system

Abstract

We provide the system. [Solution] A means for installing an artificial intelligence model on a mobile information processing terminal to detect false information and load the necessary resources into memory, A means for saving videos or news articles received from a user as input data in a buffer, A means for converting input data into an analyzable format and evaluating the reliability of the data using computer vision and natural language processing techniques, A means of displaying the obtained confidence score to the user and collecting feedback, A method for saving analysis logs within the device and anonymizing feedback data before sending it to an external server, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the evolution of communication technology, the amount of information flowing through the Internet has increased exponentially. As a result, false information, that is, fake information, is likely to spread, and its influence can not only cause personal misunderstandings but also lead to chaos in society as a whole. In addition, existing fake information detection technologies generally operate in a cloud-based manner and often do not consider privacy, so there is a need for a technology that can effectively detect fake information while protecting user privacy.

Means for Solving the Problems

[0005] This invention solves the aforementioned problems by utilizing artificial intelligence embedded in a mobile information processing terminal to evaluate the reliability of videos and news articles received by the user. Specifically, it uses an artificial intelligence model installed in the terminal to convert input data into an analyzable format and evaluates the reliability of the data using computer vision and natural language processing technologies. It also presents the user with the reliability score obtained as a result of the analysis, and provides detailed information if false information is detected. Furthermore, it provides a system that can autonomously improve the artificial intelligence model by collecting user feedback, anonymizing it, and sending it to an external server.

[0006] A "mobile information processing terminal" is an electronic device that a user can carry with them, and that transmits, receives, and processes information via a network connection.

[0007] An "artificial intelligence model" is a set of algorithms and programs trained to analyze data and automatically perform specific tasks.

[0008] A "buffer" is a memory area that temporarily holds data and efficiently transfers it to a processing unit.

[0009] "Computer vision" is a technological field that uses computers to acquire and analyze information from images and videos, mimicking human visual function.

[0010] "Natural language processing" is a field of technology that enables computers to understand, generate, and interact with human language.

[0011] A "confidence score" is an index that numerically evaluates whether specific information or data is true or not.

[0012] "Feedback" refers to user reactions and responses to the system's output, and is information that helps improve the system.

[0013] "Anonymization" refers to the process of transforming or processing data so that it cannot be used to identify specific individuals.

[0014] An "external server" is a computer system that can be accessed remotely via a network such as the internet, and is used for storing and processing data. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be 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), and the like.

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

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

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

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

[0023] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The system according to the present invention aims to detect and evaluate misinformation using an artificial intelligence model installed in a mobile information processing terminal. This system is designed to evaluate the reliability of videos and news articles received by users through their terminals.

[0037] First, the user provides the content they want to analyze, such as a video or news article, to the device. Upon receiving this input data, the device analyzes its content using an internally running artificial intelligence model. If the data format requires conversion for proper analysis, the device converts it to the appropriate format and supplies it to the analysis module.

[0038] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the input data. In this process, text is tokenized and compared against known misinformation patterns. For videos, frame analysis is used to detect consistency and characteristic patterns in the footage.

[0039] Based on the analysis, the device calculates a confidence score for the entire data set and provides this confidence score to the user. Along with the score, if any specific inconsistencies or potential misinformation are indicated, the user is also notified of the details.

[0040] Furthermore, users can send feedback on the results to their devices. This feedback is anonymized and then sent to an external server to help continuously improve the artificial intelligence model. This allows the system to improve its accuracy and reliability over time.

[0041] As a concrete example, consider a case where a user wants to verify the reliability of a news article. When the user inputs the news article into the device, the device analyzes the text of the article and compares it with existing reliable sources. If the device confirms that the article matches the characteristics and patterns of fake news, it notifies the user with a "low reliability" warning. In this way, the system of the present invention effectively identifies fake information from the information that users encounter on a daily basis and supports accurate judgment.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user activates their mobile information processing device and inputs the video or news article they want to analyze. This input data is temporarily stored on the device.

[0045] Step 2:

[0046] The terminal converts the input data into a format that can be analyzed. For videos, it extracts frames; for news articles, it tokenizes the text and performs preprocessing.

[0047] Step 3:

[0048] The device uses natural language processing technology to analyze the text contained in news articles. In particular, it detects known fake information patterns and sensational expressions and evaluates them using a language model.

[0049] Step 4:

[0050] The device uses computer vision technology to analyze each frame of the video. It identifies unnatural movement between frames and editing traces, and applies a deepfake detection algorithm.

[0051] Step 5:

[0052] The terminal integrates the aforementioned analysis results and calculates a confidence score for the entire input data. This score is calculated based on evaluations of similar historical data and information sources.

[0053] Step 6:

[0054] The device notifies the user of the trust score and analysis results. If necessary, it provides detailed information about potentially fake content and links to newly trusted sources.

[0055] Step 7:

[0056] The user enters feedback on the results into the terminal. This feedback is anonymized and sent to the server to improve the system's artificial intelligence model.

[0057] Step 8:

[0058] The terminal saves logs related to the analysis. This allows for quick reference in performing similar analyses at a later date and helps in understanding analysis trends.

[0059] Step 9:

[0060] The server uses the feedback data it receives to update the training dataset for the artificial intelligence model, thereby improving the model's performance.

[0061] (Example 1)

[0062] 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."

[0063] In modern society, diverse information is easily accessible via the internet, and this includes misinformation and intentionally distorted information. Such information can mislead users and cause social disruption. However, there is a lack of means to properly detect and evaluate misinformation, making it difficult to quickly and accurately determine its reliability. Solving this problem is essential to enable users to make accurate information judgments and prevent confusion caused by misinformation.

[0064] 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.

[0065] In this invention, the server is implemented in a mobile information processing device and includes means for activating a machine learning algorithm for detecting false information and loading the necessary computing resources into a storage device, means for storing images or information articles received from the user as input information in a temporary storage device, and means for converting the input information into an analyzable format and determining the reliability of the information using image recognition and language processing techniques. This makes it possible to quickly and accurately detect false information and support users in making decisions based on reliability.

[0066] A "mobile information processing device" refers to an electronic device that is portable by the user and capable of processing and communicating information.

[0067] A "machine learning algorithm" refers to a series of procedures that computers use to analyze data and recognize patterns.

[0068] "Misinformation" refers to information that intentionally or unintentionally distorts the facts or is likely to be misleading.

[0069] A "storage device" refers to an electronic component or device used to store and retrieve data.

[0070] "Temporary storage device" refers to a storage device used to retain data for a short period of time.

[0071] "Image recognition technology" refers to the technology of extracting specific information or patterns from images and analyzing them.

[0072] "Language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0073] An "informational article" refers to media content that provides information primarily through text.

[0074] A "confidence index" refers to a numerical indicator that quantifies the accuracy and reliability of the information provided.

[0075] "Evaluation opinions" refer to feedback from users and include views on the reliability and usefulness of specific information.

[0076] "Analysis history" refers to data that records the process and results of the analysis work, and can be referenced and verified at a later date.

[0077] "Anonymization" refers to a method of processing data in a way that makes it impossible to identify personal information.

[0078] An "external information processing device" refers to another electronic device located outside the target device that has data processing capabilities.

[0079] The system in this invention is realized by being installed in a mobile information processing device. Specifically, a machine learning algorithm for detecting misinformation is implemented and the user-provided content is analyzed. The device includes a storage device for saving data and a temporary storage device for temporarily storing data. Image recognition technology and language processing technology are also applied to identify misinformation. These enable the reliability of input information to be evaluated quickly and accurately.

[0080] Specifically, the user provides the mobile information processing device with a video or news article they wish to have analyzed. In the case of videos, the device analyzes frames and uses image recognition technology to identify consistent features. For text information, it uses language processing technology to tokenize the text and compares it with known patterns of misinformation. After analysis, a confidence index is calculated and the result is notified to the user. If the confidence index is deemed low, a warning is presented to the user. This helps users to independently assess the reliability of the information they receive.

[0081] Feedback is also a crucial aspect. Users can provide feedback on the results presented by the system. The terminal anonymizes this feedback and sends it to an external information processing device, which then uses it to improve the machine learning algorithm. This feedback loop contributes to improving the overall accuracy of the system.

[0082] A concrete example would be a scenario where a user enters a prompt such as, "Evaluate the reliability of this news article and return a reliability score," the system begins the analysis, and then presents the results to the user.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user inputs the video or news article they wish to analyze into their device. The input information is stored in temporary storage in its original data format. Specifically, for example, by pressing a button such as "Check Reliability" through a news app, the article is uploaded as data.

[0086] Step 2:

[0087] The terminal determines the format of the input data and performs conversions as necessary. For example, in the case of video, the terminal converts the data to the appropriate analysis format, and in the case of text, it formats it into a standard structure. During this process, format conversions are performed to ensure data consistency and analyzability. The output is input data in a data format suitable for analysis.

[0088] Step 3:

[0089] The device analyzes properly formatted data stored in its storage device in detail using computer vision and natural language processing techniques. Specifically, videos are analyzed frame by frame to identify consistency and characteristic patterns in the footage. Text data is tokenized and compared against known misinformation patterns. The output of this process is an overall confidence index of the information.

[0090] Step 4:

[0091] The device displays a confidence index to the user as an analysis result. The user can receive specific warnings (for example, a message indicating "low confidence") along with the confidence rating on the device screen. Information regarding the degree of confidence and the details obtained from the analysis help the user better judge the reliability of the information.

[0092] Step 5:

[0093] Users can send feedback on the presented results to the device. The device anonymizes the received feedback and forwards it to an external server. This feedback is then used to improve the machine learning algorithm. In this step, the specific actions are the collection of feedback and the anonymization of the data. The output is the anonymized feedback data.

[0094] (Application Example 1)

[0095] 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."

[0096] In today's information society, with the overwhelming amount of news and video information available, judging its reliability presents a significant challenge. In particular, content distribution services lack sufficient means for users to assess the accuracy of the information they view, potentially leading to the spread of misinformation and misconceptions. Therefore, there is a need to evaluate the reliability of information in real time and provide users with immediate access to its reliability status during viewing.

[0097] 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.

[0098] In this invention, the server includes means for installing on a mobile information processing device, activating a knowledge processing model for detecting false information, and loading necessary computing resources into a storage device; means for temporarily storing video or news content received from the user as input information; and means for converting the input information into an analyzable format and evaluating the reliability of the information using image recognition and language analysis techniques. This makes it possible in content distribution services to evaluate the reliability of information being viewed in real time and present it appropriately to the user.

[0099] A "mobile information processing device" is a portable electronic device that processes information and is used by users to input and analyze various types of information.

[0100] "Disinformation" refers to false information that is intentionally or erroneously provided, and especially unreliable information.

[0101] A "knowledge processing model" is a computational model used for the automated analysis and evaluation of information, and is typically constructed using machine learning or artificial intelligence technologies.

[0102] "Input information" refers to data provided by the user, including in the form of images and text, and is the data to be analyzed.

[0103] "Image recognition" is a technology that analyzes digital image information and automatically recognizes objects and patterns within it.

[0104] "Language analysis technology" refers to the technology used to analyze text data, understand its meaning, and process information.

[0105] "Reliability" is an indicator that represents the accuracy and truthfulness of the information obtained as a result of the analysis, and is an evaluation score provided to the user.

[0106] "Temporary memory" refers to a memory area used to store data instantaneously, and is used for the temporary retention of data.

[0107] This system operates on a mobile information processing device and detects and evaluates inaccurate information. The device receives video and text data provided by the user and stores it in temporary memory. Next, the input information is converted into an analyzable format, and its reliability is evaluated using a knowledge processing model. Image recognition and language analysis techniques are combined to detect information consistency and known inaccuracy patterns.

[0108] The server calculates the reliability score and displays it to the user in real time. This involves cross-referencing with reliable sources and identifying features and patterns that indicate low reliability. Users can understand the reliability of the information and gain insights into their decision-making process while viewing it. Furthermore, receiving feedback from users allows for continuous improvement of the knowledge processing model.

[0109] In this embodiment, to give a specific example, while the user is viewing news content, the terminal analyzes the content using a knowledge processing model and calculates its reliability. For example, when an article about a "breakthrough in new technology" is entered, the terminal evaluates the reliability of the news content and, if it is highly reliable, immediately displays "This information is reliable."

[0110] Examples of prompts to input into a generative AI model:

[0111] Please rate the reliability of the following news articles. Assign a high score for high reliability and a low score for low reliability.

[0112] Input text: "Scientists announce they have discovered a groundbreaking energy source."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The terminal receives video or news content as input from the user. It stores the input information in temporary memory. At this time, the terminal checks the format of the received data and prepares to convert it into an analyzable format.

[0116] Step 2:

[0117] The terminal converts the input information into a parseable format. For example, video data is divided into frames, and news content is tokenized by a tokenizer. This makes the data usable in a knowledge processing model.

[0118] Step 3:

[0119] The device uses a knowledge processing model to evaluate the reliability of the transformed data. It analyzes frames using image recognition technology and identifies patterns in news content using language analysis technology. This results in the calculation of a reliability score, evaluating the accuracy of the data.

[0120] Step 4:

[0121] The device displays the obtained confidence score to the user. If the confidence score is low, it provides visual warnings and information to draw attention. This allows the user to intuitively judge the reliability of the information.

[0122] Step 5:

[0123] The terminal receives responses from the user, anonymizes them, and sends them to the server. The responses are used to improve the knowledge processing model. The server uses the received data to improve the accuracy of the generated AI model and applies this to the next analysis.

[0124] 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.

[0125] The system according to the present invention enables mobile information processing terminals to evaluate the reliability of content received by the user and provide feedback that takes the user's emotions into consideration. By combining an artificial intelligence model and an emotion engine, the aim is to improve the user experience and achieve effective identification of fake information.

[0126] First, the user inputs the video or news article they want to review via the device. The input data is received by the device for reliability evaluation. In this process, the device converts the data into a parseable format, performs preprocessing, and prepares it for reliability evaluation.

[0127] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the data. The natural language processing process tokenizes the content of news articles and checks for matches with existing trusted sources and fake patterns. Computer vision technology analyzes each frame of the video to detect traces of editing or unnatural movements.

[0128] Furthermore, the device incorporates an emotion engine that analyzes the user's response to input data in real time. Based on this emotion analysis, the method of presenting the analysis results is adjusted. For example, if the user is showing anxiety, the results can be presented in a more user-friendly format.

[0129] As a result of the analysis, the device generates a trust score and notifies the user. This score may include detailed information based on the user's sentiment. The user can review the analysis results and provide feedback in different formats. This feedback is anonymized in a privacy-conscious manner and securely transmitted to the server.

[0130] As a concrete example, when a user wants to determine the reliability of a news video, the device scans the video and analyzes the title and description. In this process, the emotion engine picks up the user's reaction, which might, for example, detect surprise. Taking this into account, the results are presented in a format appropriate to the user's emotion, and together with the confidence score, it helps in making a quick and accurate decision.

[0131] Because this system operates entirely on the device, it protects user privacy while enabling advanced analysis in real time. In this way, the combination of artificial intelligence models and emotion engines makes the invention a valuable tool for users.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user accesses a mobile information processing device and selects and inputs the video or news article they want to analyze. The input data is immediately saved to a buffer on the device.

[0135] Step 2:

[0136] The terminal converts the received input data into a format that can be analyzed. For videos, individual frames are extracted, and for news articles, the text is tokenized to prepare the data for analysis.

[0137] Step 3:

[0138] The device uses natural language processing technology to analyze the content of news articles. Specifically, it understands the context, extracts keywords, and checks for the possibility of fake information by comparing it with known, reliable sources.

[0139] Step 4:

[0140] The device utilizes computer vision technology to analyze each frame of a video. It investigates the consistency of faces and backgrounds in the video, with the aim of detecting deepfakes and anomalies.

[0141] Step 5:

[0142] An emotion engine built into the device analyzes the user's actions and inputs. It identifies the emotional state in real time and dynamically adjusts how the results are presented to make the user's explanations easier to understand.

[0143] Step 6:

[0144] The device calculates a confidence score from the analyzed data and provides it to the user. At the same time, it provides additional information and warnings tailored to the user's emotions, encouraging appropriate feedback along with the score.

[0145] Step 7:

[0146] The user enters their score and feedback on the results and sends it to the device. The device anonymizes this feedback and securely transfers it to the server.

[0147] Step 8:

[0148] The server analyzes the collected feedback data and uses it as a dataset to update the artificial intelligence model. This continuously improves the model's accuracy and reliability.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] In modern society, a vast amount of information circulates on the internet, including misinformation and biased information. Instantly judging this information and selecting reliable information is not easy and places a significant burden on users. Furthermore, how information is received is influenced by users' emotions, so the method of information delivery needs to be optimized for each individual user. To solve this problem, a system is needed that not only assesses the reliability of information but also analyzes users' emotions and delivers information in an appropriate manner.

[0152] 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.

[0153] In this invention, the server includes means for installing on a mobile information processing device, activating an intelligent model for detecting misinformation, and loading necessary resources into a storage device; means for temporarily storing images or articles received from the user as input information; means for converting the input information into an analyzable format and evaluating the reliability of the information using image analysis and automatic language processing techniques; means for analyzing the user's emotions based on the evaluation and adjusting the display method according to the results; means for displaying the generated reliability level to the user and collecting opinions; and means for recording the analysis history within the device and transmitting the opinion data anonymized to a remote device. This makes it possible to quickly and accurately determine the reliability of information and provide information in a way that is adapted to the user's emotions.

[0154] A "mobile information processing device" is an electronic device that is portable and capable of collecting, processing, and communicating information.

[0155] An "intelligent model" is a program built with algorithms that analyze information, identify specific patterns, and learn to improve its functionality.

[0156] A "storage device" is a hardware component used to temporarily or permanently store data or programs.

[0157] "Temporary memory" refers to a memory area that holds data for a short period of time and allows for immediate access.

[0158] "Image analysis" is a technique that processes digital images and extracts information from them.

[0159] "Automated language processing technology" refers to technologies that enable computers to understand and generate natural language.

[0160] "Reliability assessment" is an analytical process for determining the accuracy and degree of misinformation of information.

[0161] "Analyzing emotions" is the process of identifying the user's emotional state and classifying data based on that.

[0162] A "remote device" is an external device that is connected via a communication network and used to send and receive data.

[0163] This invention is based on a mobile information processing device used by the user and utilizes an intelligent model for misinformation detection. The process primarily begins with the terminal installing and activating the intelligent model and loading the necessary resources into its storage device. Specifically, the device incorporates programs for data analysis, utilizing image analysis and automated language processing technologies. The device leverages natural language processing libraries and computer vision libraries to convert video and article data received from the user into an analyzable format.

[0164] This device is equipped with an emotion engine that analyzes responses in real time based on user input, and displays information in a format optimized for each individual user based on the evaluation results. The server also has the function of collecting anonymous opinions provided by users and securely transmitting them to the remote device. This creates a data feedback cycle, enabling continuous learning and updating of the generative AI model.

[0165] For example, if a user wants to check the reliability of a news video, the device can analyze the video and provide a reliability rating for the question posed. The system would receive highly accurate feedback in the form of a prompt such as, "How reliable is this news video?"

[0166] Through the above process, the invention enables the efficient evaluation of diverse information and the provision of information adapted to the user's emotions and needs. The system operates in real time and aims to enhance user trust.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The user inputs videos or news articles they want to evaluate via a mobile information processing device. The input data can take the form of URLs or copied text, and the device receives this data and stores it in temporary memory. In this case, user input acts as the initial trigger for the program.

[0170] Step 2:

[0171] The device converts data stored in temporary memory into an analyzable format. Specifically, it uses a natural language processing library to tokenize text data and extract key concepts. For video data, it uses a computer vision library to perform frame-by-frame image analysis and recognize objects and motion within the video. The input is raw data provided by the user, and the output is in a data format suitable for analysis.

[0172] Step 3:

[0173] The terminal uses an intelligent model to evaluate the reliability of the information based on the converted data. This stage includes a process to check for matches with known misinformation patterns. Specifically, the data is compared with an existing information base to identify similar patterns. The input to this process is the analyzable data obtained in step 2, and the output is a confidence score.

[0174] Step 4:

[0175] An emotion engine built into the device analyzes the user's emotional responses during the evaluation process. It senses and evaluates the user's facial expressions and voice data in real time, and adjusts the display method of the results based on the emotions the user expresses. The input at this stage is real-time user data, and the output is a customized display method of results that corresponds to the user's emotional state.

[0176] Step 5:

[0177] The device notifies the user of the score obtained as a result of the reliability evaluation. In addition to the reliability score, the results may include a detailed explanation based on the user's sentiment. The input here is the result data of the evaluation process, and the output is the result interface displayed to the user.

[0178] Step 6:

[0179] The user reviews the presented results and provides feedback through their device. The device anonymizes this feedback data and securely sends it to the server. The input is the user's feedback, and the output is the anonymized data sent to the server. The server stores this data and uses it to improve the generated AI model.

[0180] (Application Example 2)

[0181] 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 device 14 will be referred to as the "terminal."

[0182] In modern society, a vast amount of information circulates daily via the internet, but much of it lacks reliability. In particular, with news articles and video content, users often lack appropriate guidelines for judging their reliability, potentially leading to decision-making based on misinformation. Furthermore, providing information without considering the user's emotional state can lead to misunderstandings. Thus, there is a growing need for a system that simultaneously achieves both information reliability assessment and emotional consideration.

[0183] 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.

[0184] In this invention, the server includes means for installing on a mobile information processing terminal, activating an artificial intelligence model for detecting false information, and loading necessary computing resources into a storage device; means for storing videos or news articles received from the user as input information in the storage area; means for converting the input information into an analyzable format and evaluating the reliability of the information using image processing and natural language processing techniques; means for displaying the obtained reliability value to the user and collecting responses; means for storing analysis records within the terminal, anonymizing response data, and transmitting it to an external storage device; and means for analyzing the user's emotions and adjusting the method of presenting the analysis results according to the emotional state. This enables reliability evaluation and information presentation tailored to emotions.

[0185] A "mobile information processing terminal" is a portable computing device that allows users to process various types of information.

[0186] "Misinformation" refers to inaccurate or misleading information that is not based on facts.

[0187] An "artificial intelligence model" is a computational model built using machine learning algorithms to perform a specific task.

[0188] "Computational resources" is a general term for the hardware and software necessary for information processing.

[0189] A "memory device" is a device used to store data and programs.

[0190] "Memory space" is a place where data is temporarily stored.

[0191] "Image processing" is a technique that analyzes and transforms still images or videos to extract useful information.

[0192] "Natural language processing" is a technology that analyzes text information and understands its meaning.

[0193] "Confidence level" is an indicator that quantifies the reliability of information.

[0194] "Response" refers to feedback or reaction from the user.

[0195] "Analysis records" refer to documents that document the data and results obtained during the analysis process.

[0196] An "external storage device" is a device that can retain data for a long period of time.

[0197] "Emotional state" refers to the user's psychological condition and the emotions they are experiencing.

[0198] This invention is a system that uses a mobile information processing terminal to detect false information and present information in accordance with the user's emotions. The terminal integrates an artificial intelligence model and an emotion engine, which evaluate the reliability of the data and analyze the user's emotions.

[0199] The terminal first receives a video or news article from the user and stores it in memory as input information. Then, it converts the input information into a parseable format and evaluates the reliability of the information using image processing and natural language processing techniques. In this process, natural language processing libraries (e.g., SpaCy, NLTK) and computer vision technologies (e.g., OpenCV, TENSORFLOW®) are used for reliability evaluation. As a result of the reliability evaluation, a confidence score is generated and displayed to the user. Furthermore, user feedback is collected and processed as response data. The response data is anonymized and sent to an external storage device.

[0200] Furthermore, the device incorporates an emotion engine that analyzes the user's emotional state in real time. This allows the presentation of the analysis results to be adjusted according to the user's emotional state. For example, if the user is showing anxiety, the analysis results will be presented in a more user-friendly format.

[0201] As a concrete example, consider a scenario where a user watches a movie review video. The device scans the video and evaluates its reliability while simultaneously analyzing the user's emotions. If an emotion of surprise is detected, the results are presented in a milder tone and style.

[0202] This system allows users to obtain reliable information and receive appropriate feedback that aligns with their emotions. For example, a prompt such as, "Please rate the reliability of this video and provide emotionally appropriate feedback," can be used to initiate a reliability assessment and emotionally sensitive process.

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The device receives videos or news articles from the user. The input information is stored in the mobile information processing device's memory. This input information serves as the basis for subsequent reliability evaluation processes.

[0206] Step 2:

[0207] The terminal converts the received input information into a parseable format. In the case of videos, it is broken down into frames, and in the case of news articles, the text is tokenized. This process is carried out using natural language processing libraries and image processing tools.

[0208] Step 3:

[0209] The device uses natural language processing (NLP) techniques to analyze news articles or video subtitles. It uses tokenized text as input and detects matches with known, reliable sources and misinformation patterns. The output is a confidence score, which is further processed for display to the user.

[0210] Step 4:

[0211] The device uses computer vision technology to analyze video frames. It detects unnatural movements and signs of editing, and evaluates the reliability of the information. The input is decomposed video frames, and the output generates a reliability index for each frame.

[0212] Step 5:

[0213] The device integrates reliability scores and calculates a final confidence value. This confidence value indicates the reliability of the information presented to the user. The integration process comprehensively evaluates the scores obtained from natural language and image analysis.

[0214] Step 6:

[0215] The device analyzes the user's emotions in real time using an emotion engine. It analyzes the emotional state in response to the user's input and detects emotions such as comfort and surprise. The user's reactions are used as input data, and the output is an indicator representing the emotional state.

[0216] Step 7:

[0217] The device adjusts how it presents analysis results, along with a reliability score, to the user. Based on the user's emotions, for example, if they are surprised, the results are presented with a calming design and tone. This output allows the user to receive the information more appropriately.

[0218] Step 8:

[0219] The device collects user feedback and stores it along with analysis logs. The feedback data is anonymized and sent to an external storage device. This feedback is used to update and improve the artificial intelligence model later on.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] The system according to the present invention aims to detect and evaluate misinformation using an artificial intelligence model installed in a mobile information processing terminal. This system is designed to evaluate the reliability of videos and news articles received by users through their terminals.

[0237] First, the user provides the content they want to analyze, such as a video or news article, to the device. Upon receiving this input data, the device analyzes its content using an internally running artificial intelligence model. If the data format requires conversion for proper analysis, the device converts it to the appropriate format and supplies it to the analysis module.

[0238] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the input data. In this process, text is tokenized and compared against known misinformation patterns. For videos, frame analysis is used to detect consistency and characteristic patterns in the footage.

[0239] Based on the analysis, the device calculates a confidence score for the entire data set and provides this confidence score to the user. Along with the score, if any specific inconsistencies or potential misinformation are indicated, the user is also notified of the details.

[0240] Furthermore, users can send feedback on the results to their devices. This feedback is anonymized and then sent to an external server to help continuously improve the artificial intelligence model. This allows the system to improve its accuracy and reliability over time.

[0241] As a concrete example, consider a case where a user wants to verify the reliability of a news article. When the user inputs the news article into the device, the device analyzes the text of the article and compares it with existing reliable sources. If the device confirms that the article matches the characteristics and patterns of fake news, it notifies the user with a "low reliability" warning. In this way, the system of the present invention effectively identifies fake information from the information that users encounter on a daily basis and supports accurate judgment.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The user activates their mobile information processing device and inputs the video or news article they want to analyze. This input data is temporarily stored on the device.

[0245] Step 2:

[0246] The terminal converts the input data into a format that can be analyzed. For videos, it extracts frames; for news articles, it tokenizes the text and performs preprocessing.

[0247] Step 3:

[0248] The device uses natural language processing technology to analyze the text contained in news articles. In particular, it detects known fake information patterns and sensational expressions and evaluates them using a language model.

[0249] Step 4:

[0250] The device uses computer vision technology to analyze each frame of the video. It identifies unnatural movement between frames and editing traces, and applies a deepfake detection algorithm.

[0251] Step 5:

[0252] The terminal integrates the aforementioned analysis results and calculates a confidence score for the entire input data. This score is calculated based on evaluations of similar historical data and information sources.

[0253] Step 6:

[0254] The device notifies the user of the trust score and analysis results. If necessary, it provides detailed information about potentially fake content and links to newly trusted sources.

[0255] Step 7:

[0256] The user enters feedback on the results into the terminal. This feedback is anonymized and sent to the server to improve the system's artificial intelligence model.

[0257] Step 8:

[0258] The terminal saves logs related to the analysis. This allows for quick reference in performing similar analyses at a later date and helps in understanding analysis trends.

[0259] Step 9:

[0260] The server uses the feedback data it receives to update the training dataset for the artificial intelligence model, thereby improving the model's performance.

[0261] (Example 1)

[0262] 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."

[0263] In modern society, diverse information is easily accessible via the internet, and this includes misinformation and intentionally distorted information. Such information can mislead users and cause social disruption. However, there is a lack of means to properly detect and evaluate misinformation, making it difficult to quickly and accurately determine its reliability. Solving this problem is essential to enable users to make accurate information judgments and prevent confusion caused by misinformation.

[0264] 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.

[0265] In this invention, the server is implemented in a mobile information processing device and includes means for activating a machine learning algorithm for detecting false information and loading the necessary computing resources into a storage device, means for storing images or information articles received from the user as input information in a temporary storage device, and means for converting the input information into an analyzable format and determining the reliability of the information using image recognition and language processing techniques. This makes it possible to quickly and accurately detect false information and support users in making decisions based on reliability.

[0266] A "mobile information processing device" refers to an electronic device that is portable by the user and capable of processing and communicating information.

[0267] A "machine learning algorithm" refers to a series of procedures that computers use to analyze data and recognize patterns.

[0268] "Misinformation" refers to information that intentionally or unintentionally distorts the facts or is likely to be misleading.

[0269] A "storage device" refers to an electronic component or device used to store and retrieve data.

[0270] "Temporary storage device" refers to a storage device used to retain data for a short period of time.

[0271] "Image recognition technology" refers to the technology of extracting specific information or patterns from images and analyzing them.

[0272] "Language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0273] An "informational article" refers to media content that provides information primarily through text.

[0274] A "confidence index" refers to a numerical indicator that quantifies the accuracy and reliability of the information provided.

[0275] "Evaluation opinions" refer to feedback from users and include views on the reliability and usefulness of specific information.

[0276] "Analysis history" refers to data that records the process and results of the analysis work, and can be referenced and verified at a later date.

[0277] "Anonymization" refers to a method of processing data in a way that makes it impossible to identify personal information.

[0278] An "external information processing device" refers to another electronic device located outside the target device that has data processing capabilities.

[0279] The system in this invention is realized by being installed in a mobile information processing device. Specifically, a machine learning algorithm for detecting misinformation is implemented and the user-provided content is analyzed. The device includes a storage device for saving data and a temporary storage device for temporarily storing data. Image recognition technology and language processing technology are also applied to identify misinformation. These enable the reliability of input information to be evaluated quickly and accurately.

[0280] Specifically, the user provides the mobile information processing device with a video or news article they wish to have analyzed. In the case of videos, the device analyzes frames and uses image recognition technology to identify consistent features. For text information, it uses language processing technology to tokenize the text and compares it with known patterns of misinformation. After analysis, a confidence index is calculated and the result is notified to the user. If the confidence index is deemed low, a warning is presented to the user. This helps users to independently assess the reliability of the information they receive.

[0281] Feedback is also a crucial aspect. Users can provide feedback on the results presented by the system. The terminal anonymizes this feedback and sends it to an external information processing device, which then uses it to improve the machine learning algorithm. This feedback loop contributes to improving the overall accuracy of the system.

[0282] A concrete example would be a scenario where a user enters a prompt such as, "Evaluate the reliability of this news article and return a reliability score," the system begins the analysis, and then presents the results to the user.

[0283] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0284] Step 1:

[0285] The user inputs a video or news article to be analyzed into the terminal. The input information is stored in a temporary storage device in its original data format. As a specific operation, for example, by pressing a button such as "Check Reliability" through a news app, the article is uploaded as data.

[0286] Step 2:

[0287] The terminal determines the format of the input data and performs conversion if necessary. For example, in the case of a video, the terminal converts the data into an appropriate analysis format, and in the case of text, it formats it into a standard structure. In this process, format conversion is performed to ensure data consistency and analyzability. The output is input data with a data format suitable for analysis.

[0288] Step 3:

[0289] The terminal analyzes the appropriately formatted data stored in the storage device in detail using computer vision and natural language processing technologies. Specifically, the video is analyzed frame by frame to identify video consistency and characteristic patterns. The text data is tokenized and compared with known misinformation patterns. The output of this process is a reliability index for the entire information.

[0290] Step 4:

[0291] The terminal displays the reliability index to the user as an analysis result. The user can receive a specific warning (such as a display saying "Low reliability") together with the reliability evaluation on the terminal screen. Information regarding the degree of reliability and details obtained from the analysis serve as materials for the user to better judge the reliability of the information.

[0292] Step 5:

[0293] Users can send feedback on the presented results to the device. The device anonymizes the received feedback and forwards it to an external server. This feedback is then used to improve the machine learning algorithm. In this step, the specific actions are the collection of feedback and the anonymization of the data. The output is the anonymized feedback data.

[0294] (Application Example 1)

[0295] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0296] In today's information society, with the overwhelming amount of news and video information available, judging its reliability presents a significant challenge. In particular, content distribution services lack sufficient means for users to assess the accuracy of the information they view, potentially leading to the spread of misinformation and misconceptions. Therefore, there is a need to evaluate the reliability of information in real time and provide users with immediate access to its reliability status during viewing.

[0297] 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.

[0298] In this invention, the server includes means for installing on a mobile information processing device, activating a knowledge processing model for detecting false information, and loading necessary computing resources into a storage device; means for temporarily storing video or news content received from the user as input information; and means for converting the input information into an analyzable format and evaluating the reliability of the information using image recognition and language analysis techniques. This makes it possible in content distribution services to evaluate the reliability of information being viewed in real time and present it appropriately to the user.

[0299] A "mobile information processing device" is a portable electronic device that processes information and is used by users to input and analyze various types of information.

[0300] "False information" refers to incorrect information provided intentionally or by mistake, and particularly refers to information that cannot be trusted.

[0301] "Knowledge processing model" is a computational model for automatically analyzing and evaluating information, and is usually constructed using machine learning and artificial intelligence technologies.

[0302] "Input information" is data provided by a user, including forms such as videos and texts, and means data to be analyzed.

[0303] "Image recognition" is a technology for analyzing digital image information and automatically recognizing objects and patterns therein.

[0304] "Language analysis technology" is a technology for analyzing text data to understand its meaning and process information.

[0305] "Reliability" is an index representing the accuracy and authenticity of information obtained as an analysis result, and is an evaluation score provided to the user.

[0306] "Short-term memory" is a memory area for temporarily storing data and is used for temporarily holding data.

[0307] This system operates on a mobile information processing device and detects and evaluates inaccurate information. The terminal receives video and text data provided by the user and stores it in short-term memory. Next, the input information is converted into an analyzable format and its reliability is evaluated using a knowledge processing model. By combining image recognition and language analysis technologies, the consistency of information and known inaccurate information patterns are detected.

[0308] The server calculates the reliability score and displays it to the user in real time. This involves cross-referencing with reliable sources and identifying features and patterns that indicate low reliability. Users can understand the reliability of the information and gain insights into their decision-making process while viewing it. Furthermore, receiving feedback from users allows for continuous improvement of the knowledge processing model.

[0309] In this embodiment, to give a specific example, while the user is viewing news content, the terminal analyzes the content using a knowledge processing model and calculates its reliability. For example, when an article about a "breakthrough in new technology" is entered, the terminal evaluates the reliability of the news content and, if it is highly reliable, immediately displays "This information is reliable."

[0310] Examples of prompts to input into a generative AI model:

[0311] Please rate the reliability of the following news articles. Assign a high score for high reliability and a low score for low reliability.

[0312] Input text: "Scientists announce they have discovered a groundbreaking energy source."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The terminal receives video or news content as input from the user. It stores the input information in temporary memory. At this time, the terminal checks the format of the received data and prepares to convert it into an analyzable format.

[0316] Step 2:

[0317] The terminal converts the input information into a parseable format. For example, video data is divided into frames, and news content is tokenized by a tokenizer. This makes the data usable in a knowledge processing model.

[0318] Step 3:

[0319] The device uses a knowledge processing model to evaluate the reliability of the transformed data. It analyzes frames using image recognition technology and identifies patterns in news content using language analysis technology. This results in the calculation of a reliability score, evaluating the accuracy of the data.

[0320] Step 4:

[0321] The device displays the obtained confidence score to the user. If the confidence score is low, it provides visual warnings and information to draw attention. This allows the user to intuitively judge the reliability of the information.

[0322] Step 5:

[0323] The terminal receives responses from the user, anonymizes them, and sends them to the server. The responses are used to improve the knowledge processing model. The server uses the received data to improve the accuracy of the generated AI model and applies this to the next analysis.

[0324] 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.

[0325] The system according to the present invention enables mobile information processing terminals to evaluate the reliability of content received by the user and provide feedback that takes the user's emotions into consideration. By combining an artificial intelligence model and an emotion engine, the aim is to improve the user experience and achieve effective identification of fake information.

[0326] First, the user inputs the video or news article they want to review via the device. The input data is received by the device for reliability evaluation. In this process, the device converts the data into a parseable format, performs preprocessing, and prepares it for reliability evaluation.

[0327] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the data. The natural language processing process tokenizes the content of news articles and checks for matches with existing trusted sources and fake patterns. Computer vision technology analyzes each frame of the video to detect traces of editing or unnatural movements.

[0328] Furthermore, the device incorporates an emotion engine that analyzes the user's response to input data in real time. Based on this emotion analysis, the method of presenting the analysis results is adjusted. For example, if the user is showing anxiety, the results can be presented in a more user-friendly format.

[0329] As a result of the analysis, the device generates a trust score and notifies the user. This score may include detailed information based on the user's sentiment. The user can review the analysis results and provide feedback in different formats. This feedback is anonymized in a privacy-conscious manner and securely transmitted to the server.

[0330] As a concrete example, when a user wants to determine the reliability of a news video, the device scans the video and analyzes the title and description. In this process, the emotion engine picks up the user's reaction, which might, for example, detect surprise. Taking this into account, the results are presented in a format appropriate to the user's emotion, and together with the confidence score, it helps in making a quick and accurate decision.

[0331] Because this system operates entirely on the device, it protects user privacy while enabling advanced analysis in real time. In this way, the combination of artificial intelligence models and emotion engines makes the invention a valuable tool for users.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The user accesses a mobile information processing device and selects and inputs the video or news article they want to analyze. The input data is immediately saved to a buffer on the device.

[0335] Step 2:

[0336] The terminal converts the received input data into a format that can be analyzed. For videos, individual frames are extracted, and for news articles, the text is tokenized to prepare the data for analysis.

[0337] Step 3:

[0338] The device uses natural language processing technology to analyze the content of news articles. Specifically, it understands the context, extracts keywords, and checks for the possibility of fake information by comparing it with known, reliable sources.

[0339] Step 4:

[0340] The device utilizes computer vision technology to analyze each frame of a video. It investigates the consistency of faces and backgrounds in the video, with the aim of detecting deepfakes and anomalies.

[0341] Step 5:

[0342] An emotion engine built into the device analyzes the user's actions and inputs. It identifies the emotional state in real time and dynamically adjusts how the results are presented to make the user's explanations easier to understand.

[0343] Step 6:

[0344] The device calculates a confidence score from the analyzed data and provides it to the user. At the same time, it provides additional information and warnings tailored to the user's emotions, encouraging appropriate feedback along with the score.

[0345] Step 7:

[0346] The user enters their score and feedback on the results and sends it to the device. The device anonymizes this feedback and securely transfers it to the server.

[0347] Step 8:

[0348] The server analyzes the collected feedback data and uses it as a dataset to update the artificial intelligence model. This continuously improves the model's accuracy and reliability.

[0349] (Example 2)

[0350] 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".

[0351] In modern society, a vast amount of information circulates on the internet, including misinformation and biased information. Instantly judging this information and selecting reliable information is not easy and places a significant burden on users. Furthermore, how information is received is influenced by users' emotions, so the method of information delivery needs to be optimized for each individual user. To solve this problem, a system is needed that not only assesses the reliability of information but also analyzes users' emotions and delivers information in an appropriate manner.

[0352] 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.

[0353] In this invention, the server includes means for installing on a mobile information processing device, activating an intelligent model for detecting misinformation, and loading necessary resources into a storage device; means for temporarily storing images or articles received from the user as input information; means for converting the input information into an analyzable format and evaluating the reliability of the information using image analysis and automatic language processing techniques; means for analyzing the user's emotions based on the evaluation and adjusting the display method according to the results; means for displaying the generated reliability level to the user and collecting opinions; and means for recording the analysis history within the device and transmitting the opinion data anonymized to a remote device. This makes it possible to quickly and accurately determine the reliability of information and provide information in a way that is adapted to the user's emotions.

[0354] A "mobile information processing device" is an electronic device that is portable and capable of collecting, processing, and communicating information.

[0355] An "intelligent model" is a program built with algorithms that analyze information, identify specific patterns, and learn to improve its functionality.

[0356] A "storage device" is a hardware component used to temporarily or permanently store data or programs.

[0357] "Temporary memory" refers to a memory area that holds data for a short period of time and allows for immediate access.

[0358] "Image analysis" is a technique that processes digital images and extracts information from them.

[0359] "Automated language processing technology" refers to technologies that enable computers to understand and generate natural language.

[0360] "Reliability assessment" is an analytical process for determining the accuracy and degree of misinformation of information.

[0361] "Analyzing emotions" is the process of identifying the user's emotional state and classifying data based on that.

[0362] A "remote device" is an external device that is connected via a communication network and used to send and receive data.

[0363] This invention is based on a mobile information processing device used by the user and utilizes an intelligent model for misinformation detection. The process primarily begins with the terminal installing and activating the intelligent model and loading the necessary resources into its storage device. Specifically, the device incorporates programs for data analysis, utilizing image analysis and automated language processing technologies. The device leverages natural language processing libraries and computer vision libraries to convert video and article data received from the user into an analyzable format.

[0364] This device is equipped with an emotion engine that analyzes responses in real time based on user input, and displays information in a format optimized for each individual user based on the evaluation results. The server also has the function of collecting anonymous opinions provided by users and securely transmitting them to the remote device. This creates a data feedback cycle, enabling continuous learning and updating of the generative AI model.

[0365] For example, if a user wants to check the reliability of a news video, the device can analyze the video and provide a reliability rating for the question posed. The system would receive highly accurate feedback in the form of a prompt such as, "How reliable is this news video?"

[0366] Through the above process, the invention enables the efficient evaluation of diverse information and the provision of information adapted to the user's emotions and needs. The system operates in real time and aims to enhance user trust.

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The user inputs videos or news articles they want to evaluate via a mobile information processing device. The input data can take the form of URLs or copied text, and the device receives this data and stores it in temporary memory. In this case, user input acts as the initial trigger for the program.

[0370] Step 2:

[0371] The device converts data stored in temporary memory into an analyzable format. Specifically, it uses a natural language processing library to tokenize text data and extract key concepts. For video data, it uses a computer vision library to perform frame-by-frame image analysis and recognize objects and motion within the video. The input is raw data provided by the user, and the output is in a data format suitable for analysis.

[0372] Step 3:

[0373] The terminal uses an intelligent model to evaluate the reliability of the information based on the converted data. This stage includes a process to check for matches with known misinformation patterns. Specifically, the data is compared with an existing information base to identify similar patterns. The input to this process is the analyzable data obtained in step 2, and the output is a confidence score.

[0374] Step 4:

[0375] An emotion engine built into the device analyzes the user's emotional responses during the evaluation process. It senses and evaluates the user's facial expressions and voice data in real time, and adjusts the display method of the results based on the emotions the user expresses. The input at this stage is real-time user data, and the output is a customized display method of results that corresponds to the user's emotional state.

[0376] Step 5:

[0377] The device notifies the user of the score obtained as a result of the reliability evaluation. In addition to the reliability score, the results may include a detailed explanation based on the user's sentiment. The input here is the result data of the evaluation process, and the output is the result interface displayed to the user.

[0378] Step 6:

[0379] The user reviews the presented results and provides feedback through their device. The device anonymizes this feedback data and securely sends it to the server. The input is the user's feedback, and the output is the anonymized data sent to the server. The server stores this data and uses it to improve the generated AI model.

[0380] (Application Example 2)

[0381] 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 as the "terminal".

[0382] In modern society, a vast amount of information circulates daily via the internet, but much of it lacks reliability. In particular, with news articles and video content, users often lack appropriate guidelines for judging their reliability, potentially leading to decision-making based on misinformation. Furthermore, providing information without considering the user's emotional state can lead to misunderstandings. Thus, there is a growing need for a system that simultaneously achieves both information reliability assessment and emotional consideration.

[0383] 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.

[0384] In this invention, the server includes means for installing on a mobile information processing terminal, activating an artificial intelligence model for detecting false information, and loading necessary computing resources into a storage device; means for storing videos or news articles received from the user as input information in the storage area; means for converting the input information into an analyzable format and evaluating the reliability of the information using image processing and natural language processing techniques; means for displaying the obtained reliability value to the user and collecting responses; means for storing analysis records within the terminal, anonymizing response data, and transmitting it to an external storage device; and means for analyzing the user's emotions and adjusting the method of presenting the analysis results according to the emotional state. This enables reliability evaluation and information presentation tailored to emotions.

[0385] A "mobile information processing terminal" is a portable computing device that allows users to process various types of information.

[0386] "Misinformation" refers to inaccurate or misleading information that is not based on facts.

[0387] An "artificial intelligence model" is a computational model built using machine learning algorithms to perform a specific task.

[0388] "Computational resources" is a general term for the hardware and software necessary for information processing.

[0389] A "memory device" is a device used to store data and programs.

[0390] "Memory space" is a place where data is temporarily stored.

[0391] "Image processing" is a technique that analyzes and transforms still images or videos to extract useful information.

[0392] "Natural language processing" is a technology that analyzes text information and understands its meaning.

[0393] "Confidence level" is an indicator that quantifies the reliability of information.

[0394] "Response" refers to feedback or reaction from the user.

[0395] "Analysis records" refer to documents that document the data and results obtained during the analysis process.

[0396] An "external storage device" is a device that can retain data for a long period of time.

[0397] "Emotional state" refers to the user's psychological condition and the emotions they are experiencing.

[0398] This invention is a system that uses a mobile information processing terminal to detect false information and present information in accordance with the user's emotions. The terminal integrates an artificial intelligence model and an emotion engine, which evaluate the reliability of the data and analyze the user's emotions.

[0399] The terminal first receives a video or news article from the user and stores it in memory as input information. Then, it converts the input information into a parseable format and evaluates the reliability of the information using image processing and natural language processing techniques. In this process, natural language processing libraries (e.g., SpaCy, NLTK) and computer vision technologies (e.g., OpenCV, TensorFlow) are used for reliability evaluation. As a result of the reliability evaluation, a confidence score is generated and displayed to the user. Furthermore, user feedback is collected and processed as response data. The response data is anonymized and sent to an external storage device.

[0400] Furthermore, the device incorporates an emotion engine that analyzes the user's emotional state in real time. This allows the presentation of the analysis results to be adjusted according to the user's emotional state. For example, if the user is showing anxiety, the analysis results will be presented in a more user-friendly format.

[0401] As a concrete example, consider a scenario where a user watches a movie review video. The device scans the video and evaluates its reliability while simultaneously analyzing the user's emotions. If an emotion of surprise is detected, the results are presented in a milder tone and style.

[0402] This system allows users to obtain reliable information and receive appropriate feedback that aligns with their emotions. For example, a prompt such as, "Please rate the reliability of this video and provide emotionally appropriate feedback," can be used to initiate a reliability assessment and emotionally sensitive process.

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] The device receives videos or news articles from the user. The input information is stored in the mobile information processing device's memory. This input information serves as the basis for subsequent reliability evaluation processes.

[0406] Step 2:

[0407] The terminal converts the received input information into a parseable format. In the case of videos, it is broken down into frames, and in the case of news articles, the text is tokenized. This process is carried out using natural language processing libraries and image processing tools.

[0408] Step 3:

[0409] The device uses natural language processing (NLP) techniques to analyze news articles or video subtitles. It uses tokenized text as input and detects matches with known, reliable sources and misinformation patterns. The output is a confidence score, which is further processed for display to the user.

[0410] Step 4:

[0411] The device uses computer vision technology to analyze video frames. It detects unnatural movements and signs of editing, and evaluates the reliability of the information. The input is decomposed video frames, and the output generates a reliability index for each frame.

[0412] Step 5:

[0413] The device integrates reliability scores and calculates a final confidence value. This confidence value indicates the reliability of the information presented to the user. The integration process comprehensively evaluates the scores obtained from natural language and image analysis.

[0414] Step 6:

[0415] The device analyzes the user's emotions in real time using an emotion engine. It analyzes the emotional state in response to the user's input and detects emotions such as comfort and surprise. The user's reactions are used as input data, and the output is an indicator representing the emotional state.

[0416] Step 7:

[0417] The device adjusts how it presents analysis results, along with a reliability score, to the user. Based on the user's emotions, for example, if they are surprised, the results are presented with a calming design and tone. This output allows the user to receive the information more appropriately.

[0418] Step 8:

[0419] The device collects user feedback and stores it along with analysis logs. The feedback data is anonymized and sent to an external storage device. This feedback is used to update and improve the artificial intelligence model later on.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] [Third Embodiment]

[0424] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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".

[0436] The system according to the present invention aims to detect and evaluate misinformation using an artificial intelligence model installed in a mobile information processing terminal. This system is designed to evaluate the reliability of videos and news articles received by users through their terminals.

[0437] First, the user provides the content they want to analyze, such as a video or news article, to the device. Upon receiving this input data, the device analyzes its content using an internally running artificial intelligence model. If the data format requires conversion for proper analysis, the device converts it to the appropriate format and supplies it to the analysis module.

[0438] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the input data. In this process, text is tokenized and compared against known misinformation patterns. For videos, frame analysis is used to detect consistency and characteristic patterns in the footage.

[0439] Based on the analysis, the device calculates a confidence score for the entire data set and provides this confidence score to the user. Along with the score, if any specific inconsistencies or potential misinformation are indicated, the user is also notified of the details.

[0440] Furthermore, users can send feedback on the results to their devices. This feedback is anonymized and then sent to an external server to help continuously improve the artificial intelligence model. This allows the system to improve its accuracy and reliability over time.

[0441] As a concrete example, consider a case where a user wants to verify the reliability of a news article. When the user inputs the news article into the device, the device analyzes the text of the article and compares it with existing reliable sources. If the device confirms that the article matches the characteristics and patterns of fake news, it notifies the user with a "low reliability" warning. In this way, the system of the present invention effectively identifies fake information from the information that users encounter on a daily basis and supports accurate judgment.

[0442] The following describes the processing flow.

[0443] Step 1:

[0444] The user activates their mobile information processing device and inputs the video or news article they want to analyze. This input data is temporarily stored on the device.

[0445] Step 2:

[0446] The terminal converts the input data into a format that can be analyzed. For videos, it extracts frames; for news articles, it tokenizes the text and performs preprocessing.

[0447] Step 3:

[0448] The device uses natural language processing technology to analyze the text contained in news articles. In particular, it detects known fake information patterns and sensational expressions and evaluates them using a language model.

[0449] Step 4:

[0450] The device uses computer vision technology to analyze each frame of the video. It identifies unnatural movement between frames and editing traces, and applies a deepfake detection algorithm.

[0451] Step 5:

[0452] The terminal integrates the aforementioned analysis results and calculates a confidence score for the entire input data. This score is calculated based on evaluations of similar historical data and information sources.

[0453] Step 6:

[0454] The device notifies the user of the trust score and analysis results. If necessary, it provides detailed information about potentially fake content and links to newly trusted sources.

[0455] Step 7:

[0456] The user enters feedback on the results into the terminal. This feedback is anonymized and sent to the server to improve the system's artificial intelligence model.

[0457] Step 8:

[0458] The terminal saves logs related to the analysis. This allows for quick reference in performing similar analyses at a later date and helps in understanding analysis trends.

[0459] Step 9:

[0460] The server uses the feedback data it receives to update the training dataset for the artificial intelligence model, thereby improving the model's performance.

[0461] (Example 1)

[0462] 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."

[0463] In modern society, diverse information is easily accessible via the internet, and this includes misinformation and intentionally distorted information. Such information can mislead users and cause social disruption. However, there is a lack of means to properly detect and evaluate misinformation, making it difficult to quickly and accurately determine its reliability. Solving this problem is essential to enable users to make accurate information judgments and prevent confusion caused by misinformation.

[0464] 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.

[0465] In this invention, the server is implemented in a mobile information processing device and includes means for activating a machine learning algorithm for detecting false information and loading the necessary computing resources into a storage device, means for storing images or information articles received from the user as input information in a temporary storage device, and means for converting the input information into an analyzable format and determining the reliability of the information using image recognition and language processing techniques. This makes it possible to quickly and accurately detect false information and support users in making decisions based on reliability.

[0466] A "mobile information processing device" refers to an electronic device that is portable by the user and capable of processing and communicating information.

[0467] A "machine learning algorithm" refers to a series of procedures that computers use to analyze data and recognize patterns.

[0468] "Misinformation" refers to information that intentionally or unintentionally distorts the facts or is likely to be misleading.

[0469] A "storage device" refers to an electronic component or device used to store and retrieve data.

[0470] "Temporary storage device" refers to a storage device used to retain data for a short period of time.

[0471] "Image recognition technology" refers to the technology of extracting specific information or patterns from images and analyzing them.

[0472] "Language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0473] An "informational article" refers to media content that provides information primarily through text.

[0474] A "confidence index" refers to a numerical indicator that quantifies the accuracy and reliability of the information provided.

[0475] "Evaluation opinions" refer to feedback from users and include views on the reliability and usefulness of specific information.

[0476] "Analysis history" refers to data that records the process and results of the analysis work, and can be referenced and verified at a later date.

[0477] "Anonymization" refers to a method of processing data in a way that makes it impossible to identify personal information.

[0478] An "external information processing device" refers to another electronic device located outside the target device that has data processing capabilities.

[0479] The system in this invention is realized by being installed in a mobile information processing device. Specifically, a machine learning algorithm for detecting misinformation is implemented and the user-provided content is analyzed. The device includes a storage device for saving data and a temporary storage device for temporarily storing data. Image recognition technology and language processing technology are also applied to identify misinformation. These enable the reliability of input information to be evaluated quickly and accurately.

[0480] Specifically, the user provides the mobile information processing device with a video or news article they wish to have analyzed. In the case of videos, the device analyzes frames and uses image recognition technology to identify consistent features. For text information, it uses language processing technology to tokenize the text and compares it with known patterns of misinformation. After analysis, a confidence index is calculated and the result is notified to the user. If the confidence index is deemed low, a warning is presented to the user. This helps users to independently assess the reliability of the information they receive.

[0481] Feedback is also a crucial aspect. Users can provide feedback on the results presented by the system. The terminal anonymizes this feedback and sends it to an external information processing device, which then uses it to improve the machine learning algorithm. This feedback loop contributes to improving the overall accuracy of the system.

[0482] A concrete example would be a scenario where a user enters a prompt such as, "Evaluate the reliability of this news article and return a reliability score," the system begins the analysis, and then presents the results to the user.

[0483] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0484] Step 1:

[0485] The user inputs the video or news article they wish to analyze into their device. The input information is stored in temporary storage in its original data format. Specifically, for example, by pressing a button such as "Check Reliability" through a news app, the article is uploaded as data.

[0486] Step 2:

[0487] The terminal determines the format of the input data and performs conversions as necessary. For example, in the case of video, the terminal converts the data to the appropriate analysis format, and in the case of text, it formats it into a standard structure. During this process, format conversions are performed to ensure data consistency and analyzability. The output is input data in a data format suitable for analysis.

[0488] Step 3:

[0489] The device analyzes properly formatted data stored in its storage device in detail using computer vision and natural language processing techniques. Specifically, videos are analyzed frame by frame to identify consistency and characteristic patterns in the footage. Text data is tokenized and compared against known misinformation patterns. The output of this process is an overall confidence index of the information.

[0490] Step 4:

[0491] The device displays a confidence index to the user as an analysis result. The user can receive specific warnings (for example, a message indicating "low confidence") along with the confidence rating on the device screen. Information regarding the degree of confidence and the details obtained from the analysis help the user better judge the reliability of the information.

[0492] Step 5:

[0493] Users can send feedback on the presented results to the device. The device anonymizes the received feedback and forwards it to an external server. This feedback is then used to improve the machine learning algorithm. In this step, the specific actions are the collection of feedback and the anonymization of the data. The output is the anonymized feedback data.

[0494] (Application Example 1)

[0495] 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."

[0496] In today's information society, with the overwhelming amount of news and video information available, judging its reliability presents a significant challenge. In particular, content distribution services lack sufficient means for users to assess the accuracy of the information they view, potentially leading to the spread of misinformation and misconceptions. Therefore, there is a need to evaluate the reliability of information in real time and provide users with immediate access to its reliability status during viewing.

[0497] 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.

[0498] In this invention, the server includes means for installing on a mobile information processing device, activating a knowledge processing model for detecting false information, and loading necessary computing resources into a storage device; means for temporarily storing video or news content received from the user as input information; and means for converting the input information into an analyzable format and evaluating the reliability of the information using image recognition and language analysis techniques. This makes it possible in content distribution services to evaluate the reliability of information being viewed in real time and present it appropriately to the user.

[0499] A "mobile information processing device" is a portable electronic device that processes information and is used by users to input and analyze various types of information.

[0500] "Disinformation" refers to false information that is intentionally or erroneously provided, and especially unreliable information.

[0501] A "knowledge processing model" is a computational model used for the automated analysis and evaluation of information, and is typically constructed using machine learning or artificial intelligence technologies.

[0502] "Input information" refers to data provided by the user, including in the form of images and text, and is the data to be analyzed.

[0503] "Image recognition" is a technology that analyzes digital image information and automatically recognizes objects and patterns within it.

[0504] "Language analysis technology" refers to the technology used to analyze text data, understand its meaning, and process information.

[0505] "Reliability" is an indicator that represents the accuracy and truthfulness of the information obtained as a result of the analysis, and is an evaluation score provided to the user.

[0506] "Temporary memory" refers to a memory area used to store data instantaneously, and is used for the temporary retention of data.

[0507] This system operates on a mobile information processing device and detects and evaluates inaccurate information. The device receives video and text data provided by the user and stores it in temporary memory. Next, the input information is converted into an analyzable format, and its reliability is evaluated using a knowledge processing model. Image recognition and language analysis techniques are combined to detect information consistency and known inaccuracy patterns.

[0508] The server calculates the reliability score and displays it to the user in real time. This involves cross-referencing with reliable sources and identifying features and patterns that indicate low reliability. Users can understand the reliability of the information and gain insights into their decision-making process while viewing it. Furthermore, receiving feedback from users allows for continuous improvement of the knowledge processing model.

[0509] In this embodiment, to give a specific example, while the user is viewing news content, the terminal analyzes the content using a knowledge processing model and calculates its reliability. For example, when an article about a "breakthrough in new technology" is entered, the terminal evaluates the reliability of the news content and, if it is highly reliable, immediately displays "This information is reliable."

[0510] Examples of prompts to input into a generative AI model:

[0511] Please rate the reliability of the following news articles. Assign a high score for high reliability and a low score for low reliability.

[0512] Input text: "Scientists announce they have discovered a groundbreaking energy source."

[0513] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0514] Step 1:

[0515] The terminal receives video or news content as input from the user. It stores the input information in temporary memory. At this time, the terminal checks the format of the received data and prepares to convert it into an analyzable format.

[0516] Step 2:

[0517] The terminal converts the input information into a parseable format. For example, video data is divided into frames, and news content is tokenized by a tokenizer. This makes the data usable in a knowledge processing model.

[0518] Step 3:

[0519] The device uses a knowledge processing model to evaluate the reliability of the transformed data. It analyzes frames using image recognition technology and identifies patterns in news content using language analysis technology. This results in the calculation of a reliability score, evaluating the accuracy of the data.

[0520] Step 4:

[0521] The device displays the obtained confidence score to the user. If the confidence score is low, it provides visual warnings and information to draw attention. This allows the user to intuitively judge the reliability of the information.

[0522] Step 5:

[0523] The terminal receives responses from the user, anonymizes them, and sends them to the server. The responses are used to improve the knowledge processing model. The server uses the received data to improve the accuracy of the generated AI model and applies this to the next analysis.

[0524] 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.

[0525] The system according to the present invention enables mobile information processing terminals to evaluate the reliability of content received by the user and provide feedback that takes the user's emotions into consideration. By combining an artificial intelligence model and an emotion engine, the aim is to improve the user experience and achieve effective identification of fake information.

[0526] First, the user inputs the video or news article they want to review via the device. The input data is received by the device for reliability evaluation. In this process, the device converts the data into a parseable format, performs preprocessing, and prepares it for reliability evaluation.

[0527] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the data. The natural language processing process tokenizes the content of news articles and checks for matches with existing trusted sources and fake patterns. Computer vision technology analyzes each frame of the video to detect traces of editing or unnatural movements.

[0528] Furthermore, the device incorporates an emotion engine that analyzes the user's response to input data in real time. Based on this emotion analysis, the method of presenting the analysis results is adjusted. For example, if the user is showing anxiety, the results can be presented in a more user-friendly format.

[0529] As a result of the analysis, the device generates a trust score and notifies the user. This score may include detailed information based on the user's sentiment. The user can review the analysis results and provide feedback in different formats. This feedback is anonymized in a privacy-conscious manner and securely transmitted to the server.

[0530] As a concrete example, when a user wants to determine the reliability of a news video, the device scans the video and analyzes the title and description. In this process, the emotion engine picks up the user's reaction, which might, for example, detect surprise. Taking this into account, the results are presented in a format appropriate to the user's emotion, and together with the confidence score, it helps in making a quick and accurate decision.

[0531] Because this system operates entirely on the device, it protects user privacy while enabling advanced analysis in real time. In this way, the combination of artificial intelligence models and emotion engines makes the invention a valuable tool for users.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The user accesses a mobile information processing device and selects and inputs the video or news article they want to analyze. The input data is immediately saved to a buffer on the device.

[0535] Step 2:

[0536] The terminal converts the received input data into a format that can be analyzed. For videos, individual frames are extracted, and for news articles, the text is tokenized to prepare the data for analysis.

[0537] Step 3:

[0538] The device uses natural language processing technology to analyze the content of news articles. Specifically, it understands the context, extracts keywords, and checks for the possibility of fake information by comparing it with known, reliable sources.

[0539] Step 4:

[0540] The device utilizes computer vision technology to analyze each frame of a video. It investigates the consistency of faces and backgrounds in the video, with the aim of detecting deepfakes and anomalies.

[0541] Step 5:

[0542] An emotion engine built into the device analyzes the user's actions and inputs. It identifies the emotional state in real time and dynamically adjusts how the results are presented to make the user's explanations easier to understand.

[0543] Step 6:

[0544] The device calculates a confidence score from the analyzed data and provides it to the user. At the same time, it provides additional information and warnings tailored to the user's emotions, encouraging appropriate feedback along with the score.

[0545] Step 7:

[0546] The user enters their score and feedback on the results and sends it to the device. The device anonymizes this feedback and securely transfers it to the server.

[0547] Step 8:

[0548] The server analyzes the collected feedback data and uses it as a dataset to update the artificial intelligence model. This continuously improves the model's accuracy and reliability.

[0549] (Example 2)

[0550] 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."

[0551] In modern society, a vast amount of information circulates on the internet, including misinformation and biased information. Instantly judging this information and selecting reliable information is not easy and places a significant burden on users. Furthermore, how information is received is influenced by users' emotions, so the method of information delivery needs to be optimized for each individual user. To solve this problem, a system is needed that not only assesses the reliability of information but also analyzes users' emotions and delivers information in an appropriate manner.

[0552] 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.

[0553] In this invention, the server includes means for installing on a mobile information processing device, activating an intelligent model for detecting misinformation, and loading necessary resources into a storage device; means for temporarily storing images or articles received from the user as input information; means for converting the input information into an analyzable format and evaluating the reliability of the information using image analysis and automatic language processing techniques; means for analyzing the user's emotions based on the evaluation and adjusting the display method according to the results; means for displaying the generated reliability level to the user and collecting opinions; and means for recording the analysis history within the device and transmitting the opinion data anonymized to a remote device. This makes it possible to quickly and accurately determine the reliability of information and provide information in a way that is adapted to the user's emotions.

[0554] A "mobile information processing device" is an electronic device that is portable and capable of collecting, processing, and communicating information.

[0555] An "intelligent model" is a program built with algorithms that analyze information, identify specific patterns, and learn to improve its functionality.

[0556] A "storage device" is a hardware component used to temporarily or permanently store data or programs.

[0557] "Temporary memory" refers to a memory area that holds data for a short period of time and allows for immediate access.

[0558] "Image analysis" is a technique that processes digital images and extracts information from them.

[0559] "Automated language processing technology" refers to technologies that enable computers to understand and generate natural language.

[0560] "Reliability assessment" is an analytical process for determining the accuracy and degree of misinformation of information.

[0561] "Analyzing emotions" is the process of identifying the user's emotional state and classifying data based on that.

[0562] A "remote device" is an external device that is connected via a communication network and used to send and receive data.

[0563] This invention is based on a mobile information processing device used by the user and utilizes an intelligent model for misinformation detection. The process primarily begins with the terminal installing and activating the intelligent model and loading the necessary resources into its storage device. Specifically, the device incorporates programs for data analysis, utilizing image analysis and automated language processing technologies. The device leverages natural language processing libraries and computer vision libraries to convert video and article data received from the user into an analyzable format.

[0564] This device is equipped with an emotion engine that analyzes responses in real time based on user input, and displays information in a format optimized for each individual user based on the evaluation results. The server also has the function of collecting anonymous opinions provided by users and securely transmitting them to the remote device. This creates a data feedback cycle, enabling continuous learning and updating of the generative AI model.

[0565] For example, if a user wants to check the reliability of a news video, the device can analyze the video and provide a reliability rating for the question posed. The system would receive highly accurate feedback in the form of a prompt such as, "How reliable is this news video?"

[0566] Through the above process, the invention enables the efficient evaluation of diverse information and the provision of information adapted to the user's emotions and needs. The system operates in real time and aims to enhance user trust.

[0567] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0568] Step 1:

[0569] The user inputs videos or news articles they want to evaluate via a mobile information processing device. The input data can take the form of URLs or copied text, and the device receives this data and stores it in temporary memory. In this case, user input acts as the initial trigger for the program.

[0570] Step 2:

[0571] The device converts data stored in temporary memory into an analyzable format. Specifically, it uses a natural language processing library to tokenize text data and extract key concepts. For video data, it uses a computer vision library to perform frame-by-frame image analysis and recognize objects and motion within the video. The input is raw data provided by the user, and the output is in a data format suitable for analysis.

[0572] Step 3:

[0573] The terminal uses an intelligent model to evaluate the reliability of the information based on the converted data. This stage includes a process to check for matches with known misinformation patterns. Specifically, the data is compared with an existing information base to identify similar patterns. The input to this process is the analyzable data obtained in step 2, and the output is a confidence score.

[0574] Step 4:

[0575] An emotion engine built into the device analyzes the user's emotional responses during the evaluation process. It senses and evaluates the user's facial expressions and voice data in real time, and adjusts the display method of the results based on the emotions the user expresses. The input at this stage is real-time user data, and the output is a customized display method of results that corresponds to the user's emotional state.

[0576] Step 5:

[0577] The device notifies the user of the score obtained as a result of the reliability evaluation. In addition to the reliability score, the results may include a detailed explanation based on the user's sentiment. The input here is the result data of the evaluation process, and the output is the result interface displayed to the user.

[0578] Step 6:

[0579] The user reviews the presented results and provides feedback through their device. The device anonymizes this feedback data and securely sends it to the server. The input is the user's feedback, and the output is the anonymized data sent to the server. The server stores this data and uses it to improve the generated AI model.

[0580] (Application Example 2)

[0581] 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."

[0582] In modern society, a vast amount of information circulates daily via the internet, but much of it lacks reliability. In particular, with news articles and video content, users often lack appropriate guidelines for judging their reliability, potentially leading to decision-making based on misinformation. Furthermore, providing information without considering the user's emotional state can lead to misunderstandings. Thus, there is a growing need for a system that simultaneously achieves both information reliability assessment and emotional consideration.

[0583] 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.

[0584] In this invention, the server includes means for installing on a mobile information processing terminal, activating an artificial intelligence model for detecting false information, and loading necessary computing resources into a storage device; means for storing videos or news articles received from the user as input information in the storage area; means for converting the input information into an analyzable format and evaluating the reliability of the information using image processing and natural language processing techniques; means for displaying the obtained reliability value to the user and collecting responses; means for storing analysis records within the terminal, anonymizing response data, and transmitting it to an external storage device; and means for analyzing the user's emotions and adjusting the method of presenting the analysis results according to the emotional state. This enables reliability evaluation and information presentation tailored to emotions.

[0585] A "mobile information processing terminal" is a portable computing device that allows users to process various types of information.

[0586] "Misinformation" refers to inaccurate or misleading information that is not based on facts.

[0587] An "artificial intelligence model" is a computational model built using machine learning algorithms to perform a specific task.

[0588] "Computational resources" is a general term for the hardware and software necessary for information processing.

[0589] A "memory device" is a device used to store data and programs.

[0590] "Memory space" is a place where data is temporarily stored.

[0591] "Image processing" is a technique that analyzes and transforms still images or videos to extract useful information.

[0592] "Natural language processing" is a technology that analyzes text information and understands its meaning.

[0593] "Confidence level" is an indicator that quantifies the reliability of information.

[0594] "Response" refers to feedback or reaction from the user.

[0595] "Analysis records" refer to documents that document the data and results obtained during the analysis process.

[0596] An "external storage device" is a device that can retain data for a long period of time.

[0597] "Emotional state" refers to the user's psychological condition and the emotions they are experiencing.

[0598] This invention is a system that uses a mobile information processing terminal to detect false information and present information in accordance with the user's emotions. The terminal integrates an artificial intelligence model and an emotion engine, which evaluate the reliability of the data and analyze the user's emotions.

[0599] The terminal first receives a video or news article from the user and stores it in memory as input information. Then, it converts the input information into a parseable format and evaluates the reliability of the information using image processing and natural language processing techniques. In this process, natural language processing libraries (e.g., SpaCy, NLTK) and computer vision technologies (e.g., OpenCV, TensorFlow) are used for reliability evaluation. As a result of the reliability evaluation, a confidence score is generated and displayed to the user. Furthermore, user feedback is collected and processed as response data. The response data is anonymized and sent to an external storage device.

[0600] Furthermore, the device incorporates an emotion engine that analyzes the user's emotional state in real time. This allows the presentation of the analysis results to be adjusted according to the user's emotional state. For example, if the user is showing anxiety, the analysis results will be presented in a more user-friendly format.

[0601] As a concrete example, consider a scenario where a user watches a movie review video. The device scans the video and evaluates its reliability while simultaneously analyzing the user's emotions. If an emotion of surprise is detected, the results are presented in a milder tone and style.

[0602] This system allows users to obtain reliable information and receive appropriate feedback that aligns with their emotions. For example, a prompt such as, "Please rate the reliability of this video and provide emotionally appropriate feedback," can be used to initiate a reliability assessment and emotionally sensitive process.

[0603] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0604] Step 1:

[0605] The device receives videos or news articles from the user. The input information is stored in the mobile information processing device's memory. This input information serves as the basis for subsequent reliability evaluation processes.

[0606] Step 2:

[0607] The terminal converts the received input information into a parseable format. In the case of videos, it is broken down into frames, and in the case of news articles, the text is tokenized. This process is carried out using natural language processing libraries and image processing tools.

[0608] Step 3:

[0609] The device uses natural language processing (NLP) techniques to analyze news articles or video subtitles. It uses tokenized text as input and detects matches with known, reliable sources and misinformation patterns. The output is a confidence score, which is further processed for display to the user.

[0610] Step 4:

[0611] The device uses computer vision technology to analyze video frames. It detects unnatural movements and signs of editing, and evaluates the reliability of the information. The input is decomposed video frames, and the output generates a reliability index for each frame.

[0612] Step 5:

[0613] The device integrates reliability scores and calculates a final confidence value. This confidence value indicates the reliability of the information presented to the user. The integration process comprehensively evaluates the scores obtained from natural language and image analysis.

[0614] Step 6:

[0615] The device analyzes the user's emotions in real time using an emotion engine. It analyzes the emotional state in response to the user's input and detects emotions such as comfort and surprise. The user's reactions are used as input data, and the output is an indicator representing the emotional state.

[0616] Step 7:

[0617] The device adjusts how it presents analysis results, along with a reliability score, to the user. Based on the user's emotions, for example, if they are surprised, the results are presented with a calming design and tone. This output allows the user to receive the information more appropriately.

[0618] Step 8:

[0619] The device collects user feedback and stores it along with analysis logs. The feedback data is anonymized and sent to an external storage device. This feedback is used to update and improve the artificial intelligence model later on.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] [Fourth Embodiment]

[0624] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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).

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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".

[0637] The system according to the present invention aims to detect and evaluate misinformation using an artificial intelligence model installed in a mobile information processing terminal. This system is designed to evaluate the reliability of videos and news articles received by users through their terminals.

[0638] First, the user provides the content they want to analyze, such as a video or news article, to the device. Upon receiving this input data, the device analyzes its content using an internally running artificial intelligence model. If the data format requires conversion for proper analysis, the device converts it to the appropriate format and supplies it to the analysis module.

[0639] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the input data. In this process, text is tokenized and compared against known misinformation patterns. For videos, frame analysis is used to detect consistency and characteristic patterns in the footage.

[0640] Based on the analysis, the device calculates a confidence score for the entire data set and provides this confidence score to the user. Along with the score, if any specific inconsistencies or potential misinformation are indicated, the user is also notified of the details.

[0641] Furthermore, users can send feedback on the results to their devices. This feedback is anonymized and then sent to an external server to help continuously improve the artificial intelligence model. This allows the system to improve its accuracy and reliability over time.

[0642] As a concrete example, consider a case where a user wants to verify the reliability of a news article. When the user inputs the news article into the device, the device analyzes the text of the article and compares it with existing reliable sources. If the device confirms that the article matches the characteristics and patterns of fake news, it notifies the user with a "low reliability" warning. In this way, the system of the present invention effectively identifies fake information from the information that users encounter on a daily basis and supports accurate judgment.

[0643] The following describes the processing flow.

[0644] Step 1:

[0645] The user activates their mobile information processing device and inputs the video or news article they want to analyze. This input data is temporarily stored on the device.

[0646] Step 2:

[0647] The terminal converts the input data into a format that can be analyzed. For videos, it extracts frames; for news articles, it tokenizes the text and performs preprocessing.

[0648] Step 3:

[0649] The device uses natural language processing technology to analyze the text contained in news articles. In particular, it detects known fake information patterns and sensational expressions and evaluates them using a language model.

[0650] Step 4:

[0651] The device uses computer vision technology to analyze each frame of the video. It identifies unnatural movement between frames and editing traces, and applies a deepfake detection algorithm.

[0652] Step 5:

[0653] The terminal integrates the aforementioned analysis results and calculates a confidence score for the entire input data. This score is calculated based on evaluations of similar historical data and information sources.

[0654] Step 6:

[0655] The device notifies the user of the trust score and analysis results. If necessary, it provides detailed information about potentially fake content and links to newly trusted sources.

[0656] Step 7:

[0657] The user enters feedback on the results into the terminal. This feedback is anonymized and sent to the server to improve the system's artificial intelligence model.

[0658] Step 8:

[0659] The terminal saves logs related to the analysis. This allows for quick reference in performing similar analyses at a later date and helps in understanding analysis trends.

[0660] Step 9:

[0661] The server uses the feedback data it receives to update the training dataset for the artificial intelligence model, thereby improving the model's performance.

[0662] (Example 1)

[0663] 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".

[0664] In modern society, diverse information is easily accessible via the internet, and this includes misinformation and intentionally distorted information. Such information can mislead users and cause social disruption. However, there is a lack of means to properly detect and evaluate misinformation, making it difficult to quickly and accurately determine its reliability. Solving this problem is essential to enable users to make accurate information judgments and prevent confusion caused by misinformation.

[0665] 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.

[0666] In this invention, the server is implemented in a mobile information processing device and includes means for activating a machine learning algorithm for detecting false information and loading the necessary computing resources into a storage device, means for storing images or information articles received from the user as input information in a temporary storage device, and means for converting the input information into an analyzable format and determining the reliability of the information using image recognition and language processing techniques. This makes it possible to quickly and accurately detect false information and support users in making decisions based on reliability.

[0667] A "mobile information processing device" refers to an electronic device that is portable by the user and capable of processing and communicating information.

[0668] A "machine learning algorithm" refers to a series of procedures that computers use to analyze data and recognize patterns.

[0669] "Misinformation" refers to information that intentionally or unintentionally distorts the facts or is likely to be misleading.

[0670] A "storage device" refers to an electronic component or device used to store and retrieve data.

[0671] "Temporary storage device" refers to a storage device used to retain data for a short period of time.

[0672] "Image recognition technology" refers to the technology of extracting specific information or patterns from images and analyzing them.

[0673] "Language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0674] An "informational article" refers to media content that provides information primarily through text.

[0675] A "confidence index" refers to a numerical indicator that quantifies the accuracy and reliability of the information provided.

[0676] "Evaluation opinions" refer to feedback from users and include views on the reliability and usefulness of specific information.

[0677] "Analysis history" refers to data that records the process and results of the analysis work, and can be referenced and verified at a later date.

[0678] "Anonymization" refers to a method of processing data in a way that makes it impossible to identify personal information.

[0679] An "external information processing device" refers to another electronic device located outside the target device that has data processing capabilities.

[0680] The system in this invention is realized by being installed in a mobile information processing device. Specifically, a machine learning algorithm for detecting misinformation is implemented and the user-provided content is analyzed. The device includes a storage device for saving data and a temporary storage device for temporarily storing data. Image recognition technology and language processing technology are also applied to identify misinformation. These enable the reliability of input information to be evaluated quickly and accurately.

[0681] Specifically, the user provides the mobile information processing device with a video or news article they wish to have analyzed. In the case of videos, the device analyzes frames and uses image recognition technology to identify consistent features. For text information, it uses language processing technology to tokenize the text and compares it with known patterns of misinformation. After analysis, a confidence index is calculated and the result is notified to the user. If the confidence index is deemed low, a warning is presented to the user. This helps users to independently assess the reliability of the information they receive.

[0682] Feedback is also a crucial aspect. Users can provide feedback on the results presented by the system. The terminal anonymizes this feedback and sends it to an external information processing device, which then uses it to improve the machine learning algorithm. This feedback loop contributes to improving the overall accuracy of the system.

[0683] A concrete example would be a scenario where a user enters a prompt such as, "Evaluate the reliability of this news article and return a reliability score," the system begins the analysis, and then presents the results to the user.

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The user inputs the video or news article they wish to analyze into their device. The input information is stored in temporary storage in its original data format. Specifically, for example, by pressing a button such as "Check Reliability" through a news app, the article is uploaded as data.

[0687] Step 2:

[0688] The terminal determines the format of the input data and performs conversions as necessary. For example, in the case of video, the terminal converts the data to the appropriate analysis format, and in the case of text, it formats it into a standard structure. During this process, format conversions are performed to ensure data consistency and analyzability. The output is input data in a data format suitable for analysis.

[0689] Step 3:

[0690] The device analyzes properly formatted data stored in its storage device in detail using computer vision and natural language processing techniques. Specifically, videos are analyzed frame by frame to identify consistency and characteristic patterns in the footage. Text data is tokenized and compared against known misinformation patterns. The output of this process is an overall confidence index of the information.

[0691] Step 4:

[0692] The device displays a confidence index to the user as an analysis result. The user can receive specific warnings (for example, a message indicating "low confidence") along with the confidence rating on the device screen. Information regarding the degree of confidence and the details obtained from the analysis help the user better judge the reliability of the information.

[0693] Step 5:

[0694] Users can send feedback on the presented results to the device. The device anonymizes the received feedback and forwards it to an external server. This feedback is then used to improve the machine learning algorithm. In this step, the specific actions are the collection of feedback and the anonymization of the data. The output is the anonymized feedback data.

[0695] (Application Example 1)

[0696] 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".

[0697] In today's information society, with the overwhelming amount of news and video information available, judging its reliability presents a significant challenge. In particular, content distribution services lack sufficient means for users to assess the accuracy of the information they view, potentially leading to the spread of misinformation and misconceptions. Therefore, there is a need to evaluate the reliability of information in real time and provide users with immediate access to its reliability status during viewing.

[0698] 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.

[0699] In this invention, the server includes means for installing on a mobile information processing device, activating a knowledge processing model for detecting false information, and loading necessary computing resources into a storage device; means for temporarily storing video or news content received from the user as input information; and means for converting the input information into an analyzable format and evaluating the reliability of the information using image recognition and language analysis techniques. This makes it possible in content distribution services to evaluate the reliability of information being viewed in real time and present it appropriately to the user.

[0700] A "mobile information processing device" is a portable electronic device that processes information and is used by users to input and analyze various types of information.

[0701] "Disinformation" refers to false information that is intentionally or erroneously provided, and especially unreliable information.

[0702] A "knowledge processing model" is a computational model used for the automated analysis and evaluation of information, and is typically constructed using machine learning or artificial intelligence technologies.

[0703] "Input information" refers to data provided by the user, including in the form of images and text, and is the data to be analyzed.

[0704] "Image recognition" is a technology that analyzes digital image information and automatically recognizes objects and patterns within it.

[0705] "Language analysis technology" refers to the technology used to analyze text data, understand its meaning, and process information.

[0706] "Reliability" is an indicator that represents the accuracy and truthfulness of the information obtained as a result of the analysis, and is an evaluation score provided to the user.

[0707] "Temporary memory" refers to a memory area used to store data instantaneously, and is used for the temporary retention of data.

[0708] This system operates on a mobile information processing device and detects and evaluates inaccurate information. The device receives video and text data provided by the user and stores it in temporary memory. Next, the input information is converted into an analyzable format, and its reliability is evaluated using a knowledge processing model. Image recognition and language analysis techniques are combined to detect information consistency and known inaccuracy patterns.

[0709] The server calculates the reliability score and displays it to the user in real time. This involves cross-referencing with reliable sources and identifying features and patterns that indicate low reliability. Users can understand the reliability of the information and gain insights into their decision-making process while viewing it. Furthermore, receiving feedback from users allows for continuous improvement of the knowledge processing model.

[0710] In this embodiment, to give a specific example, while the user is viewing news content, the terminal analyzes the content using a knowledge processing model and calculates its reliability. For example, when an article about a "breakthrough in new technology" is entered, the terminal evaluates the reliability of the news content and, if it is highly reliable, immediately displays "This information is reliable."

[0711] Examples of prompts to input into a generative AI model:

[0712] Please rate the reliability of the following news articles. Assign a high score for high reliability and a low score for low reliability.

[0713] Input text: "Scientists announce they have discovered a groundbreaking energy source."

[0714] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0715] Step 1:

[0716] The terminal receives video or news content as input from the user. It stores the input information in temporary memory. At this time, the terminal checks the format of the received data and prepares to convert it into an analyzable format.

[0717] Step 2:

[0718] The terminal converts the input information into a parseable format. For example, video data is divided into frames, and news content is tokenized by a tokenizer. This makes the data usable in a knowledge processing model.

[0719] Step 3:

[0720] The device uses a knowledge processing model to evaluate the reliability of the transformed data. It analyzes frames using image recognition technology and identifies patterns in news content using language analysis technology. This results in the calculation of a reliability score, evaluating the accuracy of the data.

[0721] Step 4:

[0722] The device displays the obtained confidence score to the user. If the confidence score is low, it provides visual warnings and information to draw attention. This allows the user to intuitively judge the reliability of the information.

[0723] Step 5:

[0724] The terminal receives responses from the user, anonymizes them, and sends them to the server. The responses are used to improve the knowledge processing model. The server uses the received data to improve the accuracy of the generated AI model and applies this to the next analysis.

[0725] 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.

[0726] The system according to the present invention enables mobile information processing terminals to evaluate the reliability of content received by the user and provide feedback that takes the user's emotions into consideration. By combining an artificial intelligence model and an emotion engine, the aim is to improve the user experience and achieve effective identification of fake information.

[0727] First, the user inputs the video or news article they want to review via the device. The input data is received by the device for reliability evaluation. In this process, the device converts the data into a parseable format, performs preprocessing, and prepares it for reliability evaluation.

[0728] Next, the device utilizes natural language processing and computer vision technologies to perform a detailed analysis of the data. The natural language processing process tokenizes the content of news articles and checks for matches with existing trusted sources and fake patterns. Computer vision technology analyzes each frame of the video to detect traces of editing or unnatural movements.

[0729] Furthermore, the device incorporates an emotion engine that analyzes the user's response to input data in real time. Based on this emotion analysis, the method of presenting the analysis results is adjusted. For example, if the user is showing anxiety, the results can be presented in a more user-friendly format.

[0730] As a result of the analysis, the device generates a trust score and notifies the user. This score may include detailed information based on the user's sentiment. The user can review the analysis results and provide feedback in different formats. This feedback is anonymized in a privacy-conscious manner and securely transmitted to the server.

[0731] As a concrete example, when a user wants to determine the reliability of a news video, the device scans the video and analyzes the title and description. In this process, the emotion engine picks up the user's reaction, which might, for example, detect surprise. Taking this into account, the results are presented in a format appropriate to the user's emotion, and together with the confidence score, it helps in making a quick and accurate decision.

[0732] Because this system operates entirely on the device, it protects user privacy while enabling advanced analysis in real time. In this way, the combination of artificial intelligence models and emotion engines makes the invention a valuable tool for users.

[0733] The following describes the processing flow.

[0734] Step 1:

[0735] The user accesses a mobile information processing device and selects and inputs the video or news article they want to analyze. The input data is immediately saved to a buffer on the device.

[0736] Step 2:

[0737] The terminal converts the received input data into a format that can be analyzed. For videos, individual frames are extracted, and for news articles, the text is tokenized to prepare the data for analysis.

[0738] Step 3:

[0739] The device uses natural language processing technology to analyze the content of news articles. Specifically, it understands the context, extracts keywords, and checks for the possibility of fake information by comparing it with known, reliable sources.

[0740] Step 4:

[0741] The device utilizes computer vision technology to analyze each frame of a video. It investigates the consistency of faces and backgrounds in the video, with the aim of detecting deepfakes and anomalies.

[0742] Step 5:

[0743] An emotion engine built into the device analyzes the user's actions and inputs. It identifies the emotional state in real time and dynamically adjusts how the results are presented to make the user's explanations easier to understand.

[0744] Step 6:

[0745] The device calculates a confidence score from the analyzed data and provides it to the user. At the same time, it provides additional information and warnings tailored to the user's emotions, encouraging appropriate feedback along with the score.

[0746] Step 7:

[0747] The user enters their score and feedback on the results and sends it to the device. The device anonymizes this feedback and securely transfers it to the server.

[0748] Step 8:

[0749] The server analyzes the collected feedback data and uses it as a dataset to update the artificial intelligence model. This continuously improves the model's accuracy and reliability.

[0750] (Example 2)

[0751] 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".

[0752] In modern society, a vast amount of information circulates on the internet, including misinformation and biased information. Instantly judging this information and selecting reliable information is not easy and places a significant burden on users. Furthermore, how information is received is influenced by users' emotions, so the method of information delivery needs to be optimized for each individual user. To solve this problem, a system is needed that not only assesses the reliability of information but also analyzes users' emotions and delivers information in an appropriate manner.

[0753] 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.

[0754] In this invention, the server includes means for installing on a mobile information processing device, activating an intelligent model for detecting misinformation, and loading necessary resources into a storage device; means for temporarily storing images or articles received from the user as input information; means for converting the input information into an analyzable format and evaluating the reliability of the information using image analysis and automatic language processing techniques; means for analyzing the user's emotions based on the evaluation and adjusting the display method according to the results; means for displaying the generated reliability level to the user and collecting opinions; and means for recording the analysis history within the device and transmitting the opinion data anonymized to a remote device. This makes it possible to quickly and accurately determine the reliability of information and provide information in a way that is adapted to the user's emotions.

[0755] A "mobile information processing device" is an electronic device that is portable and capable of collecting, processing, and communicating information.

[0756] An "intelligent model" is a program built with algorithms that analyze information, identify specific patterns, and learn to improve its functionality.

[0757] A "storage device" is a hardware component used to temporarily or permanently store data or programs.

[0758] "Temporary memory" refers to a memory area that holds data for a short period of time and allows for immediate access.

[0759] "Image analysis" is a technique that processes digital images and extracts information from them.

[0760] "Automated language processing technology" refers to technologies that enable computers to understand and generate natural language.

[0761] "Reliability assessment" is an analytical process for determining the accuracy and degree of misinformation of information.

[0762] "Analyzing emotions" is the process of identifying the user's emotional state and classifying data based on that.

[0763] A "remote device" is an external device that is connected via a communication network and used to send and receive data.

[0764] This invention is based on a mobile information processing device used by the user and utilizes an intelligent model for misinformation detection. The process primarily begins with the terminal installing and activating the intelligent model and loading the necessary resources into its storage device. Specifically, the device incorporates programs for data analysis, utilizing image analysis and automated language processing technologies. The device leverages natural language processing libraries and computer vision libraries to convert video and article data received from the user into an analyzable format.

[0765] This device is equipped with an emotion engine that analyzes responses in real time based on user input, and displays information in a format optimized for each individual user based on the evaluation results. The server also has the function of collecting anonymous opinions provided by users and securely transmitting them to the remote device. This creates a data feedback cycle, enabling continuous learning and updating of the generative AI model.

[0766] For example, if a user wants to check the reliability of a news video, the device can analyze the video and provide a reliability rating for the question posed. The system would receive highly accurate feedback in the form of a prompt such as, "How reliable is this news video?"

[0767] Through the above process, the invention enables the efficient evaluation of diverse information and the provision of information adapted to the user's emotions and needs. The system operates in real time and aims to enhance user trust.

[0768] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0769] Step 1:

[0770] The user inputs videos or news articles they want to evaluate via a mobile information processing device. The input data can take the form of URLs or copied text, and the device receives this data and stores it in temporary memory. In this case, user input acts as the initial trigger for the program.

[0771] Step 2:

[0772] The device converts data stored in temporary memory into an analyzable format. Specifically, it uses a natural language processing library to tokenize text data and extract key concepts. For video data, it uses a computer vision library to perform frame-by-frame image analysis and recognize objects and motion within the video. The input is raw data provided by the user, and the output is in a data format suitable for analysis.

[0773] Step 3:

[0774] The terminal uses an intelligent model to evaluate the reliability of the information based on the converted data. This stage includes a process to check for matches with known misinformation patterns. Specifically, the data is compared with an existing information base to identify similar patterns. The input to this process is the analyzable data obtained in step 2, and the output is a confidence score.

[0775] Step 4:

[0776] An emotion engine built into the device analyzes the user's emotional responses during the evaluation process. It senses and evaluates the user's facial expressions and voice data in real time, and adjusts the display method of the results based on the emotions the user expresses. The input at this stage is real-time user data, and the output is a customized display method of results that corresponds to the user's emotional state.

[0777] Step 5:

[0778] The device notifies the user of the score obtained as a result of the reliability evaluation. In addition to the reliability score, the results may include a detailed explanation based on the user's sentiment. The input here is the result data of the evaluation process, and the output is the result interface displayed to the user.

[0779] Step 6:

[0780] The user reviews the presented results and provides feedback through their device. The device anonymizes this feedback data and securely sends it to the server. The input is the user's feedback, and the output is the anonymized data sent to the server. The server stores this data and uses it to improve the generated AI model.

[0781] (Application Example 2)

[0782] 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".

[0783] In modern society, a vast amount of information circulates daily via the internet, but much of it lacks reliability. In particular, with news articles and video content, users often lack appropriate guidelines for judging their reliability, potentially leading to decision-making based on misinformation. Furthermore, providing information without considering the user's emotional state can lead to misunderstandings. Thus, there is a growing need for a system that simultaneously achieves both information reliability assessment and emotional consideration.

[0784] 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.

[0785] In this invention, the server includes means for installing on a mobile information processing terminal, activating an artificial intelligence model for detecting false information, and loading necessary computing resources into a storage device; means for storing videos or news articles received from the user as input information in the storage area; means for converting the input information into an analyzable format and evaluating the reliability of the information using image processing and natural language processing techniques; means for displaying the obtained reliability value to the user and collecting responses; means for storing analysis records within the terminal, anonymizing response data, and transmitting it to an external storage device; and means for analyzing the user's emotions and adjusting the method of presenting the analysis results according to the emotional state. This enables reliability evaluation and information presentation tailored to emotions.

[0786] A "mobile information processing terminal" is a portable computing device that allows users to process various types of information.

[0787] "Misinformation" refers to inaccurate or misleading information that is not based on facts.

[0788] An "artificial intelligence model" is a computational model built using machine learning algorithms to perform a specific task.

[0789] "Computational resources" is a general term for the hardware and software necessary for information processing.

[0790] A "memory device" is a device used to store data and programs.

[0791] "Memory space" is a place where data is temporarily stored.

[0792] "Image processing" is a technique that analyzes and transforms still images or videos to extract useful information.

[0793] "Natural language processing" is a technology that analyzes text information and understands its meaning.

[0794] "Confidence level" is an indicator that quantifies the reliability of information.

[0795] "Response" refers to feedback or reaction from the user.

[0796] "Analysis records" refer to documents that document the data and results obtained during the analysis process.

[0797] An "external storage device" is a device that can retain data for a long period of time.

[0798] "Emotional state" refers to the user's psychological condition and the emotions they are experiencing.

[0799] This invention is a system that uses a mobile information processing terminal to detect false information and present information in accordance with the user's emotions. The terminal integrates an artificial intelligence model and an emotion engine, which evaluate the reliability of the data and analyze the user's emotions.

[0800] The terminal first receives a video or news article from the user and stores it in memory as input information. Then, it converts the input information into a parseable format and evaluates the reliability of the information using image processing and natural language processing techniques. In this process, natural language processing libraries (e.g., SpaCy, NLTK) and computer vision technologies (e.g., OpenCV, TensorFlow) are used for reliability evaluation. As a result of the reliability evaluation, a confidence score is generated and displayed to the user. Furthermore, user feedback is collected and processed as response data. The response data is anonymized and sent to an external storage device.

[0801] Furthermore, the device incorporates an emotion engine that analyzes the user's emotional state in real time. This allows the presentation of the analysis results to be adjusted according to the user's emotional state. For example, if the user is showing anxiety, the analysis results will be presented in a more user-friendly format.

[0802] As a concrete example, consider a scenario where a user watches a movie review video. The device scans the video and evaluates its reliability while simultaneously analyzing the user's emotions. If an emotion of surprise is detected, the results are presented in a milder tone and style.

[0803] This system allows users to obtain reliable information and receive appropriate feedback that aligns with their emotions. For example, a prompt such as, "Please rate the reliability of this video and provide emotionally appropriate feedback," can be used to initiate a reliability assessment and emotionally sensitive process.

[0804] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0805] Step 1:

[0806] The device receives videos or news articles from the user. The input information is stored in the mobile information processing device's memory. This input information serves as the basis for subsequent reliability evaluation processes.

[0807] Step 2:

[0808] The terminal converts the received input information into a parseable format. In the case of videos, it is broken down into frames, and in the case of news articles, the text is tokenized. This process is carried out using natural language processing libraries and image processing tools.

[0809] Step 3:

[0810] The device uses natural language processing (NLP) techniques to analyze news articles or video subtitles. It uses tokenized text as input and detects matches with known, reliable sources and misinformation patterns. The output is a confidence score, which is further processed for display to the user.

[0811] Step 4:

[0812] The device uses computer vision technology to analyze video frames. It detects unnatural movements and signs of editing, and evaluates the reliability of the information. The input is decomposed video frames, and the output generates a reliability index for each frame.

[0813] Step 5:

[0814] The device integrates reliability scores and calculates a final confidence value. This confidence value indicates the reliability of the information presented to the user. The integration process comprehensively evaluates the scores obtained from natural language and image analysis.

[0815] Step 6:

[0816] The device analyzes the user's emotions in real time using an emotion engine. It analyzes the emotional state in response to the user's input and detects emotions such as comfort and surprise. The user's reactions are used as input data, and the output is an indicator representing the emotional state.

[0817] Step 7:

[0818] The device adjusts how it presents analysis results, along with a reliability score, to the user. Based on the user's emotions, for example, if they are surprised, the results are presented with a calming design and tone. This output allows the user to receive the information more appropriately.

[0819] Step 8:

[0820] The device collects user feedback and stores it along with analysis logs. The feedback data is anonymized and sent to an external storage device. This feedback is used to update and improve the artificial intelligence model later on.

[0821] 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.

[0822] 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.

[0823] 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 robot 414.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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."

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] The following is further disclosed regarding the embodiments described above.

[0843] (Claim 1)

[0844] A means for installing on a mobile information processing terminal, launching an artificial intelligence model for detecting false information, and loading the necessary resources into memory,

[0845] A means for saving videos or news articles received from a user as input data in a buffer,

[0846] A means for converting input data into an analyzable format and evaluating the reliability of the data using computer vision and natural language processing techniques,

[0847] A means of displaying the obtained confidence score to the user and collecting feedback,

[0848] A method for saving analysis logs within the device and anonymizing feedback data before sending it to an external server,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, characterized in that it detects matches with known fake information patterns when evaluating the reliability of input data.

[0852] (Claim 3)

[0853] The system according to claim 1, characterized in that it autonomously updates and improves an artificial intelligence model using feedback data obtained through analysis.

[0854] "Example 1"

[0855] (Claim 1)

[0856] A means of implementing a machine learning algorithm for detecting false information and loading the necessary computing resources into a memory device,

[0857] A means for storing video or informational articles received from a user as input information in a temporary storage device,

[0858] A means for converting input information into an analyzable format and determining the reliability of the information using image recognition and language processing technologies,

[0859] A means of presenting the obtained confidence index to users and collecting their evaluation opinions,

[0860] A means for recording analysis history within the device, anonymizing evaluation opinion data, and transmitting it to an external information processing device,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, characterized in that when determining the reliability of input information, it identifies matches with known misinformation patterns.

[0864] (Claim 3)

[0865] The system according to claim 1, characterized in that it autonomously updates the machine learning algorithm and improves its functionality using evaluation opinion data obtained through analysis.

[0866] "Application Example 1"

[0867] (Claim 1)

[0868] A means for installing a knowledge processing model for detecting false information and loading the necessary computing resources into a memory device,

[0869] A means for temporarily storing video or news content received from the user as input information in a memory,

[0870] A means for converting input information into an analyzable format and evaluating the reliability of the information using image recognition and language analysis techniques,

[0871] A means for displaying the obtained confidence level to the user and collecting responses,

[0872] A means for storing analysis records within the device and anonymizing response information before sending it to an external server,

[0873] A means characterized by evaluating the reliability of information in a content distribution service and displaying the reliability level in real time while viewing,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, characterized in that, when evaluating the reliability of input information, it detects matches with known inaccurate information patterns and also provides a simple evaluation of the reliability of video.

[0877] (Claim 3)

[0878] The system according to claim 1, characterized in that it autonomously updates a knowledge processing model using response information obtained through analysis, thereby improving the reliability evaluation of content being viewed.

[0879] "Example 2 of combining an emotion engine"

[0880] (Claim 1)

[0881] A means for installing an intelligent model for detecting misinformation and loading necessary resources into a storage device,

[0882] A means for temporarily storing video or articles received from a user as input information,

[0883] A means for converting input information into an analyzable format and evaluating the reliability of the information using image analysis and automatic language processing techniques,

[0884] A means of analyzing user sentiment based on evaluations and adjusting the display method accordingly,

[0885] A means of displaying the generated confidence level to users and collecting their opinions,

[0886] A means for recording analysis history within the device and anonymizing opinion data before transmitting it to a remote device,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, characterized in that, when evaluating the reliability of input information, it detects matches with existing misinformation patterns and takes into account the emotional state of the user.

[0890] (Claim 3)

[0891] The system according to claim 1, characterized in that it automatically updates and improves an intelligent model using opinion data obtained through analysis.

[0892] "Application example 2 of combining emotional engines"

[0893] (Claim 1)

[0894] A means for installing an artificial intelligence model on a mobile information processing terminal to detect false information and load the necessary computing resources into storage,

[0895] A means for storing videos or news articles received from users as input information in a memory area,

[0896] A means for converting input information into a parseable format and evaluating the reliability of the information using image processing and natural language processing techniques,

[0897] A means of displaying the obtained confidence value to the user and collecting responses,

[0898] A means for saving analysis records within the terminal, anonymizing response data, and transmitting it to an external storage device,

[0899] A means for analyzing the user's emotions and adjusting the method of presenting the analysis results according to their emotional state,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, characterized in that, when evaluating the reliability of input information, it detects matches with known false information patterns and optimizes the presentation of results while taking into account the emotional state of the user.

[0903] (Claim 3)

[0904] The system according to claim 1, characterized in that it autonomously updates and improves the artificial intelligence model using response data obtained through analysis, and also adaptively adjusts the method of presenting analysis results based on the user's emotions. [Explanation of Symbols]

[0905] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for installing on a mobile information processing terminal, launching an artificial intelligence model for detecting false information, and loading the necessary resources into memory, A means for saving videos or news articles received from a user as input data in a buffer, A means for converting input data into an analyzable format and evaluating the reliability of the data using computer vision and natural language processing techniques, A means of displaying the obtained confidence score to the user and collecting feedback, A method for saving analysis logs within the device and anonymizing feedback data before sending it to an external server, A system that includes this.

2. The system according to claim 1, characterized in that it detects matches with known fake information patterns when evaluating the reliability of input data.

3. The system according to claim 1, characterized in that it autonomously updates and improves the artificial intelligence model using feedback data obtained through analysis.

Images