results are ultimately displayed on the device through a visual interface tailored to the user's emotional state. The interface features an adapted design and color scheme to enable users to make calm and rational judgments.

[0373] As a concrete example, suppose a user writes a review of a movie. Suppose the review includes the phrase, "It was very moving, but it's easy to get carried away by emotions." The system receives this input, detects the emotional state of "being moved" through text analysis, and evaluates its reliability while considering its influence.

[0374] An example of a prompt would be, "As a review of the movie XYZ, please assess the emotions contained in the text and calculate the degree to which they influence the rating." Through this prompt, the user's subjective opinion will be appropriately reflected in the rating system.

[0375] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0376] Step 1:

[0377] The device provides an interface for users to enter reviews and ratings. When users input information via text or voice, it is captured by the device. The entered information is then sent to the server as text data.

[0378] Step 2:

[0379] The server sends the received text data to a natural language processing engine for analysis. During this process, the server extracts sentiment from the input information. The text analysis is performed using Python libraries such as NLTK and SpaCy. The input is user reviews, and the output is sentiment information.

[0380] Step 3:

[0381] Based on the sentiment analysis results, the server initiates access to external information sources. The data to be evaluated is automatically scraped from internet news sites and review sites using various collection methods. The input is analyzed sentiment data, and the output is external information data.

[0382] Step 4:

[0383] The server uses learning model techniques to perform reliability assessments by comparing collected external information with user input data. It analyzes data consistency and inconsistencies using TensorFlow or PyTorch. In this step, sentiment data and external information are used as input, and the output is the evaluation result.

[0384] Step 5:

[0385] The server prepares to display the results in a format adapted to the user's emotional state, based on the evaluation results. It generates an interface design tailored to the user's emotions and sends it to the terminal. In this case, the input is the evaluation results, and the output is the adaptive interface.

[0386] Step 6:

[0387] The terminal displays the evaluation results to the user using an interface received from the server. Appropriate colors and designs are used to allow the user to make a calm and rational judgment. The final output is the evaluation results that the user sees on the screen. In this step, the role of the terminal is to display the evaluation results.

[0388] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0389] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0390] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0391] [Third Embodiment]

[0392] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0393] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0394] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0395] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0396] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0397] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0398] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0399] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0400] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0401] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0402] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0403] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0404] This invention is a system for quickly and accurately evaluating the reliability of information existing on the internet. This system receives information in various forms provided by users, automatically collects related data from external sources, and evaluates its reliability using machine learning techniques. The evaluation results are provided to the user through an intuitive interface.

[0405] First, the user accesses the system and inputs information they want to evaluate the reliability of, in the form of text, images, videos, etc. This information is sent to the system via the terminal. The terminal then constructs a request to send the input information to the server.

[0406] Next, based on the information received by the server, relevant data is automatically collected from external sources on the internet using scraping techniques. For example, relevant information is obtained from news sites, public databases, and fact-checking sites.

[0407] The collected external information is compared with the user-provided information by an evaluation tool on the server. Machine learning techniques are used to analyze the degree of agreement and inconsistencies between the information, and a reliability score is calculated. This score is an important indicator for evaluating the reliability of the information provided by the user.

[0408] Finally, the server formats the reliability score and related information calculated by the evaluation method and sends it back to the terminal as displayable data. The terminal presents this information to the user through a universal interface. The user can see the evaluation results at a glance and determine whether appropriate action or further investigation is needed based on the reliability level.

[0409] This configuration enables rapid verification of misinformation, supporting users in making reliable decisions. The system flexibly accepts various information formats, allowing for rapid data acquisition and accurate evaluation, thereby addressing the challenges of today's information society.

[0410] The following describes the processing flow.

[0411] Step 1:

[0412] The user opens an application or website and enters information they want to evaluate for reliability. The input format can be text, images, or videos, and the user places the information in an input form on the provided interface.

[0413] Step 2:

[0414] The terminal receives information entered by the user and constructs an HTTP request to send to the backend server. This request may include the content of the information and the user's identification information.

[0415] Step 3:

[0416] The server processes requests received from the terminal and performs scraping to collect relevant external information based on the input. The server accesses trusted news sites, databases, and fact-checking sites to retrieve the necessary data.

[0417] Step 4:

[0418] The information gathering mechanism on the server stores the data collected through scraping and passes it to the evaluation mechanism. This data is structured and converted into a format suitable for analysis.

[0419] Step 5:

[0420] The server evaluation method uses machine learning techniques to compare input user information with external information and perform reliability assessments. The evaluation includes the degree of information consistency, detection of inconsistencies, and calculation of a reliability score based on an AI model.

[0421] Step 6:

[0422] The server formats the evaluation results and generates response data to be sent to the terminal in a user-friendly format. This data includes a list of reliability scores and related information.

[0423] Step 7:

[0424] The terminal displays the evaluation results received from the server and presents them to the user. Based on these results, the user can judge the reliability of the information and refer to other sources of information as needed.

[0425] (Example 1)

[0426] Next, we will describe Example 1. 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."

[0427] In today's information society, it is crucial to quickly and accurately assess the reliability of information circulating on the internet. However, it is difficult for users to judge the reliability of information in various forms on their own, potentially contributing to the spread of misinformation. Methods are needed to prevent the spread of such misinformation and enable users to make decisions based on accurate information.

[0428] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0429] In this invention, the server includes an input means for receiving information provided by a user, an information gathering means for automatically collecting relevant data from external information sources on the Internet based on the information received from the input means, an evaluation means for comparing the external information obtained by the information gathering means with the information provided by the user and evaluating the reliability of the information using a generating AI model, and a display means for providing the user with the evaluation results, including the reliability score obtained by the evaluation means. This enables the reliability of information to be determined quickly and accurately, prevents the spread of misinformation, and allows users to make decisions based on correct information.

[0430] An "input mechanism" is a system for receiving information provided by the user.

[0431] An "information gathering means" is a system that automatically collects relevant data from external information sources on the internet based on information received from an input means.

[0432] An "evaluation method" is a system that compares external information obtained through information gathering methods with information provided by users and evaluates the reliability of the information using a generative AI model.

[0433] A "display means" is a mechanism for providing users with evaluation results, including the reliability score obtained by the evaluation means.

[0434] A "generative AI model" refers to an algorithm or model that uses machine learning techniques to analyze information and evaluate its reliability.

[0435] "Data acquisition means" refers to technologies and methods used to acquire data from external information sources on the internet as part of information gathering means.

[0436] A "reliability score" is an indicator of the reliability of information, calculated using an evaluation method.

[0437] This invention provides a system for efficiently evaluating the reliability of information on the Internet. Specifically, it takes the form of a system in which a user provides information as input, a server automatically collects related data from external sources, and evaluates it using a generated AI model.

[0438] First, the user can input information they want to evaluate the reliability of via their device. For example, they can provide information in the form of a news article's URL, its text, or images and videos. The device then creates a request to send this information to the server.

[0439] The server automatically collects data from relevant external sources on the internet using scraping techniques based on the input information. Specifically, it obtains information from news sites, public databases, and fact-checking sites. Common open-source scraping tools and dedicated APIs can be used for scraping techniques.

[0440] Subsequently, the server compares the collected external information with the input information and evaluates its reliability using a generative AI model. By utilizing machine learning techniques and natural language processing to analyze the degree of consistency and inconsistencies in the information, a reliability score is calculated. This evaluation process enables accurate analysis of the information and allows for highly accurate calculation of reliability.

[0441] The evaluation results are sent from the server to the terminal, which then presents them to the user via a universal interface. This interface is designed to visualize the reliability score in an intuitively understandable way, allowing users to quickly verify the reliability of the information.

[0442] (As a specific example) If a user wants to check the reliability of a health-related article they saw on social media, they enter the URL of the article into the system from their device. The system collects information from relevant public medical databases and trusted medical article websites, compares the content, and provides a reliability score. The user can then use this score to determine the veracity of the information in the article.

[0443] (Example of a prompt message)

[0444] "I want to verify the credibility of this article I found on social media: {article URL}. Please provide the credibility score and related information."

[0445] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0446] Step 1:

[0447] The user inputs information they want to evaluate the reliability of into the system. Specifically, they provide information in the form of text, images, videos, or URLs. The input data is collected on the user's device and formatted according to its content. The output is a request to be sent to the server.

[0448] Step 2:

[0449] The terminal receives information entered by the user and creates a request to send it to the server. During this process, the data format is standardized and processed into a format easily interpreted by the server. The input is user-provided information, and the output is data including the HTTP request to the server.

[0450] Step 3:

[0451] The server receives requests from the terminal and collects relevant data from external sources on the internet based on the information provided by the user. The technology used is web scraping, which retrieves information from news sites and public databases. The input is the information request from the terminal, and the output is the external information obtained through web scraping.

[0452] Step 4:

[0453] The server uses collected external information and a generative AI model to compare it with user-provided information. Machine learning techniques are used to analyze the degree of agreement and inconsistencies in the information, and a reliability score is calculated. The input consists of external information on the server and user information, and the output is the calculated reliability score and related evaluation results.

[0454] Step 5:

[0455] The server formats the obtained reliability score and related information and returns it to the terminal as data for display. It arranges the data in a way that is easy to visualize and processes it into a format suitable for display on the user interface. The input is evaluated reliability data, and the output is a data package formatted for display.

[0456] Step 6:

[0457] The terminal presents reliability scores and related information received from the server through an intuitive interface that the user can easily understand. The information is organized by category, and visual highlighting and graphics are used. The input is formatted data provided by the server, and the output is visual information presented to the user.

[0458] Step 7:

[0459] Based on the presented reliability score and detailed information, users judge the veracity of the information and decide on further investigation or action as needed. The input is the evaluation result presented by the device, and the output is the user's judgment and next action.

[0460] (Application Example 1)

[0461] Next, we will explain Application Example 1. In the following explanation, 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."

[0462] Much of the information circulating on the internet is of questionable reliability. Therefore, it is difficult for users to select reliable information. Furthermore, a system is needed to verify the reliability of information before it is disseminated. This is necessary to prevent the spread of misinformation and support users in making more appropriate judgments.

[0463] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0464] In this invention, the server includes a device for inputting information obtained from a user, an information collection device for automatically collecting relevant data from external information sources based on the information obtained from the input device, and an evaluation device for comparing the external information collected by the information collection device with the information from the user and evaluating the reliability of the information. This makes it possible for users to evaluate the reliability of the content they intend to post in advance and check the reliability score.

[0465] "User" refers to an individual or organization that inputs or verifies information.

[0466] "Device" refers to an instrument or system designed to perform a specific function.

[0467] An "information gathering device" refers to a device that has the function of automatically acquiring relevant data from external information sources.

[0468] An "evaluation device" refers to a device used to compare collected information and evaluate its reliability.

[0469] A "reliability score" is an index that numerically represents the reliability of information and is used by users to judge the accuracy of that information.

[0470] "External information sources" refer to information providers that are the target of information collection, such as publicly available databases and news sites on the internet.

[0471] The system of the present invention consists of multiple elements, including a user, a terminal, and a server. The user inputs content to be posted (e.g., text, images, videos, etc.) into the terminal via an input means. The terminal is responsible for transmitting this information to the server.

[0472] The server has information gathering devices, evaluation devices, and display devices, which are used to evaluate the reliability of the information. The information gathering device uses scraping technology to automatically acquire relevant data from external information sources on the internet. Specifically, for scraping, "BeautifulSoup" is used, and for data analysis, machine learning libraries such as "TensorFlow" and "PyTorch" are used.

[0473] The evaluation device analyzes the collected data, uses a generative AI model to assess the consistency and inconsistencies of the information, and calculates a reliability score. This reliability score is an indicator of how trustworthy the information is and is used by users to make decisions about disclosing the information.

[0474] The server passes the evaluation results to a display device and sends them back to the user's terminal. The terminal presents the received reliability score and related information to the user through an intuitive interface. This allows the user to verify the reliability of the information in advance and publish content with confidence.

[0475] As a concrete example, when a user posts an article about a social issue, the server evaluates the reliability of the article and checks whether it has been cross-referenced with information from major news outlets and public databases. An example of a prompt message would be: "Please evaluate the reliability of the following news article. Article title: ''. Content: ''. What related information can be collected, and how is the reliability score calculated based on that information?"

[0476] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0477] Step 1:

[0478] The terminal receives text, image, or video data entered by the user. The input data is processed into a format that is then constructed as a request to be sent to the server. This enables efficient data communication in the next step.

[0479] Step 2:

[0480] The server receives input data sent from the terminal. Based on the received data, the information gathering device prepares to automatically collect relevant data from external sources. At this stage, an appropriate scraping strategy is selected depending on the type of input information.

[0481] Step 3:

[0482] The information gathering device accesses external information sources on the internet and collects relevant information through available APIs or by utilizing scraping techniques. The collected data is stored on the server as primary data for reliability evaluation.

[0483] Step 4:

[0484] The evaluation system performs analysis using collected external data and original information provided by the user. It utilizes generative AI models and machine learning libraries to analyze the degree of consistency and inconsistencies in the information. The inputs are user information and external information, and the output is a reliability score.

[0485] Step 5:

[0486] The server formats the reliability score and related information obtained as a result of the evaluation, converting it into a user-friendly format. This allows the information to be presented on a visually intuitive user interface.

[0487] Step 6:

[0488] The terminal displays the reliability score and related information received from the server to the user using a display device. Based on the displayed data, the user checks the reliability of the content they intend to post and makes a decision on whether to publish the information as appropriate.

[0489] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0490] This invention relates to a system for evaluating the reliability of information on the internet, which also takes into account the user's emotions. This system incorporates an emotion engine that recognizes the emotions expressed and selected by the user when they input information. This prevents the reliability evaluation from being excessively influenced by the user's emotional bias.

[0491] First, the user enters the information they want to evaluate for reliability via an application or website. The entered information is then sent from the device to the server. Next, the server automatically collects relevant data from external sources using information gathering tools. It obtains data from other news sites, databases, and fact-checking services to complete the information gathering process.

[0492] A further feature of this system is its emotion engine, which analyzes user emotions. It identifies the user's emotions from the input information through text and voice analysis, and incorporates the results into the reliability evaluation. This analysis allows for the assessment of how emotions might influence reliability judgments, for example, if the user is in a highly angered state.

[0493] The evaluation method utilizes machine learning techniques to scrutinize the degree of agreement and inconsistencies between user information and external data. Furthermore, it integrates the obtained sentiment data into the evaluation, allowing for correction of emotionally over-influenced ratings.

[0494] Ultimately, the server generates the reliability evaluation results and displays them to the user via the terminal. The display method presents the results in a way that suits the user's emotional state, supporting calmer and less biased decision-making. For example, users exhibiting positive emotions are shown results with a neutral color scheme, while users exhibiting negative emotions are visually highlighted with cautionary colors.

[0495] This allows users to receive accurate reliability assessments that go beyond simple information evaluation, taking emotional influences into account. By providing reliability judgments that combine emotion and information, this system is a valuable technology in today's complex information environment.

[0496] The following describes the processing flow.

[0497] Step 1:

[0498] Users enter the information they want to evaluate via an application or website. The input can be text, images, or audio, and users place it in a designated form.

[0499] Step 2:

[0500] The terminal receives user input information and constructs an HTTP request to send it to the server. The request includes the content of the information and the user's identification information.

[0501] Step 3:

[0502] The server receives a request and uses information gathering tools to collect relevant data from external sources through scraping. This is the process of obtaining data from trusted news sites and public databases.

[0503] Step 4:

[0504] The server uses an emotion engine to recognize emotions from the information entered by the user. It uses text and voice sentiment analysis techniques to identify the emotional state the user is experiencing.

[0505] Step 5:

[0506] The server uses evaluation tools to compare user information with external information. During this process, machine learning models are used to analyze the degree of agreement and inconsistencies, and a reliability score is calculated, taking into account perceived emotions. Emotional bias is corrected by the system.

[0507] Step 6:

[0508] The server formats the evaluation results and generates response data to send back to the terminal. This data includes a reliability score, an assessment of significant sentiment, and related information.

[0509] Step 7:

[0510] The terminal displays the evaluation results received from the server and presents them to the user. The display uses appropriate formats and colors that take into account the influence of emotions, allowing the user to verify the reliability of the information from a more balanced perspective.

[0511] (Example 2)

[0512] Next, we will describe Example 2. 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."

[0513] In today's information environment, evaluating the reliability of information on the internet is extremely important. However, conventional systems fail to take into account the emotional biases of users, and as a result, reliability evaluations can be excessively influenced by emotions. This leads to the problem that the evaluation results provided are not always objective or accurate.

[0514] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0515] In this invention, the server includes means for analyzing the user's emotions and performing a reliability evaluation that takes emotional bias into account, means for automatically collecting relevant data from external sources, and means for comparing user information with external information and evaluating reliability. This makes it possible to perform a more accurate and objective reliability evaluation while taking into account the user's emotional state.

[0516] A "user" is an individual or group that uses the system to evaluate the reliability of information.

[0517] An "input means" is a device or interface used by a user to provide information they wish to evaluate to the system.

[0518] "Information gathering means" refers to a function or process that automatically acquires relevant data from external sources based on the input information.

[0519] "Evaluation means" refers to a device or program for comparing and analyzing collected external information with information from users to evaluate the reliability of the information.

[0520] "Emotion analysis means" refers to a technology or module for identifying emotional states from user input information and analyzing the impact of those emotions on trust assessment.

[0521] "Display means" refers to an interface or device that presents the reliability of the information derived by the evaluation means to the user in an easily understandable manner.

[0522] This invention aims to incorporate user emotions into a system for evaluating the reliability of information. This reduces emotional bias and provides a more accurate and objective reliability assessment.

[0523] Users first input the information they want to evaluate for reliability via a dedicated application or website. The device used is designed to transmit the information to a server over a network. Common web browsers and mobile applications are used on these devices.

[0524] The server automatically collects relevant external data based on the input information. This process utilizes news sites, databases, and fact-checking services on the internet. The collected data is used to build the information base necessary for reliability assessment. The server incorporates a high-performance data collection engine and a database management system.

[0525] Next, the server uses an emotion engine to analyze the user's emotions. By performing text and voice analysis, it identifies the emotional state from the information the user has entered. This emotion data plays a crucial role in reliability evaluation. Natural language processing and voice analysis technologies are employed for the analysis.

[0526] In the evaluation process, the server utilizes machine learning algorithms to closely compare collected external information with user input. This identifies points of agreement and disagreement in the information, and further corrects for the influence of emotions to perform an accurate reliability assessment.

[0527] Ultimately, the server presents the evaluation results to the user. During this process, customization is applied based on the user's emotional state; for example, the interface becomes neutral for users exhibiting positive emotions. This allows users to make calm and rational decisions.

[0528] An example of a prompt is, "Evaluate the reliability of this information. Generate a reliability score, taking into account the content of the information, relevant external data, and the user's emotional state." Using this prompt, the generative AI model can assist in the evaluation process.

[0529] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0530] Step 1:

[0531] The user inputs information they want to evaluate for reliability using their device. Specifically, they copy and paste the URL of a news article into a dedicated input field. The input information is then sent from the device to the server via the internet. The input is the information to be evaluated provided by the user, and the output is digital information sent from the device to the server.

[0532] Step 2:

[0533] The server automatically collects relevant data from external sources using information gathering tools. Specifically, the server accesses news APIs and databases to retrieve the corresponding information. In this step, user-provided information is passed as input, and supplemented external data is generated as output.

[0534] Step 3:

[0535] The server uses an emotion engine to analyze the user's emotions. The server performs text analysis on the input information using natural language processing techniques to determine the user's emotional state. The input is the user's text information, and the output is data indicating the user's emotional state.

[0536] Step 4:

[0537] The server uses evaluation tools to compare collected external information with user information and perform a reliability assessment. The server applies machine learning algorithms to identify similarities and inconsistencies and calculates a reliability score. The input is the collected external data and user input data, and the output is the evaluation result, including the reliability score.

[0538] Step 5:

[0539] The server transmits and displays the reliability evaluation results to the terminal in a format that reflects the user's emotional state. The server adjusts the color scheme and messages to accommodate the user's emotions when displaying the results. The input consists of the reliability evaluation results and the user's emotional state, while the output is customized display information.

[0540] (Application Example 2)

[0541] Next, we will explain application example 2. In the following explanation, 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."

[0542] In modern content distribution services, user reviews have a significant impact on content selection. Therefore, ensuring the reliability of reviews and mitigating excessive emotional bias is crucial. However, traditional systems often fail to consider user emotions and lack sufficient means to ensure the objectivity of review content, making it difficult to provide reliable information.

[0543] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0544] In this invention, the server includes an input means for information obtained from users, an information gathering means for automatically collecting relevant data from external information sources, and an evaluation means for evaluating reliability based on the collected information and sentiment. This enables accurate content evaluation that takes sentiment into account.

[0545] "User" refers to a person who operates the system and inputs information.

[0546] An "input means" is a device or interface for taking information from a user into a system.

[0547] "Information gathering means" refers to processes or mechanisms for automatically acquiring relevant data from external information sources.

[0548] "Evaluation methods" refer to functions and mechanisms for comparing user information with external information and analyzing its reliability.

[0549] "Emotion analysis means" refers to a function that identifies emotions from information entered by the user and reflects that in the reliability evaluation.

[0550] "Display means" refers to a device or interface for showing the reliability of evaluated information in a format appropriate to the user's emotional state.

[0551] "Learning model technology" is a technique that uses machine learning to analyze the degree of consistency and inconsistencies in information and determine its reliability.

[0552] "Collection method" refers to the mechanism or method for automatically collecting data from information sources.

[0553] The system that realizes this invention consists of an internet-connected server and a terminal used by the user. The server provides an interface for inputting information obtained from the user. This interface is typically implemented as an application that runs on a smartphone or computer, and enables text input and voice input.

[0554] When a user submits a review or rating, the server receives that information. The server then uses a natural language processing engine to analyze the content and scan the user's sentiment from the text data. This analysis often utilizes Python libraries such as NLTK or SpaCy.

[0555] The server then accesses external information sources and retrieves relevant data through collection methods. Generally, this process utilizes scraping techniques, where automated programs gather relevant information from news and review sites on the internet. The collected data is managed on a database built using learning model techniques and prepared for comparison.

[0556] To evaluate the consistency and inconsistencies of the data, the server utilizes evaluation tools based on machine learning libraries such as TensorFlow and PyTorch. During this process, user sentiment data is also incorporated into the evaluation, allowing for a multifaceted analysis of the review's reliability. The evaluation results are ultimately displayed on the device through a visual interface tailored to the user's emotional state. The interface features an adapted design and color scheme to enable users to make calm and rational judgments.

[0557] As a concrete example, suppose a user writes a review of a movie. Suppose the review includes the phrase, "It was very moving, but it's easy to get carried away by emotions." The system receives this input, detects the emotional state of "being moved" through text analysis, and evaluates its reliability while considering its influence.

[0558] An example of a prompt would be, "As a review of the movie XYZ, please assess the emotions contained in the text and calculate the degree to which they influence the rating." Through this prompt, the user's subjective opinion will be appropriately reflected in the rating system.

[0559] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0560] Step 1:

[0561] The device provides an interface for users to enter reviews and ratings. When users input information via text or voice, it is captured by the device. The entered information is then sent to the server as text data.

[0562] Step 2:

[0563] The server sends the received text data to a natural language processing engine for analysis. During this process, the server extracts sentiment from the input information. The text analysis is performed using Python libraries such as NLTK and SpaCy. The input is user reviews, and the output is sentiment information.

[0564] Step 3:

[0565] Based on the sentiment analysis results, the server initiates access to external information sources. The data to be evaluated is automatically scraped from internet news sites and review sites using various collection methods. The input is analyzed sentiment data, and the output is external information data.

[0566] Step 4:

[0567] The server uses learning model techniques to perform reliability assessments by comparing collected external information with user input data. It analyzes data consistency and inconsistencies using TensorFlow or PyTorch. In this step, sentiment data and external information are used as input, and the output is the evaluation result.

[0568] Step 5:

[0569] The server prepares to display the results in a format adapted to the user's emotional state, based on the evaluation results. It generates an interface design tailored to the user's emotions and sends it to the terminal. In this case, the input is the evaluation results, and the output is the adaptive interface.

[0570] Step 6:

[0571] The terminal displays the evaluation results to the user using an interface received from the server. Appropriate colors and designs are used to allow the user to make a calm and rational judgment. The final output is the evaluation results that the user sees on the screen. In this step, the role of the terminal is to display the evaluation results.

[0572] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0573] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0574] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0575] [Fourth Embodiment]

[0576] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0577] As shown in Figure 7, the 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.

[0578] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0579] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0580] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0581] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0582] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0583] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0584] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0585] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0586] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0587] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0588] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0589] This invention is a system for quickly and accurately evaluating the reliability of information existing on the internet. This system receives information in various forms provided by users, automatically collects related data from external sources, and evaluates its reliability using machine learning techniques. The evaluation results are provided to the user through an intuitive interface.

[0590] First, the user accesses the system and inputs information they want to evaluate the reliability of, in the form of text, images, videos, etc. This information is sent to the system via the terminal. The terminal then constructs a request to send the input information to the server.

[0591] Next, based on the information received by the server, relevant data is automatically collected from external sources on the internet using scraping techniques. For example, relevant information is obtained from news sites, public databases, and fact-checking sites.

[0592] The collected external information is compared with the user-provided information by an evaluation tool on the server. Machine learning techniques are used to analyze the degree of agreement and inconsistencies between the information, and a reliability score is calculated. This score is an important indicator for evaluating the reliability of the information provided by the user.

[0593] Finally, the server formats the reliability score and related information calculated by the evaluation method and sends it back to the terminal as displayable data. The terminal presents this information to the user through a universal interface. The user can see the evaluation results at a glance and determine whether appropriate action or further investigation is needed based on the reliability level.

[0594] This configuration enables rapid verification of misinformation, supporting users in making reliable decisions. The system flexibly accepts various information formats, allowing for rapid data acquisition and accurate evaluation, thereby addressing the challenges of today's information society.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The user opens an application or website and enters information they want to evaluate for reliability. The input format can be text, images, or videos, and the user places the information in an input form on the provided interface.

[0598] Step 2:

[0599] The terminal receives information entered by the user and constructs an HTTP request to send to the backend server. This request may include the content of the information and the user's identification information.

[0600] Step 3:

[0601] The server processes requests received from the terminal and performs scraping to collect relevant external information based on the input. The server accesses trusted news sites, databases, and fact-checking sites to retrieve the necessary data.

[0602] Step 4:

[0603] The information gathering mechanism on the server stores the data collected through scraping and passes it to the evaluation mechanism. This data is structured and converted into a format suitable for analysis.

[0604] Step 5:

[0605] The server evaluation method uses machine learning techniques to compare input user information with external information and perform reliability assessments. The evaluation includes the degree of information consistency, detection of inconsistencies, and calculation of a reliability score based on an AI model.

[0606] Step 6:

[0607] The server formats the evaluation results and generates response data to be sent to the terminal in a user-friendly format. This data includes a list of reliability scores and related information.

[0608] Step 7:

[0609] The terminal displays the evaluation results received from the server and presents them to the user. Based on these results, the user can judge the reliability of the information and refer to other sources of information as needed.

[0610] (Example 1)

[0611] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] In today's information society, it is crucial to quickly and accurately assess the reliability of information circulating on the internet. However, it is difficult for users to judge the reliability of information in various forms on their own, potentially contributing to the spread of misinformation. Methods are needed to prevent the spread of such misinformation and enable users to make decisions based on accurate information.

[0613] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0614] In this invention, the server includes an input means for receiving information provided by a user, an information gathering means for automatically collecting relevant data from external information sources on the Internet based on the information received from the input means, an evaluation means for comparing the external information obtained by the information gathering means with the information provided by the user and evaluating the reliability of the information using a generating AI model, and a display means for providing the user with the evaluation results, including the reliability score obtained by the evaluation means. This enables the reliability of information to be determined quickly and accurately, prevents the spread of misinformation, and allows users to make decisions based on correct information.

[0615] An "input mechanism" is a system for receiving information provided by the user.

[0616] An "information gathering means" is a system that automatically collects relevant data from external information sources on the internet based on information received from an input means.

[0617] An "evaluation method" is a system that compares external information obtained through information gathering methods with information provided by users and evaluates the reliability of the information using a generative AI model.

[0618] A "display means" is a mechanism for providing users with evaluation results, including the reliability score obtained by the evaluation means.

[0619] A "generative AI model" refers to an algorithm or model that uses machine learning techniques to analyze information and evaluate its reliability.

[0620] "Data acquisition means" refers to technologies and methods used to acquire data from external information sources on the internet as part of information gathering means.

[0621] A "reliability score" is an indicator of the reliability of information, calculated using an evaluation method.

[0622] This invention provides a system for efficiently evaluating the reliability of information on the Internet. Specifically, it takes the form of a system in which a user provides information as input, a server automatically collects related data from external sources, and evaluates it using a generated AI model.

[0623] First, the user can input information they want to evaluate the reliability of via their device. For example, they can provide information in the form of a news article's URL, its text, or images and videos. The device then creates a request to send this information to the server.

[0624] The server automatically collects data from relevant external sources on the internet using scraping techniques based on the input information. Specifically, it obtains information from news sites, public databases, and fact-checking sites. Common open-source scraping tools and dedicated APIs can be used for scraping techniques.

[0625] Subsequently, the server compares the collected external information with the input information and evaluates its reliability using a generative AI model. By utilizing machine learning techniques and natural language processing to analyze the degree of consistency and inconsistencies in the information, a reliability score is calculated. This evaluation process enables accurate analysis of the information and allows for highly accurate calculation of reliability.

[0626] The evaluation results are sent from the server to the terminal, which then presents them to the user via a universal interface. This interface is designed to visualize the reliability score in an intuitively understandable way, allowing users to quickly verify the reliability of the information.

[0627] (As a specific example) If a user wants to check the reliability of a health-related article they saw on social media, they enter the URL of the article into the system from their device. The system collects information from relevant public medical databases and trusted medical article websites, compares the content, and provides a reliability score. The user can then use this score to determine the veracity of the information in the article.

[0628] (Example of a prompt message)

[0629] "I want to verify the credibility of this article I found on social media: {article URL}. Please provide the credibility score and related information."

[0630] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0631] Step 1:

[0632] The user inputs information they want to evaluate the reliability of into the system. Specifically, they provide information in the form of text, images, videos, or URLs. The input data is collected on the user's device and formatted according to its content. The output is a request to be sent to the server.

[0633] Step 2:

[0634] The terminal receives information entered by the user and creates a request to send it to the server. During this process, the data format is standardized and processed into a format easily interpreted by the server. The input is user-provided information, and the output is data including the HTTP request to the server.

[0635] Step 3:

[0636] The server receives requests from the terminal and collects relevant data from external sources on the internet based on the information provided by the user. The technology used is web scraping, which retrieves information from news sites and public databases. The input is the information request from the terminal, and the output is the external information obtained through web scraping.

[0637] Step 4:

[0638] The server uses collected external information and a generative AI model to compare it with user-provided information. Machine learning techniques are used to analyze the degree of agreement and inconsistencies in the information, and a reliability score is calculated. The input consists of external information on the server and user information, and the output is the calculated reliability score and related evaluation results.

[0639] Step 5:

[0640] The server formats the obtained reliability score and related information and returns it to the terminal as data for display. It arranges the data in a way that is easy to visualize and processes it into a format suitable for display on the user interface. The input is evaluated reliability data, and the output is a data package formatted for display.

[0641] Step 6:

[0642] The terminal presents reliability scores and related information received from the server through an intuitive interface that the user can easily understand. The information is organized by category, and visual highlighting and graphics are used. The input is formatted data provided by the server, and the output is visual information presented to the user.

[0643] Step 7:

[0644] Based on the presented reliability score and detailed information, users judge the veracity of the information and decide on further investigation or action as needed. The input is the evaluation result presented by the device, and the output is the user's judgment and next action.

[0645] (Application Example 1)

[0646] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] Much of the information circulating on the internet is of questionable reliability. Therefore, it is difficult for users to select reliable information. Furthermore, a system is needed to verify the reliability of information before it is disseminated. This is necessary to prevent the spread of misinformation and support users in making more appropriate judgments.

[0648] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0649] In this invention, the server includes a device for inputting information obtained from a user, an information collection device for automatically collecting relevant data from external information sources based on the information obtained from the input device, and an evaluation device for comparing the external information collected by the information collection device with the information from the user and evaluating the reliability of the information. This makes it possible for users to evaluate the reliability of the content they intend to post in advance and check the reliability score.

[0650] "User" refers to an individual or organization that inputs or verifies information.

[0651] "Device" refers to an instrument or system designed to perform a specific function.

[0652] An "information gathering device" refers to a device that has the function of automatically acquiring relevant data from external information sources.

[0653] An "evaluation device" refers to a device used to compare collected information and evaluate its reliability.

[0654] A "reliability score" is an index that numerically represents the reliability of information and is used by users to judge the accuracy of that information.

[0655] "External information sources" refer to information providers that are the target of information collection, such as publicly available databases and news sites on the internet.

[0656] The system of the present invention consists of multiple elements, including a user, a terminal, and a server. The user inputs content to be posted (e.g., text, images, videos, etc.) into the terminal via an input means. The terminal is responsible for transmitting this information to the server.

[0657] The server has information gathering devices, evaluation devices, and display devices, which are used to evaluate the reliability of the information. The information gathering device uses scraping technology to automatically acquire relevant data from external information sources on the internet. Specifically, for scraping, "BeautifulSoup" is used, and for data analysis, machine learning libraries such as "TensorFlow" and "PyTorch" are used.

[0658] The evaluation device analyzes the collected data, uses a generative AI model to assess the consistency and inconsistencies of the information, and calculates a reliability score. This reliability score is an indicator of how trustworthy the information is and is used by users to make decisions about disclosing the information.

[0659] The server passes the evaluation results to a display device and sends them back to the user's terminal. The terminal presents the received reliability score and related information to the user through an intuitive interface. This allows the user to verify the reliability of the information in advance and publish content with confidence.

[0660] As a concrete example, when a user posts an article about a social issue, the server evaluates the reliability of the article and checks whether it has been cross-referenced with information from major news outlets and public databases. An example of a prompt message would be: "Please evaluate the reliability of the following news article. Article title: ''. Content: ''. What related information can be collected, and how is the reliability score calculated based on that information?"

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] The terminal receives text, image, or video data entered by the user. The input data is processed into a format that is then constructed as a request to be sent to the server. This enables efficient data communication in the next step.

[0664] Step 2:

[0665] The server receives input data sent from the terminal. Based on the received data, the information gathering device prepares to automatically collect relevant data from external sources. At this stage, an appropriate scraping strategy is selected depending on the type of input information.

[0666] Step 3:

[0667] The information gathering device accesses external information sources on the internet and collects relevant information through available APIs or by utilizing scraping techniques. The collected data is stored on the server as primary data for reliability evaluation.

[0668] Step 4:

[0669] The evaluation system performs analysis using collected external data and original information provided by the user. It utilizes generative AI models and machine learning libraries to analyze the degree of consistency and inconsistencies in the information. The inputs are user information and external information, and the output is a reliability score.

[0670] Step 5:

[0671] The server formats the reliability score and related information obtained as a result of the evaluation, converting it into a user-friendly format. This allows the information to be presented on a visually intuitive user interface.

[0672] Step 6:

[0673] The terminal displays the reliability score and related information received from the server to the user using a display device. Based on the displayed data, the user checks the reliability of the content they intend to post and makes a decision on whether to publish the information as appropriate.

[0674] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0675] This invention relates to a system for evaluating the reliability of information on the internet, which also takes into account the user's emotions. This system incorporates an emotion engine that recognizes the emotions expressed and selected by the user when they input information. This prevents the reliability evaluation from being excessively influenced by the user's emotional bias.

[0676] First, the user enters the information they want to evaluate for reliability via an application or website. The entered information is then sent from the device to the server. Next, the server automatically collects relevant data from external sources using information gathering tools. It obtains data from other news sites, databases, and fact-checking services to complete the information gathering process.

[0677] A further feature of this system is its emotion engine, which analyzes user emotions. It identifies the user's emotions from the input information through text and voice analysis, and incorporates the results into the reliability evaluation. This analysis allows for the assessment of how emotions might influence reliability judgments, for example, if the user is in a highly angered state.

[0678] The evaluation method utilizes machine learning techniques to scrutinize the degree of agreement and inconsistencies between user information and external data. Furthermore, it integrates the obtained sentiment data into the evaluation, allowing for correction of emotionally over-influenced ratings.

[0679] Ultimately, the server generates the reliability evaluation results and displays them to the user via the terminal. The display method presents the results in a way that suits the user's emotional state, supporting calmer and less biased decision-making. For example, users exhibiting positive emotions are shown results with a neutral color scheme, while users exhibiting negative emotions are visually highlighted with cautionary colors.

[0680] This allows users to receive accurate reliability assessments that go beyond simple information evaluation, taking emotional influences into account. By providing reliability judgments that combine emotion and information, this system is a valuable technology in today's complex information environment.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] Users enter the information they want to evaluate via an application or website. The input can be text, images, or audio, and users place it in a designated form.

[0684] Step 2:

[0685] The terminal receives user input information and constructs an HTTP request to send it to the server. The request includes the content of the information and the user's identification information.

[0686] Step 3:

[0687] The server receives a request and uses information gathering tools to collect relevant data from external sources through scraping. This is the process of obtaining data from trusted news sites and public databases.

[0688] Step 4:

[0689] The server uses an emotion engine to recognize emotions from the information entered by the user. It uses text and voice sentiment analysis techniques to identify the emotional state the user is experiencing.

[0690] Step 5:

[0691] The server uses evaluation tools to compare user information with external information. During this process, machine learning models are used to analyze the degree of agreement and inconsistencies, and a reliability score is calculated, taking into account perceived emotions. Emotional bias is corrected by the system.

[0692] Step 6:

[0693] The server formats the evaluation results and generates response data to send back to the terminal. This data includes a reliability score, an assessment of significant sentiment, and related information.

[0694] Step 7:

[0695] The terminal displays the evaluation results received from the server and presents them to the user. The display uses appropriate formats and colors that take into account the influence of emotions, allowing the user to verify the reliability of the information from a more balanced perspective.

[0696] (Example 2)

[0697] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In today's information environment, evaluating the reliability of information on the internet is extremely important. However, conventional systems fail to take into account the emotional biases of users, and as a result, reliability evaluations can be excessively influenced by emotions. This leads to the problem that the evaluation results provided are not always objective or accurate.

[0699] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0700] In this invention, the server includes means for analyzing the user's emotions and performing a reliability evaluation that takes emotional bias into account, means for automatically collecting relevant data from external sources, and means for comparing user information with external information and evaluating reliability. This makes it possible to perform a more accurate and objective reliability evaluation while taking into account the user's emotional state.

[0701] A "user" is an individual or group that uses the system to evaluate the reliability of information.

[0702] An "input means" is a device or interface used by a user to provide information they wish to evaluate to the system.

[0703] "Information gathering means" refers to a function or process that automatically acquires relevant data from external sources based on the input information.

[0704] "Evaluation means" refers to a device or program for comparing and analyzing collected external information with information from users to evaluate the reliability of the information.

[0705] "Emotion analysis means" refers to a technology or module for identifying emotional states from user input information and analyzing the impact of those emotions on trust assessment.

[0706] "Display means" refers to an interface or device that presents the reliability of the information derived by the evaluation means to the user in an easily understandable manner.

[0707] This invention aims to incorporate user emotions into a system for evaluating the reliability of information. This reduces emotional bias and provides a more accurate and objective reliability assessment.

[0708] Users first input the information they want to evaluate for reliability via a dedicated application or website. The device used is designed to transmit the information to a server over a network. Common web browsers and mobile applications are used on these devices.

[0709] The server automatically collects relevant external data based on the input information. This process utilizes news sites, databases, and fact-checking services on the internet. The collected data is used to build the information base necessary for reliability assessment. The server incorporates a high-performance data collection engine and a database management system.

[0710] Next, the server uses an emotion engine to analyze the user's emotions. By performing text and voice analysis, it identifies the emotional state from the information the user has entered. This emotion data plays a crucial role in reliability evaluation. Natural language processing and voice analysis technologies are employed for the analysis.

[0711] In the evaluation process, the server utilizes machine learning algorithms to closely compare collected external information with user input. This identifies points of agreement and disagreement in the information, and further corrects for the influence of emotions to perform an accurate reliability assessment.

[0712] Ultimately, the server presents the evaluation results to the user. During this process, customization is applied based on the user's emotional state; for example, the interface becomes neutral for users exhibiting positive emotions. This allows users to make calm and rational decisions.

[0713] An example of a prompt is, "Evaluate the reliability of this information. Generate a reliability score, taking into account the content of the information, relevant external data, and the user's emotional state." Using this prompt, the generative AI model can assist in the evaluation process.

[0714] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0715] Step 1:

[0716] The user inputs information they want to evaluate for reliability using their device. Specifically, they copy and paste the URL of a news article into a dedicated input field. The input information is then sent from the device to the server via the internet. The input is the information to be evaluated provided by the user, and the output is digital information sent from the device to the server.

[0717] Step 2:

[0718] The server automatically collects relevant data from external sources using information gathering tools. Specifically, the server accesses news APIs and databases to retrieve the corresponding information. In this step, user-provided information is passed as input, and supplemented external data is generated as output.

[0719] Step 3:

[0720] The server uses an emotion engine to analyze the user's emotions. The server performs text analysis on the input information using natural language processing techniques to determine the user's emotional state. The input is the user's text information, and the output is data indicating the user's emotional state.

[0721] Step 4:

[0722] The server uses evaluation tools to compare collected external information with user information and perform a reliability assessment. The server applies machine learning algorithms to identify similarities and inconsistencies and calculates a reliability score. The input is the collected external data and user input data, and the output is the evaluation result, including the reliability score.

[0723] Step 5:

[0724] The server transmits and displays the reliability evaluation results to the terminal in a format that reflects the user's emotional state. The server adjusts the color scheme and messages to accommodate the user's emotions when displaying the results. The input consists of the reliability evaluation results and the user's emotional state, while the output is customized display information.

[0725] (Application Example 2)

[0726] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0727] In modern content distribution services, user reviews have a significant impact on content selection. Therefore, ensuring the reliability of reviews and mitigating excessive emotional bias is crucial. However, traditional systems often fail to consider user emotions and lack sufficient means to ensure the objectivity of review content, making it difficult to provide reliable information.

[0728] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0729] In this invention, the server includes an input means for information obtained from users, an information gathering means for automatically collecting relevant data from external information sources, and an evaluation means for evaluating reliability based on the collected information and sentiment. This enables accurate content evaluation that takes sentiment into account.

[0730] "User" refers to a person who operates the system and inputs information.

[0731] An "input means" is a device or interface for taking information from a user into a system.

[0732] "Information gathering means" refers to processes or mechanisms for automatically acquiring relevant data from external information sources.

[0733] "Evaluation methods" refer to functions and mechanisms for comparing user information with external information and analyzing its reliability.

[0734] "Emotion analysis means" refers to a function that identifies emotions from information entered by the user and reflects that in the reliability evaluation.

[0735] "Display means" refers to a device or interface for showing the reliability of evaluated information in a format appropriate to the user's emotional state.

[0736] "Learning model technology" is a technique that uses machine learning to analyze the degree of consistency and inconsistencies in information and determine its reliability.

[0737] "Collection method" refers to the mechanism or method for automatically collecting data from information sources.

[0738] The system that realizes this invention consists of an internet-connected server and a terminal used by the user. The server provides an interface for inputting information obtained from the user. This interface is typically implemented as an application that runs on a smartphone or computer, and enables text input and voice input.

[0739] When a user submits a review or rating, the server receives that information. The server then uses a natural language processing engine to analyze the content and scan the user's sentiment from the text data. This analysis often utilizes Python libraries such as NLTK or SpaCy.

[0740] The server then accesses external information sources and retrieves relevant data through collection methods. Generally, this process utilizes scraping techniques, where automated programs gather relevant information from news and review sites on the internet. The collected data is managed on a database built using learning model techniques and prepared for comparison.

[0741] To evaluate the consistency and inconsistencies of the data, the server utilizes evaluation tools based on machine learning libraries such as TensorFlow and PyTorch. During this process, user sentiment data is also incorporated into the evaluation, allowing for a multifaceted analysis of the review's reliability. The evaluation results are ultimately displayed on the device through a visual interface tailored to the user's emotional state. The interface features an adapted design and color scheme to enable users to make calm and rational judgments.

[0742] As a concrete example, suppose a user writes a review of a movie. Suppose the review includes the phrase, "It was very moving, but it's easy to get carried away by emotions." The system receives this input, detects the emotional state of "being moved" through text analysis, and evaluates its reliability while considering its influence.

[0743] An example of a prompt would be, "As a review of the movie XYZ, please assess the emotions contained in the text and calculate the degree to which they influence the rating." Through this prompt, the user's subjective opinion will be appropriately reflected in the rating system.

[0744] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0745] Step 1:

[0746] The device provides an interface for users to enter reviews and ratings. When users input information via text or voice, it is captured by the device. The entered information is then sent to the server as text data.

[0747] Step 2:

[0748] The server sends the received text data to a natural language processing engine for analysis. During this process, the server extracts sentiment from the input information. The text analysis is performed using Python libraries such as NLTK and SpaCy. The input is user reviews, and the output is sentiment information.

[0749] Step 3:

[0750] Based on the sentiment analysis results, the server initiates access to external information sources. The data to be evaluated is automatically scraped from internet news sites and review sites using various collection methods. The input is analyzed sentiment data, and the output is external information data.

[0751] Step 4:

[0752] The server uses learning model techniques to perform reliability assessments by comparing collected external information with user input data. It analyzes data consistency and inconsistencies using TensorFlow or PyTorch. In this step, sentiment data and external information are used as input, and the output is the evaluation result.

[0753] Step 5:

[0754] The server prepares to display the results in a format adapted to the user's emotional state, based on the evaluation results. It generates an interface design tailored to the user's emotions and sends it to the terminal. In this case, the input is the evaluation results, and the output is the adaptive interface.

[0755] Step 6:

[0756] The terminal displays the evaluation results to the user using an interface received from the server. Appropriate colors and designs are used to allow the user to make a calm and rational judgment. The final output is the evaluation results that the user sees on the screen. In this step, the role of the terminal is to display the evaluation results.

[0757] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0758] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0759] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0760] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0761] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0762] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0763] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0764] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0765] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0766] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0767] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0768] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0769] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0770] 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.

[0771] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0772] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0773] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0774] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0775] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0776] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0777] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0778] The following is further disclosed regarding the embodiments described above.

[0779] (Claim 1)

[0780] The information obtained from the user is used as an input method,

[0781] Information gathering means that automatically collects relevant data from external information sources based on the information obtained from the input means,

[0782] An evaluation means that compares external information collected by the information collection means with information from the user and evaluates the reliability of the information,

[0783] A display means that presents to the user the reliability of the information evaluated by the evaluation means,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, wherein the information gathering means includes automated scraping means for obtaining data from an external information source.

[0787] (Claim 3)

[0788] The system according to claim 1, wherein the evaluation means performs reliability evaluation by analyzing the degree of agreement and inconsistencies between the user information and external information using machine learning technology.

[0789] "Example 1"

[0790] (Claim 1)

[0791] An input method for receiving information provided by the user,

[0792] Information gathering means that automatically collects relevant data from external information sources on the internet based on the information received from the input means,

[0793] An evaluation means that compares external information obtained by the information gathering means with information provided by the user and evaluates the reliability of the information using a generated AI model,

[0794] A display means for providing the user with evaluation results, including the reliability score obtained by the evaluation means,

[0795] A system that includes this.

[0796] (Claim 2)

[0797] The system according to claim 1, wherein the information gathering means includes automated data acquisition means for obtaining data from external information sources on the Internet, and employs scraping technology.

[0798] (Claim 3)

[0799] The system according to claim 1, wherein the evaluation means performs a reliability evaluation by utilizing machine learning technology to analyze the similarities and inconsistencies between the information from the user and external information, and by calculating a reliability score.

[0800] "Application Example 1"

[0801] (Claim 1)

[0802] A device for inputting information obtained from users,

[0803] An information gathering device that automatically collects related data from an external information source based on the information obtained from the aforementioned input device,

[0804] An evaluation device that compares external information collected by the information collection device with information from the user and evaluates the reliability of the information,

[0805] A display device that presents to the user the reliability of the information evaluated by the evaluation device,

[0806] Based on the aforementioned reliability evaluation, a device provides a reliability score to support the publication of content,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, wherein the information gathering device includes automated information gathering techniques for acquiring data from an external information source.

[0810] (Claim 3)

[0811] The system according to claim 1, wherein the evaluation device performs a reliability evaluation by analyzing the degree of agreement and inconsistencies between the user information and external information using machine learning technology, and calculates a reliability score based on the evaluation.

[0812] "Example 2 of combining an emotion engine"

[0813] (Claim 1)

[0814] A means of inputting information obtained from users,

[0815] A means for automatically collecting relevant data from an external information source based on the information obtained from the aforementioned input means,

[0816] A means for comparing external information collected by the aforementioned information collection means with information from the aforementioned user and for evaluating the reliability of the information,

[0817] The evaluation means includes means for analyzing the user's emotions and performing a reliability evaluation that takes emotional bias into consideration,

[0818] A means for presenting the reliability of the information evaluated by the aforementioned evaluation means according to the user's emotional state,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, wherein the information gathering means includes automated data acquisition means for obtaining data from an external information source.

[0822] (Claim 3)

[0823] The system according to claim 1, wherein the evaluation means performs reliability evaluation by analyzing the degree of agreement and inconsistencies between the user information and external information using machine learning technology.

[0824] "Application example 2 when combining with an emotional engine"

[0825] (Claim 1)

[0826] The information obtained from the user is used as an input method,

[0827] Information gathering means that automatically collects relevant data from external information sources based on the information obtained from the input means,

[0828] An evaluation means that compares external information collected by the information collection means with information from the user and evaluates the reliability of the information,

[0829] A sentiment analysis method that analyzes emotions from information entered by users and integrates those emotions into reliability evaluation,

[0830] A display means that displays the reliability of the information evaluated by the evaluation means according to the user's emotional state,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, wherein the information gathering means includes automated gathering means for obtaining data from an external information source.

[0834] (Claim 3)

[0835] The system according to claim 1, wherein the evaluation means performs reliability evaluation by analyzing the degree of agreement and inconsistencies between the user information and external information using learning model technology. [Explanation of Symbols]

[0836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. The information obtained from the user is used as an input method, Information gathering means that automatically collects relevant data from external information sources based on the information obtained from the input means, An evaluation means that compares external information collected by the information collection means with information from the user and evaluates the reliability of the information, A display means that presents to the user the reliability of the information evaluated by the evaluation means, A system that includes this.

2. The system according to claim 1, wherein the information gathering means includes automated scraping means for obtaining data from an external information source.

3. The system according to claim 1, wherein the evaluation means performs reliability evaluation by analyzing the degree of agreement and inconsistencies between the user information and external information using machine learning technology.

Images