system

Abstract

We provide the system. [Solution] Means for collecting information, A means of evaluating the credibility of the collected information, A means of generating news articles based on evaluation results, A means of classifying the generated news articles, Means of predicting future events, A means of distributing news articles that include prediction results, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern information - based society, there is an abundance of diverse information on social networking services and the Internet. However, since it includes information with low credibility and fake news, there is a problem that it is difficult to quickly obtain accurate and highly reliable information. Also, it is necessary to enable users to appropriately formulate risk management and business strategies by predicting future events while ensuring the freshness and credibility of information.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides means for collecting information, means for evaluating the credibility of the collected information, and means for generating news articles based on the evaluation results. Furthermore, by constructing a system that includes means for classifying the generated news articles and means for predicting future events, and that distributes news articles including the prediction results, the invention provides users with consistently reliable information and supports efficient decision-making.

[0006] "Means of collecting information" refers to devices and methods for acquiring data in real time from social networking services and websites.

[0007] "Means for evaluating credibility" refers to devices and methods that analyze and determine the accuracy and reliability of collected information using various criteria and algorithms.

[0008] "Means for generating news articles" refers to devices or methods that automatically create articles using natural language generation technology or similar techniques based on evaluated information.

[0009] "Means for classifying news articles" refers to devices or methods for organizing generated news articles according to predetermined categories.

[0010] "Means of predicting future events" refer to devices and methods that use technologies such as AI to estimate possible future events based on collected data and past trends.

[0011] "Means of distributing news articles" refers to devices and methods that effectively deliver generated news articles and future predictions to users' terminals or other devices. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered 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), and the like.

[0019] 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."

[0020] [First Embodiment]

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

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0027] 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.

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

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The information distribution system of the present invention is implemented using a combination of a server, a terminal, and a user. The server is responsible for collecting, evaluating, generating, classifying, and distributing information. Each element is described in detail below.

[0034] Server operation

[0035] The server collects information data in real time from external social networking services and news sites. The collected data is first organized and stored in a database. Then, the server applies AI algorithms to analyze the credibility of the collected data. In this process, metrics such as the reliability of the information source, the degree of consistency with past data, and the volume of posts are used.

[0036] Information whose credibility has been assessed is automatically converted into news articles using generative AI. The generated news articles are categorized into predefined categories (e.g., politics, economics, sports, etc.). Furthermore, the server predicts future events based on past trends and current information, and adds this predictive information to the news articles.

[0037] Terminal operation

[0038] The device delivers news articles and forecast information received from the server to the user. The device displays the received content in a user-friendly interface and immediately notifies the user via push notifications or other means as needed.

[0039] User actions

[0040] Users can view news articles displayed on their devices and utilize predictive information to aid in risk management and strategy development. They can also research news and predictions that interest them in more detail, enjoying rapid access to information.

[0041] Specific example

[0042] For example, if a disaster occurs in a certain area, the server immediately collects relevant information, analyzes its credibility, and instantly generates an article. The generated article includes not only the current situation but also future risk information predicted by AI. The terminal receives this and notifies the user, enabling the provision of fast and reliable information.

[0043] Through the above, this system provides a new form of information distribution that balances information reliability and speed. As a result, users can always obtain reliable and up-to-date information, which will support them in making appropriate decisions.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects information related to specific keywords and hashtags in real time from social networking services and news websites. This information is obtained using APIs or web scraping techniques and stored in a database.

[0047] Step 2:

[0048] The server analyzes the metadata of the collected data and evaluates the credibility of the information. Here, a credibility score is calculated based on the reliability of the source, the frequency and number of shares of posts, and past performance.

[0049] Step 3:

[0050] The server filters out information whose credibility score exceeds a certain threshold and provides the selected information to a natural language generation model. This model is then used to automatically generate news articles based on the information.

[0051] Step 4:

[0052] The server categorizes the generated news articles (e.g., politics, economics, sports). A text classification algorithm based on content analysis of the articles is used for this classification.

[0053] Step 5:

[0054] The server runs a future prediction model based on historical data and current trends to predict specific future events. The prediction results are added to the news article.

[0055] Step 6:

[0056] The server sends the final news articles and forecast information to the terminal, allowing the user to access the latest information.

[0057] Step 7:

[0058] The terminal displays news articles and forecast information received from the server in a user interface. The terminal uses a notification function as needed to inform the user of important information.

[0059] Step 8:

[0060] Users can view news articles provided through their devices and check forecast information to help them make informed decisions and judgments.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In modern society, the volume and speed of information continue to increase, making it crucial to quickly collect, analyze, and deliver reliable information to users. However, existing information systems have been insufficient in evaluating data reliability and adding predictive information, limiting their ability to support users' informed decision-making. Therefore, there is a growing demand for information that is more reliable and predicts future trends.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for acquiring information from an information medium, means for analyzing the stored information and evaluating its reliability, and means for estimating future events using time-series analysis. This enables the rapid storage and analysis of highly reliable information, and the provision of information with a view to the future.

[0066] "Information media" refers to a general term for external online platforms and websites used to obtain information.

[0067] "Means of acquiring information" refers to the methods and processes used to collect data from information media, and typically includes APIs and web scraping techniques.

[0068] "Means of storage" refers to the process used to organize and save acquired data, and includes the use of database management systems.

[0069] "Means of evaluating reliability" refers to algorithms and methods used to analyze accumulated data and determine the truthfulness and reliability of that information.

[0070] "Means of generating documents" refers to technologies and processes for automatically creating new information content or articles based on analysis results.

[0071] "Methods for classifying by category" refers to the process of organizing and classifying generated documents based on their content and theme.

[0072] "Means of estimating future events using time series analysis" refers to techniques and methods for analyzing past data and predicting events that may occur in the future based on that analysis.

[0073] "Means of distribution" refers to the processes and technologies used to deliver generated and classified information to end users, typically utilizing network communication methods.

[0074] A "computer terminal" refers to an electronic device used to receive and display information, and includes personal computers and smart devices.

[0075] "Methods for organizing data by criteria" refers to the process of filtering collected data based on specific standards or conditions to extract only the necessary information.

[0076] This invention relates to an advanced information distribution system that collects, analyzes, generates, and distributes information. The specific implementation methods for each component are described below.

[0077] First, the server has the means to retrieve information from information sources. Specifically, it uses Python or other programming languages ​​to make API requests and collect data from social networks and news sites. This data is received in JSON format and organized and stored in a database system (e.g., MySQL® or PostgreSQL). This accumulation process makes searching and analysis more efficient.

[0078] Next, the server applies AI algorithms and machine learning techniques to analyze the accumulated information and evaluate its reliability. The analysis utilizes the scikit-learn library in Python to score the data's credibility based on its correlation with past data and the reliability of its information sources.

[0079] Based on the analyzed information, the server automatically generates documents using a natural language generation AI model (generative AI). The generative AI model utilizes a large-scale language model API and creates news articles and informational content using prompts. For example, it might use the prompt, "Please create a reliable news article based on the current economic situation."

[0080] Furthermore, the server uses a natural language processing library (e.g., spaCy) to categorize the generated documents. This classification organizes the documents thematically, improving the relevance of the information provided to the user.

[0081] To provide predictive information, the server performs time series analysis to estimate future events. Using analysis libraries such as Prophet, it predicts future trends from historical data, providing users with insights into future developments.

[0082] The device receives documents and forecast information delivered from the server and provides this information to the user. The device interface is designed to be user-friendly and can be operated intuitively using React and Flutter®. In addition, it sends real-time push notifications for important information to provide users with quick updates.

[0083] Users can view information displayed on their devices and make appropriate decisions based on reliable articles and predictive data. Users can also access detailed information to conduct further research based on the provided information.

[0084] This system ensures the reliability and speed of information, supporting users in taking action based on accurate information.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server retrieves information from various sources. This involves sending API requests and extracting data from social networks and news sites. The input is external API endpoint information, and the output is received data in JSON format. This data is extracted via the Python requests library and forms the basis for proceeding to the next stage. Specifically, the server automatically executes API requests at regularly scheduled time intervals.

[0088] Step 2:

[0089] The server stores the acquired information in a database. This includes methods for storing structured data using a database management system. The input is the JSON data acquired in step 1, and the output is the normalized information stored in the database. This process uses SQL queries to organize the data and create indexes, improving subsequent search efficiency.

[0090] Step 3:

[0091] The server evaluates the reliability of the accumulated information. An AI algorithm is used to calculate a reliability score for the input data. The input is information stored in a database, and the output is the reliability score assigned to each piece of information. Specifically, the scikit-learn library in Python is used to compare and evaluate the data against historical data to determine whether a certain score criterion is met.

[0092] Step 4:

[0093] The server generates documents based on highly reliable information. Using a generative AI model, it takes pre-evaluated reliability information as input and automatically generates documents as output. Specifically, the generative AI API is called with the prompt "Please create a highly reliable news article based on the current economic situation" to generate a news article.

[0094] Step 5:

[0095] The server categorizes the generated documents. Using natural language processing technology, it analyzes the input generated documents and obtains the categorized documents as output. By using the spaCy library to identify the content of the documents and classify them into predetermined categories, it enables the provision of highly relevant information.

[0096] Step 6:

[0097] The server estimates future events through time series analysis. Predictive analysis is performed on historical data. The input is historical data from a database, and the output is predicted future trend information. Predictive analysis from time series data is performed using the Prophet library.

[0098] Step 7:

[0099] The device receives information that is ready for delivery and notifies the user. The input is categorized and predictively annotated documents sent from the server, and the output is the article displayed to the user and a push notification. Specifically, when the device app receives a new article, it displays it using an interface built with React or Flutter and immediately sends a notification via Firebase Cloud Messaging.

[0100] Step 8:

[0101] Users view and utilize information on their devices. Input is news articles displayed on the device, and output is information that influences the user's decision-making and actions. Users can satisfy their needs by reviewing article details and pursuing additional information as needed.

[0102] (Application Example 1)

[0103] 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."

[0104] In modern society, the sheer volume of information and the difficulty in discerning its veracity create a need for systems that can quickly provide users with highly reliable information and support useful decision-making. However, existing systems have the challenge of not being able to adequately meet the individual needs of users in terms of information collection, classification, and distribution.

[0105] 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.

[0106] In this invention, the server includes a device for collecting information, a device for evaluating the reliability of the collected data, and a device for generating news content based on the evaluation results. This makes it possible to quickly collect highly reliable information and efficiently deliver it in a way that matches the individual needs of users.

[0107] A "device for collecting information" is a device designed to efficiently acquire various types of information from external data sources.

[0108] A "device for evaluating the reliability of collected data" is a device designed to determine the accuracy and reliability of acquired information.

[0109] A "device for generating news content based on evaluation results" is a device that automatically creates appropriate news articles based on reliability evaluations.

[0110] A "device for classifying generated news content" is a device for organizing and classifying created news articles by theme or category.

[0111] A "device for predicting potential future events" is a device that uses current information to infer future events.

[0112] A "device for supplying news content including prediction results" is a device that provides users with news content that incorporates prediction information.

[0113] A "device for customizing information based on user location or interests" is a device that personalizes information according to the user's location and interests, and adjusts news content to meet individual needs.

[0114] To realize this invention, it is first necessary to implement a program for collecting information on a server. This server will acquire information in real time from external data sources and organize and store it in a database. The software used will be a Python®-based server application, and by utilizing frameworks such as Flask, information can be managed efficiently.

[0115] Next, to evaluate the reliability of the collected data, an AI algorithm is used. Machine learning libraries such as TENSORFLOW® and PyTorch are used to analyze the reliability of the information sources and generate reliability scores. This process utilizes historical data and reliability evaluation criteria stored in the database.

[0116] In the stage of generating news content based on evaluation results, a generation AI model is installed on the server and natural language processing technology is utilized. This automatically generates news articles from the collected data and further classifies those articles by theme.

[0117] The generated news articles are delivered to the user's device. Here, a program is executed to customize the information based on the user's location and past history. Users can instantly receive specific local information and news of interest via push notifications on devices such as smartphones.

[0118] For example, a user traveling to a specific city could be provided with real-time weather forecasts, event information, and breaking news for that area. The generation AI could use prompts like the following: "Generate the latest news related to the area indicated by the user's location, evaluate its reliability, and classify it. Prepare appropriate notifications for the user and provide information in a way that recommends content based on their interests for future visits." This prompt makes it possible to provide useful information to the user.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server collects information from external data sources. Input is raw data obtained through news APIs and social networking service APIs, while output is organized information in a database. Specifically, the server accesses each API endpoint, retrieves data using specified query parameters, and stores it in the database.

[0122] Step 2:

[0123] The server evaluates the reliability of the collected data. The input is raw data retrieved from a database, and the output is a reliability score for each data point. Specifically, the server applies a machine learning algorithm to generate a score based on the historical reliability and posting frequency of the information source.

[0124] Step 3:

[0125] The server generates news content based on the evaluation results. The input is data with reliability scores, and the output is the generated news article. Here, a generative AI model is used to perform natural language generation for each data point and apply prompt sentences to create the article. Specifically, the generative AI is sent the prompt, "Generate the latest news, evaluate its reliability, and then classify it."

[0126] Step 4:

[0127] The server classifies the generated news articles. The input is the generated news articles, and the output is articles classified by theme. Specifically, natural language processing technology is used to automatically classify the articles into categories such as politics, economics, and sports.

[0128] Step 5:

[0129] The server customizes information based on the user's location or interests. Input consists of categorized articles and user profile information, while output is a customized news feed. Specifically, it considers the user's past browsing history and current location to select the most relevant content.

[0130] Step 6:

[0131] The device receives customized information from the server and generates push notifications. The input is a customized news feed, and the output is the article information that is notified to the user. Specifically, when the device receives new information, it automatically displays a notification in the regular notification center, allowing the user to check it immediately.

[0132] Step 7:

[0133] Users view articles based on notifications from their devices and then research information that interests them further. The input is the news article displayed on the device, and the output is the acquisition of more detailed information. Specifically, when the user clicks on an article link, rich content is displayed.

[0134] 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.

[0135] The information distribution system of the present invention includes a combination of server, terminal, and user, as well as a function that includes an emotion engine for recognizing the user's emotions. The server is involved in information collection, evaluation, news generation, classification, future prediction, and distribution.

[0136] Server operation

[0137] The server collects information from social networking services and news sites. The collected information is then evaluated for credibility using a reliability rating algorithm. The selected information is automatically generated as news articles using a generative AI model and categorized. The server also analyzes data to predict future events and integrates these predictions into the news articles.

[0138] Furthermore, the server utilizes an emotion engine to understand the user's psychological state when news articles are delivered. The emotion engine recognizes emotions based on user input and responses, and uses this to customize the content of the news articles delivered and adjust the delivery frequency, thereby improving the user experience.

[0139] Terminal operation

[0140] The device displays received news articles and forecast information through its user interface. Furthermore, based on data from its emotion engine, the device selectively notifies users of information tailored to their interests and emotions. This feature ensures that the most relevant information is delivered to the user.

[0141] User actions

[0142] Users view news articles provided via their devices and check predictive information. Furthermore, user reactions and feedback are collected as sentiment data by an emotion engine, which is then reflected in future article deliveries.

[0143] Specific example

[0144] For example, when a user is notified of a news item, the emotion engine analyzes the user's facial expressions and behavior to determine their reaction. If it determines that the user is experiencing stress, the server can adjust the content of future news delivered to that user, reducing its impact and prioritizing information that brings joy and reassurance.

[0145] The system of the present invention allows users to not only collect information but also enjoy customized information tailored to their individual emotional state, thereby obtaining a more personal and valuable information experience.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The server collects information related to specific keywords in real time from social networking services and news sites. The information is obtained using external APIs or web scraping techniques and stored in a database.

[0149] Step 2:

[0150] The server runs an algorithm that considers the reliability of the source, posting frequency, and past performance to evaluate the credibility of the collected information. The evaluated information is assigned a credibility score.

[0151] Step 3:

[0152] The server filters information whose credibility score exceeds a threshold and automatically generates news articles using a natural language generation model.

[0153] Step 4:

[0154] The server classifies the generated news articles into categories (politics, economics, sports, etc.) using a text analysis algorithm.

[0155] Step 5:

[0156] The server runs a future prediction model based on historical trend data and current information to forecast highly probable future events. The predictions are then integrated into news articles.

[0157] Step 6:

[0158] The server analyzes the user's emotional data via an emotion engine and adjusts the content of news articles based on the emotional information obtained. For example, if the user is feeling stressed, it prioritizes relaxing content.

[0159] Step 7:

[0160] The device displays customized news articles and forecast information sent from the server to the user. It also uses push notifications to inform the user of important information at appropriate times.

[0161] Step 8:

[0162] Users can view news articles provided on their devices and explore further details about information they find interesting. User reactions and interactions are analyzed by an emotion engine to improve future information delivery.

[0163] Through these steps, users can receive information tailored to their emotional state in real time, resulting in a more personalized experience.

[0164] (Example 2)

[0165] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0166] In modern society, efficiently collecting highly reliable information from a vast amount of data and providing it in an appropriate format tailored to the user's psychological state is difficult. Furthermore, in order to flexibly respond to the diversifying information needs of users, information customization is required, but conventional systems lack the means to effectively achieve this.

[0167] 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.

[0168] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for generating news articles using a generative AI model. This makes it possible to provide highly reliable news articles that are tailored to the individual emotional state of each user.

[0169] "Means of collecting information" refers to functions and methods for obtaining data from various information sources on the internet.

[0170] "Means of evaluating credibility" refers to algorithms and criteria used to determine the truthfulness and reliability of collected information.

[0171] "Methods for generating news articles using generative AI models" refers to methods that use artificial intelligence to automatically generate article-formatted text based on collected data.

[0172] "Means for classifying news articles" refers to functions that divide generated articles into categories based on their content and theme.

[0173] "Methods for predicting future events" refer to methods that use data analysis and statistical models to anticipate future events and trends.

[0174] "Methods for customizing and delivering news articles based on emotional data" refers to methods for analyzing the psychological state of individual users and adjusting the content and delivery frequency of news articles to suit their needs.

[0175] "Means of analyzing and notifying users of their emotional data" refers to a function that judges the user's reactions and emotions and transmits appropriate information based on the results.

[0176] "Means of filtering information" refers to the process of selecting highly relevant data from collected information and excluding irrelevant or inappropriate data.

[0177] "Utilizing an emotion engine" refers to software technology that analyzes user emotions and adjusts information provision and user experience based on those analyses.

[0178] The information distribution system of the present invention operates primarily based on the interaction between a server, a terminal, and a user. Specific embodiments thereof are shown below.

[0179] The server has the capability to collect data from various sources on the internet. This is done using APIs and web scraping techniques, and the obtained data is stored in a database. The collected information is analyzed by an algorithm that evaluates its credibility, and only highly reliable information is extracted. This evaluation is based on the reliability of the source and the consistency of the information.

[0180] Next, a generative AI model is used to automatically generate news articles from reliable information. This AI model is an existing general-purpose model for natural language processing. An example of a prompt used in this process is: "Based on the following information, please generate a positive and reassuring news article. We want to include positive topics because this news may be stressful for users."

[0181] The generated news articles are categorized by the server based on their content. For example, categories such as sports, politics, and technology are considered. Furthermore, the server uses data analysis and statistical methods to predict future events. This involves trend analysis of historical data and machine learning algorithms.

[0182] Furthermore, the server is equipped with an emotion engine that analyzes the user's psychological state. The emotion engine analyzes data obtained from the user's device (e.g., browsing history and feedback) to determine their psychological state. Based on this information, news articles are customized and their delivery frequency is adjusted to provide a more personalized user experience.

[0183] The device has the functionality to display customized articles sent from the server on the user interface. The timing of information notifications can be adjusted according to the user's usage patterns. This allows users to receive the information they are most interested in at the optimal time.

[0184] Users view news articles provided via their devices and provide feedback as needed. This feedback is collected on the server and used to improve future information delivery. For example, positive feedback from users will guide the system in prioritizing notifications for articles in similar categories.

[0185] Thus, the system of the present invention provides a highly personalized information experience by collecting, generating, and distributing information that meets the individual needs of the user.

[0186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0187] Step 1:

[0188] The server collects data from information sources on the internet. Specifically, it uses various APIs and web scraping techniques to collect data from news sites and social media. The input for this process is specific keywords or information categories, and the output is the retrieved raw data. The server automatically stores this data in a database.

[0189] Step 2:

[0190] The server evaluates the credibility of the collected information. The input is the raw data collected in step 1, and the output is the data whose credibility has been evaluated. Specifically, it analyzes the reliability of the information source and its degree of consistency with past data, and applies an algorithm to eliminate uncertain information. In this process, the evaluation points of the information source are scored, and only data whose score exceeds a certain standard is passed on to the next step.

[0191] Step 3:

[0192] The server uses a generative AI model with highly reliable information to create news articles. The input is reliable data, and the output is a news article written in natural language. The generative AI model is given easily recognizable prompts, such as "Create a positive news article based on facts." As a result, the AI ​​automatically generates the text of the news article.

[0193] Step 4:

[0194] The server categorizes the generated news articles. The input is the generated news articles, and the output is the categorized news articles. Specifically, it analyzes the content of the articles and applies natural language processing techniques to determine categories such as sports, politics, and technology.

[0195] Step 5:

[0196] The server performs data analysis and predicts future events. The input consists of historical data and data based on current trends, while the output is the predicted future events. Statistical methods and machine learning algorithms are used to predict potential future occurrences, and this information is incorporated into news articles.

[0197] Step 6:

[0198] The server uses an emotion engine to analyze user sentiment data and customize news articles. Input is the user's past browsing history and reaction data, and output is a customized news article. By analyzing sentiment data, it becomes possible to recommend news articles tailored to each user's psychological state.

[0199] Step 7:

[0200] The device delivers customized news articles to the user. The input is news articles sent from the server, and the output is information displayed in the user interface. The user interface adjusts the timing of information notifications based on the user's interests and activities to provide an optimal experience.

[0201] Step 8:

[0202] Users view the delivered news articles and provide feedback. The input is the news articles received through their devices, and the output is the user's reactions and evaluations. The feedback received is collected by the server and used to improve future information distribution. Feedback may be provided in the form of explicit "likes" or comments, or it may be collected through implicit activity such as viewing time and click frequency.

[0203] (Application Example 2)

[0204] 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."

[0205] Traditional information distribution systems delivered uniform content without considering the user's psychological state, making it difficult to provide information tailored to the user's interests and emotions. As a result, the user experience deteriorated, and the system failed to provide sufficient information value.

[0206] 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.

[0207] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for recognizing the user's emotional state. This enables the delivery of customized news content based on the user's emotions.

[0208] "Means of collecting information" refers to devices or software that acquire data from social networking services or news sites.

[0209] "Means for evaluating credibility" refers to devices or software that use algorithms to determine the accuracy and reliability of collected information.

[0210] "Means for generating news content" refers to devices or software that use generative AI models to automatically create news articles and content based on selected information.

[0211] "Classification means" refers to a device or software that performs the process of dividing generated news content into specific categories.

[0212] "Means of predicting future events" refers to devices or software that execute algorithms to predict future events based on collected and analyzed data.

[0213] "Means of distribution" refers to networks and communication devices for delivering generated and categorized news content to users.

[0214] "Means for recognizing a user's emotional state" refers to devices or software that use emotion engines or sensors to acquire user input and responses and analyze their psychological state based on that information.

[0215] "Means of customization" refers to devices or software that perform a process to adjust the content of news content delivered in accordance with the recognized emotions of the user.

[0216] The system for implementing this invention consists of a server, a terminal, and a user. The server is responsible for collecting information, evaluating its credibility, and generating news content. Specifically, the server collects information from news sites and social networking services. It applies a credibility evaluation algorithm to the collected information to determine its credibility. The selected data is automatically generated as news content using a generative AI model and classified into specific categories. Furthermore, the server applies a future prediction algorithm to predict future events and integrates the results into the news content.

[0217] The server uses an emotion engine to analyze the user's psychological state. By analyzing user input and feedback, the server customizes the news content it delivers to match the user's emotions based on the resulting emotion data. For this purpose, it uses "Microsoft® Azure® Emotion API" as an emotion recognition library. In addition, it utilizes "OpenAI® GPT-4®" as a generative AI model.

[0218] Meanwhile, the device has the function of displaying received news content through a user interface. The device is equipped with a camera, microphone, and biometric sensors, which are used to acquire the user's facial expressions, voice, and even heart rate in real time. Based on this, an emotion engine evaluates the user's emotions and selects appropriate content to notify them.

[0219] For example, if the emotion engine detects stress in a user while they are browsing the news using smart glasses during their commute, the system will prioritize delivering articles and videos that promote relaxation. An example of a prompt in this case might be: "Generate entertainment news for when the user is relaxed. Include positive content while incorporating a unique perspective that will capture the user's attention. Examples: recent movie releases or lighthearted topics."

[0220] Users view news content provided through their devices, and their reactions and feedback are analyzed again by the sentiment engine and used to customize future content delivery. Through this process, a more personalized and valuable information experience is realized for users.

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The server collects information from social networking services and news sites. It uses various data sources on the internet as input, obtaining the latest information using APIs and scraping techniques. The output is a set of collected raw data.

[0224] Step 2:

[0225] The server evaluates the credibility of the collected information. Using the raw data obtained in Step 1 as input, it applies a reliability evaluation algorithm (e.g., analysis based on data source and past content performance). The output is data that has been evaluated and selected based on its reliability.

[0226] Step 3:

[0227] The server generates news content using a generative AI model based on highly reliable data. The input consists of the filtered data from step 2 and prompts applied to the generative AI model. A news article is generated using the generative AI model (e.g., OpenAI GPT-4), and the output is automatically generated news content.

[0228] Step 4:

[0229] The server categorizes the generated news content. Using the news content generated in step 3 as input, it performs content-based categorization using natural language processing techniques. The output is the news content categorized.

[0230] Step 5:

[0231] The server recognizes the user's emotional state through an emotion engine. It uses user feedback and real-time biometric data (e.g., camera images and audio data) as input. An emotion recognition model (e.g., Microsoft Azure Emotion API) is used to determine the user's psychological state, and the user's emotional data is obtained as output.

[0232] Step 6:

[0233] The server customizes news content based on the user's sentiment data. It uses the sentiment data obtained in step 5 and the news content classified in step 4 as input. A customization algorithm is applied to select content relevant to the user, resulting in customized content as output.

[0234] Step 7:

[0235] The terminal displays customized news content sent from the server in its user interface. It receives the customized content obtained in step 6 as input. As output, user-optimized content is displayed on the terminal, providing an experience tailored to the user's interests and emotions.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] [Second Embodiment]

[0240] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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).

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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".

[0252] The information distribution system of the present invention is implemented using a combination of a server, a terminal, and a user. The server is responsible for collecting, evaluating, generating, classifying, and distributing information. Each element is described in detail below.

[0253] Server operation

[0254] The server collects information data in real time from external social networking services and news sites. The collected data is first organized and stored in a database. Then, the server applies AI algorithms to analyze the credibility of the collected data. In this process, metrics such as the reliability of the information source, the degree of consistency with past data, and the volume of posts are used.

[0255] Information whose credibility has been assessed is automatically converted into news articles using generative AI. The generated news articles are categorized into predefined categories (e.g., politics, economics, sports, etc.). Furthermore, the server predicts future events based on past trends and current information, and adds this predictive information to the news articles.

[0256] Terminal operation

[0257] The device delivers news articles and forecast information received from the server to the user. The device displays the received content in a user-friendly interface and immediately notifies the user via push notifications or other means as needed.

[0258] User actions

[0259] Users can view news articles displayed on their devices and utilize predictive information to aid in risk management and strategy development. They can also research news and predictions that interest them in more detail, enjoying rapid access to information.

[0260] Specific example

[0261] For example, if a disaster occurs in a certain area, the server immediately collects relevant information, analyzes its credibility, and instantly generates an article. The generated article includes not only the current situation but also future risk information predicted by AI. The terminal receives this and notifies the user, enabling the provision of fast and reliable information.

[0262] Through the above, this system provides a new form of information distribution that balances information reliability and speed. As a result, users can always obtain reliable and up-to-date information, which will support them in making appropriate decisions.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] The server collects information related to specific keywords and hashtags in real time from social networking services and news websites. This information is obtained using APIs or web scraping techniques and stored in a database.

[0266] Step 2:

[0267] The server analyzes the metadata of the collected data and evaluates the credibility of the information. Here, a credibility score is calculated based on the reliability of the source, the frequency and number of shares of posts, and past performance.

[0268] Step 3:

[0269] The server filters out information whose credibility score exceeds a certain threshold and provides the selected information to a natural language generation model. This model is then used to automatically generate news articles based on the information.

[0270] Step 4:

[0271] The server categorizes the generated news articles (e.g., politics, economics, sports). A text classification algorithm based on content analysis of the articles is used for this classification.

[0272] Step 5:

[0273] The server runs a future prediction model based on historical data and current trends to predict specific future events. The prediction results are added to the news article.

[0274] Step 6:

[0275] The server sends the final news articles and forecast information to the terminal, allowing the user to access the latest information.

[0276] Step 7:

[0277] The terminal displays news articles and forecast information received from the server in a user interface. The terminal uses a notification function as needed to inform the user of important information.

[0278] Step 8:

[0279] Users can view news articles provided through their devices and check forecast information to help them make informed decisions and judgments.

[0280] (Example 1)

[0281] 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."

[0282] In modern society, the volume and speed of information continue to increase, making it crucial to quickly collect, analyze, and deliver reliable information to users. However, existing information systems have been insufficient in evaluating data reliability and adding predictive information, limiting their ability to support users' informed decision-making. Therefore, there is a growing demand for information that is more reliable and predicts future trends.

[0283] 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.

[0284] In this invention, the server includes means for acquiring information from an information medium, means for analyzing the accumulated information to evaluate reliability, and means for estimating future events using time series analysis. As a result, highly reliable information can be quickly accumulated and analyzed, enabling information provision with a view to the future.

[0285] The "information medium" is a general term for external online platforms and websites for acquiring information.

[0286] The "means for acquiring information" refers to the methods and processes used to collect data from an information medium, usually including APIs and web scraping technologies.

[0287] The "means for storing" is the process used to organize and store the acquired data, including making use of a database management system.

[0288] The "means for evaluating reliability" refers to the algorithms and methods for analyzing the accumulated data to judge the authenticity and reliability of the information.

[0289] The "means for generating a document" refers to the technologies and processes for automatically creating new information content and articles based on the analysis results.

[0290] The "means for classifying by category" refers to the process for organizing and classifying the generated documents based on their content and themes.

[0291] The "means for estimating future events using time series analysis" refers to the technologies and methods for analyzing past data and predicting events that may occur in the future based on this.

[0292] The "means for distributing" refers to the processes and technologies for delivering the generated and classified information to end users, usually using communication means on the network.

[0293] A "computer terminal" refers to an electronic device used to receive and display information, and includes personal computers and smart devices.

[0294] "Methods for organizing data by criteria" refers to the process of filtering collected data based on specific standards or conditions to extract only the necessary information.

[0295] This invention relates to an advanced information distribution system that collects, analyzes, generates, and distributes information. The specific implementation methods for each component are described below.

[0296] First, the server has the means to retrieve information from information sources. Specifically, it uses Python or other programming languages ​​to make API requests and collect data from social networks and news sites. This data is received in JSON format and organized and stored in a database system (e.g., MySQL or PostgreSQL). This accumulation process makes searching and analysis more efficient.

[0297] Next, the server applies AI algorithms and machine learning techniques to analyze the accumulated information and evaluate its reliability. The analysis utilizes the scikit-learn library in Python to score the data's credibility based on its correlation with past data and the reliability of its information sources.

[0298] Based on the analyzed information, the server automatically generates documents using a natural language generation AI model (generative AI). The generative AI model utilizes a large-scale language model API and creates news articles and informational content using prompts. For example, it might use the prompt, "Please create a reliable news article based on the current economic situation."

[0299] Furthermore, the server uses a natural language processing library (e.g., spaCy) to categorize the generated documents. This classification organizes the documents thematically, improving the relevance of the information provided to the user.

[0300] To provide predictive information, the server performs time series analysis to estimate future events. By using an analysis library such as Prophet to predict future trends from past data, it provides users with insights into future trends.

[0301] The terminal receives the documents and predictive information distributed from the server and provides this information to the user. The interface of the terminal is designed to be user-friendly and can be intuitively operated using React or Flutter. Also, for important information, push notifications are sent in real time to provide users with prompt information.

[0302] The user can view the information displayed on the terminal and make appropriate decisions based on reliable articles and prediction data. The user can also access detailed information to conduct further investigations from the provided information.

[0303] This system ensures the reliability and speed of information and supports users to act based on reliable information.

[0304] The flow of the specific process in Example 1 will be described using FIG. 11.

[0305] Step 1:

[0306] The server obtains information from an information medium. For this, it uses means such as sending an API request and extracting data from social networks and news sites. The input is external API endpoint information, and the output is the received JSON-formatted data. This data is extracted via the Python requests library and forms the basis for proceeding to the next stage. As a specific operation, the server automatically executes API requests at regularly set time intervals.

[0307] Step 2:

[0308] The server stores the acquired information in a database. This includes methods for storing structured data using a database management system. The input is the JSON data acquired in step 1, and the output is the normalized information stored in the database. This process uses SQL queries to organize the data and create indexes, improving subsequent search efficiency.

[0309] Step 3:

[0310] The server evaluates the reliability of the accumulated information. An AI algorithm is used to calculate a reliability score for the input data. The input is information stored in a database, and the output is the reliability score assigned to each piece of information. Specifically, the scikit-learn library in Python is used to compare and evaluate the data against historical data to determine whether a certain score criterion is met.

[0311] Step 4:

[0312] The server generates documents based on highly reliable information. Using a generative AI model, it takes pre-evaluated reliability information as input and automatically generates documents as output. Specifically, the generative AI API is called with the prompt "Please create a highly reliable news article based on the current economic situation" to generate a news article.

[0313] Step 5:

[0314] The server categorizes the generated documents. Using natural language processing technology, it analyzes the input generated documents and obtains the categorized documents as output. By using the spaCy library to identify the content of the documents and classify them into predetermined categories, it enables the provision of highly relevant information.

[0315] Step 6:

[0316] The server estimates future events through time series analysis. Predictive analysis is performed on historical data. The input is historical data from a database, and the output is predicted future trend information. Predictive analysis from time series data is performed using the Prophet library.

[0317] Step 7:

[0318] The device receives information that is ready for delivery and notifies the user. The input is categorized and predictively annotated documents sent from the server, and the output is the article displayed to the user and a push notification. Specifically, when the device app receives a new article, it displays it using an interface built with React or Flutter and immediately sends a notification via Firebase Cloud Messaging.

[0319] Step 8:

[0320] Users view and utilize information on their devices. Input is news articles displayed on the device, and output is information that influences the user's decision-making and actions. Users can satisfy their needs by reviewing article details and pursuing additional information as needed.

[0321] (Application Example 1)

[0322] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0323] In modern society, the sheer volume of information and the difficulty in discerning its veracity create a need for systems that can quickly provide users with highly reliable information and support useful decision-making. However, existing systems have the challenge of not being able to adequately meet the individual needs of users in terms of information collection, classification, and distribution.

[0324] 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.

[0325] In this invention, the server includes a device for collecting information, a device for evaluating the reliability of the collected data, and a device for generating news content based on the evaluation results. This makes it possible to quickly collect highly reliable information and efficiently deliver it in a way that matches the individual needs of users.

[0326] A "device for collecting information" is a device designed to efficiently acquire various types of information from external data sources.

[0327] A "device for evaluating the reliability of collected data" is a device designed to determine the accuracy and reliability of acquired information.

[0328] A "device for generating news content based on evaluation results" is a device that automatically creates appropriate news articles based on reliability evaluations.

[0329] A "device for classifying generated news content" is a device for organizing and classifying created news articles by theme or category.

[0330] A "device for predicting potential future events" is a device that uses current information to infer future events.

[0331] A "device for supplying news content including prediction results" is a device that provides users with news content that incorporates prediction information.

[0332] A "device for customizing information based on user location or interests" is a device that personalizes information according to the user's location and interests, and adjusts news content to meet individual needs.

[0333] To realize this invention, it is first necessary to implement a program for collecting information on a server. This server will acquire information in real time from external data sources and organize and store it in a database. The software used will be a Python-based server application, and by utilizing a framework such as Flask, information can be managed efficiently.

[0334] Next, to evaluate the reliability of the collected data, AI algorithms are used. Machine learning libraries such as TensorFlow and PyTorch are used to analyze the reliability of the information sources and generate reliability scores. This process utilizes historical data and reliability evaluation criteria stored in the database.

[0335] In the stage of generating news content based on evaluation results, a generation AI model is installed on the server and natural language processing technology is utilized. This automatically generates news articles from the collected data and further classifies those articles by theme.

[0336] The generated news articles are delivered to the user's device. Here, a program is executed to customize the information based on the user's location and past history. Users can instantly receive specific local information and news of interest via push notifications on devices such as smartphones.

[0337] For example, a user traveling to a specific city could be provided with real-time weather forecasts, event information, and breaking news for that area. The generation AI could use prompts like the following: "Generate the latest news related to the area indicated by the user's location, evaluate its reliability, and classify it. Prepare appropriate notifications for the user and provide information in a way that recommends content based on their interests for future visits." This prompt makes it possible to provide useful information to the user.

[0338] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0339] Step 1:

[0340] The server collects information from external data sources. Input is raw data obtained through news APIs and social networking service APIs, while output is organized information in a database. Specifically, the server accesses each API endpoint, retrieves data using specified query parameters, and stores it in the database.

[0341] Step 2:

[0342] The server evaluates the reliability of the collected data. The input is raw data retrieved from a database, and the output is a reliability score for each data point. Specifically, the server applies a machine learning algorithm to generate a score based on the historical reliability and posting frequency of the information source.

[0343] Step 3:

[0344] The server generates news content based on the evaluation results. The input is data with reliability scores, and the output is the generated news article. Here, a generative AI model is used to perform natural language generation for each data point and apply prompt sentences to create the article. Specifically, the generative AI is sent the prompt, "Generate the latest news, evaluate its reliability, and then classify it."

[0345] Step 4:

[0346] The server classifies the generated news articles. The input is the generated news articles, and the output is articles classified by theme. Specifically, natural language processing technology is used to automatically classify the articles into categories such as politics, economics, and sports.

[0347] Step 5:

[0348] The server customizes information based on the user's location or interests. Input consists of categorized articles and user profile information, while output is a customized news feed. Specifically, it considers the user's past browsing history and current location to select the most relevant content.

[0349] Step 6:

[0350] The device receives customized information from the server and generates push notifications. The input is a customized news feed, and the output is the article information that is notified to the user. Specifically, when the device receives new information, it automatically displays a notification in the regular notification center, allowing the user to check it immediately.

[0351] Step 7:

[0352] Users view articles based on notifications from their devices and then research information that interests them further. The input is the news article displayed on the device, and the output is the acquisition of more detailed information. Specifically, when the user clicks on an article link, rich content is displayed.

[0353] 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.

[0354] The information distribution system of the present invention includes a combination of server, terminal, and user, as well as a function that includes an emotion engine for recognizing the user's emotions. The server is involved in information collection, evaluation, news generation, classification, future prediction, and distribution.

[0355] Server operation

[0356] The server collects information from social networking services and news sites. The collected information is then evaluated for credibility using a reliability rating algorithm. The selected information is automatically generated as news articles using a generative AI model and categorized. The server also analyzes data to predict future events and integrates these predictions into the news articles.

[0357] Furthermore, the server utilizes an emotion engine to understand the user's psychological state when news articles are delivered. The emotion engine recognizes emotions based on user input and responses, and uses this to customize the content of the news articles delivered and adjust the delivery frequency, thereby improving the user experience.

[0358] Terminal operation

[0359] The device displays received news articles and forecast information through its user interface. Furthermore, based on data from its emotion engine, the device selectively notifies users of information tailored to their interests and emotions. This feature ensures that the most relevant information is delivered to the user.

[0360] User actions

[0361] Users view news articles provided via their devices and check predictive information. Furthermore, user reactions and feedback are collected as sentiment data by an emotion engine, which is then reflected in future article deliveries.

[0362] Specific example

[0363] For example, when a user is notified of a news item, the emotion engine analyzes the user's facial expressions and behavior to determine their reaction. If it determines that the user is experiencing stress, the server can adjust the content of future news delivered to that user, reducing its impact and prioritizing information that brings joy and reassurance.

[0364] The system of the present invention allows users to not only collect information but also enjoy customized information tailored to their individual emotional state, thereby obtaining a more personal and valuable information experience.

[0365] The following describes the processing flow.

[0366] Step 1:

[0367] The server collects information related to specific keywords in real time from social networking services and news sites. The information is obtained using external APIs or web scraping techniques and stored in a database.

[0368] Step 2:

[0369] The server runs an algorithm that considers the reliability of the source, posting frequency, and past performance to evaluate the credibility of the collected information. The evaluated information is assigned a credibility score.

[0370] Step 3:

[0371] The server filters information whose credibility score exceeds a threshold and automatically generates news articles using a natural language generation model.

[0372] Step 4:

[0373] The server classifies the generated news articles into categories (politics, economics, sports, etc.) using a text analysis algorithm.

[0374] Step 5:

[0375] The server runs a future prediction model based on historical trend data and current information to forecast highly probable future events. The predictions are then integrated into news articles.

[0376] Step 6:

[0377] The server analyzes the user's emotional data via an emotion engine and adjusts the content of news articles based on the emotional information obtained. For example, if the user is feeling stressed, it prioritizes relaxing content.

[0378] Step 7:

[0379] The device displays customized news articles and forecast information sent from the server to the user. It also uses push notifications to inform the user of important information at appropriate times.

[0380] Step 8:

[0381] Users can view news articles provided on their devices and explore further details about information they find interesting. User reactions and interactions are analyzed by an emotion engine to improve future information delivery.

[0382] Through these steps, users can receive information tailored to their emotional state in real time, resulting in a more personalized experience.

[0383] (Example 2)

[0384] 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".

[0385] In modern society, efficiently collecting highly reliable information from a vast amount of data and providing it in an appropriate format tailored to the user's psychological state is difficult. Furthermore, in order to flexibly respond to the diversifying information needs of users, information customization is required, but conventional systems lack the means to effectively achieve this.

[0386] 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.

[0387] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for generating news articles using a generative AI model. This makes it possible to provide highly reliable news articles that are tailored to the individual emotional state of each user.

[0388] "Means of collecting information" refers to functions and methods for obtaining data from various information sources on the internet.

[0389] "Means of evaluating credibility" refers to algorithms and criteria used to determine the truthfulness and reliability of collected information.

[0390] "Methods for generating news articles using generative AI models" refers to methods that use artificial intelligence to automatically generate article-formatted text based on collected data.

[0391] "Means for classifying news articles" refers to functions that divide generated articles into categories based on their content and theme.

[0392] "Methods for predicting future events" refer to methods that use data analysis and statistical models to anticipate future events and trends.

[0393] "Methods for customizing and delivering news articles based on emotional data" refers to methods for analyzing the psychological state of individual users and adjusting the content and delivery frequency of news articles to suit their needs.

[0394] "Means of analyzing and notifying users of their emotional data" refers to a function that judges the user's reactions and emotions and transmits appropriate information based on the results.

[0395] "Means of filtering information" refers to the process of selecting highly relevant data from collected information and excluding irrelevant or inappropriate data.

[0396] "Utilizing an emotion engine" refers to software technology that analyzes user emotions and adjusts information provision and user experience based on those analyses.

[0397] The information distribution system of the present invention operates primarily based on the interaction between a server, a terminal, and a user. Specific embodiments thereof are shown below.

[0398] The server has the capability to collect data from various sources on the internet. This is done using APIs and web scraping techniques, and the obtained data is stored in a database. The collected information is analyzed by an algorithm that evaluates its credibility, and only highly reliable information is extracted. This evaluation is based on the reliability of the source and the consistency of the information.

[0399] Next, a generative AI model is used to automatically generate news articles from reliable information. This AI model is an existing general-purpose model for natural language processing. An example of a prompt used in this process is: "Based on the following information, please generate a positive and reassuring news article. We want to include positive topics because this news may be stressful for users."

[0400] The generated news articles are categorized by the server based on their content. For example, categories such as sports, politics, and technology are considered. Furthermore, the server uses data analysis and statistical methods to predict future events. This involves trend analysis of historical data and machine learning algorithms.

[0401] Furthermore, the server is equipped with an emotion engine that analyzes the user's psychological state. The emotion engine analyzes data obtained from the user's device (e.g., browsing history and feedback) to determine their psychological state. Based on this information, news articles are customized and their delivery frequency is adjusted to provide a more personalized user experience.

[0402] The device has the functionality to display customized articles sent from the server on the user interface. The timing of information notifications can be adjusted according to the user's usage patterns. This allows users to receive the information they are most interested in at the optimal time.

[0403] Users view news articles provided via their devices and provide feedback as needed. This feedback is collected on the server and used to improve future information delivery. For example, positive feedback from users will guide the system in prioritizing notifications for articles in similar categories.

[0404] Thus, the system of the present invention provides a highly personalized information experience by collecting, generating, and distributing information that meets the individual needs of the user.

[0405] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0406] Step 1:

[0407] The server collects data from information sources on the internet. Specifically, it uses various APIs and web scraping techniques to collect data from news sites and social media. The input for this process is specific keywords or information categories, and the output is the retrieved raw data. The server automatically stores this data in a database.

[0408] Step 2:

[0409] The server evaluates the credibility of the collected information. The input is the raw data collected in step 1, and the output is the data whose credibility has been evaluated. Specifically, it analyzes the reliability of the information source and its degree of consistency with past data, and applies an algorithm to eliminate uncertain information. In this process, the evaluation points of the information source are scored, and only data whose score exceeds a certain standard is passed on to the next step.

[0410] Step 3:

[0411] The server uses a generative AI model with highly reliable information to create news articles. The input is reliable data, and the output is a news article written in natural language. The generative AI model is given easily recognizable prompts, such as "Create a positive news article based on facts." As a result, the AI ​​automatically generates the text of the news article.

[0412] Step 4:

[0413] The server categorizes the generated news articles. The input is the generated news articles, and the output is the categorized news articles. Specifically, it analyzes the content of the articles and applies natural language processing techniques to determine categories such as sports, politics, and technology.

[0414] Step 5:

[0415] The server performs data analysis and predicts future events. The input consists of historical data and data based on current trends, while the output is the predicted future events. Statistical methods and machine learning algorithms are used to predict potential future occurrences, and this information is incorporated into news articles.

[0416] Step 6:

[0417] The server uses an emotion engine to analyze user sentiment data and customize news articles. Input is the user's past browsing history and reaction data, and output is a customized news article. By analyzing sentiment data, it becomes possible to recommend news articles tailored to each user's psychological state.

[0418] Step 7:

[0419] The device delivers customized news articles to the user. The input is news articles sent from the server, and the output is information displayed in the user interface. The user interface adjusts the timing of information notifications based on the user's interests and activities to provide an optimal experience.

[0420] Step 8:

[0421] Users view the delivered news articles and provide feedback. The input is the news articles received through their devices, and the output is the user's reactions and evaluations. The feedback received is collected by the server and used to improve future information distribution. Feedback may be provided in the form of explicit "likes" or comments, or it may be collected through implicit activity such as viewing time and click frequency.

[0422] (Application Example 2)

[0423] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0424] Traditional information distribution systems delivered uniform content without considering the user's psychological state, making it difficult to provide information tailored to the user's interests and emotions. As a result, the user experience deteriorated, and the system failed to provide sufficient information value.

[0425] 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.

[0426] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for recognizing the user's emotional state. This enables the delivery of customized news content based on the user's emotions.

[0427] "Means of collecting information" refers to devices or software that acquire data from social networking services or news sites.

[0428] "Means for evaluating credibility" refers to devices or software that use algorithms to determine the accuracy and reliability of collected information.

[0429] "Means for generating news content" refers to devices or software that use generative AI models to automatically create news articles and content based on selected information.

[0430] "Classification means" refers to a device or software that performs the process of dividing generated news content into specific categories.

[0431] "Means of predicting future events" refers to devices or software that execute algorithms to predict future events based on collected and analyzed data.

[0432] "Means of distribution" refers to networks and communication devices for delivering generated and categorized news content to users.

[0433] "Means for recognizing a user's emotional state" refers to devices or software that use emotion engines or sensors to acquire user input and responses and analyze their psychological state based on that information.

[0434] "Means of customization" refers to devices or software that perform a process to adjust the content of news content delivered in accordance with the recognized emotions of the user.

[0435] The system for implementing this invention consists of a server, a terminal, and a user. The server is responsible for collecting information, evaluating its credibility, and generating news content. Specifically, the server collects information from news sites and social networking services. It applies a credibility evaluation algorithm to the collected information to determine its credibility. The selected data is automatically generated as news content using a generative AI model and classified into specific categories. Furthermore, the server applies a future prediction algorithm to predict future events and integrates the results into the news content.

[0436] The server uses an emotion engine to analyze the user's psychological state. By analyzing user input and feedback, the server customizes the news content it delivers to match the user's emotions based on the resulting emotion data. For this purpose, it uses the "Microsoft Azure Emotion API" as an emotion recognition library. It also utilizes "OpenAI GPT-4" as a generative AI model.

[0437] Meanwhile, the device has the function of displaying received news content through a user interface. The device is equipped with a camera, microphone, and biometric sensors, which are used to acquire the user's facial expressions, voice, and even heart rate in real time. Based on this, an emotion engine evaluates the user's emotions and selects appropriate content to notify them.

[0438] For example, if the emotion engine detects stress in a user while they are browsing the news using smart glasses during their commute, the system will prioritize delivering articles and videos that promote relaxation. An example of a prompt in this case might be: "Generate entertainment news for when the user is relaxed. Include positive content while incorporating a unique perspective that will capture the user's attention. Examples: recent movie releases or lighthearted topics."

[0439] Users view news content provided through their devices, and their reactions and feedback are analyzed again by the sentiment engine and used to customize future content delivery. Through this process, a more personalized and valuable information experience is realized for users.

[0440] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0441] Step 1:

[0442] The server collects information from social networking services and news sites. It uses various data sources on the internet as input, obtaining the latest information using APIs and scraping techniques. The output is a set of collected raw data.

[0443] Step 2:

[0444] The server evaluates the credibility of the collected information. Using the raw data obtained in Step 1 as input, it applies a reliability evaluation algorithm (e.g., analysis based on data source and past content performance). The output is data that has been evaluated and selected based on its reliability.

[0445] Step 3:

[0446] The server generates news content using a generative AI model based on highly reliable data. The input consists of the filtered data from step 2 and prompts applied to the generative AI model. A news article is generated using the generative AI model (e.g., OpenAI GPT-4), and the output is automatically generated news content.

[0447] Step 4:

[0448] The server categorizes the generated news content. Using the news content generated in step 3 as input, it performs content-based categorization using natural language processing techniques. The output is the news content categorized.

[0449] Step 5:

[0450] The server recognizes the user's emotional state through an emotion engine. It uses user feedback and real-time biometric data (e.g., camera images and audio data) as input. An emotion recognition model (e.g., Microsoft Azure Emotion API) is used to determine the user's psychological state, and the user's emotional data is obtained as output.

[0451] Step 6:

[0452] The server customizes news content based on the user's sentiment data. It uses the sentiment data obtained in step 5 and the news content classified in step 4 as input. A customization algorithm is applied to select content relevant to the user, resulting in customized content as output.

[0453] Step 7:

[0454] The terminal displays customized news content sent from the server in its user interface. It receives the customized content obtained in step 6 as input. As output, user-optimized content is displayed on the terminal, providing an experience tailored to the user's interests and emotions.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] [Third Embodiment]

[0459] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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".

[0471] The information distribution system of the present invention is implemented using a combination of a server, a terminal, and a user. The server is responsible for collecting, evaluating, generating, classifying, and distributing information. Each element is described in detail below.

[0472] Server operation

[0473] The server collects information data in real time from external social networking services and news sites. The collected data is first organized and stored in a database. Then, the server applies AI algorithms to analyze the credibility of the collected data. In this process, metrics such as the reliability of the information source, the degree of consistency with past data, and the volume of posts are used.

[0474] Information whose credibility has been assessed is automatically converted into news articles using generative AI. The generated news articles are categorized into predefined categories (e.g., politics, economics, sports, etc.). Furthermore, the server predicts future events based on past trends and current information, and adds this predictive information to the news articles.

[0475] Terminal operation

[0476] The device delivers news articles and forecast information received from the server to the user. The device displays the received content in a user-friendly interface and immediately notifies the user via push notifications or other means as needed.

[0477] User actions

[0478] Users can view news articles displayed on their devices and utilize predictive information to aid in risk management and strategy development. They can also research news and predictions that interest them in more detail, enjoying rapid access to information.

[0479] Specific example

[0480] For example, if a disaster occurs in a certain area, the server immediately collects relevant information, analyzes its credibility, and instantly generates an article. The generated article includes not only the current situation but also future risk information predicted by AI. The terminal receives this and notifies the user, enabling the provision of fast and reliable information.

[0481] Through the above, this system provides a new form of information distribution that balances information reliability and speed. As a result, users can always obtain reliable and up-to-date information, which will support them in making appropriate decisions.

[0482] The following describes the processing flow.

[0483] Step 1:

[0484] The server collects information related to specific keywords and hashtags in real time from social networking services and news websites. This information is obtained using APIs or web scraping techniques and stored in a database.

[0485] Step 2:

[0486] The server analyzes the metadata of the collected data and evaluates the credibility of the information. Here, a credibility score is calculated based on the reliability of the source, the frequency and number of shares of posts, and past performance.

[0487] Step 3:

[0488] The server filters out information whose credibility score exceeds a certain threshold and provides the selected information to a natural language generation model. This model is then used to automatically generate news articles based on the information.

[0489] Step 4:

[0490] The server categorizes the generated news articles (e.g., politics, economics, sports). A text classification algorithm based on content analysis of the articles is used for this classification.

[0491] Step 5:

[0492] The server runs a future prediction model based on historical data and current trends to predict specific future events. The prediction results are added to the news article.

[0493] Step 6:

[0494] The server sends the final news articles and forecast information to the terminal, allowing the user to access the latest information.

[0495] Step 7:

[0496] The terminal displays news articles and forecast information received from the server in a user interface. The terminal uses a notification function as needed to inform the user of important information.

[0497] Step 8:

[0498] Users can view news articles provided through their devices and check forecast information to help them make informed decisions and judgments.

[0499] (Example 1)

[0500] 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."

[0501] In modern society, the volume and speed of information continue to increase, making it crucial to quickly collect, analyze, and deliver reliable information to users. However, existing information systems have been insufficient in evaluating data reliability and adding predictive information, limiting their ability to support users' informed decision-making. Therefore, there is a growing demand for information that is more reliable and predicts future trends.

[0502] 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.

[0503] In this invention, the server includes means for acquiring information from an information medium, means for analyzing the stored information and evaluating its reliability, and means for estimating future events using time-series analysis. This enables the rapid storage and analysis of highly reliable information, and the provision of information with a view to the future.

[0504] "Information media" refers to a general term for external online platforms and websites used to obtain information.

[0505] "Means of acquiring information" refers to the methods and processes used to collect data from information media, and typically includes APIs and web scraping techniques.

[0506] "Means of storage" refers to the process used to organize and save acquired data, and includes the use of database management systems.

[0507] "Means of evaluating reliability" refers to algorithms and methods used to analyze accumulated data and determine the truthfulness and reliability of that information.

[0508] "Means of generating documents" refers to technologies and processes for automatically creating new information content or articles based on analysis results.

[0509] "Methods for classifying by category" refers to the process of organizing and classifying generated documents based on their content and theme.

[0510] "Means of estimating future events using time series analysis" refers to techniques and methods for analyzing past data and predicting events that may occur in the future based on that analysis.

[0511] "Means of distribution" refers to the processes and technologies used to deliver generated and classified information to end users, typically utilizing network communication methods.

[0512] A "computer terminal" refers to an electronic device used to receive and display information, and includes personal computers and smart devices.

[0513] "Methods for organizing data by criteria" refers to the process of filtering collected data based on specific standards or conditions to extract only the necessary information.

[0514] This invention relates to an advanced information distribution system that collects, analyzes, generates, and distributes information. The specific implementation methods for each component are described below.

[0515] First, the server has the means to retrieve information from information sources. Specifically, it uses Python or other programming languages ​​to make API requests and collect data from social networks and news sites. This data is received in JSON format and organized and stored in a database system (e.g., MySQL or PostgreSQL). This accumulation process makes searching and analysis more efficient.

[0516] Next, the server applies AI algorithms and machine learning techniques to analyze the accumulated information and evaluate its reliability. The analysis utilizes the scikit-learn library in Python to score the data's credibility based on its correlation with past data and the reliability of its information sources.

[0517] Based on the analyzed information, the server automatically generates documents using a natural language generation AI model (generative AI). The generative AI model utilizes a large-scale language model API and creates news articles and informational content using prompts. For example, it might use the prompt, "Please create a reliable news article based on the current economic situation."

[0518] Furthermore, the server uses a natural language processing library (e.g., spaCy) to categorize the generated documents. This classification organizes the documents thematically, improving the relevance of the information provided to the user.

[0519] To provide predictive information, the server performs time series analysis to estimate future events. Using analysis libraries such as Prophet, it predicts future trends from historical data, providing users with insights into future developments.

[0520] The device receives documents and forecast information delivered from the server and provides this information to the user. The device interface is designed to be user-friendly and intuitive to operate using React and Flutter. In addition, it sends real-time push notifications for important information to provide users with quick updates.

[0521] Users can view information displayed on their devices and make appropriate decisions based on reliable articles and predictive data. Users can also access detailed information to conduct further research based on the provided information.

[0522] This system ensures the reliability and speed of information, supporting users in taking action based on accurate information.

[0523] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0524] Step 1:

[0525] The server retrieves information from various sources. This involves sending API requests and extracting data from social networks and news sites. The input is external API endpoint information, and the output is received data in JSON format. This data is extracted via the Python requests library and forms the basis for proceeding to the next stage. Specifically, the server automatically executes API requests at regularly scheduled time intervals.

[0526] Step 2:

[0527] The server stores the acquired information in a database. This includes methods for storing structured data using a database management system. The input is the JSON data acquired in step 1, and the output is the normalized information stored in the database. This process uses SQL queries to organize the data and create indexes, improving subsequent search efficiency.

[0528] Step 3:

[0529] The server evaluates the reliability of the accumulated information. An AI algorithm is used to calculate a reliability score for the input data. The input is information stored in a database, and the output is the reliability score assigned to each piece of information. Specifically, the scikit-learn library in Python is used to compare and evaluate the data against historical data to determine whether a certain score criterion is met.

[0530] Step 4:

[0531] The server generates documents based on highly reliable information. Using a generative AI model, it takes pre-evaluated reliability information as input and automatically generates documents as output. Specifically, the generative AI API is called with the prompt "Please create a highly reliable news article based on the current economic situation" to generate a news article.

[0532] Step 5:

[0533] The server categorizes the generated documents. Using natural language processing technology, it analyzes the input generated documents and obtains the categorized documents as output. By using the spaCy library to identify the content of the documents and classify them into predetermined categories, it enables the provision of highly relevant information.

[0534] Step 6:

[0535] The server estimates future events through time series analysis. Predictive analysis is performed on historical data. The input is historical data from a database, and the output is predicted future trend information. Predictive analysis from time series data is performed using the Prophet library.

[0536] Step 7:

[0537] The device receives information that is ready for delivery and notifies the user. The input is categorized and predictively annotated documents sent from the server, and the output is the article displayed to the user and a push notification. Specifically, when the device app receives a new article, it displays it using an interface built with React or Flutter and immediately sends a notification via Firebase Cloud Messaging.

[0538] Step 8:

[0539] Users view and utilize information on their devices. Input is news articles displayed on the device, and output is information that influences the user's decision-making and actions. Users can satisfy their needs by reviewing article details and pursuing additional information as needed.

[0540] (Application Example 1)

[0541] 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."

[0542] In modern society, the sheer volume of information and the difficulty in discerning its veracity create a need for systems that can quickly provide users with highly reliable information and support useful decision-making. However, existing systems have the challenge of not being able to adequately meet the individual needs of users in terms of information collection, classification, and distribution.

[0543] 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.

[0544] In this invention, the server includes a device for collecting information, a device for evaluating the reliability of the collected data, and a device for generating news content based on the evaluation results. This makes it possible to quickly collect highly reliable information and efficiently deliver it in a way that matches the individual needs of users.

[0545] A "device for collecting information" is a device designed to efficiently acquire various types of information from external data sources.

[0546] A "device for evaluating the reliability of collected data" is a device designed to determine the accuracy and reliability of acquired information.

[0547] A "device for generating news content based on evaluation results" is a device that automatically creates appropriate news articles based on reliability evaluations.

[0548] A "device for classifying generated news content" is a device for organizing and classifying created news articles by theme or category.

[0549] A "device for predicting potential future events" is a device that uses current information to infer future events.

[0550] A "device for supplying news content including prediction results" is a device that provides users with news content that incorporates prediction information.

[0551] A "device for customizing information based on user location or interests" is a device that personalizes information according to the user's location and interests, and adjusts news content to meet individual needs.

[0552] To realize this invention, it is first necessary to implement a program for collecting information on a server. This server will acquire information in real time from external data sources and organize and store it in a database. The software used will be a Python-based server application, and by utilizing a framework such as Flask, information can be managed efficiently.

[0553] Next, to evaluate the reliability of the collected data, AI algorithms are used. Machine learning libraries such as TensorFlow and PyTorch are used to analyze the reliability of the information sources and generate reliability scores. This process utilizes historical data and reliability evaluation criteria stored in the database.

[0554] In the stage of generating news content based on evaluation results, a generation AI model is installed on the server and natural language processing technology is utilized. This automatically generates news articles from the collected data and further classifies those articles by theme.

[0555] The generated news articles are delivered to the user's device. Here, a program is executed to customize the information based on the user's location and past history. Users can instantly receive specific local information and news of interest via push notifications on devices such as smartphones.

[0556] For example, a user traveling to a specific city could be provided with real-time weather forecasts, event information, and breaking news for that area. The generation AI could use prompts like the following: "Generate the latest news related to the area indicated by the user's location, evaluate its reliability, and classify it. Prepare appropriate notifications for the user and provide information in a way that recommends content based on their interests for future visits." This prompt makes it possible to provide useful information to the user.

[0557] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0558] Step 1:

[0559] The server collects information from external data sources. Input is raw data obtained through news APIs and social networking service APIs, while output is organized information in a database. Specifically, the server accesses each API endpoint, retrieves data using specified query parameters, and stores it in the database.

[0560] Step 2:

[0561] The server evaluates the reliability of the collected data. The input is raw data retrieved from a database, and the output is a reliability score for each data point. Specifically, the server applies a machine learning algorithm to generate a score based on the historical reliability and posting frequency of the information source.

[0562] Step 3:

[0563] The server generates news content based on the evaluation results. The input is data with reliability scores, and the output is the generated news article. Here, a generative AI model is used to perform natural language generation for each data point and apply prompt sentences to create the article. Specifically, the generative AI is sent the prompt, "Generate the latest news, evaluate its reliability, and then classify it."

[0564] Step 4:

[0565] The server classifies the generated news articles. The input is the generated news articles, and the output is articles classified by theme. Specifically, natural language processing technology is used to automatically classify the articles into categories such as politics, economics, and sports.

[0566] Step 5:

[0567] The server customizes information based on the user's location or interests. Input consists of categorized articles and user profile information, while output is a customized news feed. Specifically, it considers the user's past browsing history and current location to select the most relevant content.

[0568] Step 6:

[0569] The device receives customized information from the server and generates push notifications. The input is a customized news feed, and the output is the article information that is notified to the user. Specifically, when the device receives new information, it automatically displays a notification in the regular notification center, allowing the user to check it immediately.

[0570] Step 7:

[0571] Users view articles based on notifications from their devices and then research information that interests them further. The input is the news article displayed on the device, and the output is the acquisition of more detailed information. Specifically, when the user clicks on an article link, rich content is displayed.

[0572] 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.

[0573] The information distribution system of the present invention includes a combination of server, terminal, and user, as well as a function that includes an emotion engine for recognizing the user's emotions. The server is involved in information collection, evaluation, news generation, classification, future prediction, and distribution.

[0574] Server operation

[0575] The server collects information from social networking services and news sites. The collected information is then evaluated for credibility using a reliability rating algorithm. The selected information is automatically generated as news articles using a generative AI model and categorized. The server also analyzes data to predict future events and integrates these predictions into the news articles.

[0576] Furthermore, the server utilizes an emotion engine to understand the user's psychological state when news articles are delivered. The emotion engine recognizes emotions based on user input and responses, and uses this to customize the content of the news articles delivered and adjust the delivery frequency, thereby improving the user experience.

[0577] Terminal operation

[0578] The device displays received news articles and forecast information through its user interface. Furthermore, based on data from its emotion engine, the device selectively notifies users of information tailored to their interests and emotions. This feature ensures that the most relevant information is delivered to the user.

[0579] User actions

[0580] Users view news articles provided via their devices and check predictive information. Furthermore, user reactions and feedback are collected as sentiment data by an emotion engine, which is then reflected in future article deliveries.

[0581] Specific example

[0582] For example, when a user is notified of a news item, the emotion engine analyzes the user's facial expressions and behavior to determine their reaction. If it determines that the user is experiencing stress, the server can adjust the content of future news delivered to that user, reducing its impact and prioritizing information that brings joy and reassurance.

[0583] The system of the present invention allows users to not only collect information but also enjoy customized information tailored to their individual emotional state, thereby obtaining a more personal and valuable information experience.

[0584] The following describes the processing flow.

[0585] Step 1:

[0586] The server collects information related to specific keywords in real time from social networking services and news sites. The information is obtained using external APIs or web scraping techniques and stored in a database.

[0587] Step 2:

[0588] The server runs an algorithm that considers the reliability of the source, posting frequency, and past performance to evaluate the credibility of the collected information. The evaluated information is assigned a credibility score.

[0589] Step 3:

[0590] The server filters information whose credibility score exceeds a threshold and automatically generates news articles using a natural language generation model.

[0591] Step 4:

[0592] The server classifies the generated news articles into categories (politics, economics, sports, etc.) using a text analysis algorithm.

[0593] Step 5:

[0594] The server runs a future prediction model based on historical trend data and current information to forecast highly probable future events. The predictions are then integrated into news articles.

[0595] Step 6:

[0596] The server analyzes the user's emotional data via an emotion engine and adjusts the content of news articles based on the emotional information obtained. For example, if the user is feeling stressed, it prioritizes relaxing content.

[0597] Step 7:

[0598] The device displays customized news articles and forecast information sent from the server to the user. It also uses push notifications to inform the user of important information at appropriate times.

[0599] Step 8:

[0600] Users can view news articles provided on their devices and explore further details about information they find interesting. User reactions and interactions are analyzed by an emotion engine to improve future information delivery.

[0601] Through these steps, users can receive information tailored to their emotional state in real time, resulting in a more personalized experience.

[0602] (Example 2)

[0603] 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."

[0604] In modern society, efficiently collecting highly reliable information from a vast amount of data and providing it in an appropriate format tailored to the user's psychological state is difficult. Furthermore, in order to flexibly respond to the diversifying information needs of users, information customization is required, but conventional systems lack the means to effectively achieve this.

[0605] 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.

[0606] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for generating news articles using a generative AI model. This makes it possible to provide highly reliable news articles that are tailored to the individual emotional state of each user.

[0607] "Means of collecting information" refers to functions and methods for obtaining data from various information sources on the internet.

[0608] "Means of evaluating credibility" refers to algorithms and criteria used to determine the truthfulness and reliability of collected information.

[0609] "Methods for generating news articles using generative AI models" refers to methods that use artificial intelligence to automatically generate article-formatted text based on collected data.

[0610] "Means for classifying news articles" refers to functions that divide generated articles into categories based on their content and theme.

[0611] "Methods for predicting future events" refer to methods that use data analysis and statistical models to anticipate future events and trends.

[0612] "Methods for customizing and delivering news articles based on emotional data" refers to methods for analyzing the psychological state of individual users and adjusting the content and delivery frequency of news articles to suit their needs.

[0613] "Means of analyzing and notifying users of their emotional data" refers to a function that judges the user's reactions and emotions and transmits appropriate information based on the results.

[0614] "Means of filtering information" refers to the process of selecting highly relevant data from collected information and excluding irrelevant or inappropriate data.

[0615] "Utilizing an emotion engine" refers to software technology that analyzes user emotions and adjusts information provision and user experience based on those analyses.

[0616] The information distribution system of the present invention operates primarily based on the interaction between a server, a terminal, and a user. Specific embodiments thereof are shown below.

[0617] The server has the capability to collect data from various sources on the internet. This is done using APIs and web scraping techniques, and the obtained data is stored in a database. The collected information is analyzed by an algorithm that evaluates its credibility, and only highly reliable information is extracted. This evaluation is based on the reliability of the source and the consistency of the information.

[0618] Next, a generative AI model is used to automatically generate news articles from reliable information. This AI model is an existing general-purpose model for natural language processing. An example of a prompt used in this process is: "Based on the following information, please generate a positive and reassuring news article. We want to include positive topics because this news may be stressful for users."

[0619] The generated news articles are categorized by the server based on their content. For example, categories such as sports, politics, and technology are considered. Furthermore, the server uses data analysis and statistical methods to predict future events. This involves trend analysis of historical data and machine learning algorithms.

[0620] Furthermore, the server is equipped with an emotion engine that analyzes the user's psychological state. The emotion engine analyzes data obtained from the user's device (e.g., browsing history and feedback) to determine their psychological state. Based on this information, news articles are customized and their delivery frequency is adjusted to provide a more personalized user experience.

[0621] The device has the functionality to display customized articles sent from the server on the user interface. The timing of information notifications can be adjusted according to the user's usage patterns. This allows users to receive the information they are most interested in at the optimal time.

[0622] Users view news articles provided via their devices and provide feedback as needed. This feedback is collected on the server and used to improve future information delivery. For example, positive feedback from users will guide the system in prioritizing notifications for articles in similar categories.

[0623] Thus, the system of the present invention provides a highly personalized information experience by collecting, generating, and distributing information that meets the individual needs of the user.

[0624] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0625] Step 1:

[0626] The server collects data from information sources on the internet. Specifically, it uses various APIs and web scraping techniques to collect data from news sites and social media. The input for this process is specific keywords or information categories, and the output is the retrieved raw data. The server automatically stores this data in a database.

[0627] Step 2:

[0628] The server evaluates the credibility of the collected information. The input is the raw data collected in step 1, and the output is the data whose credibility has been evaluated. Specifically, it analyzes the reliability of the information source and its degree of consistency with past data, and applies an algorithm to eliminate uncertain information. In this process, the evaluation points of the information source are scored, and only data whose score exceeds a certain standard is passed on to the next step.

[0629] Step 3:

[0630] The server uses a generative AI model with highly reliable information to create news articles. The input is reliable data, and the output is a news article written in natural language. The generative AI model is given easily recognizable prompts, such as "Create a positive news article based on facts." As a result, the AI ​​automatically generates the text of the news article.

[0631] Step 4:

[0632] The server categorizes the generated news articles. The input is the generated news articles, and the output is the categorized news articles. Specifically, it analyzes the content of the articles and applies natural language processing techniques to determine categories such as sports, politics, and technology.

[0633] Step 5:

[0634] The server performs data analysis and predicts future events. The input consists of historical data and data based on current trends, while the output is the predicted future events. Statistical methods and machine learning algorithms are used to predict potential future occurrences, and this information is incorporated into news articles.

[0635] Step 6:

[0636] The server uses an emotion engine to analyze user sentiment data and customize news articles. Input is the user's past browsing history and reaction data, and output is a customized news article. By analyzing sentiment data, it becomes possible to recommend news articles tailored to each user's psychological state.

[0637] Step 7:

[0638] The device delivers customized news articles to the user. The input is news articles sent from the server, and the output is information displayed in the user interface. The user interface adjusts the timing of information notifications based on the user's interests and activities to provide an optimal experience.

[0639] Step 8:

[0640] Users view the delivered news articles and provide feedback. The input is the news articles received through their devices, and the output is the user's reactions and evaluations. The feedback received is collected by the server and used to improve future information distribution. Feedback may be provided in the form of explicit "likes" or comments, or it may be collected through implicit activity such as viewing time and click frequency.

[0641] (Application Example 2)

[0642] 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."

[0643] Traditional information distribution systems delivered uniform content without considering the user's psychological state, making it difficult to provide information tailored to the user's interests and emotions. As a result, the user experience deteriorated, and the system failed to provide sufficient information value.

[0644] 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.

[0645] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for recognizing the user's emotional state. This enables the delivery of customized news content based on the user's emotions.

[0646] "Means of collecting information" refers to devices or software that acquire data from social networking services or news sites.

[0647] "Means for evaluating credibility" refers to devices or software that use algorithms to determine the accuracy and reliability of collected information.

[0648] "Means for generating news content" refers to devices or software that use generative AI models to automatically create news articles and content based on selected information.

[0649] "Classification means" refers to a device or software that performs the process of dividing generated news content into specific categories.

[0650] "Means of predicting future events" refers to devices or software that execute algorithms to predict future events based on collected and analyzed data.

[0651] "Means of distribution" refers to networks and communication devices for delivering generated and categorized news content to users.

[0652] "Means for recognizing a user's emotional state" refers to devices or software that use emotion engines or sensors to acquire user input and responses and analyze their psychological state based on that information.

[0653] "Means of customization" refers to devices or software that perform a process to adjust the content of news content delivered in accordance with the recognized emotions of the user.

[0654] The system for implementing this invention consists of a server, a terminal, and a user. The server is responsible for collecting information, evaluating its credibility, and generating news content. Specifically, the server collects information from news sites and social networking services. It applies a credibility evaluation algorithm to the collected information to determine its credibility. The selected data is automatically generated as news content using a generative AI model and classified into specific categories. Furthermore, the server applies a future prediction algorithm to predict future events and integrates the results into the news content.

[0655] The server uses an emotion engine to analyze the user's psychological state. By analyzing user input and feedback, the server customizes the news content it delivers to match the user's emotions based on the resulting emotion data. For this purpose, it uses the "Microsoft Azure Emotion API" as an emotion recognition library. It also utilizes "OpenAI GPT-4" as a generative AI model.

[0656] Meanwhile, the device has the function of displaying received news content through a user interface. The device is equipped with a camera, microphone, and biometric sensors, which are used to acquire the user's facial expressions, voice, and even heart rate in real time. Based on this, an emotion engine evaluates the user's emotions and selects appropriate content to notify them.

[0657] For example, if the emotion engine detects stress in a user while they are browsing the news using smart glasses during their commute, the system will prioritize delivering articles and videos that promote relaxation. An example of a prompt in this case might be: "Generate entertainment news for when the user is relaxed. Include positive content while incorporating a unique perspective that will capture the user's attention. Examples: recent movie releases or lighthearted topics."

[0658] Users view news content provided through their devices, and their reactions and feedback are analyzed again by the sentiment engine and used to customize future content delivery. Through this process, a more personalized and valuable information experience is realized for users.

[0659] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0660] Step 1:

[0661] The server collects information from social networking services and news sites. It uses various data sources on the internet as input, obtaining the latest information using APIs and scraping techniques. The output is a set of collected raw data.

[0662] Step 2:

[0663] The server evaluates the credibility of the collected information. Using the raw data obtained in Step 1 as input, it applies a reliability evaluation algorithm (e.g., analysis based on data source and past content performance). The output is data that has been evaluated and selected based on its reliability.

[0664] Step 3:

[0665] The server generates news content using a generative AI model based on highly reliable data. The input consists of the filtered data from step 2 and prompts applied to the generative AI model. A news article is generated using the generative AI model (e.g., OpenAI GPT-4), and the output is automatically generated news content.

[0666] Step 4:

[0667] The server categorizes the generated news content. Using the news content generated in step 3 as input, it performs content-based categorization using natural language processing techniques. The output is the news content categorized.

[0668] Step 5:

[0669] The server recognizes the user's emotional state through an emotion engine. It uses user feedback and real-time biometric data (e.g., camera images and audio data) as input. An emotion recognition model (e.g., Microsoft Azure Emotion API) is used to determine the user's psychological state, and the user's emotional data is obtained as output.

[0670] Step 6:

[0671] The server customizes news content based on the user's sentiment data. It uses the sentiment data obtained in step 5 and the news content classified in step 4 as input. A customization algorithm is applied to select content relevant to the user, resulting in customized content as output.

[0672] Step 7:

[0673] The terminal displays customized news content sent from the server in its user interface. It receives the customized content obtained in step 6 as input. As output, user-optimized content is displayed on the terminal, providing an experience tailored to the user's interests and emotions.

[0674] 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.

[0675] 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.

[0676] 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.

[0677] [Fourth Embodiment]

[0678] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0679] 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.

[0680] 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).

[0681] 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.

[0682] 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.

[0683] 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).

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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".

[0691] The information distribution system of the present invention is implemented using a combination of a server, a terminal, and a user. The server is responsible for collecting, evaluating, generating, classifying, and distributing information. Each element is described in detail below.

[0692] Server operation

[0693] The server collects information data in real time from external social networking services and news sites. The collected data is first organized and stored in a database. Then, the server applies AI algorithms to analyze the credibility of the collected data. In this process, metrics such as the reliability of the information source, the degree of consistency with past data, and the volume of posts are used.

[0694] Information whose credibility has been assessed is automatically converted into news articles using generative AI. The generated news articles are categorized into predefined categories (e.g., politics, economics, sports, etc.). Furthermore, the server predicts future events based on past trends and current information, and adds this predictive information to the news articles.

[0695] Terminal operation

[0696] The device delivers news articles and forecast information received from the server to the user. The device displays the received content in a user-friendly interface and immediately notifies the user via push notifications or other means as needed.

[0697] User actions

[0698] Users can view news articles displayed on their devices and utilize predictive information to aid in risk management and strategy development. They can also research news and predictions that interest them in more detail, enjoying rapid access to information.

[0699] Specific example

[0700] For example, if a disaster occurs in a certain area, the server immediately collects relevant information, analyzes its credibility, and instantly generates an article. The generated article includes not only the current situation but also future risk information predicted by AI. The terminal receives this and notifies the user, enabling the provision of fast and reliable information.

[0701] Through the above, this system provides a new form of information distribution that balances information reliability and speed. As a result, users can always obtain reliable and up-to-date information, which will support them in making appropriate decisions.

[0702] The following describes the processing flow.

[0703] Step 1:

[0704] The server collects information related to specific keywords and hashtags in real time from social networking services and news websites. This information is obtained using APIs or web scraping techniques and stored in a database.

[0705] Step 2:

[0706] The server analyzes the metadata of the collected data and evaluates the credibility of the information. Here, a credibility score is calculated based on the reliability of the source, the frequency and number of shares of posts, and past performance.

[0707] Step 3:

[0708] The server filters out information whose credibility score exceeds a certain threshold and provides the selected information to a natural language generation model. This model is then used to automatically generate news articles based on the information.

[0709] Step 4:

[0710] The server categorizes the generated news articles (e.g., politics, economics, sports). A text classification algorithm based on content analysis of the articles is used for this classification.

[0711] Step 5:

[0712] The server runs a future prediction model based on historical data and current trends to predict specific future events. The prediction results are added to the news article.

[0713] Step 6:

[0714] The server sends the final news articles and forecast information to the terminal, allowing the user to access the latest information.

[0715] Step 7:

[0716] The terminal displays news articles and forecast information received from the server in a user interface. The terminal uses a notification function as needed to inform the user of important information.

[0717] Step 8:

[0718] Users can view news articles provided through their devices and check forecast information to help them make informed decisions and judgments.

[0719] (Example 1)

[0720] 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".

[0721] In modern society, the volume and speed of information continue to increase, making it crucial to quickly collect, analyze, and deliver reliable information to users. However, existing information systems have been insufficient in evaluating data reliability and adding predictive information, limiting their ability to support users' informed decision-making. Therefore, there is a growing demand for information that is more reliable and predicts future trends.

[0722] 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.

[0723] In this invention, the server includes means for acquiring information from an information medium, means for analyzing the stored information and evaluating its reliability, and means for estimating future events using time-series analysis. This enables the rapid storage and analysis of highly reliable information, and the provision of information with a view to the future.

[0724] "Information media" refers to a general term for external online platforms and websites used to obtain information.

[0725] "Means of acquiring information" refers to the methods and processes used to collect data from information media, and typically includes APIs and web scraping techniques.

[0726] "Means of storage" refers to the process used to organize and save acquired data, and includes the use of database management systems.

[0727] "Means of evaluating reliability" refers to algorithms and methods used to analyze accumulated data and determine the truthfulness and reliability of that information.

[0728] "Means of generating documents" refers to technologies and processes for automatically creating new information content or articles based on analysis results.

[0729] "Methods for classifying by category" refers to the process of organizing and classifying generated documents based on their content and theme.

[0730] "Means of estimating future events using time series analysis" refers to techniques and methods for analyzing past data and predicting events that may occur in the future based on that analysis.

[0731] "Means of distribution" refers to the processes and technologies used to deliver generated and classified information to end users, typically utilizing network communication methods.

[0732] A "computer terminal" refers to an electronic device used to receive and display information, and includes personal computers and smart devices.

[0733] "Methods for organizing data by criteria" refers to the process of filtering collected data based on specific standards or conditions to extract only the necessary information.

[0734] This invention relates to an advanced information distribution system that collects, analyzes, generates, and distributes information. The specific implementation methods for each component are described below.

[0735] First, the server has the means to retrieve information from information sources. Specifically, it uses Python or other programming languages ​​to make API requests and collect data from social networks and news sites. This data is received in JSON format and organized and stored in a database system (e.g., MySQL or PostgreSQL). This accumulation process makes searching and analysis more efficient.

[0736] Next, the server applies AI algorithms and machine learning techniques to analyze the accumulated information and evaluate its reliability. The analysis utilizes the scikit-learn library in Python to score the data's credibility based on its correlation with past data and the reliability of its information sources.

[0737] Based on the analyzed information, the server automatically generates documents using a natural language generation AI model (generative AI). The generative AI model utilizes a large-scale language model API and creates news articles and informational content using prompts. For example, it might use the prompt, "Please create a reliable news article based on the current economic situation."

[0738] Furthermore, the server uses a natural language processing library (e.g., spaCy) to categorize the generated documents. This classification organizes the documents thematically, improving the relevance of the information provided to the user.

[0739] To provide predictive information, the server performs time series analysis to estimate future events. Using analysis libraries such as Prophet, it predicts future trends from historical data, providing users with insights into future developments.

[0740] The device receives documents and forecast information delivered from the server and provides this information to the user. The device interface is designed to be user-friendly and intuitive to operate using React and Flutter. In addition, it sends real-time push notifications for important information to provide users with quick updates.

[0741] Users can view information displayed on their devices and make appropriate decisions based on reliable articles and predictive data. Users can also access detailed information to conduct further research based on the provided information.

[0742] This system ensures the reliability and speed of information, supporting users in taking action based on accurate information.

[0743] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0744] Step 1:

[0745] The server retrieves information from various sources. This involves sending API requests and extracting data from social networks and news sites. The input is external API endpoint information, and the output is received data in JSON format. This data is extracted via the Python requests library and forms the basis for proceeding to the next stage. Specifically, the server automatically executes API requests at regularly scheduled time intervals.

[0746] Step 2:

[0747] The server stores the acquired information in a database. This includes methods for storing structured data using a database management system. The input is the JSON data acquired in step 1, and the output is the normalized information stored in the database. This process uses SQL queries to organize the data and create indexes, improving subsequent search efficiency.

[0748] Step 3:

[0749] The server evaluates the reliability of the accumulated information. An AI algorithm is used to calculate a reliability score for the input data. The input is information stored in a database, and the output is the reliability score assigned to each piece of information. Specifically, the scikit-learn library in Python is used to compare and evaluate the data against historical data to determine whether a certain score criterion is met.

[0750] Step 4:

[0751] The server generates documents based on highly reliable information. Using a generative AI model, it takes pre-evaluated reliability information as input and automatically generates documents as output. Specifically, the generative AI API is called with the prompt "Please create a highly reliable news article based on the current economic situation" to generate a news article.

[0752] Step 5:

[0753] The server categorizes the generated documents. Using natural language processing technology, it analyzes the input generated documents and obtains the categorized documents as output. By using the spaCy library to identify the content of the documents and classify them into predetermined categories, it enables the provision of highly relevant information.

[0754] Step 6:

[0755] The server estimates future events through time series analysis. Predictive analysis is performed on historical data. The input is historical data from a database, and the output is predicted future trend information. Predictive analysis from time series data is performed using the Prophet library.

[0756] Step 7:

[0757] The device receives information that is ready for delivery and notifies the user. The input is categorized and predictively annotated documents sent from the server, and the output is the article displayed to the user and a push notification. Specifically, when the device app receives a new article, it displays it using an interface built with React or Flutter and immediately sends a notification via Firebase Cloud Messaging.

[0758] Step 8:

[0759] Users view and utilize information on their devices. Input is news articles displayed on the device, and output is information that influences the user's decision-making and actions. Users can satisfy their needs by reviewing article details and pursuing additional information as needed.

[0760] (Application Example 1)

[0761] 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".

[0762] In modern society, the sheer volume of information and the difficulty in discerning its veracity create a need for systems that can quickly provide users with highly reliable information and support useful decision-making. However, existing systems have the challenge of not being able to adequately meet the individual needs of users in terms of information collection, classification, and distribution.

[0763] 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.

[0764] In this invention, the server includes a device for collecting information, a device for evaluating the reliability of the collected data, and a device for generating news content based on the evaluation results. This makes it possible to quickly collect highly reliable information and efficiently deliver it in a way that matches the individual needs of users.

[0765] A "device for collecting information" is a device designed to efficiently acquire various types of information from external data sources.

[0766] A "device for evaluating the reliability of collected data" is a device designed to determine the accuracy and reliability of acquired information.

[0767] A "device for generating news content based on evaluation results" is a device that automatically creates appropriate news articles based on reliability evaluations.

[0768] A "device for classifying generated news content" is a device for organizing and classifying created news articles by theme or category.

[0769] A "device for predicting potential future events" is a device that uses current information to infer future events.

[0770] A "device for supplying news content including prediction results" is a device that provides users with news content that incorporates prediction information.

[0771] A "device for customizing information based on user location or interests" is a device that personalizes information according to the user's location and interests, and adjusts news content to meet individual needs.

[0772] To realize this invention, it is first necessary to implement a program for collecting information on a server. This server will acquire information in real time from external data sources and organize and store it in a database. The software used will be a Python-based server application, and by utilizing a framework such as Flask, information can be managed efficiently.

[0773] Next, to evaluate the reliability of the collected data, AI algorithms are used. Machine learning libraries such as TensorFlow and PyTorch are used to analyze the reliability of the information sources and generate reliability scores. This process utilizes historical data and reliability evaluation criteria stored in the database.

[0774] In the stage of generating news content based on evaluation results, a generation AI model is installed on the server and natural language processing technology is utilized. This automatically generates news articles from the collected data and further classifies those articles by theme.

[0775] The generated news articles are delivered to the user's device. Here, a program is executed to customize the information based on the user's location and past history. Users can instantly receive specific local information and news of interest via push notifications on devices such as smartphones.

[0776] For example, a user traveling to a specific city could be provided with real-time weather forecasts, event information, and breaking news for that area. The generation AI could use prompts like the following: "Generate the latest news related to the area indicated by the user's location, evaluate its reliability, and classify it. Prepare appropriate notifications for the user and provide information in a way that recommends content based on their interests for future visits." This prompt makes it possible to provide useful information to the user.

[0777] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0778] Step 1:

[0779] The server collects information from external data sources. Input is raw data obtained through news APIs and social networking service APIs, while output is organized information in a database. Specifically, the server accesses each API endpoint, retrieves data using specified query parameters, and stores it in the database.

[0780] Step 2:

[0781] The server evaluates the reliability of the collected data. The input is raw data retrieved from a database, and the output is a reliability score for each data point. Specifically, the server applies a machine learning algorithm to generate a score based on the historical reliability and posting frequency of the information source.

[0782] Step 3:

[0783] The server generates news content based on the evaluation results. The input is data with reliability scores, and the output is the generated news article. Here, a generative AI model is used to perform natural language generation for each data point and apply prompt sentences to create the article. Specifically, the generative AI is sent the prompt, "Generate the latest news, evaluate its reliability, and then classify it."

[0784] Step 4:

[0785] The server classifies the generated news articles. The input is the generated news articles, and the output is articles classified by theme. Specifically, natural language processing technology is used to automatically classify the articles into categories such as politics, economics, and sports.

[0786] Step 5:

[0787] The server customizes information based on the user's location or interests. Input consists of categorized articles and user profile information, while output is a customized news feed. Specifically, it considers the user's past browsing history and current location to select the most relevant content.

[0788] Step 6:

[0789] The device receives customized information from the server and generates push notifications. The input is a customized news feed, and the output is the article information that is notified to the user. Specifically, when the device receives new information, it automatically displays a notification in the regular notification center, allowing the user to check it immediately.

[0790] Step 7:

[0791] Users view articles based on notifications from their devices and then research information that interests them further. The input is the news article displayed on the device, and the output is the acquisition of more detailed information. Specifically, when the user clicks on an article link, rich content is displayed.

[0792] 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.

[0793] The information distribution system of the present invention includes a combination of server, terminal, and user, as well as a function that includes an emotion engine for recognizing the user's emotions. The server is involved in information collection, evaluation, news generation, classification, future prediction, and distribution.

[0794] Server operation

[0795] The server collects information from social networking services and news sites. The collected information is then evaluated for credibility using a reliability rating algorithm. The selected information is automatically generated as news articles using a generative AI model and categorized. The server also analyzes data to predict future events and integrates these predictions into the news articles.

[0796] Furthermore, the server utilizes an emotion engine to understand the user's psychological state when news articles are delivered. The emotion engine recognizes emotions based on user input and responses, and uses this to customize the content of the news articles delivered and adjust the delivery frequency, thereby improving the user experience.

[0797] Terminal operation

[0798] The device displays received news articles and forecast information through its user interface. Furthermore, based on data from its emotion engine, the device selectively notifies users of information tailored to their interests and emotions. This feature ensures that the most relevant information is delivered to the user.

[0799] User actions

[0800] Users view news articles provided via their devices and check predictive information. Furthermore, user reactions and feedback are collected as sentiment data by an emotion engine, which is then reflected in future article deliveries.

[0801] Specific example

[0802] For example, when a user is notified of a news item, the emotion engine analyzes the user's facial expressions and behavior to determine their reaction. If it determines that the user is experiencing stress, the server can adjust the content of future news delivered to that user, reducing its impact and prioritizing information that brings joy and reassurance.

[0803] The system of the present invention allows users to not only collect information but also enjoy customized information tailored to their individual emotional state, thereby obtaining a more personal and valuable information experience.

[0804] The following describes the processing flow.

[0805] Step 1:

[0806] The server collects information related to specific keywords in real time from social networking services and news sites. The information is obtained using external APIs or web scraping techniques and stored in a database.

[0807] Step 2:

[0808] The server runs an algorithm that considers the reliability of the source, posting frequency, and past performance to evaluate the credibility of the collected information. The evaluated information is assigned a credibility score.

[0809] Step 3:

[0810] The server filters information whose credibility score exceeds a threshold and automatically generates news articles using a natural language generation model.

[0811] Step 4:

[0812] The server classifies the generated news articles into categories (politics, economics, sports, etc.) using a text analysis algorithm.

[0813] Step 5:

[0814] The server runs a future prediction model based on historical trend data and current information to forecast highly probable future events. The predictions are then integrated into news articles.

[0815] Step 6:

[0816] The server analyzes the user's emotional data via an emotion engine and adjusts the content of news articles based on the emotional information obtained. For example, if the user is feeling stressed, it prioritizes relaxing content.

[0817] Step 7:

[0818] The device displays customized news articles and forecast information sent from the server to the user. It also uses push notifications to inform the user of important information at appropriate times.

[0819] Step 8:

[0820] Users can view news articles provided on their devices and explore further details about information they find interesting. User reactions and interactions are analyzed by an emotion engine to improve future information delivery.

[0821] Through these steps, users can receive information tailored to their emotional state in real time, resulting in a more personalized experience.

[0822] (Example 2)

[0823] 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".

[0824] In modern society, efficiently collecting highly reliable information from a vast amount of data and providing it in an appropriate format tailored to the user's psychological state is difficult. Furthermore, in order to flexibly respond to the diversifying information needs of users, information customization is required, but conventional systems lack the means to effectively achieve this.

[0825] 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.

[0826] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for generating news articles using a generative AI model. This makes it possible to provide highly reliable news articles that are tailored to the individual emotional state of each user.

[0827] "Means of collecting information" refers to functions and methods for obtaining data from various information sources on the internet.

[0828] "Means of evaluating credibility" refers to algorithms and criteria used to determine the truthfulness and reliability of collected information.

[0829] "Methods for generating news articles using generative AI models" refers to methods that use artificial intelligence to automatically generate article-formatted text based on collected data.

[0830] "Means for classifying news articles" refers to functions that divide generated articles into categories based on their content and theme.

[0831] "Methods for predicting future events" refer to methods that use data analysis and statistical models to anticipate future events and trends.

[0832] "Methods for customizing and delivering news articles based on emotional data" refers to methods for analyzing the psychological state of individual users and adjusting the content and delivery frequency of news articles to suit their needs.

[0833] "Means of analyzing and notifying users of their emotional data" refers to a function that judges the user's reactions and emotions and transmits appropriate information based on the results.

[0834] "Means of filtering information" refers to the process of selecting highly relevant data from collected information and excluding irrelevant or inappropriate data.

[0835] "Utilizing an emotion engine" refers to software technology that analyzes user emotions and adjusts information provision and user experience based on those analyses.

[0836] The information distribution system of the present invention operates primarily based on the interaction between a server, a terminal, and a user. Specific embodiments thereof are shown below.

[0837] The server has the capability to collect data from various sources on the internet. This is done using APIs and web scraping techniques, and the obtained data is stored in a database. The collected information is analyzed by an algorithm that evaluates its credibility, and only highly reliable information is extracted. This evaluation is based on the reliability of the source and the consistency of the information.

[0838] Next, a generative AI model is used to automatically generate news articles from reliable information. This AI model is an existing general-purpose model for natural language processing. An example of a prompt used in this process is: "Based on the following information, please generate a positive and reassuring news article. We want to include positive topics because this news may be stressful for users."

[0839] The generated news articles are categorized by the server based on their content. For example, categories such as sports, politics, and technology are considered. Furthermore, the server uses data analysis and statistical methods to predict future events. This involves trend analysis of historical data and machine learning algorithms.

[0840] Furthermore, the server is equipped with an emotion engine that analyzes the user's psychological state. The emotion engine analyzes data obtained from the user's device (e.g., browsing history and feedback) to determine their psychological state. Based on this information, news articles are customized and their delivery frequency is adjusted to provide a more personalized user experience.

[0841] The device has the functionality to display customized articles sent from the server on the user interface. The timing of information notifications can be adjusted according to the user's usage patterns. This allows users to receive the information they are most interested in at the optimal time.

[0842] Users view news articles provided via their devices and provide feedback as needed. This feedback is collected on the server and used to improve future information delivery. For example, positive feedback from users will guide the system in prioritizing notifications for articles in similar categories.

[0843] Thus, the system of the present invention provides a highly personalized information experience by collecting, generating, and distributing information that meets the individual needs of the user.

[0844] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0845] Step 1:

[0846] The server collects data from information sources on the internet. Specifically, it uses various APIs and web scraping techniques to collect data from news sites and social media. The input for this process is specific keywords or information categories, and the output is the retrieved raw data. The server automatically stores this data in a database.

[0847] Step 2:

[0848] The server evaluates the credibility of the collected information. The input is the raw data collected in step 1, and the output is the data whose credibility has been evaluated. Specifically, it analyzes the reliability of the information source and its degree of consistency with past data, and applies an algorithm to eliminate uncertain information. In this process, the evaluation points of the information source are scored, and only data whose score exceeds a certain standard is passed on to the next step.

[0849] Step 3:

[0850] The server uses a generative AI model with highly reliable information to create news articles. The input is reliable data, and the output is a news article written in natural language. The generative AI model is given easily recognizable prompts, such as "Create a positive news article based on facts." As a result, the AI ​​automatically generates the text of the news article.

[0851] Step 4:

[0852] The server categorizes the generated news articles. The input is the generated news articles, and the output is the categorized news articles. Specifically, it analyzes the content of the articles and applies natural language processing techniques to determine categories such as sports, politics, and technology.

[0853] Step 5:

[0854] The server performs data analysis and predicts future events. The input consists of historical data and data based on current trends, while the output is the predicted future events. Statistical methods and machine learning algorithms are used to predict potential future occurrences, and this information is incorporated into news articles.

[0855] Step 6:

[0856] The server uses an emotion engine to analyze user sentiment data and customize news articles. Input is the user's past browsing history and reaction data, and output is a customized news article. By analyzing sentiment data, it becomes possible to recommend news articles tailored to each user's psychological state.

[0857] Step 7:

[0858] The device delivers customized news articles to the user. The input is news articles sent from the server, and the output is information displayed in the user interface. The user interface adjusts the timing of information notifications based on the user's interests and activities to provide an optimal experience.

[0859] Step 8:

[0860] Users view the delivered news articles and provide feedback. The input is the news articles received through their devices, and the output is the user's reactions and evaluations. The feedback received is collected by the server and used to improve future information distribution. Feedback may be provided in the form of explicit "likes" or comments, or it may be collected through implicit activity such as viewing time and click frequency.

[0861] (Application Example 2)

[0862] 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".

[0863] Traditional information distribution systems delivered uniform content without considering the user's psychological state, making it difficult to provide information tailored to the user's interests and emotions. As a result, the user experience deteriorated, and the system failed to provide sufficient information value.

[0864] 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.

[0865] In this invention, the server includes means for collecting information, means for evaluating the credibility of the collected information, and means for recognizing the user's emotional state. This enables the delivery of customized news content based on the user's emotions.

[0866] "Means of collecting information" refers to devices or software that acquire data from social networking services or news sites.

[0867] "Means for evaluating credibility" refers to devices or software that use algorithms to determine the accuracy and reliability of collected information.

[0868] "Means for generating news content" refers to devices or software that use generative AI models to automatically create news articles and content based on selected information.

[0869] "Classification means" refers to a device or software that performs the process of dividing generated news content into specific categories.

[0870] "Means of predicting future events" refers to devices or software that execute algorithms to predict future events based on collected and analyzed data.

[0871] "Means of distribution" refers to networks and communication devices for delivering generated and categorized news content to users.

[0872] "Means for recognizing a user's emotional state" refers to devices or software that use emotion engines or sensors to acquire user input and responses and analyze their psychological state based on that information.

[0873] "Means of customization" refers to devices or software that perform a process to adjust the content of news content delivered in accordance with the recognized emotions of the user.

[0874] The system for implementing this invention consists of a server, a terminal, and a user. The server is responsible for collecting information, evaluating its credibility, and generating news content. Specifically, the server collects information from news sites and social networking services. It applies a credibility evaluation algorithm to the collected information to determine its credibility. The selected data is automatically generated as news content using a generative AI model and classified into specific categories. Furthermore, the server applies a future prediction algorithm to predict future events and integrates the results into the news content.

[0875] The server uses an emotion engine to analyze the user's psychological state. By analyzing user input and feedback, the server customizes the news content it delivers to match the user's emotions based on the resulting emotion data. For this purpose, it uses the "Microsoft Azure Emotion API" as an emotion recognition library. It also utilizes "OpenAI GPT-4" as a generative AI model.

[0876] Meanwhile, the device has the function of displaying received news content through a user interface. The device is equipped with a camera, microphone, and biometric sensors, which are used to acquire the user's facial expressions, voice, and even heart rate in real time. Based on this, an emotion engine evaluates the user's emotions and selects appropriate content to notify them.

[0877] For example, if the emotion engine detects stress in a user while they are browsing the news using smart glasses during their commute, the system will prioritize delivering articles and videos that promote relaxation. An example of a prompt in this case might be: "Generate entertainment news for when the user is relaxed. Include positive content while incorporating a unique perspective that will capture the user's attention. Examples: recent movie releases or lighthearted topics."

[0878] Users view news content provided through their devices, and their reactions and feedback are analyzed again by the sentiment engine and used to customize future content delivery. Through this process, a more personalized and valuable information experience is realized for users.

[0879] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0880] Step 1:

[0881] The server collects information from social networking services and news sites. It uses various data sources on the internet as input, obtaining the latest information using APIs and scraping techniques. The output is a set of collected raw data.

[0882] Step 2:

[0883] The server evaluates the credibility of the collected information. Using the raw data obtained in Step 1 as input, it applies a reliability evaluation algorithm (e.g., analysis based on data source and past content performance). The output is data that has been evaluated and selected based on its reliability.

[0884] Step 3:

[0885] The server generates news content using a generative AI model based on highly reliable data. The input consists of the filtered data from step 2 and prompts applied to the generative AI model. A news article is generated using the generative AI model (e.g., OpenAI GPT-4), and the output is automatically generated news content.

[0886] Step 4:

[0887] The server categorizes the generated news content. Using the news content generated in step 3 as input, it performs content-based categorization using natural language processing techniques. The output is the news content categorized.

[0888] Step 5:

[0889] The server recognizes the user's emotional state through an emotion engine. It uses user feedback and real-time biometric data (e.g., camera images and audio data) as input. An emotion recognition model (e.g., Microsoft Azure Emotion API) is used to determine the user's psychological state, and the user's emotional data is obtained as output.

[0890] Step 6:

[0891] The server customizes news content based on the user's sentiment data. It uses the sentiment data obtained in step 5 and the news content classified in step 4 as input. A customization algorithm is applied to select content relevant to the user, resulting in customized content as output.

[0892] Step 7:

[0893] The terminal displays customized news content sent from the server in its user interface. It receives the customized content obtained in step 6 as input. As output, user-optimized content is displayed on the terminal, providing an experience tailored to the user's interests and emotions.

[0894] 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.

[0895] 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.

[0896] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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."

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0915] The following is further disclosed regarding the embodiments described above.

[0916] (Claim 1)

[0917] Means of collecting information,

[0918] A means of evaluating the credibility of the collected information,

[0919] A means of generating news articles based on evaluation results,

[0920] A means of classifying the generated news articles,

[0921] Means of predicting future events,

[0922] A means of distributing news articles that include prediction results,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, comprising means for notifying the user's terminal of information.

[0926] (Claim 3)

[0927] The system according to claim 1, comprising means for filtering collected information.

[0928] "Example 1"

[0929] (Claim 1)

[0930] Means of obtaining information from information media,

[0931] A means of storing acquired information,

[0932] A means of analyzing accumulated information and evaluating its reliability,

[0933] Means for generating documents based on evaluation,

[0934] A means of classifying the generated documents by category,

[0935] A means of estimating future events using time series analysis,

[0936] A means for distributing documents containing estimation results,

[0937] A system that includes this.

[0938] (Claim 2)

[0939] The system according to claim 1, comprising means for notifying a computer terminal of a document.

[0940] (Claim 3)

[0941] The system according to claim 1, comprising means for organizing acquired information according to conditions.

[0942] "Application Example 1"

[0943] (Claim 1)

[0944] A device for collecting information,

[0945] A device for evaluating the reliability of collected data,

[0946] A device for generating news content based on evaluation results,

[0947] A device for classifying the generated news content,

[0948] A device for predicting events that may occur in the future,

[0949] A device for supplying news content including prediction results,

[0950] A device for customizing information based on the user's location information or interests,

[0951] A system that includes this.

[0952] (Claim 2)

[0953] The system according to claim 1, further comprising a device for notifying individual terminals of customized information.

[0954] (Claim 3)

[0955] The system according to claim 1, comprising a device for filtering collected information and generating push notifications.

[0956] "Example 2 of combining an emotion engine"

[0957] (Claim 1)

[0958] Means of collecting information,

[0959] A means of evaluating the credibility of the collected information,

[0960] A means of generating news articles using a generative AI model based on evaluation results,

[0961] A means of classifying the generated news articles,

[0962] Means of predicting future events,

[0963] A means of integrating prediction results and customizing and delivering news articles based on sentiment data,

[0964] A system that includes this.

[0965] (Claim 2)

[0966] The system according to claim 1, comprising means for analyzing user emotion data and notifying information based thereon.

[0967] (Claim 3)

[0968] The system according to claim 1, comprising means for filtering collected information and further utilizing an emotion engine to improve the user experience.

[0969] "Application example 2 of combining emotional engines"

[0970] (Claim 1)

[0971] Means of collecting information,

[0972] A means of evaluating the credibility of the collected information,

[0973] A means of generating news content based on evaluation results,

[0974] A means of classifying the generated news content,

[0975] Means of predicting future events,

[0976] A means of distributing news content that includes prediction results,

[0977] A means of recognizing the user's emotional state,

[0978] A means of customizing news content based on recognized emotional states,

[0979] A system that includes this.

[0980] (Claim 2)

[0981] The system according to claim 1, comprising means for notifying the user's terminal of information.

[0982] (Claim 3)

[0983] The system according to claim 1, comprising means for filtering collected information. [Explanation of Symbols]

[0984] 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. Means of collecting information, A means of evaluating the credibility of the collected information, A means of generating news articles based on evaluation results, A means of classifying the generated news articles, Means of predicting future events, A means of distributing news articles that include prediction results, A system that includes this.

2. The system according to claim 1, comprising means for notifying the user's terminal of information.

3. The system according to claim 1, comprising means for filtering collected information.

Images