system

Abstract

We provide the system. [Solution] A means of acquiring information that periodically collects data from internet sources, A scoring method that uses a machine learning model to score the reliability of the collected data, A filtering method for filtering out data whose score falls below a threshold, Information provision means that stores data exceeding a threshold and provides it to a communication terminal device upon request, A data processing means that, based on user requests, quickly searches for highly reliable information and provides it in a visually displayable format, 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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a large amount of unreliable and false information on the Internet, making it difficult for users to efficiently identify this information and safely and quickly access highly reliable information. Therefore, especially in the business and research fields, it is necessary to prevent judgment errors based on misinformation and support decision-making based on accurate information.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that automatically collects data from internet information sources and scores its reliability using a machine learning model. This system filters out low-scoring data and retains only high-scoring data. Furthermore, in response to information requests from users, it quickly searches the stored high-reliability data and provides it visually, enabling users to easily obtain accurate and reliable information.

[0006] "Information acquisition means" refers to the function of regularly collecting data from various information sources on the internet.

[0007] A "scoring method" refers to a function that analyzes collected data using a machine learning model and evaluates its reliability numerically.

[0008] "Filtering means" refers to a function that removes data deemed unreliable through scoring and selects and stores only highly reliable data.

[0009] "Information provision means" refers to a function that searches for highly reliable data based on user requests and provides it to the user quickly.

[0010] "Visualization means" refers to a function that displays searched information to the user in a visually easy-to-understand format.

[0011] A "machine learning model" refers to a set of algorithms used to analyze data and automatically evaluate its reliability.

[0012] A "threshold" refers to a numerical value used as a criterion for classifying the reliability of information in scoring. [Brief explanation of the drawing]

[0013] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It 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 Example 2 when an 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 an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled 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.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled 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.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system for collecting diverse information available on the internet, evaluating its reliability, and providing that information. The central function of this system is to automate data collection and reliability evaluation, thereby enabling users to efficiently obtain the highly reliable information they need.

[0035] First, the server periodically collects data from news sites, social media platforms, and other sources on the internet. This can be done by accessing these sources via APIs or by using web scraping techniques. Next, the collected information is stored in a temporary database on the server.

[0036] The server uses a machine learning model to assign a reliability score to the collected data. This score considers the historical reliability of the information source and the integrity of the content itself. This process is automated, and the server evaluates the information in real time.

[0037] After scoring is complete, the server filters out information with a reliability score below a threshold and removes it from the database. This ensures that only highly reliable information is retained when users access it.

[0038] Users can use their devices to request, for example, "the latest technology news." This request is sent from the device to the server, which searches a highly reliable information database for relevant information. The results are then sent back to the device and presented to the user in a visualized format.

[0039] As a concrete example, users who want accurate damage information in the event of a disaster can receive the latest and most reliable information by sending a request from their device. This information is free from misinformation and rumors, and users can use it as a basis for making safe decisions.

[0040] In this way, this system automatically filters large amounts of information, enabling it to quickly provide highly reliable information that users can use with confidence.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server accesses internet sources at specified time intervals and collects data through news APIs and social media APIs. The collected data includes article titles, content, and source metadata.

[0044] Step 2:

[0045] The server stores the collected data in a temporary database. This is in preparation for a subsequent reliability assessment to be performed quickly.

[0046] Step 3:

[0047] The server uses a machine learning model on the stored data to calculate a data reliability score. Factors such as the data source and the past evaluation history of its content are taken into consideration.

[0048] Step 4:

[0049] The server identifies data whose scores fall below a threshold and removes it from the temporary database. This process filters the data so that only highly reliable data remains.

[0050] Step 5:

[0051] The user sends a request to search for specific information through their device. The request is forwarded to the server by the device.

[0052] Step 6:

[0053] The server searches for relevant information from a highly reliable information database based on the request content and sends the results to the terminal.

[0054] Step 7:

[0055] The device visually displays the received information to the user. The information is formatted and presented in a way that is easily understandable to the user.

[0056] Step 8:

[0057] Users can review the information presented through their device and perform additional searches as needed.

[0058] (Example 1)

[0059] 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."

[0060] The internet contains a vast amount of information, some of which is unreliable. It is difficult for users to efficiently obtain accurate and reliable information, and sometimes they may make poor decisions based on incorrect information. To solve this problem, a means is needed to collect data from multiple sources, quickly and efficiently evaluate its reliability, and provide it to users.

[0061] 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.

[0062] In this invention, the server includes an information acquisition means for periodically collecting information from an information set, an evaluation means for evaluating the reliability of the collected information using a predictive model, and an exclusion means for excluding information whose evaluation score falls below a certain threshold. This makes it possible to quickly provide only highly reliable information to the user.

[0063] An "information aggregate" refers to multiple sources of information on the internet, including news sites and social media platforms.

[0064] "Information acquisition means" refers to mechanisms and methods for periodically collecting information from an information collection, and may include using API access or web scraping techniques.

[0065] A "predictive model" refers to an algorithm or method used to evaluate the reliability of information collected using machine learning techniques.

[0066] "Evaluation methods" refer to processes and devices that use predictive models to quantify and score the reliability of information.

[0067] An "evaluation score" is a numerical value calculated to indicate the reliability of information, and the validity of the information is judged based on this score.

[0068] A "benchmark value" is the minimum numerical value that an evaluation score should achieve; information below this value is considered unreliable.

[0069] "Exclusionary measures" refer to processes and technologies used to remove information from a database whose evaluation score falls below a certain threshold.

[0070] "Information delivery means" refers to methods and devices for providing reliable information in response to user requests.

[0071] "Means of making information visible" refers to methods and systems for presenting information to users in an easily viewable format.

[0072] This invention is a system for users to efficiently acquire highly reliable information. The system is primarily built on a server, and the processes of information collection, evaluation, and provision work in coordination.

[0073] First, the server maintains a list of multiple information sources on the internet as an information collection. This includes news sites and social media platforms. Based on this list, the server periodically collects information through API access or web scraping techniques using BeautifulSoup or Scrapy.

[0074] The collected information is stored in a temporary database on the server, and then the reliability of each piece of information is evaluated using a predictive model. The server utilizes machine learning libraries such as TENSORFLOW® and PyTorch to calculate an evaluation score, taking into account the historical data and consistency of the content of the information source.

[0075] Based on the evaluation results, information with a reliability score below a certain threshold is removed from the database by the server. This removal mechanism prevents information overload and improves the accuracy of the information supplied to users.

[0076] Users can use their terminal to request specific information from the server. For example, they might enter a prompt such as "Tell me about the latest technological advancements." Based on the request sent from the terminal, the server quickly searches for relevant and reliable information and sends the results to the terminal. The terminal then presents this information in a visual format, making it easy for the user to understand. This process might utilize a user interface built with React, for example.

[0077] As a concrete example, in the event of a natural disaster, a user who wants to quickly obtain information about safe areas can enter a prompt message on their device such as "Tell me where to evacuate safely during a disaster," and instantly receive the latest and most reliable information from the server. In this way, users can make safe decisions based on accurate information.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server begins collecting information from a data set. It receives a list of URLs from news sites and social media platforms as input. The server collects data in HTML and JSON format by sending requests via APIs or by using web scraping techniques. Software such as Scrapy or BeautifulSoup is used for this purpose. The output is the collected raw data.

[0081] Step 2:

[0082] The server organizes the collected raw data. The input is the raw data obtained in step 1. The server performs data cleaning, such as removing unnecessary information and HTML tags and unifying character encoding. As a result of this process, the output is clean data formatted into a unified format.

[0083] Step 3:

[0084] The server performs a reliability assessment on the clean data. The input is the clean data obtained in step 2. The server applies a machine learning model and calculates a reliability score based on the historical data and consistency of the information from the source. TensorFlow or PyTorch is used for this process. The output is a dataset with a reliability score assigned to each data point.

[0085] Step 4:

[0086] The server eliminates information whose reliability score falls below a threshold. The input is the reliability-evaluated dataset obtained in step 3. Data with scores below the threshold is removed from the database. This elimination mechanism ensures that only information whose reliability has been confirmed remains on the server. The output is filtered, high-reliability data.

[0087] Step 5:

[0088] The user sends an information request from their device. The input is the prompt message entered by the user. For example, a request such as "Tell me the latest AI news" is possible. This prompt message is transmitted to the server via the device. The output is the information request sent to the server.

[0089] Step 6:

[0090] The server searches for relevant information based on the user's request. The input is the information request received in step 5. The server searches the database for reliable information and extracts data that matches the request. The output is a set of information results related to the user's request.

[0091] Step 7:

[0092] The server sends the search results to the terminal and presents them visually to the user. The input is the information result set from step 6. The terminal receives the results and visualizes them in a user-friendly format. Frontend technologies such as React are used for this display. The output is the visual information presented to the user.

[0093] (Application Example 1)

[0094] 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."

[0095] The internet contains a vast amount of diverse information, making it difficult for users to quickly and efficiently find highly reliable information. Furthermore, there is a risk of unreliable information being misused, highlighting the need for safe and reliable information. This invention aims to solve these problems and provide a system that efficiently delivers highly reliable information.

[0096] 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.

[0097] In this invention, the server includes information acquisition means for periodically collecting data from information sources on the Internet, scoring means for performing reliability scoring on the collected data using a machine learning model, and filtering means for filtering data whose scores fall below a threshold. This enables users to efficiently and securely obtain highly reliable information.

[0098] "Information acquisition means" refers to a device or method for periodically collecting data from information sources on the Internet.

[0099] A "scoring means" is a device or method that uses a machine learning model to calculate a reliability score for collected data.

[0100] "Filtering means" refers to a device or method for removing data whose reliability score falls below a threshold.

[0101] "Information provision means" refers to a device or method for storing highly reliable data that exceeds a threshold and providing it to a communication terminal device upon request.

[0102] "Data processing means" refers to a device or method for quickly retrieving highly reliable information in response to user requests and presenting it in a visually displayable format.

[0103] A "communication terminal device" is a device used by users to receive and display information.

[0104] A "visually displayable format" refers to a form in which information can be visually confirmed by the user on a terminal device.

[0105] The system that implements this application is configured as follows: The server periodically collects data from various sources on the internet. This collection process utilizes web scraping techniques using Python and various APIs (e.g., news distribution APIs and social media APIs) to obtain information. The collected data is temporarily stored in databases such as MySQL® or PostgreSQL.

[0106] Next, the server uses machine learning libraries such as TensorFlow or PyTorch to score the reliability of the data. This scoring is based on past reliability data and content consistency of the source. If the score falls below the threshold, the data is filtered out. On the other hand, highly reliable data that exceeds the threshold is saved and ready for information provision.

[0107] When a user requests specific information via a communication terminal, this server quickly searches for the necessary information and presents it visually in a user-friendly format. Specifically, dashboard and graphing technologies are used for data visualization. For example, if a user requests "latest technology news," highly reliable information is prioritized and displayed in an intuitive interface.

[0108] For example, if a user requests "the latest information on the host cities of the 2024 Olympic Games," reliable information related to that topic will be displayed immediately. An example of a prompt to the generative AI model in this system is, "Use the following information to gather top news about climate change and evaluate its reliability."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server collects data from sources on the internet. It is given a list of URLs or API endpoints as input, and raw data is retrieved as output. This data is collected using Python libraries (such as BeautifulSoup and Requests). Specifically, the server parses web pages and extracts relevant text information.

[0112] Step 2:

[0113] The server temporarily stores the collected data in a database. The input is the raw data obtained in step 1, and the output is the organized information in the database. At this stage, MySQL or PostgreSQL is used to store the data in a structured format. Specifically, the server establishes a database connection and stores the information using INSERT queries.

[0114] Step 3:

[0115] The server scores the reliability of the data using a machine learning model. The input is the data saved in step 2, and the output is the data with the reliability score assigned to it. A pre-trained model is executed using libraries such as TensorFlow or PyTorch. Specifically, the server inputs the data into the model and calculates the score.

[0116] Step 4:

[0117] The server filters out and removes data whose scores fall below a threshold. The input is the scored data generated in step 3, and the output is the high-confidence data that exceeds the threshold. The filtering algorithm compares the scores and keeps only the matching data. Specifically, the filtering conditions are applied using SQL queries.

[0118] Step 5:

[0119] A user requests specific information using a communication terminal device. The input is the user's request, and the output is the corresponding request parameters. This request is received by the frontend, for example, through form input. Specifically, the terminal sends the request to the server in HTTP request format.

[0120] Step 6:

[0121] The server searches the database for highly reliable information based on the user's request and generates results. The input is the request parameters received in step 5, and the output is a set of relevant information. An SQL query is created to perform a database search. Specifically, the server extracts data that matches the criteria.

[0122] Step 7:

[0123] The server converts the search results into a user-friendly format and sends the visually displayable data to the device. The input is the search results obtained in step 6, and the output is user-friendly visually displayable data. Data formatting techniques and front-end libraries (e.g., React, Angular) are used to optimize the display. Specifically, the server packages the data in HTML format and returns it to the device.

[0124] Step 8:

[0125] The user uses a communication terminal to visually confirm information from the server and use it for decision-making. The input is the visual display data transmitted in step 7, and the output is the user's understanding and decision-making actions. Specifically, the user views the information in a browser or application and takes the necessary actions.

[0126] 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.

[0127] This invention is an information provision system that takes user emotions into consideration. It periodically collects data from internet-based information sources, evaluates the reliability of that data using a machine learning model, and optimizes information provision by recognizing the user's emotional state.

[0128] The server collects data from news sites and social media platforms and stores that information in a temporary database. The collected information is analyzed by a machine learning model, and a reliability score is calculated. Based on this score, the information is filtered, and only information that exceeds a threshold is retained.

[0129] Furthermore, the server uses an emotion engine to analyze the user's emotional state obtained from the terminal. This includes a process of inferring the user's current emotions through facial recognition technology and voice analysis. The emotion engine treats the user's emotions as parameters and plays a role in adjusting the method and content of information provided.

[0130] When a user requests information from their device, the server selects and provides the most relevant information to the device based on the emotional state recognized by the emotion engine. In this process, the tone and display format of the information may be adjusted to reduce the user's emotional burden.

[0131] For example, if a user makes a request while feeling stressed, the server can organize the information accordingly, and the device can prioritize displaying positive and reassuring information for the user. This allows the user to receive information that is appropriate to their emotional state, supporting better decision-making.

[0132] This system enhances the user experience and delivers more personalized information services by integrating emotion recognition with automated information delivery.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server periodically connects to internet information sources and uses news APIs and social media APIs to collect the latest data. The collected data includes article titles, body text, and source, and is temporarily stored in a database.

[0136] Step 2:

[0137] The server applies a machine learning model to the collected data and calculates a reliability score. This model scores based on the source's past reliability data and content evaluation.

[0138] Step 3:

[0139] The server automatically filters out data with a reliability score below a threshold, removes it, and then stores only the highly reliable data in a permanent database.

[0140] Step 4:

[0141] The device activates an emotion engine through its interface with the user to detect the user's emotional state. This is achieved through methods such as facial recognition using a camera and voice analysis using a microphone.

[0142] Step 5:

[0143] The emotion engine analyzes the detected user's emotions and sends that information to the server. The server uses this information to adjust the content and method of information provision.

[0144] Step 6:

[0145] The user requests specific information via their device. The device receives this request and requests the information from the server.

[0146] Step 7:

[0147] The server searches a highly reliable database for information that matches the user's request. Furthermore, it adjusts how the information is displayed (such as tone and content selection) taking into account data obtained from the sentiment engine.

[0148] Step 8:

[0149] The device receives information sent from the server and displays it in the most optimal format according to the user's emotional state. This allows users to comfortably use information that matches their emotional state.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0152] It is necessary to evaluate the reliability of information on the internet while providing appropriate information tailored to the user's emotional state. However, conventional systems do not integrate information reliability filtering with information optimization based on the user's emotions, making it difficult for users to obtain information that is best suited to their mental state. Furthermore, there are insufficient means to effectively utilize the influence of the user's emotional state on information provision.

[0153] 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.

[0154] In this invention, the server includes an information gathering means for periodically aggregating information, a scoring means for evaluating reliability using an artificial intelligence model, and a filtering means for removing information whose reliability does not meet specific criteria. This makes it possible to provide highly reliable information. Furthermore, by including an emotion adjustment means for detecting the emotional state from the user's input device and adjusting the information supply means, the server can provide information that is appropriate to the user's emotional state, thereby improving the user experience.

[0155] An "information gathering tool" is a system component that continuously aggregates information from multiple sources on a digital network.

[0156] A "scoring method" is a system component that utilizes artificial intelligence models to quantitatively evaluate the reliability of aggregated information and express it as a numerical value.

[0157] A "filtering mechanism" is a system component that selects and removes information whose reliability falls below a certain standard from the information evaluated by the scoring mechanism.

[0158] An "information supply means" is a system component that stores highly reliable information that has passed through a filtering means and provides it to users upon request.

[0159] An "emotion adjustment tool" is a system component that optimizes the information provided by an information supply tool based on emotional state data acquired from users.

[0160] This invention is an information management system for providing information based on the user's emotional state.

[0161] The server automatically aggregates information from various sources on the digital network using information gathering means. Specific information crawling software is used at this stage; for example, tools such as Scrapy can be used.

[0162] Next, the server evaluates the aggregated information using a scoring mechanism. This process utilizes an artificial intelligence model, and either TensorFlow or PyTorch can be used as the model. This model is used to calculate a reliability score, quantifying the reliability of the information.

[0163] Based on the scoring results, the server uses filtering mechanisms to remove information that does not meet the reliability criteria. Only highly reliable information that exceeds the threshold is stored. This filtering ensures the quality of information provided to users.

[0164] Furthermore, the device uses emotion adjustment mechanisms to analyze the user's facial expressions and voice from input devices such as cameras and microphones, and estimate their emotional state. For example, it can use facial recognition technology with OpenCV or identify emotions from voice using Google® Cloud Speech-to-Text API. As a result, the server receives the user's emotional data and adjusts the information supply mechanism.

[0165] When a user requests information, the server provides highly reliable information optimized for that emotion, and the terminal displays it to the user. The information is displayed in a visually adjusted format to match the user's emotional state, allowing the user to intuitively receive information that is relevant to their feelings.

[0166] For example, if a user makes a request using the prompt "Please recommend some relaxing content," the server can select reliable news and relaxing music and display them on the device. In this way, the system can improve the user experience and make the way information is received more personalized.

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

[0168] Step 1:

[0169] The server aggregates information from digital networks using information gathering tools. It uses a list of URLs from news sites and social media platforms as input. Its operation involves accessing each information source using crawling software (e.g., Scrapy), extracting data in a specified format, and storing it in a temporary database. The output is a set of collected raw data.

[0170] Step 2:

[0171] The server evaluates the reliability of the information using a scoring mechanism. The information aggregated in step 1 is used as input. The server analyzes the content of each piece of information using an artificial intelligence model (e.g., TensorFlow) and generates a score based on the frequency of occurrence and reliability patterns. The output is the reliability score assigned to each piece of information.

[0172] Step 3:

[0173] The server uses filtering mechanisms to remove unreliable information. The input is the information that was scored in step 2. The server is programmed to set a threshold and remove information with scores below that threshold from the database. The output consists of the set of information deemed highly reliable.

[0174] Step 4:

[0175] The device acquires the user's emotional state using emotion adjustment mechanisms. Inputs include user facial expression data and voice data acquired using a camera and microphone. The device analyzes the emotional state by applying facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., Google Cloud Speech-to-Text API). The output is the analyzed emotional data.

[0176] Step 5:

[0177] The server optimizes information delivery based on emotional data. The inputs are the emotional states collected in step 4 and the information filtered in step 3. The server processes the data collected by the emotion engine and adjusts the priority of information to match the user's emotions. The output is a list of prioritized information provided to the user.

[0178] Step 6:

[0179] The user requests information through the device. The input is a prompt from the user (for example, "Please recommend some relaxing content."). The device receives optimized information from the server, adjusts the display format to match the user's mood, and displays it on the screen. The output is information displayed in a format suitable for the user experience.

[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] Traditional information delivery systems present information without considering the user's emotional state, sometimes providing information that is unpleasant or stressful for the user. Therefore, there is a need to achieve a better user experience through flexible information delivery that takes user emotions into consideration. Furthermore, in the advertising field, displaying content that resonates with the recipient's emotions is a crucial issue in enhancing the sales promotion effectiveness for clients.

[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 emotion analysis means for analyzing the user's emotional state, display optimization means for optimizing the selection and display of information based on the analyzed emotional state, and information acquisition means for periodically collecting data from information sources on the Internet. This enables personalized information provision and advertisement display according to the user's emotional state.

[0185] "User emotional state" refers to the user's current psychological state, as determined from their facial expressions, tone of voice, and other factors.

[0186] "Emotional analysis tools" refer to a part of a system that has the function of recognizing and analyzing a user's emotional state.

[0187] "Display optimization means" refers to a part of a system that has the function of adjusting the content and format of the information displayed based on the analyzed emotional state.

[0188] "Information acquisition means" refers to a part of a system that has the function of periodically collecting data from information sources on the internet.

[0189] A "machine learning model" is an algorithm or method used to evaluate reliability based on data.

[0190] A "scoring method" is a part of a system that uses a machine learning model on collected data to quantify its reliability.

[0191] A "filtering mechanism" is a part of a system that has the function of excluding data whose score falls below a set threshold.

[0192] An "information provision means" is a part of a system that has the function of storing data that exceeds a threshold and providing it in the most optimal format when requested by the user.

[0193] This invention primarily involves a server, a terminal, and a user. The server has an information acquisition function for periodically collecting data from various sources on the internet. The collected data is then scored for reliability using a machine learning model, and only reliable information is filtered and stored. Machine learning frameworks such as TensorFlow and PyTorch can be used for scoring.

[0194] Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's emotional state during data processing. This emotion analysis is performed by acquiring the user's facial expressions and voice in real time using the smartphone's camera and microphone. The emotion analysis engine then analyzes this data to identify the user's emotional state. Technologies such as Emotion API and IBM Watson® Tone Analyzer can be used for this process.

[0195] The device displays information provided by the server in a format optimized according to the user's emotional state. This includes selecting information and adjusting the display format based on the emotional state, aiming to improve the user experience.

[0196] For example, if facial recognition technology detects a tired expression on a user's face while they are using their smartphone during their commute, the server can send advertisements for relaxing products to the device and display them effectively. This process results in personalized information delivery that reduces stress for the user.

[0197] The following prompt statements can be used in the generative AI model:

[0198] "When a user's current emotional state is 'fatigue' or 'stress,' generate information that provides a sense of reassurance. For example, suggest a short video with a relaxing effect."

[0199] In this way, it becomes possible to provide information and display advertisements based on the user's emotions, supporting better user decision-making.

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The server periodically collects data from internet sources. It uses a list of URLs as input. The data is collected using web scraping techniques and stored in a temporary database. The output is the raw, collected data.

[0203] Step 2:

[0204] The server uses a machine learning model to score the reliability of the collected data. The input consists of data in a temporary database and its metadata. TensorFlow and PyTorch are used to process the data, calculate the reliability score, and obtain the scoring result. The output is a new dataset containing the reliability scores for the data.

[0205] Step 3:

[0206] The server determines a threshold and filters out data whose score falls below the threshold. The input is the confidence score data generated in step 2. Filtering is performed to select and retain the most reliable data. The output is the reliable filtered data.

[0207] Step 4:

[0208] The device uses the smartphone's camera and microphone to acquire data in order to analyze the user's emotional state in real time. Inputs include the user's facial expressions and voice. An emotion analysis engine performs facial recognition and voice analysis to infer the user's emotional state. The output is data indicating the user's emotional state.

[0209] Step 5:

[0210] The server receives user emotional state data and optimizes information delivery based on it. Input includes filtered data and user emotional state data. Using a generative AI model, it generates or selects information that matches the user's emotions based on prompt messages. The output is an emotionally optimized set of information.

[0211] Step 6:

[0212] The terminal displays optimized information sent from the server to the user. The input includes an emotionally optimized set of information. The tone and format of the information are adjusted to match the user's emotions and displayed visually. The user experiences information consumption in a relaxed state. The output is intuitive and emotionally sensitive information displayed to the user.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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".

[0229] This invention is a system for collecting diverse information available on the internet, evaluating its reliability, and providing that information. The central function of this system is to automate data collection and reliability evaluation, thereby enabling users to efficiently obtain the highly reliable information they need.

[0230] First, the server periodically collects data from news sites, social media platforms, and other sources on the internet. This can be done by accessing these sources via APIs or by using web scraping techniques. Next, the collected information is stored in a temporary database on the server.

[0231] The server uses a machine learning model to assign a reliability score to the collected data. This score considers the historical reliability of the information source and the integrity of the content itself. This process is automated, and the server evaluates the information in real time.

[0232] After scoring is complete, the server filters out information with a reliability score below a threshold and removes it from the database. This ensures that only highly reliable information is retained when users access it.

[0233] Users can use their devices to request, for example, "the latest technology news." This request is sent from the device to the server, which searches a highly reliable information database for relevant information. The results are then sent back to the device and presented to the user in a visualized format.

[0234] As a concrete example, users who want accurate damage information in the event of a disaster can receive the latest and most reliable information by sending a request from their device. This information is free from misinformation and rumors, and users can use it as a basis for making safe decisions.

[0235] In this way, this system automatically filters large amounts of information, enabling it to quickly provide highly reliable information that users can use with confidence.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server accesses internet sources at specified time intervals and collects data through news APIs and social media APIs. The collected data includes article titles, content, and source metadata.

[0239] Step 2:

[0240] The server stores the collected data in a temporary database. This is in preparation for a subsequent reliability assessment to be performed quickly.

[0241] Step 3:

[0242] The server uses a machine learning model on the stored data to calculate a data reliability score. Factors such as the data source and the past evaluation history of its content are taken into consideration.

[0243] Step 4:

[0244] The server identifies data whose scores fall below a threshold and removes it from the temporary database. This process filters the data so that only highly reliable data remains.

[0245] Step 5:

[0246] The user sends a request to search for specific information through their device. The request is forwarded to the server by the device.

[0247] Step 6:

[0248] The server searches for relevant information from a highly reliable information database based on the request content and sends the results to the terminal.

[0249] Step 7:

[0250] The device visually displays the received information to the user. The information is formatted and presented in a way that is easily understandable to the user.

[0251] Step 8:

[0252] Users can review the information presented through their device and perform additional searches as needed.

[0253] (Example 1)

[0254] 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".

[0255] The internet contains a vast amount of information, some of which is unreliable. It is difficult for users to efficiently obtain accurate and reliable information, and sometimes they may make poor decisions based on incorrect information. To solve this problem, a means is needed to collect data from multiple sources, quickly and efficiently evaluate its reliability, and provide it to users.

[0256] 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.

[0257] In this invention, the server includes an information acquisition means for periodically collecting information from an information set, an evaluation means for evaluating the reliability of the collected information using a predictive model, and an exclusion means for excluding information whose evaluation score falls below a certain threshold. This makes it possible to quickly provide only highly reliable information to the user.

[0258] An "information aggregate" refers to multiple sources of information on the internet, including news sites and social media platforms.

[0259] "Information acquisition means" refers to mechanisms and methods for periodically collecting information from an information collection, and may include using API access or web scraping techniques.

[0260] A "predictive model" refers to an algorithm or method used to evaluate the reliability of information collected using machine learning techniques.

[0261] "Evaluation methods" refer to processes and devices that use predictive models to quantify and score the reliability of information.

[0262] An "evaluation score" is a numerical value calculated to indicate the reliability of information, and the validity of the information is judged based on this score.

[0263] A "benchmark value" is the minimum numerical value that an evaluation score should achieve; information below this value is considered unreliable.

[0264] "Exclusionary measures" refer to processes and technologies used to remove information from a database whose evaluation score falls below a certain threshold.

[0265] "Information delivery means" refers to methods and devices for providing reliable information in response to user requests.

[0266] "Means of making information visible" refers to methods and systems for presenting information to users in an easily viewable format.

[0267] This invention is a system for users to efficiently acquire highly reliable information. The system is primarily built on a server, and the processes of information collection, evaluation, and provision work in coordination.

[0268] First, the server maintains a list of multiple information sources on the internet as an information collection. This includes news sites and social media platforms. Based on this list, the server periodically collects information through API access or web scraping techniques using BeautifulSoup or Scrapy.

[0269] The collected information is stored in a temporary database on the server, and then the reliability of each piece of information is evaluated using a predictive model. The server utilizes machine learning libraries such as TensorFlow and PyTorch to calculate an evaluation score, taking into account the historical data and consistency of the information source.

[0270] Based on the evaluation results, information with a reliability score below a certain threshold is removed from the database by the server. This removal mechanism prevents information overload and improves the accuracy of the information supplied to users.

[0271] Users can use their terminal to request specific information from the server. For example, they might enter a prompt such as "Tell me about the latest technological advancements." Based on the request sent from the terminal, the server quickly searches for relevant and reliable information and sends the results to the terminal. The terminal then presents this information in a visual format, making it easy for the user to understand. This process might utilize a user interface built with React, for example.

[0272] As a concrete example, in the event of a natural disaster, a user who wants to quickly obtain information about safe areas can enter a prompt message on their device such as "Tell me where to evacuate safely during a disaster," and instantly receive the latest and most reliable information from the server. In this way, users can make safe decisions based on accurate information.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] The server begins collecting information from a data set. It receives a list of URLs from news sites and social media platforms as input. The server collects data in HTML and JSON format by sending requests via APIs or by using web scraping techniques. Software such as Scrapy or BeautifulSoup is used for this purpose. The output is the collected raw data.

[0276] Step 2:

[0277] The server organizes the collected raw data. The input is the raw data obtained in step 1. The server performs data cleaning, such as removing unnecessary information and HTML tags and unifying character encoding. As a result of this process, the output is clean data formatted into a unified format.

[0278] Step 3:

[0279] The server performs a reliability assessment on the clean data. The input is the clean data obtained in step 2. The server applies a machine learning model and calculates a reliability score based on the historical data and consistency of the information from the source. TensorFlow or PyTorch is used for this process. The output is a dataset with a reliability score assigned to each data point.

[0280] Step 4:

[0281] The server eliminates information whose reliability score falls below a threshold. The input is the reliability-evaluated dataset obtained in step 3. Data with scores below the threshold is removed from the database. This elimination mechanism ensures that only information whose reliability has been confirmed remains on the server. The output is filtered, high-reliability data.

[0282] Step 5:

[0283] The user sends an information request from the terminal. The input is the prompt text entered by the user. For example, a request like "Tell me the latest AI news" can be considered. This prompt text is transmitted to the server through the terminal. The output is an information request to the server.

[0284] Step 6:

[0285] The server searches for relevant information based on the user's request. The input is the information request received in Step 5. The server searches for highly reliable information in the database and extracts data that matches the request. The output is an information result set related to the user request.

[0286] Step 7:

[0287] The server sends the search results to the terminal and visually presents them to the user. The input is the information result set from Step 6. The terminal receives the results and visualizes them in a format that is easy for the user to understand. Front-end technologies such as React are used for this display. The output is the visual information presented to the user.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] There is a wide variety of information on the Internet, and it is difficult for users to quickly and efficiently find highly reliable information from it. In addition, there is a risk that low-reliability information may be misused, and there is a need to obtain safe and reliable information. The purpose of the present invention is to solve such problems and provide a system that efficiently provides highly reliable information.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0292] In this invention, the server includes information acquisition means for periodically collecting data from information sources on the Internet, scoring means for performing reliability scoring on the collected data using a machine learning model, and filtering means for filtering data whose scores fall below a threshold. This enables users to efficiently and securely obtain highly reliable information.

[0293] "Information acquisition means" refers to a device or method for periodically collecting data from information sources on the Internet.

[0294] A "scoring means" is a device or method that uses a machine learning model to calculate a reliability score for collected data.

[0295] "Filtering means" refers to a device or method for removing data whose reliability score falls below a threshold.

[0296] "Information provision means" refers to a device or method for storing highly reliable data that exceeds a threshold and providing it to a communication terminal device upon request.

[0297] "Data processing means" refers to a device or method for quickly retrieving highly reliable information in response to user requests and presenting it in a visually displayable format.

[0298] A "communication terminal device" is a device used by users to receive and display information.

[0299] A "visually displayable format" refers to a form in which information can be visually confirmed by the user on a terminal device.

[0300] The system that implements this application is configured as follows: The server periodically collects data from various sources on the internet. This collection process utilizes web scraping techniques using Python and various APIs (e.g., news distribution APIs and social media APIs) to obtain information. The collected data is temporarily stored in a database such as MySQL or PostgreSQL.

[0301] Next, the server uses machine learning libraries such as TensorFlow or PyTorch to score the reliability of the data. This scoring is based on past reliability data and content consistency of the source. If the score falls below the threshold, the data is filtered out. On the other hand, highly reliable data that exceeds the threshold is saved and ready for information provision.

[0302] When a user requests specific information via a communication terminal, this server quickly searches for the necessary information and presents it visually in a user-friendly format. Specifically, dashboard and graphing technologies are used for data visualization. For example, if a user requests "latest technology news," highly reliable information is prioritized and displayed in an intuitive interface.

[0303] For example, if a user requests "the latest information on the host cities of the 2024 Olympic Games," reliable information related to that topic will be displayed immediately. An example of a prompt to the generative AI model in this system is, "Use the following information to gather top news about climate change and evaluate its reliability."

[0304] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0305] Step 1:

[0306] The server collects data from information sources on the Internet. Given a list of URLs or API endpoints as input, raw data is obtained as output. This data is collected using Python libraries such as BeautifulSoup and Requests. As a specific operation, the server parses web pages and extracts relevant text information.

[0307] Step 2:

[0308] The server temporarily stores the collected data in a database. The input is the raw data obtained in Step 1, and the output is the organized information in the database. At this stage, MySQL or PostgreSQL is used to store the data in a structured format. As a specific operation, the server establishes a database connection and stores the information using an INSERT query.

[0309] Step 3:

[0310] The server scores the reliability of the data using a machine learning model. The input is the data saved in Step 2, and the output is the data with a reliability score assigned. Using libraries such as TensorFlow and PyTorch, a pre-trained model is executed. As a specific operation, the server inputs the data into the model and calculates the score.

[0311] Step 4:

[0312] The server filters and removes data whose scores are below the threshold. The input is the scored data generated in Step 3, and the output is the high-reliability data that exceeds the threshold. Using a filtering algorithm, the server compares the scores and retains only the matching data. As a specific operation, filtering conditions are applied using an SQL query.

[0313] Step 5:

[0314] A user requests specific information using a communication terminal device. The input is the user's request, and the output is the corresponding request parameters. This request is received by the frontend, for example, through form input. Specifically, the terminal sends the request to the server in HTTP request format.

[0315] Step 6:

[0316] The server searches the database for highly reliable information based on the user's request and generates results. The input is the request parameters received in step 5, and the output is a set of relevant information. An SQL query is created to perform a database search. Specifically, the server extracts data that matches the criteria.

[0317] Step 7:

[0318] The server converts the search results into a user-friendly format and sends the visually displayable data to the device. The input is the search results obtained in step 6, and the output is user-friendly visually displayable data. Data formatting techniques and front-end libraries (e.g., React, Angular) are used to optimize the display. Specifically, the server packages the data in HTML format and returns it to the device.

[0319] Step 8:

[0320] The user uses a communication terminal to visually confirm information from the server and use it for decision-making. The input is the visual display data transmitted in step 7, and the output is the user's understanding and decision-making actions. Specifically, the user views the information in a browser or application and takes the necessary actions.

[0321] 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.

[0322] This invention is an information provision system that takes user emotions into consideration. It periodically collects data from internet-based information sources, evaluates the reliability of that data using a machine learning model, and optimizes information provision by recognizing the user's emotional state.

[0323] The server collects data from news sites and social media platforms and stores that information in a temporary database. The collected information is analyzed by a machine learning model, and a reliability score is calculated. Based on this score, the information is filtered, and only information that exceeds a threshold is retained.

[0324] Furthermore, the server uses an emotion engine to analyze the user's emotional state obtained from the terminal. This includes a process of inferring the user's current emotions through facial recognition technology and voice analysis. The emotion engine treats the user's emotions as parameters and plays a role in adjusting the method and content of information provided.

[0325] When a user requests information from their device, the server selects and provides the most relevant information to the device based on the emotional state recognized by the emotion engine. In this process, the tone and display format of the information may be adjusted to reduce the user's emotional burden.

[0326] For example, if a user makes a request while feeling stressed, the server can organize the information accordingly, and the device can prioritize displaying positive and reassuring information for the user. This allows the user to receive information that is appropriate to their emotional state, supporting better decision-making.

[0327] This system enhances the user experience and delivers more personalized information services by integrating emotion recognition with automated information delivery.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The server periodically connects to internet information sources and uses news APIs and social media APIs to collect the latest data. The collected data includes article titles, body text, and source, and is temporarily stored in a database.

[0331] Step 2:

[0332] The server applies a machine learning model to the collected data and calculates a reliability score. This model scores based on the source's past reliability data and content evaluation.

[0333] Step 3:

[0334] The server automatically filters out data with a reliability score below a threshold, removes it, and then stores only the highly reliable data in a permanent database.

[0335] Step 4:

[0336] The device activates an emotion engine through its interface with the user to detect the user's emotional state. This is achieved through methods such as facial recognition using a camera and voice analysis using a microphone.

[0337] Step 5:

[0338] The emotion engine analyzes the detected user's emotions and sends that information to the server. The server uses this information to adjust the content and method of information provision.

[0339] Step 6:

[0340] The user requests specific information via their device. The device receives this request and requests the information from the server.

[0341] Step 7:

[0342] The server searches a highly reliable database for information that matches the user's request. Furthermore, it adjusts how the information is displayed (such as tone and content selection) taking into account data obtained from the sentiment engine.

[0343] Step 8:

[0344] The device receives information sent from the server and displays it in the most optimal format according to the user's emotional state. This allows users to comfortably use information that matches their emotional state.

[0345] (Example 2)

[0346] 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".

[0347] It is necessary to evaluate the reliability of information on the internet while providing appropriate information tailored to the user's emotional state. However, conventional systems do not integrate information reliability filtering with information optimization based on the user's emotions, making it difficult for users to obtain information that is best suited to their mental state. Furthermore, there are insufficient means to effectively utilize the influence of the user's emotional state on information provision.

[0348] 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.

[0349] In this invention, the server includes an information gathering means for periodically aggregating information, a scoring means for evaluating reliability using an artificial intelligence model, and a filtering means for removing information whose reliability does not meet specific criteria. This makes it possible to provide highly reliable information. Furthermore, by including an emotion adjustment means for detecting the emotional state from the user's input device and adjusting the information supply means, the server can provide information that is appropriate to the user's emotional state, thereby improving the user experience.

[0350] An "information gathering tool" is a system component that continuously aggregates information from multiple sources on a digital network.

[0351] A "scoring method" is a system component that utilizes artificial intelligence models to quantitatively evaluate the reliability of aggregated information and express it as a numerical value.

[0352] A "filtering mechanism" is a system component that selects and removes information whose reliability falls below a certain standard from the information evaluated by the scoring mechanism.

[0353] An "information supply means" is a system component that stores highly reliable information that has passed through a filtering means and provides it to users upon request.

[0354] An "emotion adjustment tool" is a system component that optimizes the information provided by an information supply tool based on emotional state data acquired from users.

[0355] This invention is an information management system for providing information based on the user's emotional state.

[0356] The server automatically aggregates information from various sources on the digital network using information gathering means. Specific information crawling software is used at this stage; for example, tools such as Scrapy can be used.

[0357] Next, the server evaluates the aggregated information using a scoring mechanism. This process utilizes an artificial intelligence model, and either TensorFlow or PyTorch can be used as the model. This model is used to calculate a reliability score, quantifying the reliability of the information.

[0358] Based on the scoring results, the server uses filtering mechanisms to remove information that does not meet the reliability criteria. Only highly reliable information that exceeds the threshold is stored. This filtering ensures the quality of information provided to users.

[0359] Furthermore, the device uses emotion adjustment mechanisms to analyze the user's facial expressions and voice from input devices such as cameras and microphones, and estimate their emotional state. For example, it can use facial recognition technology with OpenCV or identify emotions from voice using the Google Cloud Speech-to-Text API. As a result, the server receives the user's emotional data and adjusts the information supply mechanism accordingly.

[0360] When a user requests information, the server provides highly reliable information optimized for that emotion, and the terminal displays it to the user. The information is displayed in a visually adjusted format to match the user's emotional state, allowing the user to intuitively receive information that is relevant to their feelings.

[0361] For example, if a user makes a request using the prompt "Please recommend some relaxing content," the server can select reliable news and relaxing music and display them on the device. In this way, the system can improve the user experience and make the way information is received more personalized.

[0362] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0363] Step 1:

[0364] The server aggregates information from digital networks using information gathering tools. It uses a list of URLs from news sites and social media platforms as input. Its operation involves accessing each information source using crawling software (e.g., Scrapy), extracting data in a specified format, and storing it in a temporary database. The output is a set of collected raw data.

[0365] Step 2:

[0366] The server evaluates the reliability of the information using a scoring mechanism. The information aggregated in step 1 is used as input. The server analyzes the content of each piece of information using an artificial intelligence model (e.g., TensorFlow) and generates a score based on the frequency of occurrence and reliability patterns. The output is the reliability score assigned to each piece of information.

[0367] Step 3:

[0368] The server uses filtering mechanisms to remove unreliable information. The input is the information that was scored in step 2. The server is programmed to set a threshold and remove information with scores below that threshold from the database. The output consists of the set of information deemed highly reliable.

[0369] Step 4:

[0370] The device acquires the user's emotional state using emotion adjustment mechanisms. Inputs include user facial expression data and voice data acquired using a camera and microphone. The device analyzes the emotional state by applying facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., Google Cloud Speech-to-Text API). The output is the analyzed emotional data.

[0371] Step 5:

[0372] The server optimizes information delivery based on emotional data. The inputs are the emotional states collected in step 4 and the information filtered in step 3. The server processes the data collected by the emotion engine and adjusts the priority of information to match the user's emotions. The output is a list of prioritized information provided to the user.

[0373] Step 6:

[0374] The user requests information through the device. The input is a prompt from the user (for example, "Please recommend some relaxing content."). The device receives optimized information from the server, adjusts the display format to match the user's mood, and displays it on the screen. The output is information displayed in a format suitable for the user experience.

[0375] (Application Example 2)

[0376] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0377] Traditional information delivery systems present information without considering the user's emotional state, sometimes providing information that is unpleasant or stressful for the user. Therefore, there is a need to achieve a better user experience through flexible information delivery that takes user emotions into consideration. Furthermore, in the advertising field, displaying content that resonates with the recipient's emotions is a crucial issue in enhancing the sales promotion effectiveness for clients.

[0378] 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.

[0379] In this invention, the server includes emotion analysis means for analyzing the user's emotional state, display optimization means for optimizing the selection and display of information based on the analyzed emotional state, and information acquisition means for periodically collecting data from information sources on the Internet. This enables personalized information provision and advertisement display according to the user's emotional state.

[0380] "User emotional state" refers to the user's current psychological state, as determined from their facial expressions, tone of voice, and other factors.

[0381] "Emotional analysis tools" refer to a part of a system that has the function of recognizing and analyzing a user's emotional state.

[0382] "Display optimization means" refers to a part of a system that has the function of adjusting the content and format of the information displayed based on the analyzed emotional state.

[0383] "Information acquisition means" refers to a part of a system that has the function of periodically collecting data from information sources on the internet.

[0384] A "machine learning model" is an algorithm or method used to evaluate reliability based on data.

[0385] A "scoring method" is a part of a system that uses a machine learning model on collected data to quantify its reliability.

[0386] A "filtering mechanism" is a part of a system that has the function of excluding data whose score falls below a set threshold.

[0387] An "information provision means" is a part of a system that has the function of storing data that exceeds a threshold and providing it in the most optimal format when requested by the user.

[0388] This invention primarily involves a server, a terminal, and a user. The server has an information acquisition function for periodically collecting data from various sources on the internet. The collected data is then scored for reliability using a machine learning model, and only reliable information is filtered and stored. Machine learning frameworks such as TensorFlow and PyTorch can be used for scoring.

[0389] Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's emotional state during data processing. This emotion analysis is performed by acquiring the user's facial expressions and voice in real time using the smartphone's camera and microphone. The emotion analysis engine then analyzes this data to identify the user's emotional state. Technologies such as the Emotion API and IBM Watson Tone Analyzer can be used for this process.

[0390] The device displays information provided by the server in a format optimized according to the user's emotional state. This includes selecting information and adjusting the display format based on the emotional state, aiming to improve the user experience.

[0391] For example, if facial recognition technology detects a tired expression on a user's face while they are using their smartphone during their commute, the server can send advertisements for relaxing products to the device and display them effectively. This process results in personalized information delivery that reduces stress for the user.

[0392] The following prompt statements can be used in the generative AI model:

[0393] "When a user's current emotional state is 'fatigue' or 'stress,' generate information that provides a sense of reassurance. For example, suggest a short video with a relaxing effect."

[0394] In this way, it becomes possible to provide information and display advertisements based on the user's emotions, supporting better user decision-making.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] The server periodically collects data from internet sources. It uses a list of URLs as input. The data is collected using web scraping techniques and stored in a temporary database. The output is the raw, collected data.

[0398] Step 2:

[0399] The server uses a machine learning model to score the reliability of the collected data. The input consists of data in a temporary database and its metadata. TensorFlow and PyTorch are used to process the data, calculate the reliability score, and obtain the scoring result. The output is a new dataset containing the reliability scores for the data.

[0400] Step 3:

[0401] The server determines a threshold and filters out data whose score falls below the threshold. The input is the confidence score data generated in step 2. Filtering is performed to select and retain the most reliable data. The output is the reliable filtered data.

[0402] Step 4:

[0403] The device uses the smartphone's camera and microphone to acquire data in order to analyze the user's emotional state in real time. Inputs include the user's facial expressions and voice. An emotion analysis engine performs facial recognition and voice analysis to infer the user's emotional state. The output is data indicating the user's emotional state.

[0404] Step 5:

[0405] The server receives user emotional state data and optimizes information delivery based on it. Input includes filtered data and user emotional state data. Using a generative AI model, it generates or selects information that matches the user's emotions based on prompt messages. The output is an emotionally optimized set of information.

[0406] Step 6:

[0407] The terminal displays optimized information sent from the server to the user. The input includes an emotionally optimized set of information. The tone and format of the information are adjusted to match the user's emotions and displayed visually. The user experiences information consumption in a relaxed state. The output is intuitive and emotionally sensitive information displayed to the user.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] [Third Embodiment]

[0412] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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".

[0424] This invention is a system for collecting diverse information available on the internet, evaluating its reliability, and providing that information. The central function of this system is to automate data collection and reliability evaluation, thereby enabling users to efficiently obtain the highly reliable information they need.

[0425] First, the server periodically collects data from news sites, social media platforms, and other sources on the internet. This can be done by accessing these sources via APIs or by using web scraping techniques. Next, the collected information is stored in a temporary database on the server.

[0426] The server uses a machine learning model to assign a reliability score to the collected data. This score considers the historical reliability of the information source and the integrity of the content itself. This process is automated, and the server evaluates the information in real time.

[0427] After scoring is complete, the server filters out information with a reliability score below a threshold and removes it from the database. This ensures that only highly reliable information is retained when users access it.

[0428] Users can use their devices to request, for example, "the latest technology news." This request is sent from the device to the server, which searches a highly reliable information database for relevant information. The results are then sent back to the device and presented to the user in a visualized format.

[0429] As a concrete example, users who want accurate damage information in the event of a disaster can receive the latest and most reliable information by sending a request from their device. This information is free from misinformation and rumors, and users can use it as a basis for making safe decisions.

[0430] In this way, this system automatically filters large amounts of information, enabling it to quickly provide highly reliable information that users can use with confidence.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] The server accesses internet sources at specified time intervals and collects data through news APIs and social media APIs. The collected data includes article titles, content, and source metadata.

[0434] Step 2:

[0435] The server stores the collected data in a temporary database. This is in preparation for a subsequent reliability assessment to be performed quickly.

[0436] Step 3:

[0437] The server uses a machine learning model on the stored data to calculate a data reliability score. Factors such as the data source and the past evaluation history of its content are taken into consideration.

[0438] Step 4:

[0439] The server identifies data whose scores fall below a threshold and removes it from the temporary database. This process filters the data so that only highly reliable data remains.

[0440] Step 5:

[0441] The user sends a request to search for specific information through their device. The request is forwarded to the server by the device.

[0442] Step 6:

[0443] The server searches for relevant information from a highly reliable information database based on the request content and sends the results to the terminal.

[0444] Step 7:

[0445] The device visually displays the received information to the user. The information is formatted and presented in a way that is easily understandable to the user.

[0446] Step 8:

[0447] Users can review the information presented through their device and perform additional searches as needed.

[0448] (Example 1)

[0449] 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."

[0450] The internet contains a vast amount of information, some of which is unreliable. It is difficult for users to efficiently obtain accurate and reliable information, and sometimes they may make poor decisions based on incorrect information. To solve this problem, a means is needed to collect data from multiple sources, quickly and efficiently evaluate its reliability, and provide it to users.

[0451] 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.

[0452] In this invention, the server includes an information acquisition means for periodically collecting information from an information set, an evaluation means for evaluating the reliability of the collected information using a predictive model, and an exclusion means for excluding information whose evaluation score falls below a certain threshold. This makes it possible to quickly provide only highly reliable information to the user.

[0453] An "information aggregate" refers to multiple sources of information on the internet, including news sites and social media platforms.

[0454] "Information acquisition means" refers to mechanisms and methods for periodically collecting information from an information collection, and may include using API access or web scraping techniques.

[0455] A "predictive model" refers to an algorithm or method used to evaluate the reliability of information collected using machine learning techniques.

[0456] "Evaluation methods" refer to processes and devices that use predictive models to quantify and score the reliability of information.

[0457] An "evaluation score" is a numerical value calculated to indicate the reliability of information, and the validity of the information is judged based on this score.

[0458] A "benchmark value" is the minimum numerical value that an evaluation score should achieve; information below this value is considered unreliable.

[0459] "Exclusionary measures" refer to processes and technologies used to remove information from a database whose evaluation score falls below a certain threshold.

[0460] "Information delivery means" refers to methods and devices for providing reliable information in response to user requests.

[0461] "Means of making information visible" refers to methods and systems for presenting information to users in an easily viewable format.

[0462] This invention is a system for users to efficiently acquire highly reliable information. The system is primarily built on a server, and the processes of information collection, evaluation, and provision work in coordination.

[0463] First, the server maintains a list of multiple information sources on the internet as an information collection. This includes news sites and social media platforms. Based on this list, the server periodically collects information through API access or web scraping techniques using BeautifulSoup or Scrapy.

[0464] The collected information is stored in a temporary database on the server, and then the reliability of each piece of information is evaluated using a predictive model. The server utilizes machine learning libraries such as TensorFlow and PyTorch to calculate an evaluation score, taking into account the historical data and consistency of the information source.

[0465] Based on the evaluation results, information with a reliability score below a certain threshold is removed from the database by the server. This removal mechanism prevents information overload and improves the accuracy of the information supplied to users.

[0466] Users can use their terminal to request specific information from the server. For example, they might enter a prompt such as "Tell me about the latest technological advancements." Based on the request sent from the terminal, the server quickly searches for relevant and reliable information and sends the results to the terminal. The terminal then presents this information in a visual format, making it easy for the user to understand. This process might utilize a user interface built with React, for example.

[0467] As a concrete example, in the event of a natural disaster, a user who wants to quickly obtain information about safe areas can enter a prompt message on their device such as "Tell me where to evacuate safely during a disaster," and instantly receive the latest and most reliable information from the server. In this way, users can make safe decisions based on accurate information.

[0468] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0469] Step 1:

[0470] The server begins collecting information from a data set. It receives a list of URLs from news sites and social media platforms as input. The server collects data in HTML and JSON format by sending requests via APIs or by using web scraping techniques. Software such as Scrapy or BeautifulSoup is used for this purpose. The output is the collected raw data.

[0471] Step 2:

[0472] The server organizes the collected raw data. The input is the raw data obtained in step 1. The server performs data cleaning, such as removing unnecessary information and HTML tags and unifying character encoding. As a result of this process, the output is clean data formatted into a unified format.

[0473] Step 3:

[0474] The server performs a reliability assessment on the clean data. The input is the clean data obtained in step 2. The server applies a machine learning model and calculates a reliability score based on the historical data and consistency of the information from the source. TensorFlow or PyTorch is used for this process. The output is a dataset with a reliability score assigned to each data point.

[0475] Step 4:

[0476] The server eliminates information whose reliability score falls below a threshold. The input is the reliability-evaluated dataset obtained in step 3. Data with scores below the threshold is removed from the database. This elimination mechanism ensures that only information whose reliability has been confirmed remains on the server. The output is filtered, high-reliability data.

[0477] Step 5:

[0478] The user sends an information request from their device. The input is the prompt message entered by the user. For example, a request such as "Tell me the latest AI news" is possible. This prompt message is transmitted to the server via the device. The output is the information request sent to the server.

[0479] Step 6:

[0480] The server searches for relevant information based on the user's request. The input is the information request received in step 5. The server searches the database for reliable information and extracts data that matches the request. The output is a set of information results related to the user's request.

[0481] Step 7:

[0482] The server sends the search results to the terminal and presents them visually to the user. The input is the information result set from step 6. The terminal receives the results and visualizes them in a user-friendly format. Frontend technologies such as React are used for this display. The output is the visual information presented to the user.

[0483] (Application Example 1)

[0484] 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."

[0485] The internet contains a vast amount of diverse information, making it difficult for users to quickly and efficiently find highly reliable information. Furthermore, there is a risk of unreliable information being misused, highlighting the need for safe and reliable information. This invention aims to solve these problems and provide a system that efficiently delivers highly reliable information.

[0486] 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.

[0487] In this invention, the server includes information acquisition means for periodically collecting data from information sources on the Internet, scoring means for performing reliability scoring on the collected data using a machine learning model, and filtering means for filtering data whose scores fall below a threshold. This enables users to efficiently and securely obtain highly reliable information.

[0488] "Information acquisition means" refers to a device or method for periodically collecting data from information sources on the Internet.

[0489] A "scoring means" is a device or method that uses a machine learning model to calculate a reliability score for collected data.

[0490] "Filtering means" refers to a device or method for removing data whose reliability score falls below a threshold.

[0491] "Information provision means" refers to a device or method for storing highly reliable data that exceeds a threshold and providing it to a communication terminal device upon request.

[0492] "Data processing means" refers to a device or method for quickly retrieving highly reliable information in response to user requests and presenting it in a visually displayable format.

[0493] A "communication terminal device" is a device used by users to receive and display information.

[0494] A "visually displayable format" refers to a form in which information can be visually confirmed by the user on a terminal device.

[0495] The system that implements this application is configured as follows: The server periodically collects data from various sources on the internet. This collection process utilizes web scraping techniques using Python and various APIs (e.g., news distribution APIs and social media APIs) to obtain information. The collected data is temporarily stored in a database such as MySQL or PostgreSQL.

[0496] Next, the server uses machine learning libraries such as TensorFlow or PyTorch to score the reliability of the data. This scoring is based on past reliability data and content consistency of the source. If the score falls below the threshold, the data is filtered out. On the other hand, highly reliable data that exceeds the threshold is saved and ready for information provision.

[0497] When a user requests specific information via a communication terminal, this server quickly searches for the necessary information and presents it visually in a user-friendly format. Specifically, dashboard and graphing technologies are used for data visualization. For example, if a user requests "latest technology news," highly reliable information is prioritized and displayed in an intuitive interface.

[0498] For example, if a user requests "the latest information on the host cities of the 2024 Olympic Games," reliable information related to that topic will be displayed immediately. An example of a prompt to the generative AI model in this system is, "Use the following information to gather top news about climate change and evaluate its reliability."

[0499] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0500] Step 1:

[0501] The server collects data from sources on the internet. It is given a list of URLs or API endpoints as input, and raw data is retrieved as output. This data is collected using Python libraries (such as BeautifulSoup and Requests). Specifically, the server parses web pages and extracts relevant text information.

[0502] Step 2:

[0503] The server temporarily stores the collected data in a database. The input is the raw data obtained in step 1, and the output is the organized information in the database. At this stage, MySQL or PostgreSQL is used to store the data in a structured format. Specifically, the server establishes a database connection and stores the information using INSERT queries.

[0504] Step 3:

[0505] The server scores the reliability of the data using a machine learning model. The input is the data saved in step 2, and the output is the data with the reliability score assigned to it. A pre-trained model is executed using libraries such as TensorFlow or PyTorch. Specifically, the server inputs the data into the model and calculates the score.

[0506] Step 4:

[0507] The server filters out and removes data whose scores fall below a threshold. The input is the scored data generated in step 3, and the output is the high-confidence data that exceeds the threshold. The filtering algorithm compares the scores and keeps only the matching data. Specifically, the filtering conditions are applied using SQL queries.

[0508] Step 5:

[0509] A user requests specific information using a communication terminal device. The input is the user's request, and the output is the corresponding request parameters. This request is received by the frontend, for example, through form input. Specifically, the terminal sends the request to the server in HTTP request format.

[0510] Step 6:

[0511] The server searches the database for highly reliable information based on the user's request and generates results. The input is the request parameters received in step 5, and the output is a set of relevant information. An SQL query is created to perform a database search. Specifically, the server extracts data that matches the criteria.

[0512] Step 7:

[0513] The server converts the search results into a user-friendly format and sends the visually displayable data to the device. The input is the search results obtained in step 6, and the output is user-friendly visually displayable data. Data formatting techniques and front-end libraries (e.g., React, Angular) are used to optimize the display. Specifically, the server packages the data in HTML format and returns it to the device.

[0514] Step 8:

[0515] The user uses a communication terminal to visually confirm information from the server and use it for decision-making. The input is the visual display data transmitted in step 7, and the output is the user's understanding and decision-making actions. Specifically, the user views the information in a browser or application and takes the necessary actions.

[0516] 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.

[0517] This invention is an information provision system that takes user emotions into consideration. It periodically collects data from internet-based information sources, evaluates the reliability of that data using a machine learning model, and optimizes information provision by recognizing the user's emotional state.

[0518] The server collects data from news sites and social media platforms and stores that information in a temporary database. The collected information is analyzed by a machine learning model, and a reliability score is calculated. Based on this score, the information is filtered, and only information that exceeds a threshold is retained.

[0519] Furthermore, the server uses an emotion engine to analyze the user's emotional state obtained from the terminal. This includes a process of inferring the user's current emotions through facial recognition technology and voice analysis. The emotion engine treats the user's emotions as parameters and plays a role in adjusting the method and content of information provided.

[0520] When a user requests information from their device, the server selects and provides the most relevant information to the device based on the emotional state recognized by the emotion engine. In this process, the tone and display format of the information may be adjusted to reduce the user's emotional burden.

[0521] For example, if a user makes a request while feeling stressed, the server can organize the information accordingly, and the device can prioritize displaying positive and reassuring information for the user. This allows the user to receive information that is appropriate to their emotional state, supporting better decision-making.

[0522] This system enhances the user experience and delivers more personalized information services by integrating emotion recognition with automated information delivery.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] The server periodically connects to internet information sources and uses news APIs and social media APIs to collect the latest data. The collected data includes article titles, body text, and source, and is temporarily stored in a database.

[0526] Step 2:

[0527] The server applies a machine learning model to the collected data and calculates a reliability score. This model scores based on the source's past reliability data and content evaluation.

[0528] Step 3:

[0529] The server automatically filters out data with a reliability score below a threshold, removes it, and then stores only the highly reliable data in a permanent database.

[0530] Step 4:

[0531] The device activates an emotion engine through its interface with the user to detect the user's emotional state. This is achieved through methods such as facial recognition using a camera and voice analysis using a microphone.

[0532] Step 5:

[0533] The emotion engine analyzes the detected user's emotions and sends that information to the server. The server uses this information to adjust the content and method of information provision.

[0534] Step 6:

[0535] The user requests specific information via their device. The device receives this request and requests the information from the server.

[0536] Step 7:

[0537] The server searches a highly reliable database for information that matches the user's request. Furthermore, it adjusts how the information is displayed (such as tone and content selection) taking into account data obtained from the sentiment engine.

[0538] Step 8:

[0539] The device receives information sent from the server and displays it in the most optimal format according to the user's emotional state. This allows users to comfortably use information that matches their emotional state.

[0540] (Example 2)

[0541] 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."

[0542] It is necessary to evaluate the reliability of information on the internet while providing appropriate information tailored to the user's emotional state. However, conventional systems do not integrate information reliability filtering with information optimization based on the user's emotions, making it difficult for users to obtain information that is best suited to their mental state. Furthermore, there are insufficient means to effectively utilize the influence of the user's emotional state on information provision.

[0543] 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.

[0544] In this invention, the server includes an information gathering means for periodically aggregating information, a scoring means for evaluating reliability using an artificial intelligence model, and a filtering means for removing information whose reliability does not meet specific criteria. This makes it possible to provide highly reliable information. Furthermore, by including an emotion adjustment means for detecting the emotional state from the user's input device and adjusting the information supply means, the server can provide information that is appropriate to the user's emotional state, thereby improving the user experience.

[0545] An "information gathering tool" is a system component that continuously aggregates information from multiple sources on a digital network.

[0546] A "scoring method" is a system component that utilizes artificial intelligence models to quantitatively evaluate the reliability of aggregated information and express it as a numerical value.

[0547] A "filtering mechanism" is a system component that selects and removes information whose reliability falls below a certain standard from the information evaluated by the scoring mechanism.

[0548] An "information supply means" is a system component that stores highly reliable information that has passed through a filtering means and provides it to users upon request.

[0549] An "emotion adjustment tool" is a system component that optimizes the information provided by an information supply tool based on emotional state data acquired from users.

[0550] This invention is an information management system for providing information based on the user's emotional state.

[0551] The server automatically aggregates information from various sources on the digital network using information gathering means. Specific information crawling software is used at this stage; for example, tools such as Scrapy can be used.

[0552] Next, the server evaluates the aggregated information using a scoring mechanism. This process utilizes an artificial intelligence model, and either TensorFlow or PyTorch can be used as the model. This model is used to calculate a reliability score, quantifying the reliability of the information.

[0553] Based on the scoring results, the server uses filtering mechanisms to remove information that does not meet the reliability criteria. Only highly reliable information that exceeds the threshold is stored. This filtering ensures the quality of information provided to users.

[0554] Furthermore, the device uses emotion adjustment mechanisms to analyze the user's facial expressions and voice from input devices such as cameras and microphones, and estimate their emotional state. For example, it can use facial recognition technology with OpenCV or identify emotions from voice using the Google Cloud Speech-to-Text API. As a result, the server receives the user's emotional data and adjusts the information supply mechanism accordingly.

[0555] When a user requests information, the server provides highly reliable information optimized for that emotion, and the terminal displays it to the user. The information is displayed in a visually adjusted format to match the user's emotional state, allowing the user to intuitively receive information that is relevant to their feelings.

[0556] For example, if a user makes a request using the prompt "Please recommend some relaxing content," the server can select reliable news and relaxing music and display them on the device. In this way, the system can improve the user experience and make the way information is received more personalized.

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1:

[0559] The server aggregates information from digital networks using information gathering tools. It uses a list of URLs from news sites and social media platforms as input. Its operation involves accessing each information source using crawling software (e.g., Scrapy), extracting data in a specified format, and storing it in a temporary database. The output is a set of collected raw data.

[0560] Step 2:

[0561] The server evaluates the reliability of the information using a scoring mechanism. The information aggregated in step 1 is used as input. The server analyzes the content of each piece of information using an artificial intelligence model (e.g., TensorFlow) and generates a score based on the frequency of occurrence and reliability patterns. The output is the reliability score assigned to each piece of information.

[0562] Step 3:

[0563] The server uses filtering mechanisms to remove unreliable information. The input is the information that was scored in step 2. The server is programmed to set a threshold and remove information with scores below that threshold from the database. The output consists of the set of information deemed highly reliable.

[0564] Step 4:

[0565] The device acquires the user's emotional state using emotion adjustment mechanisms. Inputs include user facial expression data and voice data acquired using a camera and microphone. The device analyzes the emotional state by applying facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., Google Cloud Speech-to-Text API). The output is the analyzed emotional data.

[0566] Step 5:

[0567] The server optimizes information delivery based on emotional data. The inputs are the emotional states collected in step 4 and the information filtered in step 3. The server processes the data collected by the emotion engine and adjusts the priority of information to match the user's emotions. The output is a list of prioritized information provided to the user.

[0568] Step 6:

[0569] The user requests information through the device. The input is a prompt from the user (for example, "Please recommend some relaxing content."). The device receives optimized information from the server, adjusts the display format to match the user's mood, and displays it on the screen. The output is information displayed in a format suitable for the user experience.

[0570] (Application Example 2)

[0571] 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."

[0572] Traditional information delivery systems present information without considering the user's emotional state, sometimes providing information that is unpleasant or stressful for the user. Therefore, there is a need to achieve a better user experience through flexible information delivery that takes user emotions into consideration. Furthermore, in the advertising field, displaying content that resonates with the recipient's emotions is a crucial issue in enhancing the sales promotion effectiveness for clients.

[0573] 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.

[0574] In this invention, the server includes emotion analysis means for analyzing the user's emotional state, display optimization means for optimizing the selection and display of information based on the analyzed emotional state, and information acquisition means for periodically collecting data from information sources on the Internet. This enables personalized information provision and advertisement display according to the user's emotional state.

[0575] "User emotional state" refers to the user's current psychological state, as determined from their facial expressions, tone of voice, and other factors.

[0576] "Emotional analysis tools" refer to a part of a system that has the function of recognizing and analyzing a user's emotional state.

[0577] "Display optimization means" refers to a part of a system that has the function of adjusting the content and format of the information displayed based on the analyzed emotional state.

[0578] "Information acquisition means" refers to a part of a system that has the function of periodically collecting data from information sources on the internet.

[0579] A "machine learning model" is an algorithm or method used to evaluate reliability based on data.

[0580] A "scoring method" is a part of a system that uses a machine learning model on collected data to quantify its reliability.

[0581] A "filtering mechanism" is a part of a system that has the function of excluding data whose score falls below a set threshold.

[0582] An "information provision means" is a part of a system that has the function of storing data that exceeds a threshold and providing it in the most optimal format when requested by the user.

[0583] This invention primarily involves a server, a terminal, and a user. The server has an information acquisition function for periodically collecting data from various sources on the internet. The collected data is then scored for reliability using a machine learning model, and only reliable information is filtered and stored. Machine learning frameworks such as TensorFlow and PyTorch can be used for scoring.

[0584] Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's emotional state during data processing. This emotion analysis is performed by acquiring the user's facial expressions and voice in real time using the smartphone's camera and microphone. The emotion analysis engine then analyzes this data to identify the user's emotional state. Technologies such as the Emotion API and IBM Watson Tone Analyzer can be used for this process.

[0585] The device displays information provided by the server in a format optimized according to the user's emotional state. This includes selecting information and adjusting the display format based on the emotional state, aiming to improve the user experience.

[0586] For example, if facial recognition technology detects a tired expression on a user's face while they are using their smartphone during their commute, the server can send advertisements for relaxing products to the device and display them effectively. This process results in personalized information delivery that reduces stress for the user.

[0587] The following prompt statements can be used in the generative AI model:

[0588] "When a user's current emotional state is 'fatigue' or 'stress,' generate information that provides a sense of reassurance. For example, suggest a short video with a relaxing effect."

[0589] In this way, it becomes possible to provide information and display advertisements based on the user's emotions, supporting better user decision-making.

[0590] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0591] Step 1:

[0592] The server periodically collects data from internet sources. It uses a list of URLs as input. The data is collected using web scraping techniques and stored in a temporary database. The output is the raw, collected data.

[0593] Step 2:

[0594] The server uses a machine learning model to score the reliability of the collected data. The input consists of data in a temporary database and its metadata. TensorFlow and PyTorch are used to process the data, calculate the reliability score, and obtain the scoring result. The output is a new dataset containing the reliability scores for the data.

[0595] Step 3:

[0596] The server determines a threshold and filters out data whose score falls below the threshold. The input is the confidence score data generated in step 2. Filtering is performed to select and retain the most reliable data. The output is the reliable filtered data.

[0597] Step 4:

[0598] The device uses the smartphone's camera and microphone to acquire data in order to analyze the user's emotional state in real time. Inputs include the user's facial expressions and voice. An emotion analysis engine performs facial recognition and voice analysis to infer the user's emotional state. The output is data indicating the user's emotional state.

[0599] Step 5:

[0600] The server receives user emotional state data and optimizes information delivery based on it. Input includes filtered data and user emotional state data. Using a generative AI model, it generates or selects information that matches the user's emotions based on prompt messages. The output is an emotionally optimized set of information.

[0601] Step 6:

[0602] The terminal displays optimized information sent from the server to the user. The input includes an emotionally optimized set of information. The tone and format of the information are adjusted to match the user's emotions and displayed visually. The user experiences information consumption in a relaxed state. The output is intuitive and emotionally sensitive information displayed to the user.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] [Fourth Embodiment]

[0607] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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).

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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".

[0620] This invention is a system for collecting diverse information available on the internet, evaluating its reliability, and providing that information. The central function of this system is to automate data collection and reliability evaluation, thereby enabling users to efficiently obtain the highly reliable information they need.

[0621] First, the server periodically collects data from news sites, social media platforms, and other sources on the internet. This can be done by accessing these sources via APIs or by using web scraping techniques. Next, the collected information is stored in a temporary database on the server.

[0622] The server uses a machine learning model to assign a reliability score to the collected data. This score considers the historical reliability of the information source and the integrity of the content itself. This process is automated, and the server evaluates the information in real time.

[0623] After scoring is complete, the server filters out information with a reliability score below a threshold and removes it from the database. This ensures that only highly reliable information is retained when users access it.

[0624] Users can use their devices to request, for example, "the latest technology news." This request is sent from the device to the server, which searches a highly reliable information database for relevant information. The results are then sent back to the device and presented to the user in a visualized format.

[0625] As a concrete example, users who want accurate damage information in the event of a disaster can receive the latest and most reliable information by sending a request from their device. This information is free from misinformation and rumors, and users can use it as a basis for making safe decisions.

[0626] In this way, this system automatically filters large amounts of information, enabling it to quickly provide highly reliable information that users can use with confidence.

[0627] The following describes the processing flow.

[0628] Step 1:

[0629] The server accesses internet sources at specified time intervals and collects data through news APIs and social media APIs. The collected data includes article titles, content, and source metadata.

[0630] Step 2:

[0631] The server stores the collected data in a temporary database. This is in preparation for a subsequent reliability assessment to be performed quickly.

[0632] Step 3:

[0633] The server uses a machine learning model on the stored data to calculate a data reliability score. Factors such as the data source and the past evaluation history of its content are taken into consideration.

[0634] Step 4:

[0635] The server identifies data whose scores fall below a threshold and removes it from the temporary database. This process filters the data so that only highly reliable data remains.

[0636] Step 5:

[0637] The user sends a request to search for specific information through their device. The request is forwarded to the server by the device.

[0638] Step 6:

[0639] The server searches for relevant information from a highly reliable information database based on the request content and sends the results to the terminal.

[0640] Step 7:

[0641] The device visually displays the received information to the user. The information is formatted and presented in a way that is easily understandable to the user.

[0642] Step 8:

[0643] Users can review the information presented through their device and perform additional searches as needed.

[0644] (Example 1)

[0645] 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".

[0646] The internet contains a vast amount of information, some of which is unreliable. It is difficult for users to efficiently obtain accurate and reliable information, and sometimes they may make poor decisions based on incorrect information. To solve this problem, a means is needed to collect data from multiple sources, quickly and efficiently evaluate its reliability, and provide it to users.

[0647] 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.

[0648] In this invention, the server includes an information acquisition means for periodically collecting information from an information set, an evaluation means for evaluating the reliability of the collected information using a predictive model, and an exclusion means for excluding information whose evaluation score falls below a certain threshold. This makes it possible to quickly provide only highly reliable information to the user.

[0649] An "information aggregate" refers to multiple sources of information on the internet, including news sites and social media platforms.

[0650] "Information acquisition means" refers to mechanisms and methods for periodically collecting information from an information collection, and may include using API access or web scraping techniques.

[0651] A "predictive model" refers to an algorithm or method used to evaluate the reliability of information collected using machine learning techniques.

[0652] "Evaluation methods" refer to processes and devices that use predictive models to quantify and score the reliability of information.

[0653] An "evaluation score" is a numerical value calculated to indicate the reliability of information, and the validity of the information is judged based on this score.

[0654] A "benchmark value" is the minimum numerical value that an evaluation score should achieve; information below this value is considered unreliable.

[0655] "Exclusionary measures" refer to processes and technologies used to remove information from a database whose evaluation score falls below a certain threshold.

[0656] "Information delivery means" refers to methods and devices for providing reliable information in response to user requests.

[0657] "Means of making information visible" refers to methods and systems for presenting information to users in an easily viewable format.

[0658] This invention is a system for users to efficiently acquire highly reliable information. The system is primarily built on a server, and the processes of information collection, evaluation, and provision work in coordination.

[0659] First, the server maintains a list of multiple information sources on the internet as an information collection. This includes news sites and social media platforms. Based on this list, the server periodically collects information through API access or web scraping techniques using BeautifulSoup or Scrapy.

[0660] The collected information is stored in a temporary database on the server, and then the reliability of each piece of information is evaluated using a predictive model. The server utilizes machine learning libraries such as TensorFlow and PyTorch to calculate an evaluation score, taking into account the historical data and consistency of the information source.

[0661] Based on the evaluation results, information with a reliability score below a certain threshold is removed from the database by the server. This removal mechanism prevents information overload and improves the accuracy of the information supplied to users.

[0662] Users can use their terminal to request specific information from the server. For example, they might enter a prompt such as "Tell me about the latest technological advancements." Based on the request sent from the terminal, the server quickly searches for relevant and reliable information and sends the results to the terminal. The terminal then presents this information in a visual format, making it easy for the user to understand. This process might utilize a user interface built with React, for example.

[0663] As a concrete example, in the event of a natural disaster, a user who wants to quickly obtain information about safe areas can enter a prompt message on their device such as "Tell me where to evacuate safely during a disaster," and instantly receive the latest and most reliable information from the server. In this way, users can make safe decisions based on accurate information.

[0664] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0665] Step 1:

[0666] The server begins collecting information from a data set. It receives a list of URLs from news sites and social media platforms as input. The server collects data in HTML and JSON format by sending requests via APIs or by using web scraping techniques. Software such as Scrapy or BeautifulSoup is used for this purpose. The output is the collected raw data.

[0667] Step 2:

[0668] The server organizes the collected raw data. The input is the raw data obtained in step 1. The server performs data cleaning, such as removing unnecessary information and HTML tags and unifying character encoding. As a result of this process, the output is clean data formatted into a unified format.

[0669] Step 3:

[0670] The server performs a reliability assessment on the clean data. The input is the clean data obtained in step 2. The server applies a machine learning model and calculates a reliability score based on the historical data and consistency of the information from the source. TensorFlow or PyTorch is used for this process. The output is a dataset with a reliability score assigned to each data point.

[0671] Step 4:

[0672] The server eliminates information whose reliability score falls below a threshold. The input is the reliability-evaluated dataset obtained in step 3. Data with scores below the threshold is removed from the database. This elimination mechanism ensures that only information whose reliability has been confirmed remains on the server. The output is filtered, high-reliability data.

[0673] Step 5:

[0674] The user sends an information request from their device. The input is the prompt message entered by the user. For example, a request such as "Tell me the latest AI news" is possible. This prompt message is transmitted to the server via the device. The output is the information request sent to the server.

[0675] Step 6:

[0676] The server searches for relevant information based on the user's request. The input is the information request received in step 5. The server searches the database for reliable information and extracts data that matches the request. The output is a set of information results related to the user's request.

[0677] Step 7:

[0678] The server sends the search results to the terminal and presents them visually to the user. The input is the information result set from step 6. The terminal receives the results and visualizes them in a user-friendly format. Frontend technologies such as React are used for this display. The output is the visual information presented to the user.

[0679] (Application Example 1)

[0680] 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".

[0681] The internet contains a vast amount of diverse information, making it difficult for users to quickly and efficiently find highly reliable information. Furthermore, there is a risk of unreliable information being misused, highlighting the need for safe and reliable information. This invention aims to solve these problems and provide a system that efficiently delivers highly reliable information.

[0682] 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.

[0683] In this invention, the server includes information acquisition means for periodically collecting data from information sources on the Internet, scoring means for performing reliability scoring on the collected data using a machine learning model, and filtering means for filtering data whose scores fall below a threshold. This enables users to efficiently and securely obtain highly reliable information.

[0684] "Information acquisition means" refers to a device or method for periodically collecting data from information sources on the Internet.

[0685] A "scoring means" is a device or method that uses a machine learning model to calculate a reliability score for collected data.

[0686] "Filtering means" refers to a device or method for removing data whose reliability score falls below a threshold.

[0687] "Information provision means" refers to a device or method for storing highly reliable data that exceeds a threshold and providing it to a communication terminal device upon request.

[0688] "Data processing means" refers to a device or method for quickly retrieving highly reliable information in response to user requests and presenting it in a visually displayable format.

[0689] A "communication terminal device" is a device used by users to receive and display information.

[0690] A "visually displayable format" refers to a form in which information can be visually confirmed by the user on a terminal device.

[0691] The system that implements this application is configured as follows: The server periodically collects data from various sources on the internet. This collection process utilizes web scraping techniques using Python and various APIs (e.g., news distribution APIs and social media APIs) to obtain information. The collected data is temporarily stored in a database such as MySQL or PostgreSQL.

[0692] Next, the server uses machine learning libraries such as TensorFlow or PyTorch to score the reliability of the data. This scoring is based on past reliability data and content consistency of the source. If the score falls below the threshold, the data is filtered out. On the other hand, highly reliable data that exceeds the threshold is saved and ready for information provision.

[0693] When a user requests specific information via a communication terminal, this server quickly searches for the necessary information and presents it visually in a user-friendly format. Specifically, dashboard and graphing technologies are used for data visualization. For example, if a user requests "latest technology news," highly reliable information is prioritized and displayed in an intuitive interface.

[0694] For example, if a user requests "the latest information on the host cities of the 2024 Olympic Games," reliable information related to that topic will be displayed immediately. An example of a prompt to the generative AI model in this system is, "Use the following information to gather top news about climate change and evaluate its reliability."

[0695] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0696] Step 1:

[0697] The server collects data from sources on the internet. It is given a list of URLs or API endpoints as input, and raw data is retrieved as output. This data is collected using Python libraries (such as BeautifulSoup and Requests). Specifically, the server parses web pages and extracts relevant text information.

[0698] Step 2:

[0699] The server temporarily stores the collected data in a database. The input is the raw data obtained in step 1, and the output is the organized information in the database. At this stage, MySQL or PostgreSQL is used to store the data in a structured format. Specifically, the server establishes a database connection and stores the information using INSERT queries.

[0700] Step 3:

[0701] The server scores the reliability of the data using a machine learning model. The input is the data saved in step 2, and the output is the data with the reliability score assigned to it. A pre-trained model is executed using libraries such as TensorFlow or PyTorch. Specifically, the server inputs the data into the model and calculates the score.

[0702] Step 4:

[0703] The server filters out and removes data whose scores fall below a threshold. The input is the scored data generated in step 3, and the output is the high-confidence data that exceeds the threshold. The filtering algorithm compares the scores and keeps only the matching data. Specifically, the filtering conditions are applied using SQL queries.

[0704] Step 5:

[0705] A user requests specific information using a communication terminal device. The input is the user's request, and the output is the corresponding request parameters. This request is received by the frontend, for example, through form input. Specifically, the terminal sends the request to the server in HTTP request format.

[0706] Step 6:

[0707] The server searches the database for highly reliable information based on the user's request and generates results. The input is the request parameters received in step 5, and the output is a set of relevant information. An SQL query is created to perform a database search. Specifically, the server extracts data that matches the criteria.

[0708] Step 7:

[0709] The server converts the search results into a user-friendly format and sends the visually displayable data to the device. The input is the search results obtained in step 6, and the output is user-friendly visually displayable data. Data formatting techniques and front-end libraries (e.g., React, Angular) are used to optimize the display. Specifically, the server packages the data in HTML format and returns it to the device.

[0710] Step 8:

[0711] The user uses a communication terminal to visually confirm information from the server and use it for decision-making. The input is the visual display data transmitted in step 7, and the output is the user's understanding and decision-making actions. Specifically, the user views the information in a browser or application and takes the necessary actions.

[0712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0713] This invention is an information provision system that takes user emotions into consideration. It periodically collects data from internet-based information sources, evaluates the reliability of that data using a machine learning model, and optimizes information provision by recognizing the user's emotional state.

[0714] The server collects data from news sites and social media platforms and stores that information in a temporary database. The collected information is analyzed by a machine learning model, and a reliability score is calculated. Based on this score, the information is filtered, and only information that exceeds a threshold is retained.

[0715] Furthermore, the server uses an emotion engine to analyze the user's emotional state obtained from the terminal. This includes a process of inferring the user's current emotions through facial recognition technology and voice analysis. The emotion engine treats the user's emotions as parameters and plays a role in adjusting the method and content of information provided.

[0716] When a user requests information from their device, the server selects and provides the most relevant information to the device based on the emotional state recognized by the emotion engine. In this process, the tone and display format of the information may be adjusted to reduce the user's emotional burden.

[0717] For example, if a user makes a request while feeling stressed, the server can organize the information accordingly, and the device can prioritize displaying positive and reassuring information for the user. This allows the user to receive information that is appropriate to their emotional state, supporting better decision-making.

[0718] This system enhances the user experience and delivers more personalized information services by integrating emotion recognition with automated information delivery.

[0719] The following describes the processing flow.

[0720] Step 1:

[0721] The server periodically connects to internet information sources and uses news APIs and social media APIs to collect the latest data. The collected data includes article titles, body text, and source, and is temporarily stored in a database.

[0722] Step 2:

[0723] The server applies a machine learning model to the collected data and calculates a reliability score. This model scores based on the source's past reliability data and content evaluation.

[0724] Step 3:

[0725] The server automatically filters out data with a reliability score below a threshold, removes it, and then stores only the highly reliable data in a permanent database.

[0726] Step 4:

[0727] The device activates an emotion engine through its interface with the user to detect the user's emotional state. This is achieved through methods such as facial recognition using a camera and voice analysis using a microphone.

[0728] Step 5:

[0729] The emotion engine analyzes the detected user's emotions and sends that information to the server. The server uses this information to adjust the content and method of information provision.

[0730] Step 6:

[0731] The user requests specific information via their device. The device receives this request and requests the information from the server.

[0732] Step 7:

[0733] The server searches a highly reliable database for information that matches the user's request. Furthermore, it adjusts how the information is displayed (such as tone and content selection) taking into account data obtained from the sentiment engine.

[0734] Step 8:

[0735] The device receives information sent from the server and displays it in the most optimal format according to the user's emotional state. This allows users to comfortably use information that matches their emotional state.

[0736] (Example 2)

[0737] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0738] It is necessary to evaluate the reliability of information on the internet while providing appropriate information tailored to the user's emotional state. However, conventional systems do not integrate information reliability filtering with information optimization based on the user's emotions, making it difficult for users to obtain information that is best suited to their mental state. Furthermore, there are insufficient means to effectively utilize the influence of the user's emotional state on information provision.

[0739] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0740] In this invention, the server includes an information gathering means for periodically aggregating information, a scoring means for evaluating reliability using an artificial intelligence model, and a filtering means for removing information whose reliability does not meet specific criteria. This makes it possible to provide highly reliable information. Furthermore, by including an emotion adjustment means for detecting the emotional state from the user's input device and adjusting the information supply means, the server can provide information that is appropriate to the user's emotional state, thereby improving the user experience.

[0741] An "information gathering tool" is a system component that continuously aggregates information from multiple sources on a digital network.

[0742] A "scoring method" is a system component that utilizes artificial intelligence models to quantitatively evaluate the reliability of aggregated information and express it as a numerical value.

[0743] A "filtering mechanism" is a system component that selects and removes information whose reliability falls below a certain standard from the information evaluated by the scoring mechanism.

[0744] An "information supply means" is a system component that stores highly reliable information that has passed through a filtering means and provides it to users upon request.

[0745] An "emotion adjustment tool" is a system component that optimizes the information provided by an information supply tool based on emotional state data acquired from users.

[0746] This invention is an information management system for providing information based on the user's emotional state.

[0747] The server automatically aggregates information from various sources on the digital network using information gathering means. Specific information crawling software is used at this stage; for example, tools such as Scrapy can be used.

[0748] Next, the server evaluates the aggregated information using a scoring mechanism. This process utilizes an artificial intelligence model, and either TensorFlow or PyTorch can be used as the model. This model is used to calculate a reliability score, quantifying the reliability of the information.

[0749] Based on the scoring results, the server uses filtering mechanisms to remove information that does not meet the reliability criteria. Only highly reliable information that exceeds the threshold is stored. This filtering ensures the quality of information provided to users.

[0750] Furthermore, the device uses emotion adjustment mechanisms to analyze the user's facial expressions and voice from input devices such as cameras and microphones, and estimate their emotional state. For example, it can use facial recognition technology with OpenCV or identify emotions from voice using the Google Cloud Speech-to-Text API. As a result, the server receives the user's emotional data and adjusts the information supply mechanism accordingly.

[0751] When a user requests information, the server provides highly reliable information optimized for that emotion, and the terminal displays it to the user. The information is displayed in a visually adjusted format to match the user's emotional state, allowing the user to intuitively receive information that is relevant to their feelings.

[0752] For example, if a user makes a request using the prompt "Please recommend some relaxing content," the server can select reliable news and relaxing music and display them on the device. In this way, the system can improve the user experience and make the way information is received more personalized.

[0753] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0754] Step 1:

[0755] The server aggregates information from digital networks using information gathering tools. It uses a list of URLs from news sites and social media platforms as input. Its operation involves accessing each information source using crawling software (e.g., Scrapy), extracting data in a specified format, and storing it in a temporary database. The output is a set of collected raw data.

[0756] Step 2:

[0757] The server evaluates the reliability of the information using a scoring mechanism. The information aggregated in step 1 is used as input. The server analyzes the content of each piece of information using an artificial intelligence model (e.g., TensorFlow) and generates a score based on the frequency of occurrence and reliability patterns. The output is the reliability score assigned to each piece of information.

[0758] Step 3:

[0759] The server uses filtering mechanisms to remove unreliable information. The input is the information that was scored in step 2. The server is programmed to set a threshold and remove information with scores below that threshold from the database. The output consists of the set of information deemed highly reliable.

[0760] Step 4:

[0761] The device acquires the user's emotional state using emotion adjustment mechanisms. Inputs include user facial expression data and voice data acquired using a camera and microphone. The device analyzes the emotional state by applying facial recognition technology (e.g., OpenCV) and voice analysis technology (e.g., Google Cloud Speech-to-Text API). The output is the analyzed emotional data.

[0762] Step 5:

[0763] The server optimizes information delivery based on emotional data. The inputs are the emotional states collected in step 4 and the information filtered in step 3. The server processes the data collected by the emotion engine and adjusts the priority of information to match the user's emotions. The output is a list of prioritized information provided to the user.

[0764] Step 6:

[0765] The user requests information through the device. The input is a prompt from the user (for example, "Please recommend some relaxing content."). The device receives optimized information from the server, adjusts the display format to match the user's mood, and displays it on the screen. The output is information displayed in a format suitable for the user experience.

[0766] (Application Example 2)

[0767] 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".

[0768] Traditional information delivery systems present information without considering the user's emotional state, sometimes providing information that is unpleasant or stressful for the user. Therefore, there is a need to achieve a better user experience through flexible information delivery that takes user emotions into consideration. Furthermore, in the advertising field, displaying content that resonates with the recipient's emotions is a crucial issue in enhancing the sales promotion effectiveness for clients.

[0769] 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.

[0770] In this invention, the server includes emotion analysis means for analyzing the user's emotional state, display optimization means for optimizing the selection and display of information based on the analyzed emotional state, and information acquisition means for periodically collecting data from information sources on the Internet. This enables personalized information provision and advertisement display according to the user's emotional state.

[0771] "User emotional state" refers to the user's current psychological state, as determined from their facial expressions, tone of voice, and other factors.

[0772] "Emotional analysis tools" refer to a part of a system that has the function of recognizing and analyzing a user's emotional state.

[0773] "Display optimization means" refers to a part of a system that has the function of adjusting the content and format of the information displayed based on the analyzed emotional state.

[0774] "Information acquisition means" refers to a part of a system that has the function of periodically collecting data from information sources on the internet.

[0775] A "machine learning model" is an algorithm or method used to evaluate reliability based on data.

[0776] A "scoring method" is a part of a system that uses a machine learning model on collected data to quantify its reliability.

[0777] A "filtering mechanism" is a part of a system that has the function of excluding data whose score falls below a set threshold.

[0778] An "information provision means" is a part of a system that has the function of storing data that exceeds a threshold and providing it in the most optimal format when requested by the user.

[0779] This invention primarily involves a server, a terminal, and a user. The server has an information acquisition function for periodically collecting data from various sources on the internet. The collected data is then scored for reliability using a machine learning model, and only reliable information is filtered and stored. Machine learning frameworks such as TensorFlow and PyTorch can be used for scoring.

[0780] Furthermore, the server is equipped with an emotion analysis engine that analyzes the user's emotional state during data processing. This emotion analysis is performed by acquiring the user's facial expressions and voice in real time using the smartphone's camera and microphone. The emotion analysis engine then analyzes this data to identify the user's emotional state. Technologies such as the Emotion API and IBM Watson Tone Analyzer can be used for this process.

[0781] The device displays information provided by the server in a format optimized according to the user's emotional state. This includes selecting information and adjusting the display format based on the emotional state, aiming to improve the user experience.

[0782] For example, if facial recognition technology detects a tired expression on a user's face while they are using their smartphone during their commute, the server can send advertisements for relaxing products to the device and display them effectively. This process results in personalized information delivery that reduces stress for the user.

[0783] The following prompt statements can be used in the generative AI model:

[0784] "When a user's current emotional state is 'fatigue' or 'stress,' generate information that provides a sense of reassurance. For example, suggest a short video with a relaxing effect."

[0785] In this way, it becomes possible to provide information and display advertisements based on the user's emotions, supporting better user decision-making.

[0786] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0787] Step 1:

[0788] The server periodically collects data from internet sources. It uses a list of URLs as input. The data is collected using web scraping techniques and stored in a temporary database. The output is the raw, collected data.

[0789] Step 2:

[0790] The server uses a machine learning model to score the reliability of the collected data. The input consists of data in a temporary database and its metadata. TensorFlow and PyTorch are used to process the data, calculate the reliability score, and obtain the scoring result. The output is a new dataset containing the reliability scores for the data.

[0791] Step 3:

[0792] The server determines a threshold and filters out data whose score falls below the threshold. The input is the confidence score data generated in step 2. Filtering is performed to select and retain the most reliable data. The output is the reliable filtered data.

[0793] Step 4:

[0794] The device uses the smartphone's camera and microphone to acquire data in order to analyze the user's emotional state in real time. Inputs include the user's facial expressions and voice. An emotion analysis engine performs facial recognition and voice analysis to infer the user's emotional state. The output is data indicating the user's emotional state.

[0795] Step 5:

[0796] The server receives user emotional state data and optimizes information delivery based on it. Input includes filtered data and user emotional state data. Using a generative AI model, it generates or selects information that matches the user's emotions based on prompt messages. The output is an emotionally optimized set of information.

[0797] Step 6:

[0798] The terminal displays optimized information sent from the server to the user. The input includes an emotionally optimized set of information. The tone and format of the information are adjusted to match the user's emotions and displayed visually. The user experiences information consumption in a relaxed state. The output is intuitive and emotionally sensitive information displayed to the user.

[0799] 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.

[0800] 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.

[0801] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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."

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0820] The following is further disclosed regarding the embodiments described above.

[0821] (Claim 1)

[0822] A means of acquiring information that periodically collects data from internet sources,

[0823] A scoring method that uses a machine learning model to score the reliability of the collected data,

[0824] A filtering method for filtering out data whose score falls below a threshold,

[0825] A means of providing information that stores data exceeding a threshold and provides it to the user upon request,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, wherein in reliability scoring, a score is calculated by referring to the source's past reliability data.

[0829] (Claim 3)

[0830] The system according to claim 1, comprising visualization means for quickly retrieving relevant information based on information requests from users and providing the results to the user visually.

[0831] "Example 1"

[0832] (Claim 1)

[0833] An information acquisition means for periodically collecting information from an information collection,

[0834] An evaluation method that uses a predictive model to assess the reliability of collected information,

[0835] A means of elimination to remove information whose evaluation score falls below the threshold,

[0836] Information transport means that stores information exceeding a standard value and transports it to the user upon request,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, wherein in evaluating reliability, a score is determined by referring to past reliability information of the originating point.

[0840] (Claim 3)

[0841] The system according to claim 1, comprising means for quickly identifying relevant information based on information requests from users and making the results visible to the user.

[0842] "Application Example 1"

[0843] (Claim 1)

[0844] A means of acquiring information that periodically collects data from internet sources,

[0845] A scoring method that uses a machine learning model to score the reliability of the collected data,

[0846] A filtering method for filtering out data whose score falls below a threshold,

[0847] Information provision means that stores data exceeding a threshold and provides it to a communication terminal device upon request,

[0848] A data processing means that, based on user requests, quickly searches for highly reliable information and provides it in a visually displayable format,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, which calculates a reliability score by referring to the source's past reliability data in reliability scoring.

[0852] (Claim 3)

[0853] The system according to claim 1, comprising means for integrating and presenting reliable information from multiple sources in a visible and displayable format.

[0854] "Example 2 of combining an emotion engine"

[0855] (Claim 1)

[0856] Information gathering means that periodically aggregate information from information sources on digital networks,

[0857] A scoring method that uses an artificial intelligence model to evaluate the reliability of aggregated information,

[0858] A filtering method that removes information that does not meet specific reliability criteria based on the evaluated information,

[0859] A means of providing information that stores information that meets the standards and provides it upon request from users,

[0860] An emotion adjustment means that detects the emotional state from the user's input device and adjusts the information supply means according to that state,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, wherein in evaluating reliability, a score is calculated by referring to the past reliability history of the information source.

[0864] (Claim 3)

[0865] The system according to claim 1, comprising means for quickly searching for relevant information based on a request for information from a user and visualizing the results according to the user's emotional state.

[0866] "Application example 2 when combining with an emotional engine"

[0867] (Claim 1)

[0868] A means of analyzing the emotional state of a user,

[0869] A display optimization means that optimizes the selection and display of information based on the analyzed emotional state,

[0870] A means of acquiring information that periodically collects data from internet sources,

[0871] A scoring method that uses a machine learning model to score the reliability of the collected data,

[0872] A filtering method for filtering out data whose score falls below a threshold,

[0873] A means of providing information that stores data exceeding a threshold and provides it to the user upon request,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, wherein in reliability scoring, a score is calculated by referring to the source's past reliability data.

[0877] (Claim 3)

[0878] The system according to claim 1, comprising visualization means for quickly retrieving relevant information based on information requests from users and providing the results to the user visually. [Explanation of Symbols]

[0879] 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 of acquiring information that periodically collects data from internet sources, A scoring method that uses a machine learning model to score the reliability of the collected data, A filtering method for filtering out data whose score falls below a threshold, Information provision means that stores data exceeding a threshold and provides it to a communication terminal device upon request, A data processing means that, based on user requests, quickly searches for highly reliable information and provides it in a visually displayable format, A system that includes this.

2. The system according to claim 1, which calculates a reliability score by referring to the source's past reliability data in reliability scoring.

3. The system according to claim 1, comprising means for integrating and presenting reliable information from multiple sources in a visible and displayable format.

Images