system

Abstract

We provide the system. [Solution] Means for automatically collecting data from information sources, Means for preprocessing the collected data, A means for calculating a reliability score based on preprocessed data, A means of filtering data based on reliability scores, A means of providing filtered data to users, Includes system.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In recent years, a large amount of information has flooded online, including false information and low-reliability information. Therefore, it has become very difficult for users themselves to select highly reliable information from a vast amount of information. In particular, it has become a major issue for companies, researchers, and government agencies that wish to quickly and efficiently obtain information necessary for accurate decision-making. 【Means for Solving the Problems】 【0005】 This invention provides a means for automatically collecting data from information sources, preprocessing that data, and calculating a reliability score. Furthermore, it provides a means for constructing a system that filters the data based on the calculated reliability score and provides users with only carefully selected, highly reliable information. This allows users to easily access highly reliable information. In addition, it provides a means for improving the accuracy of reliability evaluation by analyzing user feedback and updating the algorithm. 【0006】 An "information source" is the starting point for providing digital information such as news articles, social media posts, and websites that are publicly available on the internet. 【0007】 "Means of automatically collecting data" refers to software or hardware systems that use programs to obtain information from specified sources without human intervention. 【0008】 "Preprocessing means" refers to a function that performs a series of processes to remove unnecessary information from collected raw data and convert it into an analyzable format. 【0009】 "Means for calculating reliability scores" refer to algorithms and computational methods for numerically evaluating the reliability of information based on the characteristics of the information source and the quality of its content. 【0010】 A "filtering mechanism" is a system that selects information according to pre-set criteria and implements a process to remove unnecessary or inappropriate information. 【0011】 "Means of providing information to users" refers to methods and means of displaying or distributing filtered information in a format accessible to users. 【0012】 "User feedback" refers to the opinions and evaluations that users give regarding the quality and usefulness of the information provided. 【0013】 "Methods for updating the algorithm" refer to a system that improves the accuracy of the reliability score calculation method by using newly obtained user feedback and accumulated data. [Brief explanation of the drawing] 【0014】 [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] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined. 【Embodiments for Carrying Out the Invention】 【0015】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0016】 First, the terms used in the following description will be explained. 【0017】 In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc. 【0018】 In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0019】 In the following embodiments, a 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 disks (e.g., hard disks), or magnetic tapes, etc. 【0020】 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). 【0021】 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." 【0022】 [First Embodiment] 【0023】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0024】 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. 【0025】 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). 【0026】 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. 【0027】 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. 【0028】 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. 【0029】 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. 【0030】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0031】 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. 【0032】 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. 【0033】 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. 【0034】 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". 【0035】 This invention provides a system for evaluating the reliability of online information and enabling users to efficiently access the accurate information they need. This system primarily consists of a server, terminals, and users, each operating according to its respective role. 【0036】 First, as an initial step initiated by the server, it automatically crawls information from various sources on the internet according to a pre-set schedule. The data collected through crawling is stored in a database in raw data format. The server analyzes this data, preprocesses it to remove unnecessary parts, and generates normalized data. The normalized data is then analyzed by an AI algorithm. Here, the server calculates a reliability score for each source based on parameters that are important for determining the reliability of the information. 【0037】 Next, in the step where the terminal intervenes, filtered and reliable information is received from the server and displayed on the user interface. This display allows for the provision of information tailored to the user's interests and needs, and can be updated in real time. 【0038】 For example, if a user is looking for the latest news on politics, the device receives filtered information relevant to that topic from the server and provides it to the user instantly. This allows the user to make quick and accurate decisions based on reliable information. 【0039】 Furthermore, users can send feedback on the provided information to the server via their device. This feedback is accumulated and periodically analyzed by the server. Based on this, the AI ​​algorithm that calculates the reliability score evolves daily, improving its accuracy. In this way, the system continuously evolves while increasing its reliability, enabling it to provide users with the most optimal information. 【0040】 The following describes the processing flow. 【0041】 Step 1: 【0042】 The server launches a web crawler based on a specified list of information sources, automatically collecting news articles, websites, and social media posts from the internet. The collected information is stored in a database. 【0043】 Step 2: 【0044】 The server performs data preprocessing on the collected information. This process involves removing HTML tags, normalizing special characters, and filtering spam using spam detection algorithms, resulting in clean text data. 【0045】 Step 3: 【0046】 The server applies an AI algorithm to the pre-processed text data to calculate a reliability score for each information source. This algorithm evaluates the source's past performance, the author's credibility, and the accuracy and consistency of the content through linguistic analysis. 【0047】 Step 4: 【0048】 The server filters information based on a calculated reliability score. Information with scores below a set threshold is excluded, and only information exceeding that threshold is selected. This filtered information is then scrutinized to ensure its reliability for the user. 【0049】 Step 5: 【0050】 The device receives filtered information from the server and displays it on the user interface. The information is personalized and presented in the most optimal way based on the user's areas of interest and past behavioral patterns. 【0051】 Step 6: 【0052】 Users view the provided information and input feedback on its quality and content into their device. This feedback is sent to the server in real time and stored in the feedback database. 【0053】 Step 7: 【0054】 The server analyzes regularly collected feedback and improves its AI algorithms to calculate reliability scores more accurately. This aims to continuously improve the system's accuracy and user satisfaction. 【0055】 (Example 1) 【0056】 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." 【0057】 In today's digital information environment, users are required to have quick access to reliable information. However, the increasing diversity and volume of information sources make it difficult to judge reliability and filter out biased information. To solve this problem, a system is needed that can efficiently collect data from information sources and evaluate its reliability. 【0058】 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. 【0059】 In this invention, the server includes means for selectively collecting data from information sources via a digital network, means for analyzing and normalizing the collected data, and means for calculating a score for evaluating reliability based on the normalized data. This enables users to access reliable information quickly and efficiently. 【0060】 A "digital network" refers to an electronic communication infrastructure used to send and receive information, and encompasses wide-area networks such as the internet. 【0061】 "Information sources" refer to media and platforms that provide various data and information, such as websites, news sites, and databases. 【0062】 "Means of selective data collection" refers to methods or processes for collecting data from diverse sources based on specific criteria. 【0063】 "Analysis" refers to the process of thoroughly examining collected data and extracting its structure and content in a way that is easy to understand. 【0064】 "Normalization" is the process of arranging data into a certain standard format, which improves data consistency and compatibility. 【0065】 "Means for calculating a score to evaluate reliability" refers to a method of expressing the reliability of information as a numerical value or indicator and determining its relative reliability. 【0066】 "Users" refer to individuals or organizations that use the system and are the entities that obtain and utilize the information. 【0067】 Regarding embodiments for carrying out the invention, this invention is a system that utilizes a digital network to collect information from multiple information sources and provides reliable information to users. The entire system consists of three main components: a server, a terminal, and a user. 【0068】 The server first collects data from information sources via a digital network. Specifically, it uses common software as a crawling tool (e.g., Scrapy). This makes it possible to obtain HTML data from various digital media such as websites and news portals. 【0069】 Next, the data is analyzed and normalized. The server uses the Python library Pandas to analyze the collected data and organize the necessary information. For example, it identifies the article text and publication date and time, and removes unnecessary information. This process also includes data formatting and removal of special characters. 【0070】 For the organized data, the server applies a machine learning model, such as an AI algorithm using TENSORFLOW®, to calculate a reliability score for each information source. This score is evaluated based on the consistency of the information and its past performance. This reliability score helps determine whether the information meets certain standards. 【0071】 The terminal filters data based on reliability evaluation results from the server and provides appropriate information to the user through the user interface. The user interface used here is updated in real time, ensuring that the latest information is always displayed. 【0072】 Users make decisions based on information provided through their devices. Furthermore, users can send feedback to the server regarding the validity and reliability of the information. The server collects this feedback and uses it to improve the AI ​​algorithm. Natural language processing (NLP) technology is used in this process. 【0073】 For example, if a user requests the latest news on politics, the device retrieves relevant information from the server and provides it instantly. An example of a prompt to be input to the generating AI model is, "Evaluate the reliability of the news article and output a reliability score." 【0074】 This system allows users to quickly access reliable information at all times, supporting efficient decision-making. 【0075】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0076】 Step 1: 【0077】 The server collects data from information sources via a digital network. The input is a list of URLs to be crawled. The server uses a crawling tool to retrieve HTML data from the specified URLs and saves this data in its raw form. This process involves periodic crawling based on a specified schedule. 【0078】 Step 2: 【0079】 The server parses the collected HTML data and extracts the necessary information. The input is the acquired HTML data. The server uses a data analysis library to identify the article text, publication date, author information, etc., and removes unnecessary advertisements and navigation elements. The output is a structured dataset. This normalization process ensures that the data is presented in a unified format. 【0080】 Step 3: 【0081】 The server calculates reliability scores based on normalized data. The input is the structured dataset from the previous step. The server inputs the data into an AI model, evaluates consistency of content, historical reliability data, cross-references, etc., and calculates a reliability score for each information source. The output is the reliability score associated with each article. 【0082】 Step 4: 【0083】 The terminal receives filtered, reliable information from the server and displays it on the user interface. The input is data assigned a reliability score. The terminal filters information based on the user's interests, prioritizing the display of the most relevant information. The output is an organized list of information displayed on the terminal's screen. 【0084】 Step 5: 【0085】 Users make decisions based on information provided through their devices. Users also send feedback from their devices to the server regarding the value and reliability of the information. The input is the user's feedback comments. The server collects this feedback and analyzes it as training data to improve the AI ​​model. The output provides insights for evaluating and improving the algorithm. 【0086】 (Application Example 1) 【0087】 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." 【0088】 In today's world, internet advertising is vast in number, but it often contains unreliable information. Users are at risk of being misled by these ads or being directed to dangerous websites, leading to a growing need to view only safe and trustworthy advertisements. However, current systems often require users to manually judge the reliability of ads, which is time-consuming and carries the risk of misjudgment. Therefore, there is a need to develop a system that balances safety and efficiency, allowing users to browse internet advertisements with peace of mind. 【0089】 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. 【0090】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, means for calculating a reliability score based on the preprocessed data, means for filtering the data based on the reliability score, means for evaluating the reliability of the provided advertising data and selecting and displaying highly reliable advertisements, means for dynamically updating advertising data via the user terminal, and means for improving the accuracy of advertising reliability evaluation based on user feedback. As a result, users can view only highly reliable advertisements, enabling safe internet use. 【0091】 "Information sources" refer to media and areas that provide diverse data on the internet, including websites and social media posts. 【0092】 "Means of automatically collecting data" refers to a system that obtains data from information sources through programs or algorithms without human intervention. 【0093】 "Preprocessing" is the process of removing noise from collected data and converting it into a format suitable for analysis. 【0094】 A "means for calculating reliability scores" refers to a mechanism for calculating a numerical value that evaluates the accuracy and reliability of data, and is carried out based on an algorithm. 【0095】 "A means of filtering data based on reliability scores" refers to a function that selects and handles only data that meets a certain reliability standard. 【0096】 "Means of providing filtered data to users" refers to a mechanism that presents users with selected, reliable data in a visual or other way. 【0097】 A "means for evaluating the reliability of advertising data" is a system that assesses the accuracy of the information contained in an advertisement and the reputation of its source to determine its reliability. 【0098】 "Methods for selecting and displaying highly reliable advertisements" refers to a process that displays only safe and reliable advertisements to users based on evaluation results. 【0099】 "Means of dynamically updating advertising data via the user's device" refers to a system that updates and displays the latest advertising information in real time via the user's device. 【0100】 "Methods for improving the accuracy of ad reliability evaluation based on user feedback" refers to the process of improving the accuracy of ad reliability evaluation systems by incorporating opinions and evaluations from users. 【0101】 The system implementing this invention mainly consists of a server, a user terminal, and an AI algorithm. The server automatically collects advertising data from information sources and stores it in a database. The data is first noise-removed and preprocessed into an appropriate format. The server uses an AI algorithm to evaluate the reliability of the information on this preprocessed data and calculates a reliability score. 【0102】 The user's device displays filtered advertising data received from the server based on the user's preferences. This allows the user to visually see only highly reliable advertisements. By dynamically updating data on the device, the latest information is provided to the user in real time. 【0103】 The AI ​​algorithm implements machine learning models using programming languages ​​such as Python to analyze data and evaluate reliability. This algorithm is designed to improve the accuracy of reliability evaluation over time by utilizing user feedback. The database is built using MySQL® or similar technologies to store and manage reliability scores. 【0104】 A concrete example is the ability to verify that only ads with a certain level of reliability score are displayed to users while they are using a news app on their smartphone. An example of a related prompt from a generative AI would be: "Implement a Python algorithm that evaluates the reliability of ads a user views on their smartphone and displays only highly reliable ads." 【0105】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0106】 Step 1: 【0107】 The server automatically collects advertising data from multiple sources on the internet. The input is a list of URLs of the sources, and the output is raw advertising data. The server uses a web crawler to visit these URLs and retrieve advertising information. 【0108】 Step 2: 【0109】 The server performs preprocessing, such as noise reduction, on the collected data. The input is the raw data collected in step 1, and the output is the normalized data. The server uses regular representation and filtering algorithms to extract only the necessary information. 【0110】 Step 3: 【0111】 The server analyzes pre-processed data using an AI algorithm and calculates a confidence score for each advertisement. The input is normalized data, and the output is the confidence score for each advertisement. The server uses a machine learning model to perform a process of evaluating reliability by comparing it with historical data. 【0112】 Step 4: 【0113】 The server filters and sends only ads that meet the criteria based on their reliability score to the user's device. The input is the calculated reliability score, and the output is the filtered ad data. The server selects ads with high scores and prepares them for transmission according to each user's profile. 【0114】 Step 5: 【0115】 The user's device displays filtered advertising data received from the server. The input is advertising data from the server, and the output is the advertising screen viewed by the user. The device provides an interface for displaying advertisements and visually presents highly reliable advertisements. 【0116】 Step 6: 【0117】 Users provide feedback on the displayed advertisements. This feedback is sent to the server. The input is the user's feedback information, and the output is the feedback data on the server side. Users can submit opinions and evaluations regarding the content of the advertisements and indicate suggestions for improvement. 【0118】 Step 7: 【0119】 The server analyzes user feedback, updates the algorithm for calculating reliability scores, and improves accuracy. The input is user feedback data, and the output is the updated reliability evaluation model. The server learns from the feedback and incorporates this learning into future ad reliability evaluations. 【0120】 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. 【0121】 This invention relates to an information delivery system that incorporates an emotion engine to provide online information to users in the most optimal way. This system selects and delivers information while considering the user's emotional state through interaction between the server, terminal, and user. 【0122】 First, the server collects data such as news articles, web pages, and social media posts from internet sources. This data is preprocessed, undergoing morphological analysis and spam filtering before being stored in a clean database. Next, an AI algorithm is used to calculate a reliability score, and only information that meets certain criteria is filtered out. 【0123】 The system's defining feature, the emotion engine, analyzes the user's emotions through the user interface on the device. Specifically, it infers the user's current emotional state by analyzing user input data, past usage history, and non-verbal cues obtained from voice and images. 【0124】 Once the user's emotional state is analyzed, the device determines the optimal way to deliver information based on the results. For example, if the user is feeling stressed, the device prioritizes calming information and highly entertaining content. On the other hand, if the user wants to improve their concentration, the device adjusts to provide more specialized and detailed information. 【0125】 As a concrete example, suppose a user is using a news app and the emotion engine detects the user's anxiety. In this case, the device will prioritize displaying articles that contribute to relaxation or positive news. The emotion engine also analyzes the user's feedback and updates the server's algorithm to improve the accuracy of information presentation in the future. Through this process, the system becomes more sensitive to the user's emotions over time, enabling more personalized information delivery. 【0126】 Thus, the present invention aims to provide information that not only ensures the reliability of online information but also responds to the user's emotions, thereby offering an optimized information usage experience for each individual user. 【0127】 The following describes the processing flow. 【0128】 Step 1: 【0129】 The server operates web crawlers according to a specified list of information sources, collecting news articles, blogs, and social media posts from the internet. This data is stored in a database in real time. 【0130】 Step 2: 【0131】 The server preprocesses the collected data. This includes removing unnecessary HTML tags, normalizing the text using natural language processing, and filtering out spam. The preprocessed data is then ready for analysis. 【0132】 Step 3: 【0133】 The server runs an AI algorithm that calculates a reliability score on the pre-processed data. The algorithm calculates the score based on the reliability metrics of the information source, the author's rating, and the content of the text. 【0134】 Step 4: 【0135】 The server filters the data based on a calculated reliability score. Only information whose score meets the set criteria is filtered and selected as information of priority value to the user. 【0136】 Step 5: 【0137】 The device receives filtered information from the server and displays it in the user interface. The displayed information is personalized based on the user's past behavior history and interests. 【0138】 Step 6: 【0139】 The device's built-in emotion engine analyzes emotional indicators such as user input data, eye movements, and voice tone to infer the user's emotional state. Based on these results, the information presented and the interface design are dynamically adjusted. 【0140】 Step 7: 【0141】 Users receive information that aligns with their emotions and, if necessary, input feedback into their device. This feedback is used to improve the service experience. 【0142】 Step 8: 【0143】 The server analyzes accumulated user feedback information and uses it to improve the AI ​​algorithm for calculating reliability scores and the accuracy of sentiment recognition. This update will enable the system to provide users with more effective information. 【0144】 (Example 2) 【0145】 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 will be referred to as the "terminal." 【0146】 In today's world, the amount and variety of information available online is vast, but not all of it is reliable, and it is difficult for users to obtain the most relevant information based on their emotional state. Therefore, there is a need for a system that maintains the reliability of online information while providing information that takes into account the individual emotional state of each user. 【0147】 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. 【0148】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, and means for calculating a reliability score based on the preprocessed data. This enables the selection of highly reliable information and the provision of individually optimized information according to the user's emotional state. 【0149】 "Information sources" refer to various sources of data available on the internet, such as news articles, web pages, and social media posts. 【0150】 "Means of automatically collecting data" refers to methods and devices for mechanically acquiring data from internet sources according to conditions specified by a program. 【0151】 "Preprocessing" refers to a series of steps that remove noise and unnecessary information from collected data and prepare it for analysis. 【0152】 A "reliability score" refers to a numerical value calculated to evaluate the accuracy and credibility of information. 【0153】 "Means of filtering data" refers to methods and devices for selecting useful information from unuseful information based on reliability scores. 【0154】 "Means for analyzing a user's emotional state" refers to methods and devices for inferring a user's current psychological state from their input and nonverbal cues. 【0155】 "Means of optimizing and providing information" refers to methods and devices for presenting information in an appropriate content and format according to the user's emotional state. 【0156】 "Feedback refers to the evaluations and opinions that users give in response to the information provided." 【0157】 "Means of updating algorithms" refers to methods or devices for improving the system's operation or decision-making criteria based on received feedback. 【0158】 This information provision system functions through server, terminal, and user interaction to provide optimal information tailored to the user's emotional state. 【0159】 First, the server automatically collects data from multiple sources on the internet and processes it efficiently. Specifically, it uses various RSS feeds and APIs to retrieve news articles, web pages, and social media posts in real time. The server then analyzes the text data using morphological analysis tools (e.g., MeCab) and removes unwanted data using spam filtering software (e.g., general spam filtering software). The cleaned-up information is then securely stored in a database. 【0160】 Next, the server calculates a reliability score for the preprocessed data using a machine learning model (for example, BERT or a Transformer-based model). Based on this score, only information that meets a certain level of reliability is filtered and ready to be provided to the user. 【0161】 Meanwhile, the device analyzes the user's emotional state through the user interface. This analysis is based on user input data, past usage history, and non-verbal cues obtained through voice and images. Here, voice analysis tools (e.g., general voice analysis APIs) and image recognition software (e.g., general-purpose image recognition systems) are used to analyze the user's emotions in detail. 【0162】 After determining the user's emotional state, the device decides how to provide information appropriate to that state. For example, a user experiencing stress will be prioritized with articles that promote relaxation and positive content. On the other hand, a user who wants to improve their concentration will be provided with highly specialized and detailed information. 【0163】 As a concrete example, if a user expresses anxiety while reviewing economic news, the device will strive to prioritize providing articles about economic stability and positive future outlooks. In this case, by inputting a prompt message to the generation AI model such as, "Generate positive economic news to alleviate the user's anxiety," the device will generate and provide appropriate content. 【0164】 Through this process, the system can provide optimal information tailored to the individual needs of each user, and its accuracy can be further improved through continuous feedback. 【0165】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0166】 Step 1: 【0167】 The server automatically collects data from information sources on the internet. Specifically, it retrieves article and post data from multiple news sites and social media platforms via RSS feeds and APIs. Input requires URLs and API keys from various information sources, and the output is raw, unprocessed data. 【0168】 Step 2: 【0169】 The server preprocesses the collected raw data. It analyzes the text data using morphological analysis tools and removes noise by performing spam filtering. It takes raw data as input, applies morphological analysis and spam detection, and outputs clean text data. 【0170】 Step 3: 【0171】 The server calculates a confidence score for pre-processed, clean data. A machine learning model is applied to quantify the confidence level of each piece of information. This process takes clean text data as input, calculates a score using a confidence evaluation algorithm, and produces an output that selects the most reliable information. 【0172】 Step 4: 【0173】 The server filters the data based on its reliability score. Only data with a score above a certain level is selected to proceed to the next step. The input is data with a reliability score, and the output provides filtered, useful information. 【0174】 Step 5: 【0175】 The device analyzes the user's emotional state through its user interface. It determines emotions by analyzing user input data and nonverbal cues. It takes data from voice analysis and facial recognition as input and outputs analysis results indicating the user's emotional state. 【0176】 Step 6: 【0177】 The device determines the optimal information delivery method based on the analysis results. It prompts an AI model that generates prompts tailored to the user's emotions, and then generates appropriate content. It uses the results of the emotion analysis as input and outputs professional articles or relaxing content. 【0178】 Step 7: 【0179】 Users send feedback to their devices based on the information provided. Through this feedback, the system understands the user's needs. The system receives feedback data as input and outputs it as data to improve future information provision. 【0180】 Step 8: 【0181】 The server updates the algorithm using the collected feedback. It applies machine learning and adjusts the algorithm's parameters according to user feedback. This process takes feedback data as input and outputs an updated algorithm, improving the accuracy of future information provision. 【0182】 (Application Example 2) 【0183】 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". 【0184】 In today's information-saturated world, users spend a great deal of time and effort accessing the most relevant information. Furthermore, information provided without considering the user's emotional state is not necessarily valuable to them. Therefore, there is a need to build systems that efficiently provide reliable information while taking the user's emotional state into account. 【0185】 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. 【0186】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, means for calculating a reliability score based on the preprocessed data, means for filtering the data based on the reliability score, means for analyzing the user's emotional state, and means for selecting and providing data based on the emotional state. This makes it possible to provide optimal information in accordance with the user's emotions. 【0187】 "Information sources" refer to the starting point for collecting data, and include various online content such as news articles, websites, and social media posts. 【0188】 "Means for automatically collecting data" refers to system components that perform the process of obtaining necessary data from information sources without manual intervention. 【0189】 "Means for preprocessing data" refer to system components that perform initial processing to make collected data clean and ready for analysis. 【0190】 A "means for calculating reliability scores" refers to a system component used to quantify and evaluate the reliability and validity of data. 【0191】 A "means of filtering data" refers to a system component that selects only the necessary data based on reliability scores and removes unnecessary or inaccurate data. 【0192】 A "means for analyzing a user's emotional state" refers to a system component that uses user input and nonverbal cues to determine the user's emotions at any given time. 【0193】 "Means for selecting and providing data based on emotional state" refers to system components that select and provide information in accordance with the determined emotions of the user. 【0194】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. First, the server automatically collects data from a wide variety of information sources on the internet, specifically from news articles, websites, and social media posts. The collected data is preprocessed to remove unnecessary elements and noise and stored in a clean state. Natural language processing tools are used in this process. 【0195】 Next, the server calculates a reliability score for the preprocessed data. This uses machine learning algorithms to objectively evaluate the truthfulness and quality of the data. Based on the reliability score, the server further filters the data to select only the meaningful information to provide to the user. 【0196】 The device handles user interaction. It incorporates an emotion engine that analyzes user input, past usage history, and nonverbal cues to determine the user's emotional state. This process utilizes deep learning frameworks such as TensorFlow and PyTorch. Based on the emotion analysis, it presents information from the server in the most optimal way. For example, if the user is stressed, it prioritizes providing content with relaxation effects. 【0197】 The feedback users provide while using the system is collected and analyzed by the server. This improves the accuracy of the information provided and optimizes the sentiment engine. Based on this feedback, the server updates its algorithms, improving the overall system performance over time. 【0198】 As a concrete example, suppose a user is using the system to search for entertainment content, and the emotion engine detects the user's relaxed state. In this case, the system will prioritize recommending calming music or soothing videos. Furthermore, by utilizing a generative AI model, it is possible to provide appropriate recommendations in response to an input prompt such as, "I've been feeling stressed lately, so I'm looking for relaxing content." 【0199】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0200】 Step 1: 【0201】 The server automatically collects data from information sources on the internet. The input is various information sources, and the output is the collected raw data. This process uses a web crawler to periodically retrieve information from specified websites and social media. 【0202】 Step 2: 【0203】 The server preprocesses the collected data. The input is raw data, and the output is clean data. Morphological analysis and spam filtering are performed to remove unnecessary elements and improve the quality of the data. 【0204】 Step 3: 【0205】 The server calculates a confidence score based on pre-processed data. The input is clean data, and the output is a confidence score for each data point. A machine learning algorithm is used to evaluate the accuracy and reliability of the data. This algorithm analyzes the current data in relation to historical data. 【0206】 Step 4: 【0207】 The server filters data based on reliability scores. The input is scored data, and the output is reliable data. A certain lower score threshold is set, and data that does not meet this criterion is excluded. 【0208】 Step 5: 【0209】 The device analyzes the user's emotional state. Input consists of user input data, past history, and nonverbal cues, and output is an estimated emotional state of the user. Audio and image data are analyzed using TensorFlow or PyTorch, and then analyzed by an emotion engine. 【0210】 Step 6: 【0211】 The device filters and selects data based on the user's emotional state, presenting it in the most optimal way. Input consists of established data and emotional states, while output is personalized information presented to the user. For example, it might prioritize light music when the user is relaxed, or specialized content when they need to concentrate. 【0212】 Step 7: 【0213】 Users provide feedback on the information presented. The input is the user's feedback, and the output is the feedback data sent to the server. This feedback serves as a valuable source of information for improving system performance. 【0214】 Step 8: 【0215】 The server analyzes feedback received from the user and updates the algorithm through a generative AI model. The input is user feedback data, and the output is an enhanced algorithm. This improves the accuracy of the information provided in the future and enhances the user experience. Based on data generated from the prompt "I've been feeling stressed lately, so I'm looking for some relaxing content," content delivery becomes even more personalized. 【0216】 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. 【0217】 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. 【0218】 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. 【0219】 [Second Embodiment] 【0220】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0221】 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. 【0222】 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). 【0223】 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. 【0224】 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. 【0225】 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). 【0226】 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. 【0227】 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. 【0228】 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. 【0229】 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. 【0230】 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. 【0231】 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". 【0232】 This invention provides a system for evaluating the reliability of online information and enabling users to efficiently access the accurate information they need. This system primarily consists of a server, terminals, and users, each operating according to its respective role. 【0233】 First, as an initial step initiated by the server, it automatically crawls information from various sources on the internet according to a pre-set schedule. The data collected through crawling is stored in a database in raw data format. The server analyzes this data, preprocesses it to remove unnecessary parts, and generates normalized data. The normalized data is then analyzed by an AI algorithm. Here, the server calculates a reliability score for each source based on parameters that are important for determining the reliability of the information. 【0234】 Next, in the step where the terminal intervenes, filtered and reliable information is received from the server and displayed on the user interface. This display allows for the provision of information tailored to the user's interests and needs, and can be updated in real time. 【0235】 For example, if a user is looking for the latest news on politics, the device receives filtered information relevant to that topic from the server and provides it to the user instantly. This allows the user to make quick and accurate decisions based on reliable information. 【0236】 Furthermore, users can send feedback on the provided information to the server via their device. This feedback is accumulated and periodically analyzed by the server. Based on this, the AI ​​algorithm that calculates the reliability score evolves daily, improving its accuracy. In this way, the system continuously evolves while increasing its reliability, enabling it to provide users with the most optimal information. 【0237】 The following describes the processing flow. 【0238】 Step 1: 【0239】 The server launches a web crawler based on a specified list of information sources, automatically collecting news articles, websites, and social media posts from the internet. The collected information is stored in a database. 【0240】 Step 2: 【0241】 The server performs data preprocessing on the collected information. This process involves removing HTML tags, normalizing special characters, and filtering spam using spam detection algorithms, resulting in clean text data. 【0242】 Step 3: 【0243】 The server applies an AI algorithm to the pre-processed text data to calculate a reliability score for each information source. This algorithm evaluates the source's past performance, the author's credibility, and the accuracy and consistency of the content through linguistic analysis. 【0244】 Step 4: 【0245】 The server filters information based on a calculated reliability score. Information with scores below a set threshold is excluded, and only information exceeding that threshold is selected. This filtered information is then scrutinized to ensure its reliability for the user. 【0246】 Step 5: 【0247】 The device receives filtered information from the server and displays it on the user interface. The information is personalized and presented in the most optimal way based on the user's areas of interest and past behavioral patterns. 【0248】 Step 6: 【0249】 Users view the provided information and input feedback on its quality and content into their device. This feedback is sent to the server in real time and stored in the feedback database. 【0250】 Step 7: 【0251】 The server analyzes regularly collected feedback and improves its AI algorithms to calculate reliability scores more accurately. This aims to continuously improve the system's accuracy and user satisfaction. 【0252】 (Example 1) 【0253】 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." 【0254】 In today's digital information environment, users are required to have quick access to reliable information. However, the increasing diversity and volume of information sources make it difficult to judge reliability and filter out biased information. To solve this problem, a system is needed that can efficiently collect data from information sources and evaluate its reliability. 【0255】 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. 【0256】 In this invention, the server includes means for selectively collecting data from information sources via a digital network, means for analyzing and normalizing the collected data, and means for calculating a score for evaluating reliability based on the normalized data. This enables users to access reliable information quickly and efficiently. 【0257】 A "digital network" refers to an electronic communication infrastructure used to send and receive information, and encompasses wide-area networks such as the internet. 【0258】 "Information sources" refer to media and platforms that provide various data and information, such as websites, news sites, and databases. 【0259】 "Means of selective data collection" refers to methods or processes for collecting data from diverse sources based on specific criteria. 【0260】 "Analysis" refers to the process of thoroughly examining collected data and extracting its structure and content in a way that is easy to understand. 【0261】 "Normalization" is the process of arranging data into a certain standard format, which improves data consistency and compatibility. 【0262】 "Means for calculating a score to evaluate reliability" refers to a method of expressing the reliability of information as a numerical value or indicator and determining its relative reliability. 【0263】 "Users" refer to individuals or organizations that use the system and are the entities that obtain and utilize the information. 【0264】 Regarding the embodiment for carrying out the invention, this invention is a system that utilizes a digital network to collect information from multiple information sources and provides reliable information to users. The entire system consists of three main components: a server, a terminal, and a user. 【0265】 The server first collects data from information sources via a digital network. Specifically, it uses common software as a crawling tool (e.g., Scrapy). This makes it possible to obtain HTML data from various digital media such as websites and news portals. 【0266】 Next, the data is analyzed and normalized. The server uses the Python library Pandas to analyze the collected data and organize the necessary information. For example, it identifies the article text and publication date and time, and removes unnecessary information. This process also includes data formatting and removal of special characters. 【0267】 For the organized data, the server applies a machine learning model, such as an AI algorithm using TensorFlow, to calculate a reliability score for each information source. This score is evaluated based on the consistency of the information and its past performance. This reliability score helps determine whether the information meets certain criteria. 【0268】 The terminal filters data based on reliability evaluation results from the server and provides appropriate information to the user through the user interface. The user interface used here is updated in real time, ensuring that the latest information is always displayed. 【0269】 Users make decisions based on information provided through their devices. Furthermore, users can send feedback to the server regarding the validity and reliability of the information. The server collects this feedback and uses it to improve the AI ​​algorithm. Natural language processing (NLP) technology is used in this process. 【0270】 For example, if a user requests the latest news on politics, the device retrieves relevant information from the server and provides it instantly. An example of a prompt to be input to the generating AI model is, "Evaluate the reliability of the news article and output a reliability score." 【0271】 This system allows users to quickly access reliable information at all times, supporting efficient decision-making. 【0272】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0273】 Step 1: 【0274】 The server collects data from information sources via a digital network. The input is a list of URLs to be crawled. The server uses a crawling tool to retrieve HTML data from the specified URLs and saves this data in its raw form. This process involves periodic crawling based on a specified schedule. 【0275】 Step 2: 【0276】 The server parses the collected HTML data and extracts the necessary information. The input is the acquired HTML data. The server uses a data analysis library to identify the article text, publication date, author information, etc., and removes unnecessary advertisements and navigation elements. The output is a structured dataset. This normalization process ensures that the data is presented in a unified format. 【0277】 Step 3: 【0278】 The server calculates reliability scores based on normalized data. The input is the structured dataset from the previous step. The server inputs the data into an AI model, evaluates consistency of content, historical reliability data, cross-references, etc., and calculates a reliability score for each information source. The output is the reliability score associated with each article. 【0279】 Step 4: 【0280】 The terminal receives filtered, reliable information from the server and displays it on the user interface. The input is data assigned a reliability score. The terminal filters information based on the user's interests, prioritizing the display of the most relevant information. The output is an organized list of information displayed on the terminal's screen. 【0281】 Step 5: 【0282】 The user makes decisions based on the information provided through the terminal. The user further sends feedback on the value and reliability of the information from the terminal to the server. The input is the feedback comment from the user. The server collects this feedback and analyzes it as learning data for improving the AI model. The output is insights for evaluating and improving the algorithm. 【0283】 (Application Example 1) 【0284】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal". 【0285】 In modern Internet advertising, while the number is huge, it often contains low - reliability information. Since users are at risk of being induced by such advertisements to incorrect information or dangerous sites, the need to view only safe and reliable advertisements is increasing. However, in the current system, users often have to manually judge the reliability of advertisements, which involves time and the risk of misjudgment. Therefore, it is necessary to develop a system that allows users to view Internet advertisements with confidence while achieving both safety and efficiency. 【0286】 The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0287】 In this invention, the server includes means for automatically collecting data from information sources, means for pre - processing the collected data, means for calculating a reliability score based on the pre - processed data, means for filtering data based on the reliability score, means for evaluating the reliability of the provided advertisement data and selectively displaying high - reliability advertisements, means for dynamically updating advertisement data via the user terminal, and means for improving the evaluation accuracy of advertisement reliability based on user feedback. Thereby, the user can view only high - reliability advertisements and can use the Internet safely. 【0288】 "Information sources" refer to media and areas that provide diverse data on the internet, including websites and social media posts. 【0289】 "Means of automatically collecting data" refers to a system that obtains data from information sources through programs or algorithms without human intervention. 【0290】 "Preprocessing" is the process of removing noise from collected data and converting it into a format suitable for analysis. 【0291】 A "means for calculating reliability scores" refers to a mechanism for calculating a numerical value that evaluates the accuracy and reliability of data, and is carried out based on an algorithm. 【0292】 "A means of filtering data based on reliability scores" refers to a function that selects and handles only data that meets a certain reliability standard. 【0293】 "Means of providing filtered data to users" refers to a mechanism that presents users with selected, reliable data in a visual or other way. 【0294】 A "means for evaluating the reliability of advertising data" is a system that assesses the accuracy of the information contained in an advertisement and the reputation of its source to determine its reliability. 【0295】 "Methods for selecting and displaying highly reliable advertisements" refers to a process that displays only safe and reliable advertisements to users based on evaluation results. 【0296】 "Means of dynamically updating advertising data via the user's device" refers to a system that updates and displays the latest advertising information in real time via the user's device. 【0297】 "Methods for improving the accuracy of ad reliability evaluation based on user feedback" refers to the process of improving the accuracy of ad reliability evaluation systems by incorporating opinions and evaluations from users. 【0298】 The system implementing this invention mainly consists of a server, a user terminal, and an AI algorithm. The server automatically collects advertising data from information sources and stores it in a database. The data is first noise-removed and preprocessed into an appropriate format. The server uses an AI algorithm to evaluate the reliability of the information on this preprocessed data and calculates a reliability score. 【0299】 The user's device displays filtered advertising data received from the server based on the user's preferences. This allows the user to visually see only highly reliable advertisements. By dynamically updating data on the device, the latest information is provided to the user in real time. 【0300】 The AI ​​algorithm implements machine learning models using programming languages ​​such as Python to analyze data and evaluate reliability. This algorithm is designed to improve the accuracy of reliability evaluations over time by utilizing user feedback. A database, such as MySQL, is built to store and manage reliability scores. 【0301】 A concrete example is the ability to verify that only ads with a certain level of reliability score are displayed to users while they are using a news app on their smartphone. An example of a related prompt from a generative AI would be: "Implement a Python algorithm that evaluates the reliability of ads a user views on their smartphone and displays only highly reliable ads." 【0302】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0303】 Step 1: 【0304】 The server automatically collects advertising data from multiple information sources on the Internet. The input is a list of URLs of the information sources, and the output is raw advertising data. The server uses a web crawler to visit these URLs and obtain advertising information. 【0305】 Step 2: 【0306】 The server performs preprocessing such as noise removal on the collected data. The input is the raw data collected in Step 1, and the output is normalized data. The server uses regular expressions and filtering algorithms to extract only the necessary information. 【0307】 Step 3: 【0308】 The server analyzes the preprocessed data with AI algorithms and calculates the reliability score for each advertisement. The input is the normalized data, and the output is the reliability score for each advertisement. The server uses a machine learning model to execute a process of evaluating reliability in comparison with past data. 【0309】 Step 4: 【0310】 The server filters only the advertisements that meet the criteria based on the reliability score and sends them to the user terminal. The input is the calculated reliability score, and the output is the filtered advertising data. The server selects advertisements with high scores and prepares for transmission according to the profile of each user. 【0311】 Step 5: 【0312】 The user terminal displays the filtered advertising data received from the server. The input is the advertising data from the server, and the output is the advertising screen that the user views. The terminal prepares an interface for advertising display and visually shows highly reliable advertisements. 【0313】 Step 6: 【0314】 Users provide feedback on the displayed advertisements. This feedback is sent to the server. The input is the user's feedback information, and the output is the feedback data on the server side. Users can submit opinions and evaluations regarding the content of the advertisements and indicate suggestions for improvement. 【0315】 Step 7: 【0316】 The server analyzes user feedback, updates the algorithm for calculating reliability scores, and improves accuracy. The input is user feedback data, and the output is the updated reliability evaluation model. The server learns from the feedback and incorporates this learning into future ad reliability evaluations. 【0317】 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. 【0318】 This invention relates to an information delivery system that incorporates an emotion engine to provide online information to users in the most optimal way. This system selects and delivers information while considering the user's emotional state through interaction between the server, terminal, and user. 【0319】 First, the server collects data such as news articles, web pages, and social media posts from internet sources. This data is preprocessed, undergoing morphological analysis and spam filtering before being stored in a clean database. Next, an AI algorithm is used to calculate a reliability score, and only information that meets certain criteria is filtered out. 【0320】 The system's defining feature, the emotion engine, analyzes the user's emotions through the user interface on the device. Specifically, it infers the user's current emotional state by analyzing user input data, past usage history, and non-verbal cues obtained from voice and images. 【0321】 Once the user's emotional state is analyzed, the device determines the optimal way to deliver information based on the results. For example, if the user is feeling stressed, the device prioritizes calming information and highly entertaining content. On the other hand, if the user wants to improve their concentration, the device adjusts to provide more specialized and detailed information. 【0322】 As a concrete example, suppose a user is using a news app and the emotion engine detects the user's anxiety. In this case, the device will prioritize displaying articles that contribute to relaxation or positive news. The emotion engine also analyzes the user's feedback and updates the server's algorithm to improve the accuracy of information presentation in the future. Through this process, the system becomes more sensitive to the user's emotions over time, enabling more personalized information delivery. 【0323】 Thus, the present invention aims to provide information that not only ensures the reliability of online information but also responds to the user's emotions, thereby offering an optimized information usage experience for each individual user. 【0324】 The following describes the processing flow. 【0325】 Step 1: 【0326】 The server operates web crawlers according to a specified list of information sources, collecting news articles, blogs, and social media posts from the internet. This data is stored in a database in real time. 【0327】 Step 2: 【0328】 The server preprocesses the collected data. This includes removing unnecessary HTML tags, normalizing the text using natural language processing, and filtering out spam. The preprocessed data is then ready for analysis. 【0329】 Step 3: 【0330】 The server runs an AI algorithm that calculates a reliability score on the pre-processed data. The algorithm calculates the score based on the reliability metrics of the information source, the author's rating, and the content of the text. 【0331】 Step 4: 【0332】 The server filters the data based on a calculated reliability score. Only information whose score meets the set criteria is filtered and selected as information of priority value to the user. 【0333】 Step 5: 【0334】 The device receives filtered information from the server and displays it in the user interface. The displayed information is personalized based on the user's past behavior history and interests. 【0335】 Step 6: 【0336】 The device's built-in emotion engine analyzes emotional indicators such as user input data, eye movements, and voice tone to infer the user's emotional state. Based on these results, the information presented and the interface design are dynamically adjusted. 【0337】 Step 7: 【0338】 Users receive information that aligns with their emotions and, if necessary, input feedback into their device. This feedback is used to improve the service experience. 【0339】 Step 8: 【0340】 The server analyzes accumulated user feedback information and uses it to improve the AI ​​algorithm for calculating reliability scores and the accuracy of sentiment recognition. This update will enable the system to provide users with more effective information. 【0341】 (Example 2) 【0342】 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". 【0343】 In today's world, the amount and variety of information available online is vast, but not all of it is reliable, and it is difficult for users to obtain the most relevant information based on their emotional state. Therefore, there is a need for a system that maintains the reliability of online information while providing information that takes into account the individual emotional state of each user. 【0344】 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. 【0345】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, and means for calculating a reliability score based on the preprocessed data. This enables the selection of highly reliable information and the provision of individually optimized information according to the user's emotional state. 【0346】 "Information sources" refer to various sources of data available on the internet, such as news articles, web pages, and social media posts. 【0347】 "Means of automatically collecting data" refers to methods and devices for mechanically acquiring data from internet sources according to conditions specified by a program. 【0348】 "Preprocessing" refers to a series of steps that remove noise and unnecessary information from collected data and prepare it for analysis. 【0349】 A "reliability score" refers to a numerical value calculated to evaluate the accuracy and credibility of information. 【0350】 "Means of filtering data" refers to methods and devices for selecting useful information from unuseful information based on reliability scores. 【0351】 "Means for analyzing a user's emotional state" refers to methods and devices for inferring a user's current psychological state from their input and nonverbal cues. 【0352】 "Means of optimizing and providing information" refers to methods and devices for presenting information in an appropriate content and format according to the user's emotional state. 【0353】 "Feedback refers to the evaluations and opinions that users give in response to the information provided." 【0354】 "Means of updating algorithms" refers to methods or devices for improving the system's operation or decision-making criteria based on received feedback. 【0355】 This information provision system functions through server, terminal, and user interaction to provide optimal information tailored to the user's emotional state. 【0356】 First, the server automatically collects data from multiple sources on the internet and processes it efficiently. Specifically, it uses various RSS feeds and APIs to retrieve news articles, web pages, and social media posts in real time. The server then analyzes the text data using morphological analysis tools (e.g., MeCab) and removes unwanted data using spam filtering software (e.g., general spam filtering software). The cleaned-up information is then securely stored in a database. 【0357】 Next, the server calculates a reliability score for the preprocessed data using a machine learning model (for example, BERT or a Transformer-based model). Based on this score, only information that meets a certain level of reliability is filtered and ready to be provided to the user. 【0358】 Meanwhile, the device analyzes the user's emotional state through the user interface. This analysis is based on user input data, past usage history, and non-verbal cues obtained through voice and images. Here, voice analysis tools (e.g., general voice analysis APIs) and image recognition software (e.g., general-purpose image recognition systems) are used to analyze the user's emotions in detail. 【0359】 After determining the user's emotional state, the device decides how to provide information appropriate to that state. For example, a user experiencing stress will be prioritized with articles that promote relaxation and positive content. On the other hand, a user who wants to improve their concentration will be provided with highly specialized and detailed information. 【0360】 As a concrete example, if a user expresses anxiety while reviewing economic news, the device will strive to prioritize providing articles about economic stability and positive future outlooks. In this case, by inputting a prompt message to the generation AI model such as, "Generate positive economic news to alleviate the user's anxiety," the device will generate and provide appropriate content. 【0361】 Through this process, the system can provide optimal information tailored to the individual needs of each user, and its accuracy can be further improved through continuous feedback. 【0362】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0363】 Step 1: 【0364】 The server automatically collects data from information sources on the internet. Specifically, it retrieves article and post data from multiple news sites and social media platforms via RSS feeds and APIs. Input requires URLs and API keys from various information sources, and the output is raw, unprocessed data. 【0365】 Step 2: 【0366】 The server preprocesses the collected raw data. It analyzes the text data using morphological analysis tools and removes noise by performing spam filtering. It takes raw data as input, applies morphological analysis and spam detection, and outputs clean text data. 【0367】 Step 3: 【0368】 The server calculates a confidence score for pre-processed, clean data. A machine learning model is applied to quantify the confidence level of each piece of information. This process takes clean text data as input, calculates a score using a confidence evaluation algorithm, and produces an output that selects the most reliable information. 【0369】 Step 4: 【0370】 The server filters the data based on its reliability score. Only data with a score above a certain level is selected to proceed to the next step. The input is data with a reliability score, and the output provides filtered, useful information. 【0371】 Step 5: 【0372】 The device analyzes the user's emotional state through its user interface. It determines emotions by analyzing user input data and nonverbal cues. It takes data from voice analysis and facial recognition as input and outputs analysis results indicating the user's emotional state. 【0373】 Step 6: 【0374】 The device determines the optimal information delivery method based on the analysis results. It prompts an AI model that generates prompts tailored to the user's emotions, and then generates appropriate content. It uses the results of the emotion analysis as input and outputs professional articles or relaxing content. 【0375】 Step 7: 【0376】 Users send feedback to their devices based on the information provided. Through this feedback, the system understands the user's needs. The system receives feedback data as input and outputs it as data to improve future information provision. 【0377】 Step 8: 【0378】 The server updates the algorithm using the collected feedback. It applies machine learning and adjusts the algorithm's parameters according to user feedback. This process takes feedback data as input and outputs an updated algorithm, improving the accuracy of future information provision. 【0379】 (Application Example 2) 【0380】 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." 【0381】 In today's information-saturated world, users spend a great deal of time and effort accessing the most relevant information. Furthermore, information provided without considering the user's emotional state is not necessarily valuable to them. Therefore, there is a need to build systems that efficiently provide reliable information while taking the user's emotional state into account. 【0382】 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. 【0383】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, means for calculating a reliability score based on the preprocessed data, means for filtering the data based on the reliability score, means for analyzing the user's emotional state, and means for selecting and providing data based on the emotional state. This makes it possible to provide optimal information in accordance with the user's emotions. 【0384】 "Information sources" refer to the starting point for collecting data, and include various online content such as news articles, websites, and social media posts. 【0385】 "Means for automatically collecting data" refers to system components that perform the process of obtaining necessary data from information sources without manual intervention. 【0386】 "Means for preprocessing data" refer to system components that perform initial processing to make collected data clean and ready for analysis. 【0387】 A "means for calculating reliability scores" refers to a system component used to quantify and evaluate the reliability and validity of data. 【0388】 A "means of filtering data" refers to a system component that selects only the necessary data based on reliability scores and removes unnecessary or inaccurate data. 【0389】 A "means for analyzing a user's emotional state" refers to a system component that uses user input and nonverbal cues to determine the user's emotions at any given time. 【0390】 "Means for selecting and providing data based on emotional state" refers to system components that select and provide information in accordance with the determined emotions of the user. 【0391】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. First, the server automatically collects data from a wide variety of information sources on the internet, specifically from news articles, websites, and social media posts. The collected data is preprocessed to remove unnecessary elements and noise and stored in a clean state. Natural language processing tools are used in this process. 【0392】 Next, the server calculates a reliability score for the preprocessed data. This uses machine learning algorithms to objectively evaluate the truthfulness and quality of the data. Based on the reliability score, the server further filters the data to select only the meaningful information to provide to the user. 【0393】 The device handles user interaction. It incorporates an emotion engine that analyzes user input, past usage history, and nonverbal cues to determine the user's emotional state. This process utilizes deep learning frameworks such as TensorFlow and PyTorch. Based on the emotion analysis, it presents information from the server in the most optimal way. For example, if the user is stressed, it prioritizes providing content with relaxation effects. 【0394】 The feedback users provide while using the system is collected and analyzed by the server. This improves the accuracy of the information provided and optimizes the sentiment engine. Based on this feedback, the server updates its algorithms, improving the overall system performance over time. 【0395】 As a concrete example, suppose a user is using the system to search for entertainment content, and the emotion engine detects the user's relaxed state. In this case, the system will prioritize recommending calming music or soothing videos. Furthermore, by utilizing a generative AI model, it is possible to provide appropriate recommendations in response to an input prompt such as, "I've been feeling stressed lately, so I'm looking for relaxing content." 【0396】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0397】 Step 1: 【0398】 The server automatically collects data from information sources on the internet. The input is various information sources, and the output is the collected raw data. This process uses a web crawler to periodically retrieve information from specified websites and social media. 【0399】 Step 2: 【0400】 The server preprocesses the collected data. The input is raw data, and the output is clean data. Morphological analysis and spam filtering are performed to remove unnecessary elements and improve the quality of the data. 【0401】 Step 3: 【0402】 The server calculates a confidence score based on pre-processed data. The input is clean data, and the output is a confidence score for each data point. A machine learning algorithm is used to evaluate the accuracy and reliability of the data. This algorithm analyzes the current data in relation to historical data. 【0403】 Step 4: 【0404】 The server filters data based on reliability scores. The input is scored data, and the output is reliable data. A certain lower score threshold is set, and data that does not meet this criterion is excluded. 【0405】 Step 5: 【0406】 The device analyzes the user's emotional state. Input consists of user input data, past history, and nonverbal cues, and output is an estimated emotional state of the user. Audio and image data are analyzed using TensorFlow or PyTorch, and then analyzed by an emotion engine. 【0407】 Step 6: 【0408】 The device filters and selects data based on the user's emotional state, presenting it in the most optimal way. Input consists of established data and emotional states, while output is personalized information presented to the user. For example, it might prioritize light music when the user is relaxed, or specialized content when they need to concentrate. 【0409】 Step 7: 【0410】 Users provide feedback on the information presented. The input is the user's feedback, and the output is the feedback data sent to the server. This feedback serves as a valuable source of information for improving system performance. 【0411】 Step 8: 【0412】 The server analyzes feedback received from the user and updates the algorithm through a generative AI model. The input is user feedback data, and the output is an enhanced algorithm. This improves the accuracy of the information provided in the future and enhances the user experience. Based on data generated from the prompt "I've been feeling stressed lately, so I'm looking for some relaxing content," content delivery becomes even more personalized. 【0413】 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. 【0414】 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. 【0415】 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. 【0416】 [Third Embodiment] 【0417】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0418】 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. 【0419】 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). 【0420】 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. 【0421】 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. 【0422】 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). 【0423】 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. 【0424】 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. 【0425】 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. 【0426】 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. 【0427】 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. 【0428】 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". 【0429】 This invention provides a system for evaluating the reliability of online information and enabling users to efficiently access the accurate information they need. This system primarily consists of a server, terminals, and users, each operating according to its respective role. 【0430】 First, as an initial step initiated by the server, it automatically crawls information from various sources on the internet according to a pre-set schedule. The data collected through crawling is stored in a database in raw data format. The server analyzes this data, preprocesses it to remove unnecessary parts, and generates normalized data. The normalized data is then analyzed by an AI algorithm. Here, the server calculates a reliability score for each source based on parameters that are important for determining the reliability of the information. 【0431】 Next, in the step where the terminal intervenes, filtered and reliable information is received from the server and displayed on the user interface. This display allows for the provision of information tailored to the user's interests and needs, and can be updated in real time. 【0432】 For example, if a user is looking for the latest news on politics, the device receives filtered information relevant to that topic from the server and provides it to the user instantly. This allows the user to make quick and accurate decisions based on reliable information. 【0433】 Furthermore, users can send feedback on the provided information to the server via their device. This feedback is accumulated and periodically analyzed by the server. Based on this, the AI ​​algorithm that calculates the reliability score evolves daily, improving its accuracy. In this way, the system continuously evolves while increasing its reliability, enabling it to provide users with the most optimal information. 【0434】 The following describes the processing flow. 【0435】 Step 1: 【0436】 The server launches a web crawler based on a specified list of information sources, automatically collecting news articles, websites, and social media posts from the internet. The collected information is stored in a database. 【0437】 Step 2: 【0438】 The server performs data preprocessing on the collected information. This process involves removing HTML tags, normalizing special characters, and filtering spam using spam detection algorithms, resulting in clean text data. 【0439】 Step 3: 【0440】 The server applies an AI algorithm to the pre-processed text data to calculate a reliability score for each information source. This algorithm evaluates the source's past performance, the author's credibility, and the accuracy and consistency of the content through linguistic analysis. 【0441】 Step 4: 【0442】 The server filters information based on a calculated reliability score. Information with scores below a set threshold is excluded, and only information exceeding that threshold is selected. This filtered information is then scrutinized to ensure its reliability for the user. 【0443】 Step 5: 【0444】 The device receives filtered information from the server and displays it on the user interface. The information is personalized and presented in the most optimal way based on the user's areas of interest and past behavioral patterns. 【0445】 Step 6: 【0446】 Users view the provided information and input feedback on its quality and content into their device. This feedback is sent to the server in real time and stored in the feedback database. 【0447】 Step 7: 【0448】 The server analyzes regularly collected feedback and improves its AI algorithms to calculate reliability scores more accurately. This aims to continuously improve the system's accuracy and user satisfaction. 【0449】 (Example 1) 【0450】 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." 【0451】 In today's digital information environment, users are required to have quick access to reliable information. However, the increasing diversity and volume of information sources make it difficult to judge reliability and filter out biased information. To solve this problem, a system is needed that can efficiently collect data from information sources and evaluate its reliability. 【0452】 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. 【0453】 In this invention, the server includes means for selectively collecting data from information sources via a digital network, means for analyzing and normalizing the collected data, and means for calculating a score for evaluating reliability based on the normalized data. This enables users to access reliable information quickly and efficiently. 【0454】 A "digital network" refers to an electronic communication infrastructure used to send and receive information, and encompasses wide-area networks such as the internet. 【0455】 "Information sources" refer to media and platforms that provide various data and information, such as websites, news sites, and databases. 【0456】 "Means of selective data collection" refers to methods or processes for collecting data from diverse sources based on specific criteria. 【0457】 "Analysis" refers to the process of thoroughly examining collected data and extracting its structure and content in a way that is easy to understand. 【0458】 "Normalization" is the process of arranging data into a certain standard format, which improves data consistency and compatibility. 【0459】 "Means for calculating a score to evaluate reliability" refers to a method of expressing the reliability of information as a numerical value or indicator and determining its relative reliability. 【0460】 "Users" refer to individuals or organizations that use the system and are the entities that obtain and utilize the information. 【0461】 Regarding embodiments for carrying out the invention, this invention is a system that utilizes a digital network to collect information from multiple information sources and provides reliable information to users. The entire system consists of three main components: a server, a terminal, and a user. 【0462】 The server first collects data from information sources via a digital network. Specifically, it uses common software as a crawling tool (e.g., Scrapy). This makes it possible to obtain HTML data from various digital media such as websites and news portals. 【0463】 Next, the data is analyzed and normalized. The server uses the Python library Pandas to analyze the collected data and organize the necessary information. For example, it identifies the article text and publication date and time, and removes unnecessary information. This process also includes data formatting and removal of special characters. 【0464】 For the organized data, the server applies a machine learning model, such as an AI algorithm using TensorFlow, to calculate a reliability score for each information source. This score is evaluated based on the consistency of the information and its past performance. This reliability score helps determine whether the information meets certain criteria. 【0465】 The terminal filters data based on reliability evaluation results from the server and provides appropriate information to the user through the user interface. The user interface used here is updated in real time, ensuring that the latest information is always displayed. 【0466】 Users make decisions based on information provided through their devices. Furthermore, users can send feedback to the server regarding the validity and reliability of the information. The server collects this feedback and uses it to improve the AI ​​algorithm. Natural language processing (NLP) technology is used in this process. 【0467】 For example, if a user requests the latest news on politics, the device retrieves relevant information from the server and provides it instantly. An example of a prompt to be input to the generating AI model is, "Evaluate the reliability of the news article and output a reliability score." 【0468】 This system allows users to quickly access reliable information at all times, supporting efficient decision-making. 【0469】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0470】 Step 1: 【0471】 The server collects data from information sources via a digital network. The input is a list of URLs to be crawled. The server uses a crawling tool to retrieve HTML data from the specified URLs and saves this data in its raw form. This process involves periodic crawling based on a specified schedule. 【0472】 Step 2: 【0473】 The server parses the collected HTML data and extracts the necessary information. The input is the acquired HTML data. The server uses a data analysis library to identify the article text, publication date, author information, etc., and removes unnecessary advertisements and navigation elements. The output is a structured dataset. This normalization process ensures that the data is presented in a unified format. 【0474】 Step 3: 【0475】 The server calculates reliability scores based on normalized data. The input is the structured dataset from the previous step. The server inputs the data into an AI model, evaluates consistency of content, historical reliability data, cross-references, etc., and calculates a reliability score for each information source. The output is the reliability score associated with each article. 【0476】 Step 4: 【0477】 The terminal receives filtered, reliable information from the server and displays it on the user interface. The input is data assigned a reliability score. The terminal filters information based on the user's interests, prioritizing the display of the most relevant information. The output is an organized list of information displayed on the terminal's screen. 【0478】 Step 5: 【0479】 Users make decisions based on information provided through their devices. Users also send feedback from their devices to the server regarding the value and reliability of the information. The input is the user's feedback comments. The server collects this feedback and analyzes it as training data to improve the AI ​​model. The output provides insights for evaluating and improving the algorithm. 【0480】 (Application Example 1) 【0481】 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." 【0482】 In today's world, internet advertising is vast in number, but it often contains unreliable information. Users are at risk of being misled by these ads or being directed to dangerous websites, leading to a growing need to view only safe and trustworthy advertisements. However, current systems often require users to manually judge the reliability of ads, which is time-consuming and carries the risk of misjudgment. Therefore, there is a need to develop a system that balances safety and efficiency, allowing users to browse internet advertisements with peace of mind. 【0483】 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. 【0484】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, means for calculating a reliability score based on the preprocessed data, means for filtering the data based on the reliability score, means for evaluating the reliability of the provided advertising data and selecting and displaying highly reliable advertisements, means for dynamically updating advertising data via the user terminal, and means for improving the accuracy of advertising reliability evaluation based on user feedback. As a result, users can view only highly reliable advertisements, enabling safe internet use. 【0485】 "Information sources" refer to media and areas that provide diverse data on the internet, including websites and social media posts. 【0486】 "Means of automatically collecting data" refers to a system that obtains data from information sources through programs or algorithms without human intervention. 【0487】 "Preprocessing" is the process of removing noise from collected data and converting it into a format suitable for analysis. 【0488】 A "means for calculating reliability scores" refers to a mechanism for calculating a numerical value that evaluates the accuracy and reliability of data, and is carried out based on an algorithm. 【0489】 "A means of filtering data based on reliability scores" refers to a function that selects and handles only data that meets a certain reliability standard. 【0490】 "Means of providing filtered data to users" refers to a mechanism that presents users with selected, reliable data in a visual or other way. 【0491】 A "means for evaluating the reliability of advertising data" is a system that assesses the accuracy of the information contained in an advertisement and the reputation of its source to determine its reliability. 【0492】 "Methods for selecting and displaying highly reliable advertisements" refers to a process that displays only safe and reliable advertisements to users based on evaluation results. 【0493】 "Means of dynamically updating advertising data via the user's device" refers to a system that updates and displays the latest advertising information in real time via the user's device. 【0494】 "Methods for improving the accuracy of ad reliability evaluation based on user feedback" refers to the process of improving the accuracy of ad reliability evaluation systems by incorporating opinions and evaluations from users. 【0495】 The system implementing this invention mainly consists of a server, a user terminal, and an AI algorithm. The server automatically collects advertising data from information sources and stores it in a database. The data is first noise-removed and preprocessed into an appropriate format. The server uses an AI algorithm to evaluate the reliability of the information on this preprocessed data and calculates a reliability score. 【0496】 The user's device displays filtered advertising data received from the server based on the user's preferences. This allows the user to visually see only highly reliable advertisements. By dynamically updating data on the device, the latest information is provided to the user in real time. 【0497】 The AI ​​algorithm implements machine learning models using programming languages ​​such as Python to analyze data and evaluate reliability. This algorithm is designed to improve the accuracy of reliability evaluations over time by utilizing user feedback. A database, such as MySQL, is built to store and manage reliability scores. 【0498】 A concrete example is the ability to verify that only ads with a certain level of reliability score are displayed to users while they are using a news app on their smartphone. An example of a related prompt from a generative AI would be: "Implement a Python algorithm that evaluates the reliability of ads a user views on their smartphone and displays only highly reliable ads." 【0499】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0500】 Step 1: 【0501】 The server automatically collects advertising data from multiple sources on the internet. The input is a list of URLs of the sources, and the output is raw advertising data. The server uses a web crawler to visit these URLs and retrieve advertising information. 【0502】 Step 2: 【0503】 The server performs preprocessing, such as noise reduction, on the collected data. The input is the raw data collected in step 1, and the output is the normalized data. The server uses regular representation and filtering algorithms to extract only the necessary information. 【0504】 Step 3: 【0505】 The server analyzes pre-processed data using an AI algorithm and calculates a confidence score for each advertisement. The input is normalized data, and the output is the confidence score for each advertisement. The server uses a machine learning model to perform a process of evaluating reliability by comparing it with historical data. 【0506】 Step 4: 【0507】 The server filters and sends only ads that meet the criteria based on their reliability score to the user's device. The input is the calculated reliability score, and the output is the filtered ad data. The server selects ads with high scores and prepares them for transmission according to each user's profile. 【0508】 Step 5: 【0509】 The user's device displays filtered advertising data received from the server. The input is advertising data from the server, and the output is the advertising screen viewed by the user. The device provides an interface for displaying advertisements and visually presents highly reliable advertisements. 【0510】 Step 6: 【0511】 Users provide feedback on the displayed advertisements. This feedback is sent to the server. The input is the user's feedback information, and the output is the feedback data on the server side. Users can submit opinions and evaluations regarding the content of the advertisements and indicate suggestions for improvement. 【0512】 Step 7: 【0513】 The server analyzes user feedback, updates the algorithm for calculating reliability scores, and improves accuracy. The input is user feedback data, and the output is the updated reliability evaluation model. The server learns from the feedback and incorporates this learning into future ad reliability evaluations. 【0514】 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. 【0515】 This invention relates to an information delivery system that incorporates an emotion engine to provide online information to users in the most optimal way. This system selects and delivers information while considering the user's emotional state through interaction between the server, terminal, and user. 【0516】 First, the server collects data such as news articles, web pages, and social media posts from internet sources. This data is preprocessed, undergoing morphological analysis and spam filtering before being stored in a clean database. Next, an AI algorithm is used to calculate a reliability score, and only information that meets certain criteria is filtered out. 【0517】 The system's defining feature, the emotion engine, analyzes the user's emotions through the user interface on the device. Specifically, it infers the user's current emotional state by analyzing user input data, past usage history, and non-verbal cues obtained from voice and images. 【0518】 Once the user's emotional state is analyzed, the device determines the optimal way to deliver information based on the results. For example, if the user is feeling stressed, the device prioritizes calming information and highly entertaining content. On the other hand, if the user wants to improve their concentration, the device adjusts to provide more specialized and detailed information. 【0519】 As a concrete example, suppose a user is using a news app and the emotion engine detects the user's anxiety. In this case, the device will prioritize displaying articles that contribute to relaxation or positive news. The emotion engine also analyzes the user's feedback and updates the server's algorithm to improve the accuracy of information presentation in the future. Through this process, the system becomes more sensitive to the user's emotions over time, enabling more personalized information delivery. 【0520】 Thus, the present invention aims to provide information that not only ensures the reliability of online information but also responds to the user's emotions, thereby offering an optimized information usage experience for each individual user. 【0521】 The following describes the processing flow. 【0522】 Step 1: 【0523】 The server operates web crawlers according to a specified list of information sources, collecting news articles, blogs, and social media posts from the internet. This data is stored in a database in real time. 【0524】 Step 2: 【0525】 The server preprocesses the collected data. This includes removing unnecessary HTML tags, normalizing the text using natural language processing, and filtering out spam. The preprocessed data is then ready for analysis. 【0526】 Step 3: 【0527】 The server runs an AI algorithm that calculates a reliability score on the pre-processed data. The algorithm calculates the score based on the reliability metrics of the information source, the author's rating, and the content of the text. 【0528】 Step 4: 【0529】 The server filters the data based on a calculated reliability score. Only information whose score meets the set criteria is filtered and selected as information of priority value to the user. 【0530】 Step 5: 【0531】 The device receives filtered information from the server and displays it in the user interface. The displayed information is personalized based on the user's past behavior history and interests. 【0532】 Step 6: 【0533】 The device's built-in emotion engine analyzes emotional indicators such as user input data, eye movements, and voice tone to infer the user's emotional state. Based on these results, the information presented and the interface design are dynamically adjusted. 【0534】 Step 7: 【0535】 Users receive information that aligns with their emotions and, if necessary, input feedback into their device. This feedback is used to improve the service experience. 【0536】 Step 8: 【0537】 The server analyzes accumulated user feedback information and uses it to improve the AI ​​algorithm for calculating reliability scores and the accuracy of sentiment recognition. This update will enable the system to provide users with more effective information. 【0538】 (Example 2) 【0539】 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." 【0540】 In today's world, the amount and variety of information available online is vast, but not all of it is reliable, and it is difficult for users to obtain the most relevant information based on their emotional state. Therefore, there is a need for a system that maintains the reliability of online information while providing information that takes into account the individual emotional state of each user. 【0541】 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. 【0542】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, and means for calculating a reliability score based on the preprocessed data. This enables the selection of highly reliable information and the provision of individually optimized information according to the user's emotional state. 【0543】 "Information sources" refer to various sources of data available on the internet, such as news articles, web pages, and social media posts. 【0544】 "Means of automatically collecting data" refers to methods and devices for mechanically acquiring data from internet sources according to conditions specified by a program. 【0545】 "Preprocessing" refers to a series of steps that remove noise and unnecessary information from collected data and prepare it for analysis. 【0546】 A "reliability score" refers to a numerical value calculated to evaluate the accuracy and credibility of information. 【0547】 "Means of filtering data" refers to methods and devices for selecting useful information from unuseful information based on reliability scores. 【0548】 "Means for analyzing a user's emotional state" refers to methods and devices for inferring a user's current psychological state from their input and nonverbal cues. 【0549】 "Means of optimizing and providing information" refers to methods and devices for presenting information in an appropriate content and format according to the user's emotional state. 【0550】 "Feedback refers to the evaluations and opinions that users give in response to the information provided." 【0551】 "Means of updating algorithms" refers to methods or devices for improving the system's operation or decision-making criteria based on received feedback. 【0552】 This information provision system functions through server, terminal, and user interaction to provide optimal information tailored to the user's emotional state. 【0553】 First, the server automatically collects data from multiple sources on the internet and processes it efficiently. Specifically, it uses various RSS feeds and APIs to retrieve news articles, web pages, and social media posts in real time. The server then analyzes the text data using morphological analysis tools (e.g., MeCab) and removes unwanted data using spam filtering software (e.g., general spam filtering software). The cleaned-up information is then securely stored in a database. 【0554】 Next, the server calculates a reliability score for the preprocessed data using a machine learning model (for example, BERT or a Transformer-based model). Based on this score, only information that meets a certain level of reliability is filtered and ready to be provided to the user. 【0555】 Meanwhile, the device analyzes the user's emotional state through the user interface. This analysis is based on user input data, past usage history, and non-verbal cues obtained through voice and images. Here, voice analysis tools (e.g., general voice analysis APIs) and image recognition software (e.g., general-purpose image recognition systems) are used to analyze the user's emotions in detail. 【0556】 After determining the user's emotional state, the device decides how to provide information appropriate to that state. For example, a user experiencing stress will be prioritized with articles that promote relaxation and positive content. On the other hand, a user who wants to improve their concentration will be provided with highly specialized and detailed information. 【0557】 As a concrete example, if a user expresses anxiety while reviewing economic news, the device will strive to prioritize providing articles about economic stability and positive future outlooks. In this case, by inputting a prompt message to the generation AI model such as, "Generate positive economic news to alleviate the user's anxiety," the device will generate and provide appropriate content. 【0558】 Through this process, the system can provide optimal information tailored to the individual needs of each user, and its accuracy can be further improved through continuous feedback. 【0559】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0560】 Step 1: 【0561】 The server automatically collects data from information sources on the internet. Specifically, it retrieves article and post data from multiple news sites and social media platforms via RSS feeds and APIs. Input requires URLs and API keys from various information sources, and the output is raw, unprocessed data. 【0562】 Step 2: 【0563】 The server preprocesses the collected raw data. It analyzes the text data using morphological analysis tools and removes noise by performing spam filtering. It takes raw data as input, applies morphological analysis and spam detection, and outputs clean text data. 【0564】 Step 3: 【0565】 The server calculates a confidence score for pre-processed, clean data. A machine learning model is applied to quantify the confidence level of each piece of information. This process takes clean text data as input, calculates a score using a confidence evaluation algorithm, and produces an output that selects the most reliable information. 【0566】 Step 4: 【0567】 The server filters the data based on its reliability score. Only data with a score above a certain level is selected to proceed to the next step. The input is data with a reliability score, and the output provides filtered, useful information. 【0568】 Step 5: 【0569】 The device analyzes the user's emotional state through its user interface. It determines emotions by analyzing user input data and nonverbal cues. It takes data from voice analysis and facial recognition as input and outputs analysis results indicating the user's emotional state. 【0570】 Step 6: 【0571】 The device determines the optimal information delivery method based on the analysis results. It prompts an AI model that generates prompts tailored to the user's emotions, and then generates appropriate content. It uses the results of the emotion analysis as input and outputs professional articles or relaxing content. 【0572】 Step 7: 【0573】 Users send feedback to their devices based on the information provided. Through this feedback, the system understands the user's needs. The system receives feedback data as input and outputs it as data to improve future information provision. 【0574】 Step 8: 【0575】 The server updates the algorithm using the collected feedback. It applies machine learning and adjusts the algorithm's parameters according to user feedback. This process takes feedback data as input and outputs an updated algorithm, improving the accuracy of future information provision. 【0576】 (Application Example 2) 【0577】 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." 【0578】 In today's information-saturated world, users spend a great deal of time and effort accessing the most relevant information. Furthermore, information provided without considering the user's emotional state is not necessarily valuable to them. Therefore, there is a need to build systems that efficiently provide reliable information while taking the user's emotional state into account. 【0579】 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. 【0580】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, means for calculating a reliability score based on the preprocessed data, means for filtering the data based on the reliability score, means for analyzing the user's emotional state, and means for selecting and providing data based on the emotional state. This makes it possible to provide optimal information in accordance with the user's emotions. 【0581】 "Information sources" refer to the starting point for collecting data, and include various online content such as news articles, websites, and social media posts. 【0582】 "Means for automatically collecting data" refers to system components that perform the process of obtaining necessary data from information sources without manual intervention. 【0583】 "Means for preprocessing data" refer to system components that perform initial processing to make collected data clean and ready for analysis. 【0584】 A "means for calculating reliability scores" refers to a system component used to quantify and evaluate the reliability and validity of data. 【0585】 A "means of filtering data" refers to a system component that selects only the necessary data based on reliability scores and removes unnecessary or inaccurate data. 【0586】 A "means for analyzing a user's emotional state" refers to a system component that uses user input and nonverbal cues to determine the user's emotions at any given time. 【0587】 "Means for selecting and providing data based on emotional state" refers to system components that select and provide information in accordance with the determined emotions of the user. 【0588】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. First, the server automatically collects data from a wide variety of information sources on the internet, specifically from news articles, websites, and social media posts. The collected data is preprocessed to remove unnecessary elements and noise and stored in a clean state. Natural language processing tools are used in this process. 【0589】 Next, the server calculates a reliability score for the preprocessed data. This uses machine learning algorithms to objectively evaluate the truthfulness and quality of the data. Based on the reliability score, the server further filters the data to select only the meaningful information to provide to the user. 【0590】 The device handles user interaction. It incorporates an emotion engine that analyzes user input, past usage history, and nonverbal cues to determine the user's emotional state. This process utilizes deep learning frameworks such as TensorFlow and PyTorch. Based on the emotion analysis, it presents information from the server in the most optimal way. For example, if the user is stressed, it prioritizes providing content with relaxation effects. 【0591】 The feedback users provide while using the system is collected and analyzed by the server. This improves the accuracy of the information provided and optimizes the sentiment engine. Based on this feedback, the server updates its algorithms, improving the overall system performance over time. 【0592】 As a concrete example, suppose a user is using the system to search for entertainment content, and the emotion engine detects the user's relaxed state. In this case, the system will prioritize recommending calming music or soothing videos. Furthermore, by utilizing a generative AI model, it is possible to provide appropriate recommendations in response to an input prompt such as, "I've been feeling stressed lately, so I'm looking for relaxing content." 【0593】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0594】 Step 1: 【0595】 The server automatically collects data from information sources on the internet. The input is various information sources, and the output is the collected raw data. This process uses a web crawler to periodically retrieve information from specified websites and social media. 【0596】 Step 2: 【0597】 The server preprocesses the collected data. The input is raw data, and the output is clean data. Morphological analysis and spam filtering are performed to remove unnecessary elements and improve the quality of the data. 【0598】 Step 3: 【0599】 The server calculates a confidence score based on pre-processed data. The input is clean data, and the output is a confidence score for each data point. A machine learning algorithm is used to evaluate the accuracy and reliability of the data. This algorithm analyzes the current data in relation to historical data. 【0600】 Step 4: 【0601】 The server filters data based on reliability scores. The input is scored data, and the output is reliable data. A certain lower score threshold is set, and data that does not meet this criterion is excluded. 【0602】 Step 5: 【0603】 The device analyzes the user's emotional state. Input consists of user input data, past history, and nonverbal cues, and output is an estimated emotional state of the user. Audio and image data are analyzed using TensorFlow or PyTorch, and then analyzed by an emotion engine. 【0604】 Step 6: 【0605】 The device filters and selects data based on the user's emotional state, presenting it in the most optimal way. Input consists of established data and emotional states, while output is personalized information presented to the user. For example, it might prioritize light music when the user is relaxed, or specialized content when they need to concentrate. 【0606】 Step 7: 【0607】 Users provide feedback on the information presented. The input is the user's feedback, and the output is the feedback data sent to the server. This feedback serves as a valuable source of information for improving system performance. 【0608】 Step 8: 【0609】 The server analyzes feedback received from the user and updates the algorithm through a generative AI model. The input is user feedback data, and the output is an enhanced algorithm. This improves the accuracy of the information provided in the future and enhances the user experience. Based on data generated from the prompt "I've been feeling stressed lately, so I'm looking for some relaxing content," content delivery becomes even more personalized. 【0610】 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. 【0611】 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. 【0612】 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. 【0613】 [Fourth Embodiment] 【0614】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0615】 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. 【0616】 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). 【0617】 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. 【0618】 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. 【0619】 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). 【0620】 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. 【0621】 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. 【0622】 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. 【0623】 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. 【0624】 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. 【0625】 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. 【0626】 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". 【0627】 This invention provides a system for evaluating the reliability of online information and enabling users to efficiently access the accurate information they need. This system primarily consists of a server, terminals, and users, each operating according to its respective role. 【0628】 First, as an initial step initiated by the server, it automatically crawls information from various sources on the internet according to a pre-set schedule. The data collected through crawling is stored in a database in raw data format. The server analyzes this data, preprocesses it to remove unnecessary parts, and generates normalized data. The normalized data is then analyzed by an AI algorithm. Here, the server calculates a reliability score for each source based on parameters that are important for determining the reliability of the information. 【0629】 Next, in the step where the terminal intervenes, filtered and reliable information is received from the server and displayed on the user interface. This display allows for the provision of information tailored to the user's interests and needs, and can be updated in real time. 【0630】 For example, if a user is looking for the latest news on politics, the device receives filtered information relevant to that topic from the server and provides it to the user instantly. This allows the user to make quick and accurate decisions based on reliable information. 【0631】 Furthermore, users can send feedback on the provided information to the server via their device. This feedback is accumulated and periodically analyzed by the server. Based on this, the AI ​​algorithm that calculates the reliability score evolves daily, improving its accuracy. In this way, the system continuously evolves while increasing its reliability, enabling it to provide users with the most optimal information. 【0632】 The following describes the processing flow. 【0633】 Step 1: 【0634】 The server launches a web crawler based on a specified list of information sources, automatically collecting news articles, websites, and social media posts from the internet. The collected information is stored in a database. 【0635】 Step 2: 【0636】 The server performs data preprocessing on the collected information. This process involves removing HTML tags, normalizing special characters, and filtering spam using spam detection algorithms, resulting in clean text data. 【0637】 Step 3: 【0638】 The server applies an AI algorithm to the pre-processed text data to calculate a reliability score for each information source. This algorithm evaluates the source's past performance, the author's credibility, and the accuracy and consistency of the content through linguistic analysis. 【0639】 Step 4: 【0640】 The server filters information based on a calculated reliability score. Information with scores below a set threshold is excluded, and only information exceeding that threshold is selected. This filtered information is then scrutinized to ensure its reliability for the user. 【0641】 Step 5: 【0642】 The device receives filtered information from the server and displays it on the user interface. The information is personalized and presented in the most optimal way based on the user's areas of interest and past behavioral patterns. 【0643】 Step 6: 【0644】 Users view the provided information and input feedback on its quality and content into their device. This feedback is sent to the server in real time and stored in the feedback database. 【0645】 Step 7: 【0646】 The server analyzes regularly collected feedback and improves its AI algorithms to calculate reliability scores more accurately. This aims to continuously improve the system's accuracy and user satisfaction. 【0647】 (Example 1) 【0648】 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". 【0649】 In today's digital information environment, users are required to have quick access to reliable information. However, the increasing diversity and volume of information sources make it difficult to judge reliability and filter out biased information. To solve this problem, a system is needed that can efficiently collect data from information sources and evaluate its reliability. 【0650】 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. 【0651】 In this invention, the server includes means for selectively collecting data from information sources via a digital network, means for analyzing and normalizing the collected data, and means for calculating a score for evaluating reliability based on the normalized data. This enables users to access reliable information quickly and efficiently. 【0652】 A "digital network" refers to an electronic communication infrastructure used to send and receive information, and encompasses wide-area networks such as the internet. 【0653】 "Information sources" refer to media and platforms that provide various data and information, such as websites, news sites, and databases. 【0654】 "Means of selective data collection" refers to methods or processes for collecting data from diverse sources based on specific criteria. 【0655】 "Analysis" refers to the process of thoroughly examining collected data and extracting its structure and content in a way that is easy to understand. 【0656】 "Normalization" is the process of arranging data into a certain standard format, which improves data consistency and compatibility. 【0657】 "Means for calculating a score to evaluate reliability" refers to a method of expressing the reliability of information as a numerical value or indicator and determining its relative reliability. 【0658】 "Users" refer to individuals or organizations that use the system and are the entities that obtain and utilize the information. 【0659】 Regarding the embodiment for carrying out the invention, this invention is a system that utilizes a digital network to collect information from multiple information sources and provides reliable information to users. The entire system consists of three main components: a server, a terminal, and a user. 【0660】 The server first collects data from information sources via a digital network. Specifically, it uses common software as a crawling tool (e.g., Scrapy). This makes it possible to obtain HTML data from various digital media such as websites and news portals. 【0661】 Next, the data is analyzed and normalized. The server uses the Python library Pandas to analyze the collected data and organize the necessary information. For example, it identifies the article text and publication date and time, and removes unnecessary information. This process also includes data formatting and removal of special characters. 【0662】 For the organized data, the server applies a machine learning model, such as an AI algorithm using TensorFlow, to calculate a reliability score for each information source. This score is evaluated based on the consistency of the information and its past performance. This reliability score helps determine whether the information meets certain criteria. 【0663】 The terminal filters data based on reliability evaluation results from the server and provides appropriate information to the user through the user interface. The user interface used here is updated in real time, ensuring that the latest information is always displayed. 【0664】 Users make decisions based on information provided through their devices. Furthermore, users can send feedback to the server regarding the validity and reliability of the information. The server collects this feedback and uses it to improve the AI ​​algorithm. Natural language processing (NLP) technology is used in this process. 【0665】 For example, if a user requests the latest news on politics, the device retrieves relevant information from the server and provides it instantly. An example of a prompt to be input to the generating AI model is, "Evaluate the reliability of the news article and output a reliability score." 【0666】 This system allows users to quickly access reliable information at all times, supporting efficient decision-making. 【0667】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0668】 Step 1: 【0669】 The server collects data from information sources via a digital network. The input is a list of URLs to be crawled. The server uses a crawling tool to retrieve HTML data from the specified URLs and saves this data in its raw form. This process involves periodic crawling based on a specified schedule. 【0670】 Step 2: 【0671】 The server parses the collected HTML data and extracts the necessary information. The input is the acquired HTML data. The server uses a data analysis library to identify the article text, publication date, author information, etc., and removes unnecessary advertisements and navigation elements. The output is a structured dataset. This normalization process ensures that the data is presented in a unified format. 【0672】 Step 3: 【0673】 The server calculates reliability scores based on normalized data. The input is the structured dataset from the previous step. The server inputs the data into an AI model, evaluates consistency of content, historical reliability data, cross-references, etc., and calculates a reliability score for each information source. The output is the reliability score associated with each article. 【0674】 Step 4: 【0675】 The terminal receives filtered, reliable information from the server and displays it on the user interface. The input is data assigned a reliability score. The terminal filters information based on the user's interests, prioritizing the display of the most relevant information. The output is an organized list of information displayed on the terminal's screen. 【0676】 Step 5: 【0677】 Users make decisions based on information provided through their devices. Users also send feedback from their devices to the server regarding the value and reliability of the information. The input is the user's feedback comments. The server collects this feedback and analyzes it as training data to improve the AI ​​model. The output provides insights for evaluating and improving the algorithm. 【0678】 (Application Example 1) 【0679】 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". 【0680】 In today's world, internet advertising is vast in number, but it often contains unreliable information. Users are at risk of being misled by these ads or being directed to dangerous websites, leading to a growing need to view only safe and trustworthy advertisements. However, current systems often require users to manually judge the reliability of ads, which is time-consuming and carries the risk of misjudgment. Therefore, there is a need to develop a system that balances safety and efficiency, allowing users to browse internet advertisements with peace of mind. 【0681】 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. 【0682】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, means for calculating a reliability score based on the preprocessed data, means for filtering the data based on the reliability score, means for evaluating the reliability of the provided advertising data and selecting and displaying highly reliable advertisements, means for dynamically updating advertising data via the user terminal, and means for improving the accuracy of advertising reliability evaluation based on user feedback. As a result, users can view only highly reliable advertisements, enabling safe internet use. 【0683】 "Information sources" refer to media and areas that provide diverse data on the internet, including websites and social media posts. 【0684】 "Means of automatically collecting data" refers to a system that obtains data from information sources through programs or algorithms without human intervention. 【0685】 "Preprocessing" is the process of removing noise from collected data and converting it into a format suitable for analysis. 【0686】 A "means for calculating reliability scores" refers to a mechanism for calculating a numerical value that evaluates the accuracy and reliability of data, and is carried out based on an algorithm. 【0687】 "A means of filtering data based on reliability scores" refers to a function that selects and handles only data that meets a certain reliability standard. 【0688】 "Means of providing filtered data to users" refers to a mechanism that presents users with selected, reliable data in a visual or other way. 【0689】 A "means for evaluating the reliability of advertising data" is a system that assesses the accuracy of the information contained in an advertisement and the reputation of its source to determine its reliability. 【0690】 "Methods for selecting and displaying highly reliable advertisements" refers to a process that displays only safe and reliable advertisements to users based on evaluation results. 【0691】 "Means of dynamically updating advertising data via the user's device" refers to a system that updates and displays the latest advertising information in real time via the user's device. 【0692】 "Methods for improving the accuracy of ad reliability evaluation based on user feedback" refers to the process of improving the accuracy of ad reliability evaluation systems by incorporating opinions and evaluations from users. 【0693】 The system implementing this invention mainly consists of a server, a user terminal, and an AI algorithm. The server automatically collects advertising data from information sources and stores it in a database. The data is first noise-removed and preprocessed into an appropriate format. The server uses an AI algorithm to evaluate the reliability of the information on this preprocessed data and calculates a reliability score. 【0694】 The user's device displays filtered advertising data received from the server based on the user's preferences. This allows the user to visually see only highly reliable advertisements. By dynamically updating data on the device, the latest information is provided to the user in real time. 【0695】 The AI ​​algorithm implements machine learning models using programming languages ​​such as Python to analyze data and evaluate reliability. This algorithm is designed to improve the accuracy of reliability evaluations over time by utilizing user feedback. A database, such as MySQL, is built to store and manage reliability scores. 【0696】 A concrete example is the ability to verify that only ads with a certain level of reliability score are displayed to users while they are using a news app on their smartphone. An example of a related prompt from a generative AI would be: "Implement a Python algorithm that evaluates the reliability of ads a user views on their smartphone and displays only highly reliable ads." 【0697】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0698】 Step 1: 【0699】 The server automatically collects advertising data from multiple sources on the internet. The input is a list of URLs of the sources, and the output is raw advertising data. The server uses a web crawler to visit these URLs and retrieve advertising information. 【0700】 Step 2: 【0701】 The server performs preprocessing, such as noise reduction, on the collected data. The input is the raw data collected in step 1, and the output is the normalized data. The server uses regular representation and filtering algorithms to extract only the necessary information. 【0702】 Step 3: 【0703】 The server analyzes pre-processed data using an AI algorithm and calculates a confidence score for each advertisement. The input is normalized data, and the output is the confidence score for each advertisement. The server uses a machine learning model to perform a process of evaluating reliability by comparing it with historical data. 【0704】 Step 4: 【0705】 The server filters and sends only ads that meet the criteria based on their reliability score to the user's device. The input is the calculated reliability score, and the output is the filtered ad data. The server selects ads with high scores and prepares them for transmission according to each user's profile. 【0706】 Step 5: 【0707】 The user's device displays filtered advertising data received from the server. The input is advertising data from the server, and the output is the advertising screen viewed by the user. The device provides an interface for displaying advertisements and visually presents highly reliable advertisements. 【0708】 Step 6: 【0709】 Users provide feedback on the displayed advertisements. This feedback is sent to the server. The input is the user's feedback information, and the output is the feedback data on the server side. Users can submit opinions and evaluations regarding the content of the advertisements and indicate suggestions for improvement. 【0710】 Step 7: 【0711】 The server analyzes user feedback, updates the algorithm for calculating reliability scores, and improves accuracy. The input is user feedback data, and the output is the updated reliability evaluation model. The server learns from the feedback and incorporates this learning into future ad reliability evaluations. 【0712】 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. 【0713】 This invention relates to an information delivery system that incorporates an emotion engine to provide online information to users in the most optimal way. This system selects and delivers information while considering the user's emotional state through interaction between the server, terminal, and user. 【0714】 First, the server collects data such as news articles, web pages, and social media posts from internet sources. This data is preprocessed, undergoing morphological analysis and spam filtering before being stored in a clean database. Next, an AI algorithm is used to calculate a reliability score, and only information that meets certain criteria is filtered out. 【0715】 The system's defining feature, the emotion engine, analyzes the user's emotions through the user interface on the device. Specifically, it infers the user's current emotional state by analyzing user input data, past usage history, and non-verbal cues obtained from voice and images. 【0716】 Once the user's emotional state is analyzed, the device determines the optimal way to deliver information based on the results. For example, if the user is feeling stressed, the device prioritizes calming information and highly entertaining content. On the other hand, if the user wants to improve their concentration, the device adjusts to provide more specialized and detailed information. 【0717】 As a concrete example, suppose a user is using a news app and the emotion engine detects the user's anxiety. In this case, the device will prioritize displaying articles that contribute to relaxation or positive news. The emotion engine also analyzes the user's feedback and updates the server's algorithm to improve the accuracy of information presentation in the future. Through this process, the system becomes more sensitive to the user's emotions over time, enabling more personalized information delivery. 【0718】 Thus, the present invention aims to provide information that not only ensures the reliability of online information but also responds to the user's emotions, thereby offering an optimized information usage experience for each individual user. 【0719】 The following describes the processing flow. 【0720】 Step 1: 【0721】 The server operates web crawlers according to a specified list of information sources, collecting news articles, blogs, and social media posts from the internet. This data is stored in a database in real time. 【0722】 Step 2: 【0723】 The server preprocesses the collected data. This includes removing unnecessary HTML tags, normalizing the text using natural language processing, and filtering out spam. The preprocessed data is then ready for analysis. 【0724】 Step 3: 【0725】 The server runs an AI algorithm that calculates a reliability score on the pre-processed data. The algorithm calculates the score based on the reliability metrics of the information source, the author's rating, and the content of the text. 【0726】 Step 4: 【0727】 The server filters the data based on a calculated reliability score. Only information whose score meets the set criteria is filtered and selected as information of priority value to the user. 【0728】 Step 5: 【0729】 The device receives filtered information from the server and displays it in the user interface. The displayed information is personalized based on the user's past behavior history and interests. 【0730】 Step 6: 【0731】 The device's built-in emotion engine analyzes emotional indicators such as user input data, eye movements, and voice tone to infer the user's emotional state. Based on these results, the information presented and the interface design are dynamically adjusted. 【0732】 Step 7: 【0733】 Users receive information that aligns with their emotions and, if necessary, input feedback into their device. This feedback is used to improve the service experience. 【0734】 Step 8: 【0735】 The server analyzes accumulated user feedback information and uses it to improve the AI ​​algorithm for calculating reliability scores and the accuracy of sentiment recognition. This update will enable the system to provide users with more effective information. 【0736】 (Example 2) 【0737】 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". 【0738】 In today's world, the amount and variety of information available online is vast, but not all of it is reliable, and it is difficult for users to obtain the most relevant information based on their emotional state. Therefore, there is a need for a system that maintains the reliability of online information while providing information that takes into account the individual emotional state of each user. 【0739】 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. 【0740】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, and means for calculating a reliability score based on the preprocessed data. This enables the selection of highly reliable information and the provision of individually optimized information according to the user's emotional state. 【0741】 "Information sources" refer to various sources of data available on the internet, such as news articles, web pages, and social media posts. 【0742】 "Means of automatically collecting data" refers to methods and devices for mechanically acquiring data from internet sources according to conditions specified by a program. 【0743】 "Preprocessing" refers to a series of steps that remove noise and unnecessary information from collected data and prepare it for analysis. 【0744】 A "reliability score" refers to a numerical value calculated to evaluate the accuracy and credibility of information. 【0745】 "Means of filtering data" refers to methods and devices for selecting useful information from unuseful information based on reliability scores. 【0746】 "Means for analyzing a user's emotional state" refers to methods and devices for inferring a user's current psychological state from their input and nonverbal cues. 【0747】 "Means of optimizing and providing information" refers to methods and devices for presenting information in an appropriate content and format according to the user's emotional state. 【0748】 "Feedback refers to the evaluations and opinions that users give in response to the information provided." 【0749】 "Means of updating algorithms" refers to methods or devices for improving the system's operation or decision-making criteria based on received feedback. 【0750】 This information provision system functions through server, terminal, and user interaction to provide optimal information tailored to the user's emotional state. 【0751】 First, the server automatically collects data from multiple sources on the internet and processes it efficiently. Specifically, it uses various RSS feeds and APIs to retrieve news articles, web pages, and social media posts in real time. The server then analyzes the text data using morphological analysis tools (e.g., MeCab) and removes unwanted data using spam filtering software (e.g., general spam filtering software). The cleaned-up information is then securely stored in a database. 【0752】 Next, the server calculates a reliability score for the preprocessed data using a machine learning model (for example, BERT or a Transformer-based model). Based on this score, only information that meets a certain level of reliability is filtered and ready to be provided to the user. 【0753】 Meanwhile, the device analyzes the user's emotional state through the user interface. This analysis is based on user input data, past usage history, and non-verbal cues obtained through voice and images. Here, voice analysis tools (e.g., general voice analysis APIs) and image recognition software (e.g., general-purpose image recognition systems) are used to analyze the user's emotions in detail. 【0754】 After determining the user's emotional state, the device decides how to provide information appropriate to that state. For example, a user experiencing stress will be prioritized with articles that promote relaxation and positive content. On the other hand, a user who wants to improve their concentration will be provided with highly specialized and detailed information. 【0755】 As a concrete example, if a user expresses anxiety while reviewing economic news, the device will strive to prioritize providing articles about economic stability and positive future outlooks. In this case, by inputting a prompt message to the generation AI model such as, "Generate positive economic news to alleviate the user's anxiety," the device will generate and provide appropriate content. 【0756】 Through this process, the system can provide optimal information tailored to the individual needs of each user, and its accuracy can be further improved through continuous feedback. 【0757】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0758】 Step 1: 【0759】 The server automatically collects data from information sources on the internet. Specifically, it retrieves article and post data from multiple news sites and social media platforms via RSS feeds and APIs. Input requires URLs and API keys from various information sources, and the output is raw, unprocessed data. 【0760】 Step 2: 【0761】 The server preprocesses the collected raw data. It analyzes the text data using morphological analysis tools and removes noise by performing spam filtering. It takes raw data as input, applies morphological analysis and spam detection, and outputs clean text data. 【0762】 Step 3: 【0763】 The server calculates a confidence score for pre-processed, clean data. A machine learning model is applied to quantify the confidence level of each piece of information. This process takes clean text data as input, calculates a score using a confidence evaluation algorithm, and produces an output that selects the most reliable information. 【0764】 Step 4: 【0765】 The server filters the data based on its reliability score. Only data with a score above a certain level is selected to proceed to the next step. The input is data with a reliability score, and the output provides filtered, useful information. 【0766】 Step 5: 【0767】 The device analyzes the user's emotional state through its user interface. It determines emotions by analyzing user input data and nonverbal cues. It takes data from voice analysis and facial recognition as input and outputs analysis results indicating the user's emotional state. 【0768】 Step 6: 【0769】 The device determines the optimal information delivery method based on the analysis results. It prompts an AI model that generates prompts tailored to the user's emotions, and then generates appropriate content. It uses the results of the emotion analysis as input and outputs professional articles or relaxing content. 【0770】 Step 7: 【0771】 Users send feedback to their devices based on the information provided. Through this feedback, the system understands the user's needs. The system receives feedback data as input and outputs it as data to improve future information provision. 【0772】 Step 8: 【0773】 The server updates the algorithm using the collected feedback. It applies machine learning and adjusts the algorithm's parameters according to user feedback. This process takes feedback data as input and outputs an updated algorithm, improving the accuracy of future information provision. 【0774】 (Application Example 2) 【0775】 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". 【0776】 In today's information-saturated world, users spend a great deal of time and effort accessing the most relevant information. Furthermore, information provided without considering the user's emotional state is not necessarily valuable to them. Therefore, there is a need to build systems that efficiently provide reliable information while taking the user's emotional state into account. 【0777】 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. 【0778】 In this invention, the server includes means for automatically collecting data from information sources, means for preprocessing the collected data, means for calculating a reliability score based on the preprocessed data, means for filtering the data based on the reliability score, means for analyzing the user's emotional state, and means for selecting and providing data based on the emotional state. This makes it possible to provide optimal information in accordance with the user's emotions. 【0779】 "Information sources" refer to the starting point for collecting data, and include various online content such as news articles, websites, and social media posts. 【0780】 "Means for automatically collecting data" refers to system components that perform the process of obtaining necessary data from information sources without manual intervention. 【0781】 "Means for preprocessing data" refer to system components that perform initial processing to make collected data clean and ready for analysis. 【0782】 A "means for calculating reliability scores" refers to a system component used to quantify and evaluate the reliability and validity of data. 【0783】 A "means of filtering data" refers to a system component that selects only the necessary data based on reliability scores and removes unnecessary or inaccurate data. 【0784】 A "means for analyzing a user's emotional state" refers to a system component that uses user input and nonverbal cues to determine the user's emotions at any given time. 【0785】 "Means for selecting and providing data based on emotional state" refers to system components that select and provide information in accordance with the determined emotions of the user. 【0786】 The system for realizing this invention mainly consists of three elements: a server, a terminal, and a user. First, the server automatically collects data from a wide variety of information sources on the internet, specifically from news articles, websites, and social media posts. The collected data is preprocessed to remove unnecessary elements and noise and stored in a clean state. Natural language processing tools are used in this process. 【0787】 Next, the server calculates a reliability score for the preprocessed data. This uses machine learning algorithms to objectively evaluate the truthfulness and quality of the data. Based on the reliability score, the server further filters the data to select only the meaningful information to provide to the user. 【0788】 The device handles user interaction. It incorporates an emotion engine that analyzes user input, past usage history, and nonverbal cues to determine the user's emotional state. This process utilizes deep learning frameworks such as TensorFlow and PyTorch. Based on the emotion analysis, it presents information from the server in the most optimal way. For example, if the user is stressed, it prioritizes providing content with relaxation effects. 【0789】 The feedback users provide while using the system is collected and analyzed by the server. This improves the accuracy of the information provided and optimizes the sentiment engine. Based on this feedback, the server updates its algorithms, improving the overall system performance over time. 【0790】 As a concrete example, suppose a user is using the system to search for entertainment content, and the emotion engine detects the user's relaxed state. In this case, the system will prioritize recommending calming music or soothing videos. Furthermore, by utilizing a generative AI model, it is possible to provide appropriate recommendations in response to an input prompt such as, "I've been feeling stressed lately, so I'm looking for relaxing content." 【0791】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0792】 Step 1: 【0793】 The server automatically collects data from information sources on the internet. The input is various information sources, and the output is the collected raw data. This process uses a web crawler to periodically retrieve information from specified websites and social media. 【0794】 Step 2: 【0795】 The server preprocesses the collected data. The input is raw data, and the output is clean data. Morphological analysis and spam filtering are performed to remove unnecessary elements and improve the quality of the data. 【0796】 Step 3: 【0797】 The server calculates a confidence score based on pre-processed data. The input is clean data, and the output is a confidence score for each data point. A machine learning algorithm is used to evaluate the accuracy and reliability of the data. This algorithm analyzes the current data in relation to historical data. 【0798】 Step 4: 【0799】 The server filters data based on reliability scores. The input is scored data, and the output is reliable data. A certain lower score threshold is set, and data that does not meet this criterion is excluded. 【0800】 Step 5: 【0801】 The device analyzes the user's emotional state. Input consists of user input data, past history, and nonverbal cues, and output is an estimated emotional state of the user. Audio and image data are analyzed using TensorFlow or PyTorch, and then analyzed by an emotion engine. 【0802】 Step 6: 【0803】 The device filters and selects data based on the user's emotional state, presenting it in the most optimal way. Input consists of established data and emotional states, while output is personalized information presented to the user. For example, it might prioritize light music when the user is relaxed, or specialized content when they need to concentrate. 【0804】 Step 7: 【0805】 Users provide feedback on the information presented. The input is the user's feedback, and the output is the feedback data sent to the server. This feedback serves as a valuable source of information for improving system performance. 【0806】 Step 8: 【0807】 The server analyzes feedback received from the user and updates the algorithm through a generative AI model. The input is user feedback data, and the output is an enhanced algorithm. This improves the accuracy of the information provided in the future and enhances the user experience. Based on data generated from the prompt "I've been feeling stressed lately, so I'm looking for some relaxing content," content delivery becomes even more personalized. 【0808】 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. 【0809】 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. 【0810】 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. 【0811】 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. 【0812】 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. 【0813】 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. 【0814】 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. 【0815】 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. 【0816】 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." 【0817】 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. 【0818】 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. 【0819】 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. 【0820】 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. 【0821】 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. 【0822】 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. 【0823】 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. 【0824】 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. 【0825】 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. 【0826】 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. 【0827】 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. 【0828】 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 as being incorporated by reference. 【0829】 The following is further disclosed regarding the embodiments described above. 【0830】 (Claim 1) 【0831】 Means for automatically collecting data from information sources, 【0832】 Means for preprocessing the collected data, 【0833】 A means for calculating a reliability score based on preprocessed data, 【0834】 A means of filtering data based on reliability scores, 【0835】 A means of providing filtered data to users, 【0836】 Includes system. 【0837】 (Claim 2) 【0838】 The system according to claim 1, further comprising means for receiving user feedback and analyzing said feedback to update the algorithm. 【0839】 (Claim 3) 【0840】 The system according to claim 1, comprising means for collecting data from different sources such as social media posts, websites, and news articles. 【0841】 "Example 1" 【0842】 (Claim 1) 【0843】 A means of selectively collecting data from information sources via a digital network, 【0844】 A means of analyzing and normalizing the collected data, 【0845】 A means for calculating a score to evaluate reliability based on normalized data, 【0846】 A means of selecting data according to the calculated reliability score, 【0847】 A display means for providing selected data to users, 【0848】 A system that includes this. 【0849】 (Claim 2) 【0850】 The system according to claim 1, further comprising means for obtaining user feedback and optimizing the algorithm based on said feedback. 【0851】 (Claim 3) 【0852】 The system according to claim 1, comprising means for collecting data from different information media. 【0853】 "Application Example 1" 【0854】 (Claim 1) 【0855】 Means for automatically collecting data from information sources, 【0856】 Means for preprocessing the collected data, 【0857】 A means for calculating a reliability score based on preprocessed data, 【0858】 A means of filtering data based on reliability scores, 【0859】 A means of providing filtered data to the user, 【0860】 A means for evaluating the reliability of the provided advertising data and selecting and displaying reliable advertisements, 【0861】 A means of dynamically updating advertising data via the user's terminal, 【0862】 A means to improve the accuracy of ad reliability evaluation based on user feedback, 【0863】 Includes system. 【0864】 (Claim 2) 【0865】 The system according to claim 1, further comprising means for receiving user feedback and analyzing said feedback to update the algorithm. 【0866】 (Claim 3) 【0867】 The system according to claim 1, comprising means for collecting data from different sources such as social media posts, websites, and news articles, and means for analyzing advertising information. 【0868】 "Example 2 of combining an emotion engine" 【0869】 (Claim 1) 【0870】 Means for automatically collecting data from information sources, 【0871】 Means for preprocessing the collected data, 【0872】 A means for calculating a reliability score based on preprocessed data, 【0873】 A means of filtering data based on reliability scores, 【0874】 A means of analyzing the emotional state of users, 【0875】 A means of optimizing and providing information based on emotional state, 【0876】 A system that includes this. 【0877】 (Claim 2) 【0878】 The system according to claim 1, further comprising means for receiving user feedback and analyzing said feedback to update the algorithm. 【0879】 (Claim 3) 【0880】 The system according to claim 1, comprising means for collecting data from different sources and analyzing emotions via a user interface. 【0881】 "Application example 2 when combining with an emotional engine" 【0882】 (Claim 1) 【0883】 Means for automatically collecting data from information sources, 【0884】 Means for preprocessing the collected data, 【0885】 A means for calculating a reliability score based on preprocessed data, 【0886】 A means of filtering data based on reliability scores, 【0887】 A means of analyzing the emotional state of users, 【0888】 A means of selecting and providing data based on emotional state, 【0889】 Includes system. 【0890】 (Claim 2) 【0891】 The system according to claim 1, further comprising means for receiving user feedback and analyzing said feedback to update the algorithm. 【0892】 (Claim 3) 【0893】 The system according to claim 1, comprising means for collecting data from different sources. [Explanation of symbols] 【0894】 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

[Claim 1] Means for automatically collecting data from information sources, Means for preprocessing the collected data, A means for calculating a reliability score based on preprocessed data, A means of filtering data based on reliability scores, A means of providing filtered data to users, Includes system. [Claim 2] The system according to claim 1, further comprising means for receiving user feedback and analyzing said feedback to update the algorithm. [Claim 3] The system according to claim 1, comprising means for collecting data from different sources such as social media posts, websites, and news articles.

Images