System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting news articles; means for analyzing the contents of the collected news articles to generate a summary; means for extracting keywords from the generated summary; means for generating a link to related information based on the extracted keywords; means for delivering the generated summary and the keywords to a user terminal; means for acquiring related information when a keyword displayed by the user terminal is selected; and means for displaying the acquired related information on the user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's world, users are increasingly exposed to a large amount of news information on a daily basis. However, it is difficult to effectively grasp a large amount of news and quickly access related detailed information within a limited time. As a result, users often miss the main points of news or are unable to easily gather information of interest.

[0005] Furthermore, when trying to gain a deeper understanding of the content of a news article, there is a lack of direct access to related information (products, travel plans, books, related websites, stock prices, public institutions, transportation, past related information, etc.) In this situation, there is a need to provide a system that can efficiently understand news and obtain related information. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, the present invention provides the following means.

[0007] A means of collecting news articles,

[0008] A means for analyzing the content of collected news articles and generating summaries;

[0009] means for extracting keywords from the generated summaries;

[0010] means for generating links to related information based on the extracted keywords;

[0011] means for delivering the generated summary and keywords to a user terminal;

[0012] means for acquiring related information when a displayed keyword is selected by a user terminal;

[0013] A means for displaying the acquired related information on the user terminal.

[0014] Specifically, the system collects news articles, analyzes them using natural language processing technology, and generates summaries. Next, it extracts keywords from the generated summaries and generates links to related information based on these keywords. The generated summaries and keywords are then distributed to user devices, and when a user selects a keyword, related information is retrieved and displayed. This allows users to quickly understand the summarized articles and quickly obtain detailed information related to keywords of interest. The summaries and keywords are also stored in a database, enabling efficient information management.

[0015] A "news article" is a piece of text that describes news-related information or events.

[0016] "Means of collection" refers to the software or hardware capabilities required to retrieve news articles from websites or APIs.

[0017] "Means of analysis" refers to the algorithms and software used to analyze the text of retrieved news articles and extract meaning and important parts.

[0018] "Means for generating a summary" refers to the method or software function that summarizes the important content of the analyzed news article into a short sentence.

[0019] "Keyword extraction methods" refers to techniques and algorithms used to identify important words and phrases from summarized news articles.

[0020] "Means for generating links" refers to a function for creating links to related information or web pages based on extracted keywords.

[0021] "Distribution means" refers to a technology for transmitting the generated summary article and keywords to the user's terminal via a network.

[0022] "User terminal" means a device used by a user to receive and view information, including a smartphone, tablet, PC, etc.

[0023] "Means for obtaining related information" refers to a function for searching and obtaining related information on the Internet based on keywords selected by the user.

[0024] "Display means" refers to software or hardware functionality for visually displaying relevant information on a user's device. [Brief explanation of the drawings]

[0025] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0026] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0027] First, the terms used in the following description will be explained.

[0028] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0029] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0030] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0031] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, 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), Bluetooth (registered trademark), etc.

[0032] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 1, a 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.

[0036] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0037] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0038] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0039] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0040] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0043] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0044] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0045] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0046] The present invention relates to a system that enables users to efficiently understand daily news articles and then navigate to related information based on keywords extracted from those articles. This system provides a high-quality user experience by linking the server, terminals, and users.

[0047] Basic configuration

[0048] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to user terminals, allowing users to quickly access detailed related information by selecting keywords.

[0049] Program processing

[0050] The program processing of this system will be explained in natural language below.

[0051] News article collection and analysis

[0052] 1. Collecting news articles

[0053] The server collects the latest news articles from multiple news sites using methods such as RSS feeds, APIs, and web scraping.

[0054] Example: "The server uses the news provider's API to retrieve newly posted article data."

[0055] 2. Analysis of article content

[0056] The server analyzes the collected news article text using natural language processing (NLP) technology to extract key sentences and phrases.

[0057] Example: "The server uses a parsing engine to segment the news article and identify key points."

[0058] 3. Summary Generation

[0059] The server generates a summary from the analyzed article content. The summary is a few lines long and conveys the main points of the article.

[0060] Example: "The server combines key sentences to generate a summary sentence: 'A new smartphone model has been released and is attracting a lot of attention.'"

[0061] Keyword extraction and distribution

[0062] 4. Keyword extraction

[0063] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[0064] Example: "The server extracts keywords such as 'smartphone,' 'model,' and 'announcement' from the abstract."

[0065] 5. Generating Related Links

[0066] The server generates links to related product pages, official websites, review articles, etc. based on the extracted keywords.

[0067] Example: "The server generates links to e-commerce sites and review articles related to 'smartphones'."

[0068] 6. Summary Article and Keyword Distribution

[0069] The server distributes the generated summary article and keywords to the user's terminal.

[0070] Example: "The server sends the summary article and keywords to the user's smartphone via API."

[0071] Acquisition and display of user operations and related information

[0072] 7. Keyword Selection

[0073] The user selects a keyword that interests them from the keywords displayed on the terminal.

[0074] Example: "The user taps on the keyword 'smartphone' displayed on their smartphone."

[0075] 8. Obtaining related information

[0076] The server retrieves relevant information from databases and the Internet based on the keywords selected by the user.

[0077] Example: "The server retrieves the latest product information and related site information for 'smartphones'."

[0078] 9. Display of related information

[0079] The terminal displays the acquired related information to the user, who can then use it to obtain more detailed information or purchase the product.

[0080] Example: "The device displays the purchase page and detailed reviews of the latest smartphone models."

[0081] Specific examples

[0082] For example, if the server collects a news article that says "famous company announces new smartphone," the following process will be performed:

[0083] 1. The server retrieves the news article.

[0084] 2. The server analyzes the article and generates a summary: "A well-known company announces a new smartphone."

[0085] 3. The server extracts the keywords "famous company," "smartphone," and "announcement."

[0086] 4. The server generates links to relevant product pages and review articles.

[0087] 5. The server delivers the summary and keywords to the user's device.

[0088] 6. The user selects the keyword "smartphone."

[0089] 7. The server retrieves the relevant information and displays a detailed information page to the user.

[0090] This allows users to quickly grasp summary information and instantly access related information that they are interested in. This system enables efficient news information collection and digestion, and supports users' actions quickly.

[0091] The processing flow will be explained below.

[0092] Step 1:

[0093] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, or web scraping technology, thereby securing a large amount of new article data.

[0094] Step 2:

[0095] The server analyzes the collected news articles using natural language processing (NLP) technology. Specifically, the article text is tokenized, morphological analysis is performed, and an importance score is assigned to each sentence.

[0096] Step 3:

[0097] The server extracts key sentences from the analyzed article content and generates a summary based on these. The summary is a few lines summarizing the highlights of the article.

[0098] Step 4:

[0099] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec, thereby identifying keywords related to the main themes of the article.

[0100] Step 5:

[0101] The server generates links to related information based on the extracted keywords, using URL information from a database or information obtained from the Internet.

[0102] Step 6:

[0103] The server delivers the generated summary article and keywords to the user's device, and transmits data using an API to provide information to the user in real time.

[0104] Step 7:

[0105] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the outline of the article.

[0106] Step 8:

[0107] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[0108] Step 9:

[0109] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[0110] Step 10:

[0111] The device displays relevant information to the user, including product detail pages, reviews, official websites, etc. It provides detailed links and descriptions to help users quickly access the information they are looking for.

[0112] This series of steps results in a system that allows users to quickly understand news summaries and easily access information of interest.

[0113] Example 1

[0114] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0115] In modern society, people are increasingly exposed to a huge amount of news information every day, making it important to efficiently collect, analyze, and understand that information. Furthermore, there is a need for a method that allows users to quickly extract information of interest and smoothly access related information. Conventional technologies require time and effort to manually collect and analyze news articles, and extensive research is required to find related information, making it difficult to improve the user experience.

[0116] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0117] In this invention, the server includes means for collecting news content, means for analyzing the collected news content to generate summaries, means for extracting keywords from the generated summaries, means for using natural language processing techniques to generate summaries and extract keywords, means for converting the news content, summaries, and keywords into an analyzable format, and means for searching and distributing related information via a digital network, thereby enabling efficient collection and analysis of news content and rapid access to related information of user interest.

[0118] "News content" refers to news articles and reports published online.

[0119] "Means of collection" refers to the methods or mechanisms used to obtain news content from the Internet.

[0120] "Means of analysis" refers to the method or mechanism for analyzing the content of collected news content and organizing the information.

[0121] "Means for generating a summary" refers to a method or mechanism for extracting the main points from collected and analyzed news content and summarizing them in a concise format.

[0122] "Keyword extraction means" refers to a method or mechanism for identifying and extracting important words and phrases from the generated summary.

[0123] "Means for generating links to related information" refers to a method or mechanism for creating links to related web pages or digital information based on the extracted keywords.

[0124] "User Device" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0125] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate natural language used by humans.

[0126] "Digital network" refers to the mechanism for transmitting data over the Internet and other digital communications infrastructure.

[0127] "Database" refers to a system for efficiently managing, storing, and retrieving structured information.

[0128] "Server" refers to a computer system that provides a particular service and processes and distributes data over a network.

[0129] The present invention relates to a system that enables users to efficiently grasp daily news content and then navigate to related information based on keywords extracted from that content. This system provides a high-quality user experience by linking the server, terminals, and users.

[0130] Basic configuration

[0131] This system collects news content, analyzes the content using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to users' devices.By selecting keywords, users can quickly access detailed related information.

[0132] Hardware and Software Configuration

[0133] The main components of this system include the following hardware and software:

[0134] Server: A computer system that collects, analyzes, summarizes, extracts keywords, generates related links, and distributes news content.

[0135] Software: Natural language processing libraries (e.g., spaCy), data processing libraries (e.g., pandas), communication libraries (e.g., requests).

[0136] User terminal: A device that displays the summary and keywords delivered from the server and receives user operations.

[0137] Hardware: Smartphones, tablets, computers.

[0138] Software: web browser, mobile application.

[0139] Program processing

[0140] The server collects the latest news content using RSS feeds, APIs, web scraping, etc. from news sites. The collected content is analyzed using natural language processing techniques to extract important sentences and phrases. A summary is then generated from the extracted information, and keywords are extracted. For example, a specific prompt can be given, such as "The server will use the news provider's API to obtain newly posted article data."

[0141] The generated summary and keywords are delivered from the server to the user's device. The user's device displays them, allowing the user to select keywords of interest. Once a keyword is selected, the server searches for related information based on the selected keyword and displays the retrieved information on the user's device. For example, the user taps on the keyword "smartphone" displayed on their smartphone.

[0142] Specific examples

[0143] For example, if the server collects news content such as "A famous company announces a new smartphone," the following specific processing occurs:

[0144] 1. The server sends a request to an API endpoint to retrieve news content.

[0145] 2. The server uses an NLP engine (e.g., spaCy) to analyze the news content and generate a summary.

[0146] 3. The server extracts keywords such as "famous company," "smartphone," and "announcement" from the summary.

[0147] 4. The server generates links to relevant product pages and reviews.

[0148] 5. The server delivers the summary and keywords to the user's terminal.

[0149] 6. The user taps on the keyword "smartphone" displayed on the smartphone screen.

[0150] 7. The server searches for relevant information and displays the retrieved information on the user's terminal.

[0151] Prompt Sentence Examples

[0152] Below are some examples of specific prompts to input to the generative AI model:

[0153] "Please tell me the process flow of a system that collects the latest news content, summarizes the key points, and extracts and displays related keywords."

[0154] This system allows users to quickly grasp summary information and instantly access related information that they are interested in. This enables efficient collection and analysis of news content and precise information access based on users' interests.

[0155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0156] Step 1:

[0157] News content collection

[0158] The server collects the latest news content from multiple news sites using RSS feeds, APIs, web scraping, etc.

[0159] Specific operation: The server sends a request to the news provider's API endpoint and retrieves the returned news content in JSON format.

[0160] Input: News site API endpoint, credentials.

[0161] Output: News content in JSON format.

[0162] Step 2:

[0163] News content analysis

[0164] The server analyzes the collected news content text using natural language processing (NLP) technology to extract important sentences and phrases.

[0165] What it does: The server uses an NLP library (e.g., spaCy) to tokenize the text, tag it with parts of speech, and extract key sentences and phrases.

[0166] Input: News content in JSON format.

[0167] Output: A list of key sentences and phrases.

[0168] Step 3:

[0169] Generate a summary

[0170] The server generates a summary based on the analyzed sentences and phrases, which is a few lines long and conveys the main points of the article.

[0171] Specific operation: The server combines important sentences, removes redundant parts, and constructs a summary sentence.

[0172] Input: A list of key sentences or phrases.

[0173] Output: Summary statement.

[0174] Step 4:

[0175] Keyword extraction

[0176] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[0177] Specific operation: The server tokenizes the summary sentence, extracts important nouns and verbs, and selects them as keywords.

[0178] Input: Abstract text.

[0179] Output: A list of keywords.

[0180] Step 5:

[0181] Generate related links

[0182] The server generates links to relevant web pages and digital information based on the extracted keywords.

[0183] Specific operation: The server uses a search API to obtain links related to each keyword and selects the most relevant ones.

[0184] Input: A list of keywords.

[0185] Output: A list of related links.

[0186] Step 6:

[0187] Summary and keyword distribution

[0188] The server distributes the generated summary article and keywords to the user terminal.

[0189] Specific operation: The server packages the summary article and keywords as an API response and sends it to the user's terminal.

[0190] Input: Abstract article, list of keywords.

[0191] Output: Abstract article and keywords sent to user terminal.

[0192] Step 7:

[0193] Keyword Selection

[0194] The user selects a keyword that interests them from the keywords displayed on the terminal.

[0195] Specific action: The user taps or clicks on a keyword on the screen.

[0196] Input: Keywords displayed on the user's terminal.

[0197] Output: The user's selected keywords.

[0198] Step 8:

[0199] Obtaining related information

[0200] The server retrieves relevant information from a database or the Internet based on the keywords selected by the user.

[0201] Specific operation: The server uses a database or API to search and retrieve information related to the selected keyword.

[0202] Input: Selected keyword.

[0203] Output: The relevant information retrieved.

[0204] Step 9:

[0205] Viewing related information

[0206] The terminal displays the acquired related information to the user.

[0207] Specific operation: The terminal converts the acquired information into an appropriate format and displays it.

[0208] Input: The relevant information retrieved.

[0209] Output: Relevant information displayed on the user's terminal.

[0210] (Application example 1)

[0211] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0212] Conventional news article distribution systems make it difficult for users to efficiently understand the content of news articles and quickly access information of interest. In particular, quickly obtaining links from news articles to related information requires manual searching, which takes time and effort. Another problem is the complicated process of extracting essential keywords from news and linking them to related information.

[0213] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0214] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, and means for extracting keywords from the generated summaries. This allows for efficient management of news articles and enables users to quickly access related information. The server also includes means for generating summaries using natural language processing technology and extracting keywords from the summaries using a generative AI model, and means for generating prompt sentences based on the extracted keywords and further identifying related information using the prompt sentences. This allows users to quickly obtain links to related information and detailed information by simply selecting keywords of interest, enabling efficient information gathering.

[0215] A "news article" is information reported in the form of text, images, video, etc. provided by a website or news provider.

[0216] "Means of collection" refers to the technical devices or methods used to collect news articles, such as through web scraping, RSS feeds, APIs, etc.

[0217] A "means for analyzing and generating a summary" is a technical device or method that uses natural language processing techniques to concisely summarize the key content or key points of a news article.

[0218] "Keyword extraction means" refers to a technical device or method that uses generative AI models or natural language processing techniques to extract the article's themes and important words from the summary text.

[0219] The "means for generating links to related information" is a technical device or method that creates hyperlinks to related web pages or database entries based on the extracted keywords.

[0220] A "distribution means" is a technical device or method that transmits the generated abstract and keywords to a user's device over a network.

[0221] "Displaying means" refers to a technical device or method that visually presents relevant information, summaries, and keywords on a user's device.

[0222] "Natural language processing technology" is a technology that enables computers to understand, analyze, and manipulate human language.

[0223] A "generative AI model" is an artificial intelligence technology that learns from large amounts of text data and extracts summaries and keywords from given text.

[0224] A "prompt sentence" is text data input to a generative AI model, and serves as a clue for the model to extract appropriate keywords and information.

[0225] A "user device" is an electronic device (e.g., smartphone, tablet, computer, etc.) for displaying news articles and related information.

[0226] The "means for identifying" refers to a technical device or method that searches for related information based on the extracted keywords and generated prompt sentences and provides it to the user.

[0227] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from the articles. This system is implemented using a server, a user device, natural language processing technology, and a generative AI model.

[0228] The server first collects news articles. Methods for collecting news articles include RSS feeds, API access, and web scraping. Next, the content of the collected news articles is analyzed. This analysis is performed using natural language processing (NLP) technology. Specifically, it uses Python libraries such as spaCy and transformers.

[0229] The server extracts important content from the analyzed text and generates a summary. This summary is condensed by a generative AI model into a few lines that convey the main points of the article. For example, a summary of the news article "A new smartphone has been announced and is attracting a lot of attention" is generated. Keywords are then extracted from this summary. For example, keywords such as "smartphone," "announcement," and "attention" are extracted.

[0230] Furthermore, the server generates a prompt based on the extracted keywords. This prompt is used as input data for the generative AI model to more specifically identify relevant information. An example of a prompt is, "Please tell me the latest information about the launch of a new smartphone."

[0231] Based on the extracted keywords and generated prompts, the server generates relevant links and delivers them to the user's device along with the summary, allowing the user to view the summary and keywords on their smartphone, tablet, or other device.

[0232] When a user selects a displayed keyword, the server retrieves detailed related information from a database or the Internet. The retrieved related information is then sent back to the user's device, where the user can view it. For example, if a user selects the keyword "smartphone," the server retrieves product information and review articles related to that smartphone and displays them on the user's device.

[0233] This allows users to efficiently grasp summaries of articles they are interested in and quickly access detailed information and related links. This system streamlines users' collection and digestion of news information, providing a high-quality user experience.

[0234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0235] Step 1:

[0236] The server collects news articles.

[0237] Input: News provider's API or RSS feed URL.

[0238] Data processing: The server requests news article data from the input URL or API and retrieves the article data in JSON format or other formats.

[0239] Output: A list of collected news articles.

[0240] Step 2:

[0241] The server analyzes the collected news articles and generates summaries.

[0242] Input: The list of news articles collected in step 1.

[0243] Data processing: The server uses natural language processing (NLP) techniques to analyze the content of news articles. Libraries such as spaCy and transformers are used for analysis. The server then uses a generative AI model to generate a summary that summarizes the key points.

[0244] Output: A summary for each article.

[0245] Step 3:

[0246] The server extracts keywords from the generated summary.

[0247] Input: The summary text generated in step 2.

[0248] Data processing: The server again uses natural language processing technology to extract important keywords from the summary text, using a generative AI model.

[0249] Output: A list of extracted keywords.

[0250] Step 4:

[0251] The server generates a prompt sentence based on the extracted keywords and generates a link to related information.

[0252] Input: The list of keywords extracted in step 3.

[0253] Data processing: A generative AI model generates prompts based on keywords, identifies related information from the prompts, and generates links based on this identified information.

[0254] Output: A list of the generated prompt statements and associated links.

[0255] Step 5:

[0256] The server delivers the summary, keywords and related links to the user device.

[0257] Input: Abstract generated in step 2, keywords extracted in step 3, links generated in step 4.

[0258] Data processing: The server combines these data, formats them appropriately, and sends them to the user's device.

[0259] Output: Abstract, keywords, and related links delivered to the user's device.

[0260] Step 6:

[0261] The terminal displays the delivered summary and keywords.

[0262] Input: Abstract, keywords, and related links delivered in Step 5.

[0263] Data processing: The application receives the distributed data and displays it on the user interface, which the user can view.

[0264] Output: Abstract, keywords, and related links displayed in the user interface.

[0265] Step 7:

[0266] The user selects a displayed keyword.

[0267] Input: The keyword displayed in step 6.

[0268] Data processing: The user selects a keyword, which is then sent to the server.

[0269] Output: The selected keywords sent to the server.

[0270] Step 8:

[0271] The server retrieves relevant information based on the selected keywords.

[0272] Input: The selected keyword submitted in step 7.

[0273] Data processing: The server searches and retrieves relevant information based on the selected keywords from databases and the Internet.

[0274] Output: The relevant information retrieved.

[0275] Step 9:

[0276] The server distributes the retrieved relevant information to the user device.

[0277] Input: Relevant information obtained in step 8.

[0278] Data processing: The server formats the retrieved information and sends it to the user device.

[0279] Output: Relevant information delivered to user device.

[0280] Step 10:

[0281] The terminal displays the retrieved related information.

[0282] Input: Relevant information delivered in Step 9.

[0283] Data processing: The received relevant information is processed and displayed on the user interface.

[0284] Output: Relevant information displayed on the user interface.

[0285] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0286] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system dynamically adjusts the news content and related information according to the user's emotions, providing a personalized experience.

[0287] Basic configuration

[0288] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from them, generates links to related information, and delivers and displays them to users' devices. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and optimizes the information displayed based on those emotions.

[0289] Program processing

[0290] The program processing of this system will be explained in natural language below.

[0291] News article collection and analysis

[0292] 1. Collecting news articles

[0293] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, thereby obtaining article data from a wide range of news sources.

[0294] 2. Analysis of article content

[0295] The server analyzes the text of collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating summaries.

[0296] 3. Summary Generation

[0297] The server generates a summary from the analyzed article content. The summary is concisely summarized in a few lines and conveys the essence of the article.

[0298] Keyword extraction and distribution

[0299] 4. Keyword extraction

[0300] The server extracts keywords from the abstract using natural language processing techniques such as TF-IDF and Word2Vec, thereby identifying keywords related to the main themes of the article.

[0301] 5. Generating Related Links

[0302] The server generates links to related information based on the extracted keywords, including links to product pages, official websites, review articles, etc.

[0303] 6. Summary Article and Keyword Distribution

[0304] The server delivers the generated summary article and keywords to the user's device, providing information in real time via API.

[0305] Acquisition and display of user operations and related information

[0306] 7. Keyword Selection

[0307] The user selects keywords that interest them from those displayed on the device, and performs operations by tapping or clicking.

[0308] 8. Obtaining related information

[0309] The server retrieves relevant information based on user-selected keywords, providing up-to-date information using internet searches and database queries.

[0310] 9. Display of related information

[0311] The device displays relevant information to the user, including product details, reviews, official websites, and more.

[0312] Combining Emotion Engines

[0313] One of the features of the present invention is that it incorporates an emotion engine that recognizes the user's emotions, which adds the following processing:

[0314] 10. Emotional Recognition

[0315] The device recognizes emotions from the user's facial expressions, voice, input, etc. The emotion engine uses machine learning algorithms to identify emotional states.

[0316] 11. Information Optimization

[0317] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, it provides more detailed information and related news. On the other hand, if the user is in a negative emotional state, it prioritizes the display of concise information and relaxing content.

[0318] Specific examples

[0319] For example, if a user is viewing a news article titled "New Smartphone Announcement," the following processing will occur:

[0320] 1. The server collects news articles.

[0321] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[0322] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[0323] 4. The server generates links to relevant product pages and review articles.

[0324] 5. The server delivers the summary and keywords to the user's device.

[0325] 6. The user selects the keyword "smartphone."

[0326] 7. The server retrieves the relevant information and displays the details page to the user.

[0327] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[0328] In this way, information provision can be optimized according to the user's emotions, resulting in a more personalized news viewing experience.

[0329] The processing flow will be explained below.

[0330] Step 1:

[0331] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, allowing for the rapid acquisition of new articles from a wide range of news sources.

[0332] Step 2:

[0333] The server analyzes the collected news article text using natural language processing (NLP) techniques, tokenizing the sentences in the article, performing morphological analysis, and assigning an importance score to each sentence.

[0334] Step 3:

[0335] The server generates a summary based on the analyzed article content. The summary is usually a few lines long and succinctly conveys the main points of the article.

[0336] Step 4:

[0337] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec to determine keywords that reflect the main themes of the article.

[0338] Step 5:

[0339] The server generates links to related information based on the extracted keywords, including links to related product pages, official websites, review articles, etc.

[0340] Step 6:

[0341] The server delivers the generated summary article and keywords to the user's device, using an API to send data in real time so that the user can receive the information immediately.

[0342] Step 7:

[0343] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the article's outline.

[0344] Step 8:

[0345] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[0346] Step 9:

[0347] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[0348] Step 10:

[0349] The device displays the retrieved relevant information to the user, including product detail pages, reviews, official websites, and more, allowing users to quickly access the information they are looking for.

[0350] Step 11:

[0351] The device uses an emotion engine to recognize emotions from the user's facial expressions, voice, input, etc. Machine learning algorithms are used to identify the user's emotional state.

[0352] Step 12:

[0353] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a negative emotional state, it will prioritize displaying concise information and relaxing content to optimize the user experience.

[0354] Specific examples

[0355] For example, when processing a news article titled "New Smartphone Announced," the process would proceed as follows:

[0356] 1. The server collects news articles.

[0357] 2. The server analyzes the article and generates a summary: "A new smartphone model has been announced."

[0358] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[0359] 4. The server generates links to relevant product pages and review articles.

[0360] 5. The server delivers the summary and keywords to the user's terminal.

[0361] 6. The device will display the summary article and keywords.

[0362] 7. The user selects the keyword "smartphone."

[0363] 8. The server retrieves the relevant information and displays a details page to the user.

[0364] 9. The device recognizes the user's emotions.

[0365] 10. The server optimizes and displays relevant information such as detailed reviews and purchase links based on the user's sentiment.

[0366] This series of processes allows users to efficiently grasp the news and quickly obtain relevant information that matches their emotional state.

[0367] Example 2

[0368] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0369] In recent years, information overload has made it difficult for users to quickly and efficiently obtain the information they need. With the vast amount of news articles being generated daily, it takes a great deal of time and effort for users to grasp the important content. Furthermore, there is a lack of information provided that is tailored to the user's emotional state, creating a need for improved user experience. Current technology faces the challenge of achieving a continuous flow of news article collection, analysis, and distribution, as well as information optimization through user emotion recognition. To address these challenges, an information delivery system that combines immediacy and personalization to meet user needs is needed.

[0370] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0371] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for recognizing a user's emotion, and means for optimizing display information based on the recognized user's emotion. This allows users to efficiently understand daily news articles and quickly obtain related information based on keywords extracted from the articles. Furthermore, information is dynamically adjusted according to the user's emotional state, providing a more personalized experience.

[0372] A "news article aggregator" is a software and hardware mechanism for aggregating news articles from multiple sources on the Internet.

[0373] "Means of analyzing the content of collected news articles and generating summaries" refers to the technology and process of using natural language processing technology to understand and analyze the content of news articles and generate a concise summary.

[0374] "Means for extracting keywords from the generated summaries" refers to algorithms and techniques for identifying major themes and important words from the generated summaries and extracting them as keywords.

[0375] The "means for generating links to related information based on extracted keywords" is a mechanism for dynamically generating links to related information or web pages based on extracted keywords.

[0376] "Means for delivering the generated summary and keywords to the user's terminal" refers to the communication technology and infrastructure for transmitting and delivering the generated summary and keywords to the user's terminal in real time.

[0377] "Means for recognizing user emotions" refers to emotion recognition technology and sensor devices for detecting and identifying emotions from the user's facial expressions, voice, input content, etc.

[0378] "Means for optimizing display information based on recognized user emotions" refers to a technology that dynamically changes the content and format of the information to be displayed based on the detected emotional state of the user, thereby providing information that more appropriately meets the user's needs and situation.

[0379] The present invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, the present invention is characterized by combining an emotion engine that recognizes the user's emotions, dynamically adjusting the news content and related information according to the user's emotions, providing a personalized experience.

[0380] Basic configuration

[0381] The system of the present invention includes the following components:

[0382] News article collection method

[0383] News article analysis methods

[0384] Summary generation means

[0385] Keyword extraction method

[0386] Related link generation method

[0387] Abstract and Keyword Distribution Methods

[0388] A means of recognizing user emotions

[0389] How to optimize the information displayed

[0390] News article collection and analysis

[0391] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping. This is done using Python's "Requests" library, among other tools. The collected article text is then analyzed using natural language processing (NLP) techniques. NLP libraries such as "SpaCy" and "NLTK" are used. This identifies the important parts and main themes of the article and generates a concise summary.

[0392] Keyword extraction and link generation for related information

[0393] The server uses techniques such as TF-IDF and Word2Vec to extract keywords from the generated summary. Based on the extracted keywords, the server generates links to related information, including product pages, official websites, and review articles. An API is then used to deliver the generated summary and keywords to the user's device.

[0394] User interaction and emotion recognition

[0395] Users can obtain relevant information of interest by selecting keywords displayed on their device. Based on the selected keywords, the server retrieves relevant information using Internet searches and database queries and displays it on the device. In addition, the device recognizes emotions from the user's facial expressions, voice, and input content. Software such as "OpenFace" and "Affectiva" is used as the emotion engine.

[0396] Information Optimization

[0397] The server optimizes the displayed information based on the user's recognized emotions. For example, if the user is excited, it will prioritize detailed spec reviews and purchase links, but if the user is in a negative emotional state, it will display relaxing content.

[0398] Specific examples

[0399] For example, if a user is looking at a news article about a new smartphone being announced, the following happens:

[0400] 1. The server collects news articles.

[0401] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[0402] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[0403] 4. The server generates links to relevant product pages and review articles.

[0404] 5. The server delivers the summary and keywords to the user's terminal.

[0405] 6. The user selects the keyword "smartphone."

[0406] 7. The server retrieves the relevant information and displays the details page to the user.

[0407] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[0408] Example prompts for generative AI models

[0409] An example of a prompt to input to a generative AI model is as follows:

[0410] Imagine a user is reading an article about a new smartphone. This system collects and analyzes news articles to generate summaries. It then extracts keywords from the summaries and generates links to related information. It then uses an emotion engine to recognize the user's emotions and dynamically adjusts the information displayed based on those emotions. If the user selects the keyword "smartphone," the server retrieves related information and the device displays detailed information. Please explain this process in detail, along with the system's processing steps.

[0411] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0412] Step 1: Gather news articles

[0413] Input: RSS feed URL of the news site, API endpoint, website URL to be scraped.

[0414] How it works: The server collects news articles using RSS feeds, APIs, and web scraping. Specifically, it uses the Python "Requests" library to send requests to news site APIs and parses the JSON data it receives.

[0415] Output: JSON or text data of collected news articles.

[0416] Step 2: Analyzing the article content

[0417] Input: Collected text data of news articles.

[0418] How it works: The server analyzes the content of articles using NLP libraries like SpaCy and NLTK to identify important parts and major themes of the article. The analysis includes morphological and contextual analysis.

[0419] Output: Information on the main themes and key parts of the analyzed articles.

[0420] Step 3: Generate a summary

[0421] Input: Parsed article content.

[0422] How it works: The server generates a summary based on the analysis results. The summary is concisely summarized in a few lines and conveys the essence of the article. The server uses an extractive summarization algorithm to extract sentences that are deemed particularly important.

[0423] Output: The generated summary.

[0424] Step 4: Keyword extraction

[0425] Input: The generated summary sentence.

[0426] How it works: The server extracts keywords from the abstract using techniques such as TF-IDF and Word2Vec, which identifies important keywords related to the main theme of the article.

[0427] Output: Extracted keyword list.

[0428] Step 5: Generate related links

[0429] Input: Extracted keyword list.

[0430] How it works: The server generates links to related information based on keywords. This includes URLs to product pages, official websites, review articles, etc. Link generation is done using search engine APIs and pre-collected databases.

[0431] Output: A list of generated related links.

[0432] Step 6: Summary and Keyword Distribution

[0433] Input: Generated abstract and keyword list.

[0434] How it works: The server delivers the generated summary and keywords to the user's device, providing real-time information via API and sending data to the device application.

[0435] Output: Summary and keywords delivered to the user's terminal.

[0436] Step 7: Selecting Keywords

[0437] Input: Keyword list delivered to the device.

[0438] How it works: The user selects keywords that interest them from those displayed on the device, and performs the action by tapping or clicking. This selection action is detected by the device and triggers the next step.

[0439] Output: The selected keywords.

[0440] Step 8: Obtain related information

[0441] Input: A keyword selected by the user.

[0442] How it works: The server retrieves relevant information based on the selected keywords, specifically using internet searches and database queries to gather the latest information.

[0443] Output: The relevant information retrieved.

[0444] Step 9: View related information

[0445] Input: The relevant information retrieved.

[0446] Operation: The device displays the retrieved related information to the user. This may include product detail pages, review articles, official websites, etc. The related information is displayed through a user interface.

[0447] Output: Relevant information displayed on the terminal.

[0448] Step 10: Recognize emotions

[0449] Input: User facial expressions, voice, input, etc.

[0450] How it works: The device recognizes emotions from the user's facial expressions, voice, and input. The emotion engine uses machine learning algorithms to identify emotional states, specifically software like "OpenFace" and "Affectiva."

[0451] Output: Perceived emotional state.

[0452] Step 11: Information optimization

[0453] Input: The perceived emotional state of the user.

[0454] How it works: The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, detailed spec reviews and purchase links will be prioritized. Conversely, if the user is in a negative emotional state, concise information and relaxing content will be prioritized.

[0455] Output: Information display optimized for the user's emotional state.

[0456] (Application example 2)

[0457] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0458] In today's information society, users are required to efficiently and quickly obtain the information they need from a vast amount of news articles. Furthermore, if the content of news articles and related information is provided to users without taking into account the user's emotional state, information receptivity may be reduced. Conventional news delivery systems are unable to dynamically adjust information to reflect the individual user's emotional state, limiting the improvement of usability. A new approach to solving this problem is needed.

[0459] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for acquiring related information when a keyword displayed on the user terminal is selected, means for displaying the acquired related information on the user terminal, emotion recognition means for recognizing the user's emotion, and means for dynamically changing the related information and keywords to be displayed based on the recognized user emotion. This enables a user to efficiently grasp and select related information and news content in a manner appropriate to their emotional state.

[0460] "Means for collecting news articles" is a function that automatically obtains the latest news articles from multiple news sources on the Internet.

[0461] "Means for analyzing the content of news articles and generating summaries" refers to a function that uses natural language processing technology to identify important parts and main themes of collected news articles and generate concise summaries.

[0462] The "means for extracting keywords from summaries" is a function for identifying and extracting highly relevant keywords from the generated summaries.

[0463] The "means for generating links to related information" is a function that automatically generates links to related information or web pages based on the extracted keywords.

[0464] The "means for delivering the summary and keywords to the user terminal" is a function for transmitting the generated summary and keywords to the user terminal and displaying them.

[0465] "Means for obtaining related information when a keyword displayed by a user terminal is selected" is a function for obtaining information related to a keyword when the user selects the keyword displayed on the terminal.

[0466] The "means for displaying the acquired related information on the user terminal" is a function for displaying the acquired related information on the user terminal.

[0467] The "emotion recognition means for recognizing the user's emotions" is a function for identifying the user's emotional state from the user's facial expressions, voice, and input contents.

[0468] The "means for dynamically changing the related information and keywords to be displayed" is a function for changing the content of the information and keywords to be displayed in real time based on the recognized user's emotions.

[0469] The present invention provides a system and method for efficiently understanding news articles, and further provides the ability to dynamically adjust news and related information based on user sentiment. The present invention has the following system configuration.

[0470] 1. Collecting news articles

[0471] The server collects the latest news articles from multiple news sources (news websites, RSS feeds, etc.). This can be achieved by subscribing to RSS feeds, using API integration, or using web scraping techniques. This aggregation consolidates news articles from a wide range of sources.

[0472] 2. News article analysis and summary generation

[0473] The server analyzes the collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating concise summaries. This summary generation is achieved using, for example, the nltk library and various machine learning techniques.

[0474] 3. Keyword extraction

[0475] The server uses natural language processing techniques such as Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec to extract key keywords from the generated summary, thereby identifying the main themes and relevant words of the article.

[0476] 4. Linking to related information

[0477] Based on the extracted keywords, it generates links to relevant web pages and databases, including product pages, official websites, and review articles, allowing users to access more detailed information.

[0478] 5. Summary and Keyword Distribution

[0479] The server delivers the generated summary and keywords to the user's device. This information is provided in real time via an API and can be viewed on the user's device.

[0480] 6. User operations and display of related information

[0481] Users can obtain detailed related information by tapping on keywords they are interested in from those displayed on their device. The server retrieves further related information based on the keywords selected by the user and displays it on the user's device.

[0482] 7. Emotion Recognition and Information Optimization

[0483] The device analyzes the user's facial expressions, voice, and input content to identify their emotional state using an emotion recognition engine. This emotion recognition uses machine learning algorithms such as EmotionEngine. The server dynamically adjusts the news articles and related information displayed based on the user's recognized emotion. For example, if the user is in a positive emotional state, more detailed information will be displayed first, while if the user is in a negative emotional state, brief information will be displayed first.

[0484] Specific examples

[0485] For example, if a user is viewing a news article titled "Announcement of a new smart device," the following process takes place: The server collects news articles, analyzes them, and generates summaries. Keywords such as "smart device" and "announcement" are extracted from the generated summaries. The server generates links to related product pages and review articles and delivers the summaries and keywords to the user's device. When the user selects the keyword "smart device," the server retrieves related information and displays a detailed page to the user. At this time, the device recognizes the user's emotions; for example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[0486] Prompt Sentence Examples

[0487] Prompt: "Design a system that helps users efficiently keep up with breaking news and delivers information accordingly. Additionally, add the ability to recognize the user's emotions and adjust the content accordingly."

[0488] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0489] Step 1:

[0490] The server collects news articles. Specifically, it obtains article data from multiple news sources using RSS feeds, news site APIs, and web scraping technology. It uses a list of URLs as input and obtains a list of collected text data as output.

[0491] Step 2:

[0492] The server analyzes the content of collected news articles and generates summaries. Specifically, it uses natural language processing (NLP) techniques to analyze articles and identify important parts and main themes. The article text is used as input, and a summary is obtained as output.

[0493] Step 3:

[0494] The server extracts keywords from the generated summary. In this step, it uses natural language processing techniques such as TF-IDF and Word2Vec to identify keywords. It uses the summary sentence as input and obtains a list of keywords as output.

[0495] Step 4:

[0496] The server generates links to related information based on the extracted keywords, including related product pages, official websites, review articles, etc. It uses a list of keywords as input and obtains a list of related links as output.

[0497] Step 5:

[0498] The server delivers the generated summary and keywords to the user's device, transmitting information in real time via an API. The server uses the generated summary, keywords, and a list of related links as input, and delivers data to the user's device as output.

[0499] Step 6:

[0500] The user selects keywords displayed on the device by tapping or clicking on the keyword of interest. The input is the keyword selection, and the output is the selected keyword.

[0501] Step 7:

[0502] The server retrieves relevant information based on the selected keywords. It uses internet searches and database queries to gather up-to-date relevant information. It uses the selected keywords as input and gets relevant information as output.

[0503] Step 8:

[0504] The device displays the retrieved related information to the user, including product detail pages and review articles. The retrieved related information is used as input, and the display on the user device is used as output.

[0505] Step 9:

[0506] The device uses an emotion recognition engine to recognize the user's emotions. It identifies emotions from the user's facial expressions, voice, and input content. It uses the user's facial expression data and voice data as input and obtains the user's emotional state as output.

[0507] Step 10:

[0508] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. If the user is in a positive emotional state, detailed information is displayed, and if the user is in a negative emotional state, brief information is displayed preferentially. Using the emotional state and relevant information as input, tailored information is obtained as output.

[0509] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0510] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0511] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0512] [Second embodiment]

[0513] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0514] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0515] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0516] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0517] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0518] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0519] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0520] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0521] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0522] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0523] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0524] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0525] The present invention relates to a system that enables users to efficiently understand daily news articles and then navigate to related information based on keywords extracted from those articles. This system provides a high-quality user experience by linking the server, terminals, and users.

[0526] Basic configuration

[0527] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to user terminals, allowing users to quickly access detailed related information by selecting keywords.

[0528] Program processing

[0529] The program processing of this system will be explained in natural language below.

[0530] News article collection and analysis

[0531] 1. Collecting news articles

[0532] The server collects the latest news articles from multiple news sites using methods such as RSS feeds, APIs, and web scraping.

[0533] Example: "The server uses the news provider's API to retrieve newly posted article data."

[0534] 2. Analysis of article content

[0535] The server analyzes the collected news article text using natural language processing (NLP) technology to extract key sentences and phrases.

[0536] Example: "The server uses a parsing engine to segment the news article and identify key points."

[0537] 3. Summary Generation

[0538] The server generates a summary from the analyzed article content. The summary is a few lines long and conveys the main points of the article.

[0539] Example: "The server combines key sentences to generate a summary sentence: 'A new smartphone model has been released and is attracting a lot of attention.'"

[0540] Keyword extraction and distribution

[0541] 4. Keyword extraction

[0542] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[0543] Example: "The server extracts keywords such as 'smartphone,' 'model,' and 'announcement' from the abstract."

[0544] 5. Generating Related Links

[0545] The server generates links to related product pages, official websites, review articles, etc. based on the extracted keywords.

[0546] Example: "The server generates links to e-commerce sites and review articles related to 'smartphones'."

[0547] 6. Summary Article and Keyword Distribution

[0548] The server distributes the generated summary article and keywords to the user's terminal.

[0549] Example: "The server sends the summary article and keywords to the user's smartphone via API."

[0550] Acquisition and display of user operations and related information

[0551] 7. Keyword Selection

[0552] The user selects a keyword that interests them from the keywords displayed on the terminal.

[0553] Example: "The user taps on the keyword 'smartphone' displayed on their smartphone."

[0554] 8. Obtaining related information

[0555] The server retrieves relevant information from databases and the Internet based on the keywords selected by the user.

[0556] Example: "The server retrieves the latest product information and related site information for 'smartphones'."

[0557] 9. Display of related information

[0558] The terminal displays the acquired related information to the user, who can then use it to obtain more detailed information or purchase the product.

[0559] Example: "The device displays the purchase page and detailed reviews of the latest smartphone models."

[0560] Specific examples

[0561] For example, if the server collects a news article that says "famous company announces new smartphone," the following process will be performed:

[0562] 1. The server retrieves the news article.

[0563] 2. The server analyzes the article and generates a summary: "A well-known company announces a new smartphone."

[0564] 3. The server extracts the keywords "famous company," "smartphone," and "announcement."

[0565] 4. The server generates links to relevant product pages and review articles.

[0566] 5. The server delivers the summary and keywords to the user's device.

[0567] 6. The user selects the keyword "smartphone."

[0568] 7. The server retrieves the relevant information and displays a detailed information page to the user.

[0569] This allows users to quickly grasp summary information and instantly access related information that they are interested in. This system enables efficient news information collection and digestion, and supports users' actions quickly.

[0570] The processing flow will be explained below.

[0571] Step 1:

[0572] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, or web scraping technology, thereby securing a large amount of new article data.

[0573] Step 2:

[0574] The server analyzes the collected news articles using natural language processing (NLP) technology. Specifically, the article text is tokenized, morphological analysis is performed, and an importance score is assigned to each sentence.

[0575] Step 3:

[0576] The server extracts key sentences from the analyzed article content and generates a summary based on these. The summary is a few lines summarizing the highlights of the article.

[0577] Step 4:

[0578] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec, thereby identifying keywords related to the main themes of the article.

[0579] Step 5:

[0580] The server generates links to related information based on the extracted keywords, using URL information from a database or information obtained from the Internet.

[0581] Step 6:

[0582] The server delivers the generated summary article and keywords to the user's device, and transmits data using an API to provide information to the user in real time.

[0583] Step 7:

[0584] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the outline of the article.

[0585] Step 8:

[0586] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[0587] Step 9:

[0588] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[0589] Step 10:

[0590] The device displays relevant information to the user, including product detail pages, reviews, official websites, etc. It provides detailed links and descriptions to help users quickly access the information they are looking for.

[0591] This series of steps results in a system that allows users to quickly understand news summaries and easily access information of interest.

[0592] Example 1

[0593] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0594] In modern society, people are increasingly exposed to a huge amount of news information every day, making it important to efficiently collect, analyze, and understand that information. Furthermore, there is a need for a method that allows users to quickly extract information of interest and smoothly access related information. Conventional technologies require time and effort to manually collect and analyze news articles, and extensive research is required to find related information, making it difficult to improve the user experience.

[0595] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0596] In this invention, the server includes means for collecting news content, means for analyzing the collected news content to generate summaries, means for extracting keywords from the generated summaries, means for using natural language processing techniques to generate summaries and extract keywords, means for converting the news content, summaries, and keywords into an analyzable format, and means for searching and distributing related information via a digital network, thereby enabling efficient collection and analysis of news content and rapid access to related information of user interest.

[0597] "News content" refers to news articles and reports published online.

[0598] "Means of collection" refers to the methods or mechanisms used to obtain news content from the Internet.

[0599] "Means of analysis" refers to the method or mechanism for analyzing the content of collected news content and organizing the information.

[0600] "Means for generating a summary" refers to a method or mechanism for extracting the main points from collected and analyzed news content and summarizing them in a concise format.

[0601] "Keyword extraction means" refers to a method or mechanism for identifying and extracting important words and phrases from the generated summary.

[0602] "Means for generating links to related information" refers to a method or mechanism for creating links to related web pages or digital information based on the extracted keywords.

[0603] "User Device" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0604] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate natural language used by humans.

[0605] "Digital network" refers to the mechanism for transmitting data over the Internet and other digital communications infrastructure.

[0606] "Database" refers to a system for efficiently managing, storing, and retrieving structured information.

[0607] "Server" refers to a computer system that provides a particular service and processes and distributes data over a network.

[0608] The present invention relates to a system that enables users to efficiently grasp daily news content and then navigate to related information based on keywords extracted from that content. This system provides a high-quality user experience by linking the server, terminals, and users.

[0609] Basic configuration

[0610] This system collects news content, analyzes the content using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to users' devices.By selecting keywords, users can quickly access detailed related information.

[0611] Hardware and Software Configuration

[0612] The main components of this system include the following hardware and software:

[0613] Server: A computer system that collects, analyzes, summarizes, extracts keywords, generates related links, and distributes news content.

[0614] Software: Natural language processing libraries (e.g., spaCy), data processing libraries (e.g., pandas), communication libraries (e.g., requests).

[0615] User terminal: A device that displays the summary and keywords delivered from the server and receives user operations.

[0616] Hardware: Smartphones, tablets, computers.

[0617] Software: web browser, mobile application.

[0618] Program processing

[0619] The server collects the latest news content using RSS feeds, APIs, web scraping, etc. from news sites. The collected content is analyzed using natural language processing techniques to extract important sentences and phrases. A summary is then generated from the extracted information, and keywords are extracted. For example, a specific prompt can be given, such as "The server will use the news provider's API to obtain newly posted article data."

[0620] The generated summary and keywords are delivered from the server to the user's device. The user's device displays them, allowing the user to select keywords of interest. Once a keyword is selected, the server searches for related information based on the selected keyword and displays the retrieved information on the user's device. For example, the user taps on the keyword "smartphone" displayed on their smartphone.

[0621] Specific examples

[0622] For example, if the server collects news content such as "A famous company announces a new smartphone," the following specific processing occurs:

[0623] 1. The server sends a request to an API endpoint to retrieve news content.

[0624] 2. The server uses an NLP engine (e.g., spaCy) to analyze the news content and generate a summary.

[0625] 3. The server extracts keywords such as "famous company," "smartphone," and "announcement" from the summary.

[0626] 4. The server generates links to relevant product pages and reviews.

[0627] 5. The server delivers the summary and keywords to the user's terminal.

[0628] 6. The user taps on the keyword "smartphone" displayed on the smartphone screen.

[0629] 7. The server searches for relevant information and displays the retrieved information on the user's terminal.

[0630] Prompt Sentence Examples

[0631] Below are some examples of specific prompts to input to the generative AI model:

[0632] "Please tell me the process flow of a system that collects the latest news content, summarizes the key points, and extracts and displays related keywords."

[0633] This system allows users to quickly grasp summary information and instantly access related information that they are interested in. This enables efficient collection and analysis of news content and precise information access based on users' interests.

[0634] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0635] Step 1:

[0636] News content collection

[0637] The server collects the latest news content from multiple news sites using RSS feeds, APIs, web scraping, etc.

[0638] Specific operation: The server sends a request to the news provider's API endpoint and retrieves the returned news content in JSON format.

[0639] Input: News site API endpoint, credentials.

[0640] Output: News content in JSON format.

[0641] Step 2:

[0642] News content analysis

[0643] The server analyzes the collected news content text using natural language processing (NLP) technology to extract important sentences and phrases.

[0644] What it does: The server uses an NLP library (e.g., spaCy) to tokenize the text, tag it with parts of speech, and extract key sentences and phrases.

[0645] Input: News content in JSON format.

[0646] Output: A list of key sentences and phrases.

[0647] Step 3:

[0648] Generate a summary

[0649] The server generates a summary based on the analyzed sentences and phrases, which is a few lines long and conveys the main points of the article.

[0650] Specific operation: The server combines important sentences, removes redundant parts, and constructs a summary sentence.

[0651] Input: A list of key sentences or phrases.

[0652] Output: Summary statement.

[0653] Step 4:

[0654] Keyword extraction

[0655] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[0656] Specific operation: The server tokenizes the summary sentence, extracts important nouns and verbs, and selects them as keywords.

[0657] Input: Abstract text.

[0658] Output: A list of keywords.

[0659] Step 5:

[0660] Generate related links

[0661] The server generates links to relevant web pages and digital information based on the extracted keywords.

[0662] Specific operation: The server uses a search API to obtain links related to each keyword and selects the most relevant ones.

[0663] Input: A list of keywords.

[0664] Output: A list of related links.

[0665] Step 6:

[0666] Summary and keyword distribution

[0667] The server distributes the generated summary article and keywords to the user terminal.

[0668] Specific operation: The server packages the summary article and keywords as an API response and sends it to the user's terminal.

[0669] Input: Abstract article, list of keywords.

[0670] Output: Abstract article and keywords sent to user terminal.

[0671] Step 7:

[0672] Keyword Selection

[0673] The user selects a keyword that interests them from the keywords displayed on the terminal.

[0674] Specific action: The user taps or clicks on a keyword on the screen.

[0675] Input: Keywords displayed on the user's terminal.

[0676] Output: The user's selected keywords.

[0677] Step 8:

[0678] Obtaining related information

[0679] The server retrieves relevant information from a database or the Internet based on the keywords selected by the user.

[0680] Specific operation: The server uses a database or API to search and retrieve information related to the selected keyword.

[0681] Input: Selected keyword.

[0682] Output: The relevant information retrieved.

[0683] Step 9:

[0684] Viewing related information

[0685] The terminal displays the acquired related information to the user.

[0686] Specific operation: The terminal converts the acquired information into an appropriate format and displays it.

[0687] Input: The relevant information retrieved.

[0688] Output: Relevant information displayed on the user's terminal.

[0689] (Application example 1)

[0690] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0691] Conventional news article distribution systems make it difficult for users to efficiently understand the content of news articles and quickly access information of interest. In particular, quickly obtaining links from news articles to related information requires manual searching, which takes time and effort. Another problem is the complicated process of extracting essential keywords from news and linking them to related information.

[0692] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0693] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, and means for extracting keywords from the generated summaries. This allows for efficient management of news articles and enables users to quickly access related information. The server also includes means for generating summaries using natural language processing technology and extracting keywords from the summaries using a generative AI model, and means for generating prompt sentences based on the extracted keywords and further identifying related information using the prompt sentences. This allows users to quickly obtain links to related information and detailed information by simply selecting keywords of interest, enabling efficient information gathering.

[0694] A "news article" is information reported in the form of text, images, video, etc. provided by a website or news provider.

[0695] "Means of collection" refers to the technical devices or methods used to collect news articles, such as through web scraping, RSS feeds, APIs, etc.

[0696] A "means for analyzing and generating a summary" is a technical device or method that uses natural language processing techniques to concisely summarize the key content or key points of a news article.

[0697] "Keyword extraction means" refers to a technical device or method that uses generative AI models or natural language processing techniques to extract the article's themes and important words from the summary text.

[0698] The "means for generating links to related information" is a technical device or method that creates hyperlinks to related web pages or database entries based on the extracted keywords.

[0699] A "distribution means" is a technical device or method that transmits the generated abstract and keywords to a user's device over a network.

[0700] "Displaying means" refers to a technical device or method that visually presents relevant information, summaries, and keywords on a user's device.

[0701] "Natural language processing technology" is a technology that enables computers to understand, analyze, and manipulate human language.

[0702] A "generative AI model" is an artificial intelligence technology that learns from large amounts of text data and extracts summaries and keywords from given text.

[0703] A "prompt sentence" is text data input to a generative AI model, and serves as a clue for the model to extract appropriate keywords and information.

[0704] A "user device" is an electronic device (e.g., smartphone, tablet, computer, etc.) for displaying news articles and related information.

[0705] The "means for identifying" refers to a technical device or method that searches for related information based on the extracted keywords and generated prompt sentences and provides it to the user.

[0706] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from the articles. This system is implemented using a server, a user device, natural language processing technology, and a generative AI model.

[0707] The server first collects news articles. Methods for collecting news articles include RSS feeds, API access, and web scraping. Next, the content of the collected news articles is analyzed. This analysis is performed using natural language processing (NLP) technology. Specifically, it uses Python libraries such as spaCy and transformers.

[0708] The server extracts important content from the analyzed text and generates a summary. This summary is condensed by a generative AI model into a few lines that convey the main points of the article. For example, a summary of the news article "A new smartphone has been announced and is attracting a lot of attention" is generated. Keywords are then extracted from this summary. For example, keywords such as "smartphone," "announcement," and "attention" are extracted.

[0709] Furthermore, the server generates a prompt based on the extracted keywords. This prompt is used as input data for the generative AI model to more specifically identify relevant information. An example of a prompt is, "Please tell me the latest information about the launch of a new smartphone."

[0710] Based on the extracted keywords and generated prompts, the server generates relevant links and delivers them to the user's device along with the summary, allowing the user to view the summary and keywords on their smartphone, tablet, or other device.

[0711] When a user selects a displayed keyword, the server retrieves detailed related information from a database or the Internet. The retrieved related information is then sent back to the user's device, where the user can view it. For example, if a user selects the keyword "smartphone," the server retrieves product information and review articles related to that smartphone and displays them on the user's device.

[0712] This allows users to efficiently grasp summaries of articles they are interested in and quickly access detailed information and related links. This system streamlines users' collection and digestion of news information, providing a high-quality user experience.

[0713] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0714] Step 1:

[0715] The server collects news articles.

[0716] Input: News provider's API or RSS feed URL.

[0717] Data processing: The server requests news article data from the input URL or API and retrieves the article data in JSON format or other formats.

[0718] Output: A list of collected news articles.

[0719] Step 2:

[0720] The server analyzes the collected news articles and generates summaries.

[0721] Input: The list of news articles collected in step 1.

[0722] Data processing: The server uses natural language processing (NLP) techniques to analyze the content of news articles. Libraries such as spaCy and transformers are used for analysis. The server then uses a generative AI model to generate a summary that summarizes the key points.

[0723] Output: A summary for each article.

[0724] Step 3:

[0725] The server extracts keywords from the generated summary.

[0726] Input: The summary text generated in step 2.

[0727] Data processing: The server again uses natural language processing technology to extract important keywords from the summary text, using a generative AI model.

[0728] Output: A list of extracted keywords.

[0729] Step 4:

[0730] The server generates a prompt sentence based on the extracted keywords and generates a link to related information.

[0731] Input: The list of keywords extracted in step 3.

[0732] Data processing: A generative AI model generates prompts based on keywords, identifies related information from the prompts, and generates links based on this identified information.

[0733] Output: A list of the generated prompt statements and associated links.

[0734] Step 5:

[0735] The server delivers the summary, keywords and related links to the user device.

[0736] Input: Abstract generated in step 2, keywords extracted in step 3, links generated in step 4.

[0737] Data processing: The server combines these data, formats them appropriately, and sends them to the user's device.

[0738] Output: Abstract, keywords, and related links delivered to the user's device.

[0739] Step 6:

[0740] The terminal displays the delivered summary and keywords.

[0741] Input: Abstract, keywords, and related links delivered in Step 5.

[0742] Data processing: The application receives the distributed data and displays it on the user interface, which the user can view.

[0743] Output: Abstract, keywords, and related links displayed in the user interface.

[0744] Step 7:

[0745] The user selects a displayed keyword.

[0746] Input: The keyword displayed in step 6.

[0747] Data processing: The user selects a keyword, which is then sent to the server.

[0748] Output: The selected keywords sent to the server.

[0749] Step 8:

[0750] The server retrieves relevant information based on the selected keywords.

[0751] Input: The selected keyword submitted in step 7.

[0752] Data processing: The server searches and retrieves relevant information based on the selected keywords from databases and the Internet.

[0753] Output: The relevant information retrieved.

[0754] Step 9:

[0755] The server distributes the retrieved relevant information to the user device.

[0756] Input: Relevant information obtained in step 8.

[0757] Data processing: The server formats the retrieved information and sends it to the user device.

[0758] Output: Relevant information delivered to user device.

[0759] Step 10:

[0760] The terminal displays the retrieved related information.

[0761] Input: Relevant information delivered in Step 9.

[0762] Data processing: The received relevant information is processed and displayed on the user interface.

[0763] Output: Relevant information displayed on the user interface.

[0764] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0765] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system dynamically adjusts the news content and related information according to the user's emotions, providing a personalized experience.

[0766] Basic configuration

[0767] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from them, generates links to related information, and delivers and displays them to users' devices. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and optimizes the information displayed based on those emotions.

[0768] Program processing

[0769] The program processing of this system will be explained in natural language below.

[0770] News article collection and analysis

[0771] 1. Collecting news articles

[0772] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, thereby obtaining article data from a wide range of news sources.

[0773] 2. Analysis of article content

[0774] The server analyzes the text of collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating summaries.

[0775] 3. Summary Generation

[0776] The server generates a summary from the analyzed article content. The summary is concisely summarized in a few lines and conveys the essence of the article.

[0777] Keyword extraction and distribution

[0778] 4. Keyword extraction

[0779] The server extracts keywords from the abstract using natural language processing techniques such as TF-IDF and Word2Vec, thereby identifying keywords related to the main themes of the article.

[0780] 5. Generating Related Links

[0781] The server generates links to related information based on the extracted keywords, including links to product pages, official websites, review articles, etc.

[0782] 6. Summary Article and Keyword Distribution

[0783] The server delivers the generated summary article and keywords to the user's device, providing information in real time via API.

[0784] Acquisition and display of user operations and related information

[0785] 7. Keyword Selection

[0786] The user selects keywords that interest them from those displayed on the device, and performs operations by tapping or clicking.

[0787] 8. Obtaining related information

[0788] The server retrieves relevant information based on user-selected keywords, providing up-to-date information using internet searches and database queries.

[0789] 9. Display of related information

[0790] The device displays relevant information to the user, including product details, reviews, official websites, and more.

[0791] Combining Emotion Engines

[0792] One of the features of the present invention is that it incorporates an emotion engine that recognizes the user's emotions, which adds the following processing:

[0793] 10. Emotional Recognition

[0794] The device recognizes emotions from the user's facial expressions, voice, input, etc. The emotion engine uses machine learning algorithms to identify emotional states.

[0795] 11. Information Optimization

[0796] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, it provides more detailed information and related news. On the other hand, if the user is in a negative emotional state, it prioritizes the display of concise information and relaxing content.

[0797] Specific examples

[0798] For example, if a user is viewing a news article titled "New Smartphone Announcement," the following processing will occur:

[0799] 1. The server collects news articles.

[0800] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[0801] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[0802] 4. The server generates links to relevant product pages and review articles.

[0803] 5. The server delivers the summary and keywords to the user's device.

[0804] 6. The user selects the keyword "smartphone."

[0805] 7. The server retrieves the relevant information and displays the details page to the user.

[0806] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[0807] In this way, information provision can be optimized according to the user's emotions, resulting in a more personalized news viewing experience.

[0808] The processing flow will be explained below.

[0809] Step 1:

[0810] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, allowing for the rapid acquisition of new articles from a wide range of news sources.

[0811] Step 2:

[0812] The server analyzes the collected news article text using natural language processing (NLP) techniques, tokenizing the sentences in the article, performing morphological analysis, and assigning an importance score to each sentence.

[0813] Step 3:

[0814] The server generates a summary based on the analyzed article content. The summary is usually a few lines long and succinctly conveys the main points of the article.

[0815] Step 4:

[0816] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec to determine keywords that reflect the main themes of the article.

[0817] Step 5:

[0818] The server generates links to related information based on the extracted keywords, including links to related product pages, official websites, review articles, etc.

[0819] Step 6:

[0820] The server delivers the generated summary article and keywords to the user's device, using an API to send data in real time so that the user can receive the information immediately.

[0821] Step 7:

[0822] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the article's outline.

[0823] Step 8:

[0824] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[0825] Step 9:

[0826] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[0827] Step 10:

[0828] The device displays the retrieved relevant information to the user, including product detail pages, reviews, official websites, and more, allowing users to quickly access the information they are looking for.

[0829] Step 11:

[0830] The device uses an emotion engine to recognize emotions from the user's facial expressions, voice, input, etc. Machine learning algorithms are used to identify the user's emotional state.

[0831] Step 12:

[0832] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a negative emotional state, it will prioritize displaying concise information and relaxing content to optimize the user experience.

[0833] Specific examples

[0834] For example, when processing a news article titled "New Smartphone Announced," the process would proceed as follows:

[0835] 1. The server collects news articles.

[0836] 2. The server analyzes the article and generates a summary: "A new smartphone model has been announced."

[0837] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[0838] 4. The server generates links to relevant product pages and review articles.

[0839] 5. The server delivers the summary and keywords to the user's terminal.

[0840] 6. The device will display the summary article and keywords.

[0841] 7. The user selects the keyword "smartphone."

[0842] 8. The server retrieves the relevant information and displays a details page to the user.

[0843] 9. The device recognizes the user's emotions.

[0844] 10. The server optimizes and displays relevant information such as detailed reviews and purchase links based on the user's sentiment.

[0845] This series of processes allows users to efficiently grasp the news and quickly obtain relevant information that matches their emotional state.

[0846] Example 2

[0847] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0848] In recent years, information overload has made it difficult for users to quickly and efficiently obtain the information they need. With the vast amount of news articles being generated daily, it takes a great deal of time and effort for users to grasp the important content. Furthermore, there is a lack of information provided that is tailored to the user's emotional state, creating a need for improved user experience. Current technology faces the challenge of achieving a continuous flow of news article collection, analysis, and distribution, as well as information optimization through user emotion recognition. To address these challenges, an information delivery system that combines immediacy and personalization to meet user needs is needed.

[0849] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0850] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for recognizing a user's emotion, and means for optimizing display information based on the recognized user's emotion. This allows users to efficiently understand daily news articles and quickly obtain related information based on keywords extracted from the articles. Furthermore, information is dynamically adjusted according to the user's emotional state, providing a more personalized experience.

[0851] A "news article aggregator" is a software and hardware mechanism for aggregating news articles from multiple sources on the Internet.

[0852] "Means of analyzing the content of collected news articles and generating summaries" refers to the technology and process of using natural language processing technology to understand and analyze the content of news articles and generate a concise summary.

[0853] "Means for extracting keywords from the generated summaries" refers to algorithms and techniques for identifying major themes and important words from the generated summaries and extracting them as keywords.

[0854] The "means for generating links to related information based on extracted keywords" is a mechanism for dynamically generating links to related information or web pages based on extracted keywords.

[0855] "Means for delivering the generated summary and keywords to the user's terminal" refers to the communication technology and infrastructure for transmitting and delivering the generated summary and keywords to the user's terminal in real time.

[0856] "Means for recognizing user emotions" refers to emotion recognition technology and sensor devices for detecting and identifying emotions from the user's facial expressions, voice, input content, etc.

[0857] "Means for optimizing display information based on recognized user emotions" refers to a technology that dynamically changes the content and format of the information to be displayed based on the detected emotional state of the user, thereby providing information that more appropriately meets the user's needs and situation.

[0858] The present invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, the present invention is characterized by combining an emotion engine that recognizes the user's emotions, dynamically adjusting the news content and related information according to the user's emotions, providing a personalized experience.

[0859] Basic configuration

[0860] The system of the present invention includes the following components:

[0861] News article collection method

[0862] News article analysis methods

[0863] Summary generation means

[0864] Keyword extraction method

[0865] Related link generation method

[0866] Abstract and Keyword Distribution Methods

[0867] A means of recognizing user emotions

[0868] How to optimize the information displayed

[0869] News article collection and analysis

[0870] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping. This is done using Python's "Requests" library, among other tools. The collected article text is then analyzed using natural language processing (NLP) techniques. NLP libraries such as "SpaCy" and "NLTK" are used. This identifies the important parts and main themes of the article and generates a concise summary.

[0871] Keyword extraction and link generation for related information

[0872] The server uses techniques such as TF-IDF and Word2Vec to extract keywords from the generated summary. Based on the extracted keywords, the server generates links to related information, including product pages, official websites, and review articles. An API is then used to deliver the generated summary and keywords to the user's device.

[0873] User interaction and emotion recognition

[0874] Users can obtain relevant information of interest by selecting keywords displayed on their device. Based on the selected keywords, the server retrieves relevant information using Internet searches and database queries and displays it on the device. In addition, the device recognizes emotions from the user's facial expressions, voice, and input content. Software such as "OpenFace" and "Affectiva" is used as the emotion engine.

[0875] Information Optimization

[0876] The server optimizes the displayed information based on the user's recognized emotions. For example, if the user is excited, it will prioritize detailed spec reviews and purchase links, but if the user is in a negative emotional state, it will display relaxing content.

[0877] Specific examples

[0878] For example, if a user is looking at a news article about a new smartphone being announced, the following happens:

[0879] 1. The server collects news articles.

[0880] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[0881] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[0882] 4. The server generates links to relevant product pages and review articles.

[0883] 5. The server delivers the summary and keywords to the user's terminal.

[0884] 6. The user selects the keyword "smartphone."

[0885] 7. The server retrieves the relevant information and displays the details page to the user.

[0886] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[0887] Example prompts for generative AI models

[0888] An example of a prompt to input to a generative AI model is as follows:

[0889] Imagine a user is reading an article about a new smartphone. This system collects and analyzes news articles to generate summaries. It then extracts keywords from the summaries and generates links to related information. It then uses an emotion engine to recognize the user's emotions and dynamically adjusts the information displayed based on those emotions. If the user selects the keyword "smartphone," the server retrieves related information and the device displays detailed information. Please explain this process in detail, along with the system's processing steps.

[0890] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0891] Step 1: Gather news articles

[0892] Input: RSS feed URL of the news site, API endpoint, website URL to be scraped.

[0893] How it works: The server collects news articles using RSS feeds, APIs, and web scraping. Specifically, it uses the Python "Requests" library to send requests to news site APIs and parses the JSON data it receives.

[0894] Output: JSON or text data of collected news articles.

[0895] Step 2: Analyzing the article content

[0896] Input: Collected text data of news articles.

[0897] How it works: The server analyzes the content of articles using NLP libraries like SpaCy and NLTK to identify important parts and major themes of the article. The analysis includes morphological and contextual analysis.

[0898] Output: Information on the main themes and key parts of the analyzed articles.

[0899] Step 3: Generate a summary

[0900] Input: Parsed article content.

[0901] How it works: The server generates a summary based on the analysis results. The summary is concisely summarized in a few lines and conveys the essence of the article. The server uses an extractive summarization algorithm to extract sentences that are deemed particularly important.

[0902] Output: The generated summary.

[0903] Step 4: Keyword extraction

[0904] Input: The generated summary sentence.

[0905] How it works: The server extracts keywords from the abstract using techniques such as TF-IDF and Word2Vec, which identifies important keywords related to the main theme of the article.

[0906] Output: Extracted keyword list.

[0907] Step 5: Generate related links

[0908] Input: Extracted keyword list.

[0909] How it works: The server generates links to related information based on keywords. This includes URLs to product pages, official websites, review articles, etc. Link generation is done using search engine APIs and pre-collected databases.

[0910] Output: A list of generated related links.

[0911] Step 6: Summary and Keyword Distribution

[0912] Input: Generated abstract and keyword list.

[0913] How it works: The server delivers the generated summary and keywords to the user's device, providing real-time information via API and sending data to the device application.

[0914] Output: Summary and keywords delivered to the user's terminal.

[0915] Step 7: Selecting Keywords

[0916] Input: Keyword list delivered to the device.

[0917] How it works: The user selects keywords that interest them from those displayed on the device, and performs the action by tapping or clicking. This selection action is detected by the device and triggers the next step.

[0918] Output: The selected keywords.

[0919] Step 8: Obtain related information

[0920] Input: A keyword selected by the user.

[0921] How it works: The server retrieves relevant information based on the selected keywords, specifically using internet searches and database queries to gather the latest information.

[0922] Output: The relevant information retrieved.

[0923] Step 9: View related information

[0924] Input: The relevant information retrieved.

[0925] Operation: The device displays the retrieved related information to the user. This may include product detail pages, review articles, official websites, etc. The related information is displayed through a user interface.

[0926] Output: Relevant information displayed on the terminal.

[0927] Step 10: Recognize emotions

[0928] Input: User facial expressions, voice, input, etc.

[0929] How it works: The device recognizes emotions from the user's facial expressions, voice, and input. The emotion engine uses machine learning algorithms to identify emotional states, specifically software like "OpenFace" and "Affectiva."

[0930] Output: Perceived emotional state.

[0931] Step 11: Information optimization

[0932] Input: The perceived emotional state of the user.

[0933] How it works: The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, detailed spec reviews and purchase links will be prioritized. Conversely, if the user is in a negative emotional state, concise information and relaxing content will be prioritized.

[0934] Output: Information display optimized for the user's emotional state.

[0935] (Application example 2)

[0936] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0937] In today's information society, users are required to efficiently and quickly obtain the information they need from a vast amount of news articles. Furthermore, if the content of news articles and related information is provided to users without taking into account the user's emotional state, information receptivity may be reduced. Conventional news delivery systems are unable to dynamically adjust information to reflect the individual user's emotional state, limiting the improvement of usability. A new approach to solving this problem is needed.

[0938] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for acquiring related information when a keyword displayed on the user terminal is selected, means for displaying the acquired related information on the user terminal, emotion recognition means for recognizing the user's emotion, and means for dynamically changing the related information and keywords to be displayed based on the recognized user emotion. This enables a user to efficiently grasp and select related information and news content in a manner appropriate to their emotional state.

[0939] "Means for collecting news articles" is a function that automatically obtains the latest news articles from multiple news sources on the Internet.

[0940] "Means for analyzing the content of news articles and generating summaries" refers to a function that uses natural language processing technology to identify important parts and main themes of collected news articles and generate concise summaries.

[0941] The "means for extracting keywords from summaries" is a function for identifying and extracting highly relevant keywords from the generated summaries.

[0942] The "means for generating links to related information" is a function that automatically generates links to related information or web pages based on the extracted keywords.

[0943] The "means for delivering the summary and keywords to the user terminal" is a function for transmitting the generated summary and keywords to the user terminal and displaying them.

[0944] "Means for obtaining related information when a keyword displayed by a user terminal is selected" is a function for obtaining information related to a keyword when the user selects the keyword displayed on the terminal.

[0945] The "means for displaying the acquired related information on the user terminal" is a function for displaying the acquired related information on the user terminal.

[0946] The "emotion recognition means for recognizing the user's emotions" is a function for identifying the user's emotional state from the user's facial expressions, voice, and input contents.

[0947] The "means for dynamically changing the related information and keywords to be displayed" is a function for changing the content of the information and keywords to be displayed in real time based on the recognized user's emotions.

[0948] The present invention provides a system and method for efficiently understanding news articles, and further provides the ability to dynamically adjust news and related information based on user sentiment. The present invention has the following system configuration.

[0949] 1. Collecting news articles

[0950] The server collects the latest news articles from multiple news sources (news websites, RSS feeds, etc.). This can be achieved by subscribing to RSS feeds, using API integration, or using web scraping techniques. This aggregation consolidates news articles from a wide range of sources.

[0951] 2. News article analysis and summary generation

[0952] The server analyzes the collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating concise summaries. This summary generation is achieved using, for example, the nltk library and various machine learning techniques.

[0953] 3. Keyword extraction

[0954] The server uses natural language processing techniques such as Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec to extract key keywords from the generated summary, thereby identifying the main themes and relevant words of the article.

[0955] 4. Linking to related information

[0956] Based on the extracted keywords, it generates links to relevant web pages and databases, including product pages, official websites, and review articles, allowing users to access more detailed information.

[0957] 5. Summary and Keyword Distribution

[0958] The server delivers the generated summary and keywords to the user's device. This information is provided in real time via an API and can be viewed on the user's device.

[0959] 6. User operations and display of related information

[0960] Users can obtain detailed related information by tapping on keywords they are interested in from those displayed on their device. The server retrieves further related information based on the keywords selected by the user and displays it on the user's device.

[0961] 7. Emotion Recognition and Information Optimization

[0962] The device analyzes the user's facial expressions, voice, and input content to identify their emotional state using an emotion recognition engine. This emotion recognition uses machine learning algorithms such as EmotionEngine. The server dynamically adjusts the news articles and related information displayed based on the user's recognized emotion. For example, if the user is in a positive emotional state, more detailed information will be displayed first, while if the user is in a negative emotional state, brief information will be displayed first.

[0963] Specific examples

[0964] For example, if a user is viewing a news article titled "Announcement of a new smart device," the following process takes place: The server collects news articles, analyzes them, and generates summaries. Keywords such as "smart device" and "announcement" are extracted from the generated summaries. The server generates links to related product pages and review articles and delivers the summaries and keywords to the user's device. When the user selects the keyword "smart device," the server retrieves related information and displays a detailed page to the user. At this time, the device recognizes the user's emotions; for example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[0965] Prompt Sentence Examples

[0966] Prompt: "Design a system that helps users efficiently keep up with breaking news and delivers information accordingly. Additionally, add the ability to recognize the user's emotions and adjust the content accordingly."

[0967] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0968] Step 1:

[0969] The server collects news articles. Specifically, it obtains article data from multiple news sources using RSS feeds, news site APIs, and web scraping technology. It uses a list of URLs as input and obtains a list of collected text data as output.

[0970] Step 2:

[0971] The server analyzes the content of collected news articles and generates summaries. Specifically, it uses natural language processing (NLP) techniques to analyze articles and identify important parts and main themes. The article text is used as input, and a summary is obtained as output.

[0972] Step 3:

[0973] The server extracts keywords from the generated summary. In this step, it uses natural language processing techniques such as TF-IDF and Word2Vec to identify keywords. It uses the summary sentence as input and obtains a list of keywords as output.

[0974] Step 4:

[0975] The server generates links to related information based on the extracted keywords, including related product pages, official websites, review articles, etc. It uses a list of keywords as input and obtains a list of related links as output.

[0976] Step 5:

[0977] The server delivers the generated summary and keywords to the user's device, transmitting information in real time via an API. The server uses the generated summary, keywords, and a list of related links as input, and delivers data to the user's device as output.

[0978] Step 6:

[0979] The user selects keywords displayed on the device by tapping or clicking on the keyword of interest. The input is the keyword selection, and the output is the selected keyword.

[0980] Step 7:

[0981] The server retrieves relevant information based on the selected keywords. It uses internet searches and database queries to gather up-to-date relevant information. It uses the selected keywords as input and gets relevant information as output.

[0982] Step 8:

[0983] The device displays the retrieved related information to the user, including product detail pages and review articles. The retrieved related information is used as input, and the display on the user device is used as output.

[0984] Step 9:

[0985] The device uses an emotion recognition engine to recognize the user's emotions. It identifies emotions from the user's facial expressions, voice, and input content. It uses the user's facial expression data and voice data as input and obtains the user's emotional state as output.

[0986] Step 10:

[0987] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. If the user is in a positive emotional state, detailed information is displayed, and if the user is in a negative emotional state, brief information is displayed preferentially. Using the emotional state and relevant information as input, tailored information is obtained as output.

[0988] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0989] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0990] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0991] [Third embodiment]

[0992] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0993] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0994] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0995] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0996] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0997] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0998] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0999] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1000] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1001] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1002] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1003] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1004] The present invention relates to a system that enables users to efficiently understand daily news articles and then navigate to related information based on keywords extracted from those articles. This system provides a high-quality user experience by linking the server, terminals, and users.

[1005] Basic configuration

[1006] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to user terminals, allowing users to quickly access detailed related information by selecting keywords.

[1007] Program processing

[1008] The program processing of this system will be explained in natural language below.

[1009] News article collection and analysis

[1010] 1. Collecting news articles

[1011] The server collects the latest news articles from multiple news sites using methods such as RSS feeds, APIs, and web scraping.

[1012] Example: "The server uses the news provider's API to retrieve newly posted article data."

[1013] 2. Analysis of article content

[1014] The server analyzes the collected news article text using natural language processing (NLP) technology to extract key sentences and phrases.

[1015] Example: "The server uses a parsing engine to segment the news article and identify key points."

[1016] 3. Summary Generation

[1017] The server generates a summary from the analyzed article content. The summary is a few lines long and conveys the main points of the article.

[1018] Example: "The server combines key sentences to generate a summary sentence: 'A new smartphone model has been released and is attracting a lot of attention.'"

[1019] Keyword extraction and distribution

[1020] 4. Keyword extraction

[1021] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[1022] Example: "The server extracts keywords such as 'smartphone,' 'model,' and 'announcement' from the abstract."

[1023] 5. Generating Related Links

[1024] The server generates links to related product pages, official websites, review articles, etc. based on the extracted keywords.

[1025] Example: "The server generates links to e-commerce sites and review articles related to 'smartphones'."

[1026] 6. Summary Article and Keyword Distribution

[1027] The server distributes the generated summary article and keywords to the user's terminal.

[1028] Example: "The server sends the summary article and keywords to the user's smartphone via API."

[1029] Acquisition and display of user operations and related information

[1030] 7. Keyword Selection

[1031] The user selects a keyword that interests them from the keywords displayed on the terminal.

[1032] Example: "The user taps on the keyword 'smartphone' displayed on their smartphone."

[1033] 8. Obtaining related information

[1034] The server retrieves relevant information from databases and the Internet based on the keywords selected by the user.

[1035] Example: "The server retrieves the latest product information and related site information for 'smartphones'."

[1036] 9. Display of related information

[1037] The terminal displays the acquired related information to the user, who can then use it to obtain more detailed information or purchase the product.

[1038] Example: "The device displays the purchase page and detailed reviews of the latest smartphone models."

[1039] Specific examples

[1040] For example, if the server collects a news article that says "famous company announces new smartphone," the following process will be performed:

[1041] 1. The server retrieves the news article.

[1042] 2. The server analyzes the article and generates a summary: "A well-known company announces a new smartphone."

[1043] 3. The server extracts the keywords "famous company," "smartphone," and "announcement."

[1044] 4. The server generates links to relevant product pages and review articles.

[1045] 5. The server delivers the summary and keywords to the user's device.

[1046] 6. The user selects the keyword "smartphone."

[1047] 7. The server retrieves the relevant information and displays a detailed information page to the user.

[1048] This allows users to quickly grasp summary information and instantly access related information that they are interested in. This system enables efficient news information collection and digestion, and supports users' actions quickly.

[1049] The processing flow will be explained below.

[1050] Step 1:

[1051] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, or web scraping technology, thereby securing a large amount of new article data.

[1052] Step 2:

[1053] The server analyzes the collected news articles using natural language processing (NLP) technology. Specifically, the article text is tokenized, morphological analysis is performed, and an importance score is assigned to each sentence.

[1054] Step 3:

[1055] The server extracts key sentences from the analyzed article content and generates a summary based on these. The summary is a few lines summarizing the highlights of the article.

[1056] Step 4:

[1057] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec, thereby identifying keywords related to the main themes of the article.

[1058] Step 5:

[1059] The server generates links to related information based on the extracted keywords, using URL information from a database or information obtained from the Internet.

[1060] Step 6:

[1061] The server delivers the generated summary article and keywords to the user's device, and transmits data using an API to provide information to the user in real time.

[1062] Step 7:

[1063] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the outline of the article.

[1064] Step 8:

[1065] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[1066] Step 9:

[1067] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[1068] Step 10:

[1069] The device displays relevant information to the user, including product detail pages, reviews, official websites, etc. It provides detailed links and descriptions to help users quickly access the information they are looking for.

[1070] This series of steps results in a system that allows users to quickly understand news summaries and easily access information of interest.

[1071] Example 1

[1072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1073] In modern society, people are increasingly exposed to a huge amount of news information every day, making it important to efficiently collect, analyze, and understand that information. Furthermore, there is a need for a method that allows users to quickly extract information of interest and smoothly access related information. Conventional technologies require time and effort to manually collect and analyze news articles, and extensive research is required to find related information, making it difficult to improve the user experience.

[1074] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1075] In this invention, the server includes means for collecting news content, means for analyzing the collected news content to generate summaries, means for extracting keywords from the generated summaries, means for using natural language processing techniques to generate summaries and extract keywords, means for converting the news content, summaries, and keywords into an analyzable format, and means for searching and distributing related information via a digital network, thereby enabling efficient collection and analysis of news content and rapid access to related information of user interest.

[1076] "News content" refers to news articles and reports published online.

[1077] "Means of collection" refers to the methods or mechanisms used to obtain news content from the Internet.

[1078] "Means of analysis" refers to the method or mechanism for analyzing the content of collected news content and organizing the information.

[1079] "Means for generating a summary" refers to a method or mechanism for extracting the main points from collected and analyzed news content and summarizing them in a concise format.

[1080] "Keyword extraction means" refers to a method or mechanism for identifying and extracting important words and phrases from the generated summary.

[1081] "Means for generating links to related information" refers to a method or mechanism for creating links to related web pages or digital information based on the extracted keywords.

[1082] "User Device" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[1083] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate natural language used by humans.

[1084] "Digital network" refers to the mechanism for transmitting data over the Internet and other digital communications infrastructure.

[1085] "Database" refers to a system for efficiently managing, storing, and retrieving structured information.

[1086] "Server" refers to a computer system that provides a particular service and processes and distributes data over a network.

[1087] The present invention relates to a system that enables users to efficiently grasp daily news content and then navigate to related information based on keywords extracted from that content. This system provides a high-quality user experience by linking the server, terminals, and users.

[1088] Basic configuration

[1089] This system collects news content, analyzes the content using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to users' devices.By selecting keywords, users can quickly access detailed related information.

[1090] Hardware and Software Configuration

[1091] The main components of this system include the following hardware and software:

[1092] Server: A computer system that collects, analyzes, summarizes, extracts keywords, generates related links, and distributes news content.

[1093] Software: Natural language processing libraries (e.g., spaCy), data processing libraries (e.g., pandas), communication libraries (e.g., requests).

[1094] User terminal: A device that displays the summary and keywords delivered from the server and receives user operations.

[1095] Hardware: Smartphones, tablets, computers.

[1096] Software: web browser, mobile application.

[1097] Program processing

[1098] The server collects the latest news content using RSS feeds, APIs, web scraping, etc. from news sites. The collected content is analyzed using natural language processing techniques to extract important sentences and phrases. A summary is then generated from the extracted information, and keywords are extracted. For example, a specific prompt can be given, such as "The server will use the news provider's API to obtain newly posted article data."

[1099] The generated summary and keywords are delivered from the server to the user's device. The user's device displays them, allowing the user to select keywords of interest. Once a keyword is selected, the server searches for related information based on the selected keyword and displays the retrieved information on the user's device. For example, the user taps on the keyword "smartphone" displayed on their smartphone.

[1100] Specific examples

[1101] For example, if the server collects news content such as "A famous company announces a new smartphone," the following specific processing occurs:

[1102] 1. The server sends a request to an API endpoint to retrieve news content.

[1103] 2. The server uses an NLP engine (e.g., spaCy) to analyze the news content and generate a summary.

[1104] 3. The server extracts keywords such as "famous company," "smartphone," and "announcement" from the summary.

[1105] 4. The server generates links to relevant product pages and reviews.

[1106] 5. The server delivers the summary and keywords to the user's terminal.

[1107] 6. The user taps on the keyword "smartphone" displayed on the smartphone screen.

[1108] 7. The server searches for relevant information and displays the retrieved information on the user's terminal.

[1109] Prompt Sentence Examples

[1110] Below are some examples of specific prompts to input to the generative AI model:

[1111] "Please tell me the process flow of a system that collects the latest news content, summarizes the key points, and extracts and displays related keywords."

[1112] This system allows users to quickly grasp summary information and instantly access related information that they are interested in. This enables efficient collection and analysis of news content and precise information access based on users' interests.

[1113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1114] Step 1:

[1115] News content collection

[1116] The server collects the latest news content from multiple news sites using RSS feeds, APIs, web scraping, etc.

[1117] Specific operation: The server sends a request to the news provider's API endpoint and retrieves the returned news content in JSON format.

[1118] Input: News site API endpoint, credentials.

[1119] Output: News content in JSON format.

[1120] Step 2:

[1121] News content analysis

[1122] The server analyzes the collected news content text using natural language processing (NLP) technology to extract important sentences and phrases.

[1123] What it does: The server uses an NLP library (e.g., spaCy) to tokenize the text, tag it with parts of speech, and extract key sentences and phrases.

[1124] Input: News content in JSON format.

[1125] Output: A list of key sentences and phrases.

[1126] Step 3:

[1127] Generate a summary

[1128] The server generates a summary based on the analyzed sentences and phrases, which is a few lines long and conveys the main points of the article.

[1129] Specific operation: The server combines important sentences, removes redundant parts, and constructs a summary sentence.

[1130] Input: A list of key sentences or phrases.

[1131] Output: Summary statement.

[1132] Step 4:

[1133] Keyword extraction

[1134] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[1135] Specific operation: The server tokenizes the summary sentence, extracts important nouns and verbs, and selects them as keywords.

[1136] Input: Abstract text.

[1137] Output: A list of keywords.

[1138] Step 5:

[1139] Generate related links

[1140] The server generates links to relevant web pages and digital information based on the extracted keywords.

[1141] Specific operation: The server uses a search API to obtain links related to each keyword and selects the most relevant ones.

[1142] Input: A list of keywords.

[1143] Output: A list of related links.

[1144] Step 6:

[1145] Summary and keyword distribution

[1146] The server distributes the generated summary article and keywords to the user terminal.

[1147] Specific operation: The server packages the summary article and keywords as an API response and sends it to the user's terminal.

[1148] Input: Abstract article, list of keywords.

[1149] Output: Abstract article and keywords sent to user terminal.

[1150] Step 7:

[1151] Keyword Selection

[1152] The user selects a keyword that interests them from the keywords displayed on the terminal.

[1153] Specific action: The user taps or clicks on a keyword on the screen.

[1154] Input: Keywords displayed on the user's terminal.

[1155] Output: The user's selected keywords.

[1156] Step 8:

[1157] Obtaining related information

[1158] The server retrieves relevant information from a database or the Internet based on the keywords selected by the user.

[1159] Specific operation: The server uses a database or API to search and retrieve information related to the selected keyword.

[1160] Input: Selected keyword.

[1161] Output: The relevant information retrieved.

[1162] Step 9:

[1163] Viewing related information

[1164] The terminal displays the acquired related information to the user.

[1165] Specific operation: The terminal converts the acquired information into an appropriate format and displays it.

[1166] Input: The relevant information retrieved.

[1167] Output: Relevant information displayed on the user's terminal.

[1168] (Application example 1)

[1169] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1170] Conventional news article distribution systems make it difficult for users to efficiently understand the content of news articles and quickly access information of interest. In particular, quickly obtaining links from news articles to related information requires manual searching, which takes time and effort. Another problem is the complicated process of extracting essential keywords from news and linking them to related information.

[1171] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1172] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, and means for extracting keywords from the generated summaries. This allows for efficient management of news articles and enables users to quickly access related information. The server also includes means for generating summaries using natural language processing technology and extracting keywords from the summaries using a generative AI model, and means for generating prompt sentences based on the extracted keywords and further identifying related information using the prompt sentences. This allows users to quickly obtain links to related information and detailed information by simply selecting keywords of interest, enabling efficient information gathering.

[1173] A "news article" is information reported in the form of text, images, video, etc. provided by a website or news provider.

[1174] "Means of collection" refers to the technical devices or methods used to collect news articles, such as through web scraping, RSS feeds, APIs, etc.

[1175] A "means for analyzing and generating a summary" is a technical device or method that uses natural language processing techniques to concisely summarize the key content or key points of a news article.

[1176] "Keyword extraction means" refers to a technical device or method that uses generative AI models or natural language processing techniques to extract the article's themes and important words from the summary text.

[1177] The "means for generating links to related information" is a technical device or method that creates hyperlinks to related web pages or database entries based on the extracted keywords.

[1178] A "distribution means" is a technical device or method that transmits the generated abstract and keywords to a user's device over a network.

[1179] "Displaying means" refers to a technical device or method that visually presents relevant information, summaries, and keywords on a user's device.

[1180] "Natural language processing technology" is a technology that enables computers to understand, analyze, and manipulate human language.

[1181] A "generative AI model" is an artificial intelligence technology that learns from large amounts of text data and extracts summaries and keywords from given text.

[1182] A "prompt sentence" is text data input to a generative AI model, and serves as a clue for the model to extract appropriate keywords and information.

[1183] A "user device" is an electronic device (e.g., smartphone, tablet, computer, etc.) for displaying news articles and related information.

[1184] The "means for identifying" refers to a technical device or method that searches for related information based on the extracted keywords and generated prompt sentences and provides it to the user.

[1185] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from the articles. This system is implemented using a server, a user device, natural language processing technology, and a generative AI model.

[1186] The server first collects news articles. Methods for collecting news articles include RSS feeds, API access, and web scraping. Next, the content of the collected news articles is analyzed. This analysis is performed using natural language processing (NLP) technology. Specifically, it uses Python libraries such as spaCy and transformers.

[1187] The server extracts important content from the analyzed text and generates a summary. This summary is condensed by a generative AI model into a few lines that convey the main points of the article. For example, a summary of the news article "A new smartphone has been announced and is attracting a lot of attention" is generated. Keywords are then extracted from this summary. For example, keywords such as "smartphone," "announcement," and "attention" are extracted.

[1188] Furthermore, the server generates a prompt based on the extracted keywords. This prompt is used as input data for the generative AI model to more specifically identify relevant information. An example of a prompt is, "Please tell me the latest information about the launch of a new smartphone."

[1189] Based on the extracted keywords and generated prompts, the server generates relevant links and delivers them to the user's device along with the summary, allowing the user to view the summary and keywords on their smartphone, tablet, or other device.

[1190] When a user selects a displayed keyword, the server retrieves detailed related information from a database or the Internet. The retrieved related information is then sent back to the user's device, where the user can view it. For example, if a user selects the keyword "smartphone," the server retrieves product information and review articles related to that smartphone and displays them on the user's device.

[1191] This allows users to efficiently grasp summaries of articles they are interested in and quickly access detailed information and related links. This system streamlines users' collection and digestion of news information, providing a high-quality user experience.

[1192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1193] Step 1:

[1194] The server collects news articles.

[1195] Input: News provider's API or RSS feed URL.

[1196] Data processing: The server requests news article data from the input URL or API and retrieves the article data in JSON format or other formats.

[1197] Output: A list of collected news articles.

[1198] Step 2:

[1199] The server analyzes the collected news articles and generates summaries.

[1200] Input: The list of news articles collected in step 1.

[1201] Data processing: The server uses natural language processing (NLP) techniques to analyze the content of news articles. Libraries such as spaCy and transformers are used for analysis. The server then uses a generative AI model to generate a summary that summarizes the key points.

[1202] Output: A summary for each article.

[1203] Step 3:

[1204] The server extracts keywords from the generated summary.

[1205] Input: The summary text generated in step 2.

[1206] Data processing: The server again uses natural language processing technology to extract important keywords from the summary text, using a generative AI model.

[1207] Output: A list of extracted keywords.

[1208] Step 4:

[1209] The server generates a prompt sentence based on the extracted keywords and generates a link to related information.

[1210] Input: The list of keywords extracted in step 3.

[1211] Data processing: A generative AI model generates prompts based on keywords, identifies related information from the prompts, and generates links based on this identified information.

[1212] Output: A list of the generated prompt statements and associated links.

[1213] Step 5:

[1214] The server delivers the summary, keywords and related links to the user device.

[1215] Input: Abstract generated in step 2, keywords extracted in step 3, links generated in step 4.

[1216] Data processing: The server combines these data, formats them appropriately, and sends them to the user's device.

[1217] Output: Abstract, keywords, and related links delivered to the user's device.

[1218] Step 6:

[1219] The terminal displays the delivered summary and keywords.

[1220] Input: Abstract, keywords, and related links delivered in Step 5.

[1221] Data processing: The application receives the distributed data and displays it on the user interface, which the user can view.

[1222] Output: Abstract, keywords, and related links displayed in the user interface.

[1223] Step 7:

[1224] The user selects a displayed keyword.

[1225] Input: The keyword displayed in step 6.

[1226] Data processing: The user selects a keyword, which is then sent to the server.

[1227] Output: The selected keywords sent to the server.

[1228] Step 8:

[1229] The server retrieves relevant information based on the selected keywords.

[1230] Input: The selected keyword submitted in step 7.

[1231] Data processing: The server searches and retrieves relevant information based on the selected keywords from databases and the Internet.

[1232] Output: The relevant information retrieved.

[1233] Step 9:

[1234] The server distributes the retrieved relevant information to the user device.

[1235] Input: Relevant information obtained in step 8.

[1236] Data processing: The server formats the retrieved information and sends it to the user device.

[1237] Output: Relevant information delivered to user device.

[1238] Step 10:

[1239] The terminal displays the retrieved related information.

[1240] Input: Relevant information delivered in Step 9.

[1241] Data processing: The received relevant information is processed and displayed on the user interface.

[1242] Output: Relevant information displayed on the user interface.

[1243] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1244] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system dynamically adjusts the news content and related information according to the user's emotions, providing a personalized experience.

[1245] Basic configuration

[1246] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from them, generates links to related information, and delivers and displays them to users' devices. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and optimizes the information displayed based on those emotions.

[1247] Program processing

[1248] The program processing of this system will be explained in natural language below.

[1249] News article collection and analysis

[1250] 1. Collecting news articles

[1251] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, thereby obtaining article data from a wide range of news sources.

[1252] 2. Analysis of article content

[1253] The server analyzes the text of collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating summaries.

[1254] 3. Summary Generation

[1255] The server generates a summary from the analyzed article content. The summary is concisely summarized in a few lines and conveys the essence of the article.

[1256] Keyword extraction and distribution

[1257] 4. Keyword extraction

[1258] The server extracts keywords from the abstract using natural language processing techniques such as TF-IDF and Word2Vec, thereby identifying keywords related to the main themes of the article.

[1259] 5. Generating Related Links

[1260] The server generates links to related information based on the extracted keywords, including links to product pages, official websites, review articles, etc.

[1261] 6. Summary Article and Keyword Distribution

[1262] The server delivers the generated summary article and keywords to the user's device, providing information in real time via API.

[1263] Acquisition and display of user operations and related information

[1264] 7. Keyword Selection

[1265] The user selects keywords that interest them from those displayed on the device, and performs operations by tapping or clicking.

[1266] 8. Obtaining related information

[1267] The server retrieves relevant information based on user-selected keywords, providing up-to-date information using internet searches and database queries.

[1268] 9. Display of related information

[1269] The device displays relevant information to the user, including product details, reviews, official websites, and more.

[1270] Combining Emotion Engines

[1271] One of the features of the present invention is that it incorporates an emotion engine that recognizes the user's emotions, which adds the following processing:

[1272] 10. Emotional Recognition

[1273] The device recognizes emotions from the user's facial expressions, voice, input, etc. The emotion engine uses machine learning algorithms to identify emotional states.

[1274] 11. Information Optimization

[1275] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, it provides more detailed information and related news. On the other hand, if the user is in a negative emotional state, it prioritizes the display of concise information and relaxing content.

[1276] Specific examples

[1277] For example, if a user is viewing a news article titled "New Smartphone Announcement," the following processing will occur:

[1278] 1. The server collects news articles.

[1279] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[1280] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[1281] 4. The server generates links to relevant product pages and review articles.

[1282] 5. The server delivers the summary and keywords to the user's device.

[1283] 6. The user selects the keyword "smartphone."

[1284] 7. The server retrieves the relevant information and displays the details page to the user.

[1285] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[1286] In this way, information provision can be optimized according to the user's emotions, resulting in a more personalized news viewing experience.

[1287] The processing flow will be explained below.

[1288] Step 1:

[1289] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, allowing for the rapid acquisition of new articles from a wide range of news sources.

[1290] Step 2:

[1291] The server analyzes the collected news article text using natural language processing (NLP) techniques, tokenizing the sentences in the article, performing morphological analysis, and assigning an importance score to each sentence.

[1292] Step 3:

[1293] The server generates a summary based on the analyzed article content. The summary is usually a few lines long and succinctly conveys the main points of the article.

[1294] Step 4:

[1295] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec to determine keywords that reflect the main themes of the article.

[1296] Step 5:

[1297] The server generates links to related information based on the extracted keywords, including links to related product pages, official websites, review articles, etc.

[1298] Step 6:

[1299] The server delivers the generated summary article and keywords to the user's device, using an API to send data in real time so that the user can receive the information immediately.

[1300] Step 7:

[1301] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the article's outline.

[1302] Step 8:

[1303] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[1304] Step 9:

[1305] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[1306] Step 10:

[1307] The device displays the retrieved relevant information to the user, including product detail pages, reviews, official websites, and more, allowing users to quickly access the information they are looking for.

[1308] Step 11:

[1309] The device uses an emotion engine to recognize emotions from the user's facial expressions, voice, input, etc. Machine learning algorithms are used to identify the user's emotional state.

[1310] Step 12:

[1311] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a negative emotional state, it will prioritize displaying concise information and relaxing content to optimize the user experience.

[1312] Specific examples

[1313] For example, when processing a news article titled "New Smartphone Announced," the process would proceed as follows:

[1314] 1. The server collects news articles.

[1315] 2. The server analyzes the article and generates a summary: "A new smartphone model has been announced."

[1316] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[1317] 4. The server generates links to relevant product pages and review articles.

[1318] 5. The server delivers the summary and keywords to the user's terminal.

[1319] 6. The device will display the summary article and keywords.

[1320] 7. The user selects the keyword "smartphone."

[1321] 8. The server retrieves the relevant information and displays a details page to the user.

[1322] 9. The device recognizes the user's emotions.

[1323] 10. The server optimizes and displays relevant information such as detailed reviews and purchase links based on the user's sentiment.

[1324] This series of processes allows users to efficiently grasp the news and quickly obtain relevant information that matches their emotional state.

[1325] Example 2

[1326] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1327] In recent years, information overload has made it difficult for users to quickly and efficiently obtain the information they need. With the vast amount of news articles being generated daily, it takes a great deal of time and effort for users to grasp the important content. Furthermore, there is a lack of information provided that is tailored to the user's emotional state, creating a need for improved user experience. Current technology faces the challenge of achieving a continuous flow of news article collection, analysis, and distribution, as well as information optimization through user emotion recognition. To address these challenges, an information delivery system that combines immediacy and personalization to meet user needs is needed.

[1328] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1329] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for recognizing a user's emotion, and means for optimizing display information based on the recognized user's emotion. This allows users to efficiently understand daily news articles and quickly obtain related information based on keywords extracted from the articles. Furthermore, information is dynamically adjusted according to the user's emotional state, providing a more personalized experience.

[1330] A "news article aggregator" is a software and hardware mechanism for aggregating news articles from multiple sources on the Internet.

[1331] "Means of analyzing the content of collected news articles and generating summaries" refers to the technology and process of using natural language processing technology to understand and analyze the content of news articles and generate a concise summary.

[1332] "Means for extracting keywords from the generated summaries" refers to algorithms and techniques for identifying major themes and important words from the generated summaries and extracting them as keywords.

[1333] The "means for generating links to related information based on extracted keywords" is a mechanism for dynamically generating links to related information or web pages based on extracted keywords.

[1334] "Means for delivering the generated summary and keywords to the user's terminal" refers to the communication technology and infrastructure for transmitting and delivering the generated summary and keywords to the user's terminal in real time.

[1335] "Means for recognizing user emotions" refers to emotion recognition technology and sensor devices for detecting and identifying emotions from the user's facial expressions, voice, input content, etc.

[1336] "Means for optimizing display information based on recognized user emotions" refers to a technology that dynamically changes the content and format of the information to be displayed based on the detected emotional state of the user, thereby providing information that more appropriately meets the user's needs and situation.

[1337] The present invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, the present invention is characterized by combining an emotion engine that recognizes the user's emotions, dynamically adjusting the news content and related information according to the user's emotions, providing a personalized experience.

[1338] Basic configuration

[1339] The system of the present invention includes the following components:

[1340] News article collection method

[1341] News article analysis methods

[1342] Summary generation means

[1343] Keyword extraction method

[1344] Related link generation method

[1345] Abstract and Keyword Distribution Methods

[1346] A means of recognizing user emotions

[1347] How to optimize the information displayed

[1348] News article collection and analysis

[1349] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping. This is done using Python's "Requests" library, among other tools. The collected article text is then analyzed using natural language processing (NLP) techniques. NLP libraries such as "SpaCy" and "NLTK" are used. This identifies the important parts and main themes of the article and generates a concise summary.

[1350] Keyword extraction and link generation for related information

[1351] The server uses techniques such as TF-IDF and Word2Vec to extract keywords from the generated summary. Based on the extracted keywords, the server generates links to related information, including product pages, official websites, and review articles. An API is then used to deliver the generated summary and keywords to the user's device.

[1352] User interaction and emotion recognition

[1353] Users can obtain relevant information of interest by selecting keywords displayed on their device. Based on the selected keywords, the server retrieves relevant information using Internet searches and database queries and displays it on the device. In addition, the device recognizes emotions from the user's facial expressions, voice, and input content. Software such as "OpenFace" and "Affectiva" is used as the emotion engine.

[1354] Information Optimization

[1355] The server optimizes the displayed information based on the user's recognized emotions. For example, if the user is excited, it will prioritize detailed spec reviews and purchase links, but if the user is in a negative emotional state, it will display relaxing content.

[1356] Specific examples

[1357] For example, if a user is looking at a news article about a new smartphone being announced, the following happens:

[1358] 1. The server collects news articles.

[1359] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[1360] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[1361] 4. The server generates links to relevant product pages and review articles.

[1362] 5. The server delivers the summary and keywords to the user's terminal.

[1363] 6. The user selects the keyword "smartphone."

[1364] 7. The server retrieves the relevant information and displays the details page to the user.

[1365] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[1366] Example prompts for generative AI models

[1367] An example of a prompt to input to a generative AI model is as follows:

[1368] Imagine a user is reading an article about a new smartphone. This system collects and analyzes news articles to generate summaries. It then extracts keywords from the summaries and generates links to related information. It then uses an emotion engine to recognize the user's emotions and dynamically adjusts the information displayed based on those emotions. If the user selects the keyword "smartphone," the server retrieves related information and the device displays detailed information. Please explain this process in detail, along with the system's processing steps.

[1369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1370] Step 1: Gather news articles

[1371] Input: RSS feed URL of the news site, API endpoint, website URL to be scraped.

[1372] How it works: The server collects news articles using RSS feeds, APIs, and web scraping. Specifically, it uses the Python "Requests" library to send requests to news site APIs and parses the JSON data it receives.

[1373] Output: JSON or text data of collected news articles.

[1374] Step 2: Analyzing the article content

[1375] Input: Collected text data of news articles.

[1376] How it works: The server analyzes the content of articles using NLP libraries like SpaCy and NLTK to identify important parts and major themes of the article. The analysis includes morphological and contextual analysis.

[1377] Output: Information on the main themes and key parts of the analyzed articles.

[1378] Step 3: Generate a summary

[1379] Input: Parsed article content.

[1380] How it works: The server generates a summary based on the analysis results. The summary is concisely summarized in a few lines and conveys the essence of the article. The server uses an extractive summarization algorithm to extract sentences that are deemed particularly important.

[1381] Output: The generated summary.

[1382] Step 4: Keyword extraction

[1383] Input: The generated summary sentence.

[1384] How it works: The server extracts keywords from the abstract using techniques such as TF-IDF and Word2Vec, which identifies important keywords related to the main theme of the article.

[1385] Output: Extracted keyword list.

[1386] Step 5: Generate related links

[1387] Input: Extracted keyword list.

[1388] How it works: The server generates links to related information based on keywords. This includes URLs to product pages, official websites, review articles, etc. Link generation is done using search engine APIs and pre-collected databases.

[1389] Output: A list of generated related links.

[1390] Step 6: Summary and Keyword Distribution

[1391] Input: Generated abstract and keyword list.

[1392] How it works: The server delivers the generated summary and keywords to the user's device, providing real-time information via API and sending data to the device application.

[1393] Output: Summary and keywords delivered to the user's terminal.

[1394] Step 7: Selecting Keywords

[1395] Input: Keyword list delivered to the device.

[1396] How it works: The user selects keywords that interest them from those displayed on the device, and performs the action by tapping or clicking. This selection action is detected by the device and triggers the next step.

[1397] Output: The selected keywords.

[1398] Step 8: Obtain related information

[1399] Input: A keyword selected by the user.

[1400] How it works: The server retrieves relevant information based on the selected keywords, specifically using internet searches and database queries to gather the latest information.

[1401] Output: The relevant information retrieved.

[1402] Step 9: View related information

[1403] Input: The relevant information retrieved.

[1404] Operation: The device displays the retrieved related information to the user. This may include product detail pages, review articles, official websites, etc. The related information is displayed through a user interface.

[1405] Output: Relevant information displayed on the terminal.

[1406] Step 10: Recognize emotions

[1407] Input: User facial expressions, voice, input, etc.

[1408] How it works: The device recognizes emotions from the user's facial expressions, voice, and input. The emotion engine uses machine learning algorithms to identify emotional states, specifically software like "OpenFace" and "Affectiva."

[1409] Output: Perceived emotional state.

[1410] Step 11: Information optimization

[1411] Input: The perceived emotional state of the user.

[1412] How it works: The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, detailed spec reviews and purchase links will be prioritized. Conversely, if the user is in a negative emotional state, concise information and relaxing content will be prioritized.

[1413] Output: Information display optimized for the user's emotional state.

[1414] (Application example 2)

[1415] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1416] In today's information society, users are required to efficiently and quickly obtain the information they need from a vast amount of news articles. Furthermore, if the content of news articles and related information is provided to users without taking into account the user's emotional state, information receptivity may be reduced. Conventional news delivery systems are unable to dynamically adjust information to reflect the individual user's emotional state, limiting the improvement of usability. A new approach to solving this problem is needed.

[1417] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for acquiring related information when a keyword displayed on the user terminal is selected, means for displaying the acquired related information on the user terminal, emotion recognition means for recognizing the user's emotion, and means for dynamically changing the related information and keywords to be displayed based on the recognized user emotion. This enables a user to efficiently grasp and select related information and news content in a manner appropriate to their emotional state.

[1418] "Means for collecting news articles" is a function that automatically obtains the latest news articles from multiple news sources on the Internet.

[1419] "Means for analyzing the content of news articles and generating summaries" refers to a function that uses natural language processing technology to identify important parts and main themes of collected news articles and generate concise summaries.

[1420] The "means for extracting keywords from summaries" is a function for identifying and extracting highly relevant keywords from the generated summaries.

[1421] The "means for generating links to related information" is a function that automatically generates links to related information or web pages based on the extracted keywords.

[1422] The "means for delivering the summary and keywords to the user terminal" is a function for transmitting the generated summary and keywords to the user terminal and displaying them.

[1423] "Means for obtaining related information when a keyword displayed by a user terminal is selected" is a function for obtaining information related to a keyword when the user selects the keyword displayed on the terminal.

[1424] The "means for displaying the acquired related information on the user terminal" is a function for displaying the acquired related information on the user terminal.

[1425] The "emotion recognition means for recognizing the user's emotions" is a function for identifying the user's emotional state from the user's facial expressions, voice, and input contents.

[1426] The "means for dynamically changing the related information and keywords to be displayed" is a function for changing the content of the information and keywords to be displayed in real time based on the recognized user's emotions.

[1427] The present invention provides a system and method for efficiently understanding news articles, and further provides the ability to dynamically adjust news and related information based on user sentiment. The present invention has the following system configuration.

[1428] 1. Collecting news articles

[1429] The server collects the latest news articles from multiple news sources (news websites, RSS feeds, etc.). This can be achieved by subscribing to RSS feeds, using API integration, or using web scraping techniques. This aggregation consolidates news articles from a wide range of sources.

[1430] 2. News article analysis and summary generation

[1431] The server analyzes the collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating concise summaries. This summary generation is achieved using, for example, the nltk library and various machine learning techniques.

[1432] 3. Keyword extraction

[1433] The server uses natural language processing techniques such as Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec to extract key keywords from the generated summary, thereby identifying the main themes and relevant words of the article.

[1434] 4. Linking to related information

[1435] Based on the extracted keywords, it generates links to relevant web pages and databases, including product pages, official websites, and review articles, allowing users to access more detailed information.

[1436] 5. Summary and Keyword Distribution

[1437] The server delivers the generated summary and keywords to the user's device. This information is provided in real time via an API and can be viewed on the user's device.

[1438] 6. User operations and display of related information

[1439] Users can obtain detailed related information by tapping on keywords they are interested in from those displayed on their device. The server retrieves further related information based on the keywords selected by the user and displays it on the user's device.

[1440] 7. Emotion Recognition and Information Optimization

[1441] The device analyzes the user's facial expressions, voice, and input content to identify their emotional state using an emotion recognition engine. This emotion recognition uses machine learning algorithms such as EmotionEngine. The server dynamically adjusts the news articles and related information displayed based on the user's recognized emotion. For example, if the user is in a positive emotional state, more detailed information will be displayed first, while if the user is in a negative emotional state, brief information will be displayed first.

[1442] Specific examples

[1443] For example, if a user is viewing a news article titled "Announcement of a new smart device," the following process takes place: The server collects news articles, analyzes them, and generates summaries. Keywords such as "smart device" and "announcement" are extracted from the generated summaries. The server generates links to related product pages and review articles and delivers the summaries and keywords to the user's device. When the user selects the keyword "smart device," the server retrieves related information and displays a detailed page to the user. At this time, the device recognizes the user's emotions; for example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[1444] Prompt Sentence Examples

[1445] Prompt: "Design a system that helps users efficiently keep up with breaking news and delivers information accordingly. Additionally, add the ability to recognize the user's emotions and adjust the content accordingly."

[1446] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1447] Step 1:

[1448] The server collects news articles. Specifically, it obtains article data from multiple news sources using RSS feeds, news site APIs, and web scraping technology. It uses a list of URLs as input and obtains a list of collected text data as output.

[1449] Step 2:

[1450] The server analyzes the content of collected news articles and generates summaries. Specifically, it uses natural language processing (NLP) techniques to analyze articles and identify important parts and main themes. The article text is used as input, and a summary is obtained as output.

[1451] Step 3:

[1452] The server extracts keywords from the generated summary. In this step, it uses natural language processing techniques such as TF-IDF and Word2Vec to identify keywords. It uses the summary sentence as input and obtains a list of keywords as output.

[1453] Step 4:

[1454] The server generates links to related information based on the extracted keywords, including related product pages, official websites, review articles, etc. It uses a list of keywords as input and obtains a list of related links as output.

[1455] Step 5:

[1456] The server delivers the generated summary and keywords to the user's device, transmitting information in real time via an API. The server uses the generated summary, keywords, and a list of related links as input, and delivers data to the user's device as output.

[1457] Step 6:

[1458] The user selects keywords displayed on the device by tapping or clicking on the keyword of interest. The input is the keyword selection, and the output is the selected keyword.

[1459] Step 7:

[1460] The server retrieves relevant information based on the selected keywords. It uses internet searches and database queries to gather up-to-date relevant information. It uses the selected keywords as input and gets relevant information as output.

[1461] Step 8:

[1462] The device displays the retrieved related information to the user, including product detail pages and review articles. The retrieved related information is used as input, and the display on the user device is used as output.

[1463] Step 9:

[1464] The device uses an emotion recognition engine to recognize the user's emotions. It identifies emotions from the user's facial expressions, voice, and input content. It uses the user's facial expression data and voice data as input and obtains the user's emotional state as output.

[1465] Step 10:

[1466] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. If the user is in a positive emotional state, detailed information is displayed, and if the user is in a negative emotional state, brief information is displayed preferentially. Using the emotional state and relevant information as input, tailored information is obtained as output.

[1467] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1468] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1469] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1470] [Fourth embodiment]

[1471] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1472] 7, a 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.

[1473] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1474] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1475] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1476] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1477] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1478] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1479] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1480] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1481] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1482] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1483] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1484] The present invention relates to a system that enables users to efficiently understand daily news articles and then navigate to related information based on keywords extracted from those articles. This system provides a high-quality user experience by linking the server, terminals, and users.

[1485] Basic configuration

[1486] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to user terminals, allowing users to quickly access detailed related information by selecting keywords.

[1487] Program processing

[1488] The program processing of this system will be explained in natural language below.

[1489] News article collection and analysis

[1490] 1. Collecting news articles

[1491] The server collects the latest news articles from multiple news sites using methods such as RSS feeds, APIs, and web scraping.

[1492] Example: "The server uses the news provider's API to retrieve newly posted article data."

[1493] 2. Analysis of article content

[1494] The server analyzes the collected news article text using natural language processing (NLP) technology to extract key sentences and phrases.

[1495] Example: "The server uses a parsing engine to segment the news article and identify key points."

[1496] 3. Summary Generation

[1497] The server generates a summary from the analyzed article content. The summary is a few lines long and conveys the main points of the article.

[1498] Example: "The server combines key sentences to generate a summary sentence: 'A new smartphone model has been released and is attracting a lot of attention.'"

[1499] Keyword extraction and distribution

[1500] 4. Keyword extraction

[1501] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[1502] Example: "The server extracts keywords such as 'smartphone,' 'model,' and 'announcement' from the abstract."

[1503] 5. Generating Related Links

[1504] The server generates links to related product pages, official websites, review articles, etc. based on the extracted keywords.

[1505] Example: "The server generates links to e-commerce sites and review articles related to 'smartphones'."

[1506] 6. Summary Article and Keyword Distribution

[1507] The server distributes the generated summary article and keywords to the user's terminal.

[1508] Example: "The server sends the summary article and keywords to the user's smartphone via API."

[1509] Acquisition and display of user operations and related information

[1510] 7. Keyword Selection

[1511] The user selects a keyword that interests them from the keywords displayed on the terminal.

[1512] Example: "The user taps on the keyword 'smartphone' displayed on their smartphone."

[1513] 8. Obtaining related information

[1514] The server retrieves relevant information from databases and the Internet based on the keywords selected by the user.

[1515] Example: "The server retrieves the latest product information and related site information for 'smartphones'."

[1516] 9. Display of related information

[1517] The terminal displays the acquired related information to the user, who can then use it to obtain more detailed information or purchase the product.

[1518] Example: "The device displays the purchase page and detailed reviews of the latest smartphone models."

[1519] Specific examples

[1520] For example, if the server collects a news article that says "famous company announces new smartphone," the following process will be performed:

[1521] 1. The server retrieves the news article.

[1522] 2. The server analyzes the article and generates a summary: "A well-known company announces a new smartphone."

[1523] 3. The server extracts the keywords "famous company," "smartphone," and "announcement."

[1524] 4. The server generates links to relevant product pages and review articles.

[1525] 5. The server delivers the summary and keywords to the user's device.

[1526] 6. The user selects the keyword "smartphone."

[1527] 7. The server retrieves the relevant information and displays a detailed information page to the user.

[1528] This allows users to quickly grasp summary information and instantly access related information that they are interested in. This system enables efficient news information collection and digestion, and supports users' actions quickly.

[1529] The processing flow will be explained below.

[1530] Step 1:

[1531] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, or web scraping technology, thereby securing a large amount of new article data.

[1532] Step 2:

[1533] The server analyzes the collected news articles using natural language processing (NLP) technology. Specifically, the article text is tokenized, morphological analysis is performed, and an importance score is assigned to each sentence.

[1534] Step 3:

[1535] The server extracts key sentences from the analyzed article content and generates a summary based on these. The summary is a few lines summarizing the highlights of the article.

[1536] Step 4:

[1537] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec, thereby identifying keywords related to the main themes of the article.

[1538] Step 5:

[1539] The server generates links to related information based on the extracted keywords, using URL information from a database or information obtained from the Internet.

[1540] Step 6:

[1541] The server delivers the generated summary article and keywords to the user's device, and transmits data using an API to provide information to the user in real time.

[1542] Step 7:

[1543] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the outline of the article.

[1544] Step 8:

[1545] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[1546] Step 9:

[1547] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[1548] Step 10:

[1549] The device displays relevant information to the user, including product detail pages, reviews, official websites, etc. It provides detailed links and descriptions to help users quickly access the information they are looking for.

[1550] This series of steps results in a system that allows users to quickly understand news summaries and easily access information of interest.

[1551] Example 1

[1552] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1553] In modern society, people are increasingly exposed to a huge amount of news information every day, making it important to efficiently collect, analyze, and understand that information. Furthermore, there is a need for a method that allows users to quickly extract information of interest and smoothly access related information. Conventional technologies require time and effort to manually collect and analyze news articles, and extensive research is required to find related information, making it difficult to improve the user experience.

[1554] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1555] In this invention, the server includes means for collecting news content, means for analyzing the collected news content to generate summaries, means for extracting keywords from the generated summaries, means for using natural language processing techniques to generate summaries and extract keywords, means for converting the news content, summaries, and keywords into an analyzable format, and means for searching and distributing related information via a digital network, thereby enabling efficient collection and analysis of news content and rapid access to related information of user interest.

[1556] "News content" refers to news articles and reports published online.

[1557] "Means of collection" refers to the methods or mechanisms used to obtain news content from the Internet.

[1558] "Means of analysis" refers to the method or mechanism for analyzing the content of collected news content and organizing the information.

[1559] "Means for generating a summary" refers to a method or mechanism for extracting the main points from collected and analyzed news content and summarizing them in a concise format.

[1560] "Keyword extraction means" refers to a method or mechanism for identifying and extracting important words and phrases from the generated summary.

[1561] "Means for generating links to related information" refers to a method or mechanism for creating links to related web pages or digital information based on the extracted keywords.

[1562] "User Device" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[1563] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate natural language used by humans.

[1564] "Digital network" refers to the mechanism for transmitting data over the Internet and other digital communications infrastructure.

[1565] "Database" refers to a system for efficiently managing, storing, and retrieving structured information.

[1566] "Server" refers to a computer system that provides a particular service and processes and distributes data over a network.

[1567] The present invention relates to a system that enables users to efficiently grasp daily news content and then navigate to related information based on keywords extracted from that content. This system provides a high-quality user experience by linking the server, terminals, and users.

[1568] Basic configuration

[1569] This system collects news content, analyzes the content using natural language processing technology to generate summaries, extracts keywords from the summaries, generates links to related information, and delivers and displays these to users' devices.By selecting keywords, users can quickly access detailed related information.

[1570] Hardware and Software Configuration

[1571] The main components of this system include the following hardware and software:

[1572] Server: A computer system that collects, analyzes, summarizes, extracts keywords, generates related links, and distributes news content.

[1573] Software: Natural language processing libraries (e.g., spaCy), data processing libraries (e.g., pandas), communication libraries (e.g., requests).

[1574] User terminal: A device that displays the summary and keywords delivered from the server and receives user operations.

[1575] Hardware: Smartphones, tablets, computers.

[1576] Software: web browser, mobile application.

[1577] Program processing

[1578] The server collects the latest news content using RSS feeds, APIs, web scraping, etc. from news sites. The collected content is analyzed using natural language processing techniques to extract important sentences and phrases. A summary is then generated from the extracted information, and keywords are extracted. For example, a specific prompt can be given, such as "The server will use the news provider's API to obtain newly posted article data."

[1579] The generated summary and keywords are delivered from the server to the user's device. The user's device displays them, allowing the user to select keywords of interest. Once a keyword is selected, the server searches for related information based on the selected keyword and displays the retrieved information on the user's device. For example, the user taps on the keyword "smartphone" displayed on their smartphone.

[1580] Specific examples

[1581] For example, if the server collects news content such as "A famous company announces a new smartphone," the following specific processing occurs:

[1582] 1. The server sends a request to an API endpoint to retrieve news content.

[1583] 2. The server uses an NLP engine (e.g., spaCy) to analyze the news content and generate a summary.

[1584] 3. The server extracts keywords such as "famous company," "smartphone," and "announcement" from the summary.

[1585] 4. The server generates links to relevant product pages and reviews.

[1586] 5. The server delivers the summary and keywords to the user's terminal.

[1587] 6. The user taps on the keyword "smartphone" displayed on the smartphone screen.

[1588] 7. The server searches for relevant information and displays the retrieved information on the user's terminal.

[1589] Prompt Sentence Examples

[1590] Below are some examples of specific prompts to input to the generative AI model:

[1591] "Please tell me the process flow of a system that collects the latest news content, summarizes the key points, and extracts and displays related keywords."

[1592] This system allows users to quickly grasp summary information and instantly access related information that they are interested in. This enables efficient collection and analysis of news content and precise information access based on users' interests.

[1593] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1594] Step 1:

[1595] News content collection

[1596] The server collects the latest news content from multiple news sites using RSS feeds, APIs, web scraping, etc.

[1597] Specific operation: The server sends a request to the news provider's API endpoint and retrieves the returned news content in JSON format.

[1598] Input: News site API endpoint, credentials.

[1599] Output: News content in JSON format.

[1600] Step 2:

[1601] News content analysis

[1602] The server analyzes the collected news content text using natural language processing (NLP) technology to extract important sentences and phrases.

[1603] What it does: The server uses an NLP library (e.g., spaCy) to tokenize the text, tag it with parts of speech, and extract key sentences and phrases.

[1604] Input: News content in JSON format.

[1605] Output: A list of key sentences and phrases.

[1606] Step 3:

[1607] Generate a summary

[1608] The server generates a summary based on the analyzed sentences and phrases, which is a few lines long and conveys the main points of the article.

[1609] Specific operation: The server combines important sentences, removes redundant parts, and constructs a summary sentence.

[1610] Input: A list of key sentences or phrases.

[1611] Output: Summary statement.

[1612] Step 4:

[1613] Keyword extraction

[1614] The server uses natural language processing technology to extract keywords from the generated summary, which reflect the important themes of the article.

[1615] Specific operation: The server tokenizes the summary sentence, extracts important nouns and verbs, and selects them as keywords.

[1616] Input: Abstract text.

[1617] Output: A list of keywords.

[1618] Step 5:

[1619] Generate related links

[1620] The server generates links to relevant web pages and digital information based on the extracted keywords.

[1621] Specific operation: The server uses a search API to obtain links related to each keyword and selects the most relevant ones.

[1622] Input: A list of keywords.

[1623] Output: A list of related links.

[1624] Step 6:

[1625] Summary and keyword distribution

[1626] The server distributes the generated summary article and keywords to the user terminal.

[1627] Specific operation: The server packages the summary article and keywords as an API response and sends it to the user's terminal.

[1628] Input: Abstract article, list of keywords.

[1629] Output: Abstract article and keywords sent to user terminal.

[1630] Step 7:

[1631] Keyword Selection

[1632] The user selects a keyword that interests them from the keywords displayed on the terminal.

[1633] Specific action: The user taps or clicks on a keyword on the screen.

[1634] Input: Keywords displayed on the user's terminal.

[1635] Output: The user's selected keywords.

[1636] Step 8:

[1637] Obtaining related information

[1638] The server retrieves relevant information from a database or the Internet based on the keywords selected by the user.

[1639] Specific operation: The server uses a database or API to search and retrieve information related to the selected keyword.

[1640] Input: Selected keyword.

[1641] Output: The relevant information retrieved.

[1642] Step 9:

[1643] Viewing related information

[1644] The terminal displays the acquired related information to the user.

[1645] Specific operation: The terminal converts the acquired information into an appropriate format and displays it.

[1646] Input: The relevant information retrieved.

[1647] Output: Relevant information displayed on the user's terminal.

[1648] (Application example 1)

[1649] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1650] Conventional news article distribution systems make it difficult for users to efficiently understand the content of news articles and quickly access information of interest. In particular, quickly obtaining links from news articles to related information requires manual searching, which takes time and effort. Another problem is the complicated process of extracting essential keywords from news and linking them to related information.

[1651] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1652] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, and means for extracting keywords from the generated summaries. This allows for efficient management of news articles and enables users to quickly access related information. The server also includes means for generating summaries using natural language processing technology and extracting keywords from the summaries using a generative AI model, and means for generating prompt sentences based on the extracted keywords and further identifying related information using the prompt sentences. This allows users to quickly obtain links to related information and detailed information by simply selecting keywords of interest, enabling efficient information gathering.

[1653] A "news article" is information reported in the form of text, images, video, etc. provided by a website or news provider.

[1654] "Means of collection" refers to the technical devices or methods used to collect news articles, such as through web scraping, RSS feeds, APIs, etc.

[1655] A "means for analyzing and generating a summary" is a technical device or method that uses natural language processing techniques to concisely summarize the key content or key points of a news article.

[1656] "Keyword extraction means" refers to a technical device or method that uses generative AI models or natural language processing techniques to extract the article's themes and important words from the summary text.

[1657] The "means for generating links to related information" is a technical device or method that creates hyperlinks to related web pages or database entries based on the extracted keywords.

[1658] A "distribution means" is a technical device or method that transmits the generated abstract and keywords to a user's device over a network.

[1659] "Displaying means" refers to a technical device or method that visually presents relevant information, summaries, and keywords on a user's device.

[1660] "Natural language processing technology" is a technology that enables computers to understand, analyze, and manipulate human language.

[1661] A "generative AI model" is an artificial intelligence technology that learns from large amounts of text data and extracts summaries and keywords from given text.

[1662] A "prompt sentence" is text data input to a generative AI model, and serves as a clue for the model to extract appropriate keywords and information.

[1663] A "user device" is an electronic device (e.g., smartphone, tablet, computer, etc.) for displaying news articles and related information.

[1664] The "means for identifying" refers to a technical device or method that searches for related information based on the extracted keywords and generated prompt sentences and provides it to the user.

[1665] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from the articles. This system is implemented using a server, a user device, natural language processing technology, and a generative AI model.

[1666] The server first collects news articles. Methods for collecting news articles include RSS feeds, API access, and web scraping. Next, the content of the collected news articles is analyzed. This analysis is performed using natural language processing (NLP) technology. Specifically, it uses Python libraries such as spaCy and transformers.

[1667] The server extracts important content from the analyzed text and generates a summary. This summary is condensed by a generative AI model into a few lines that convey the main points of the article. For example, a summary of the news article "A new smartphone has been announced and is attracting a lot of attention" is generated. Keywords are then extracted from this summary. For example, keywords such as "smartphone," "announcement," and "attention" are extracted.

[1668] Furthermore, the server generates a prompt based on the extracted keywords. This prompt is used as input data for the generative AI model to more specifically identify relevant information. An example of a prompt is, "Please tell me the latest information about the launch of a new smartphone."

[1669] Based on the extracted keywords and generated prompts, the server generates relevant links and delivers them to the user's device along with the summary, allowing the user to view the summary and keywords on their smartphone, tablet, or other device.

[1670] When a user selects a displayed keyword, the server retrieves detailed related information from a database or the Internet. The retrieved related information is then sent back to the user's device, where the user can view it. For example, if a user selects the keyword "smartphone," the server retrieves product information and review articles related to that smartphone and displays them on the user's device.

[1671] This allows users to efficiently grasp summaries of articles they are interested in and quickly access detailed information and related links. This system streamlines users' collection and digestion of news information, providing a high-quality user experience.

[1672] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1673] Step 1:

[1674] The server collects news articles.

[1675] Input: News provider's API or RSS feed URL.

[1676] Data processing: The server requests news article data from the input URL or API and retrieves the article data in JSON format or other formats.

[1677] Output: A list of collected news articles.

[1678] Step 2:

[1679] The server analyzes the collected news articles and generates summaries.

[1680] Input: The list of news articles collected in step 1.

[1681] Data processing: The server uses natural language processing (NLP) techniques to analyze the content of news articles. Libraries such as spaCy and transformers are used for analysis. The server then uses a generative AI model to generate a summary that summarizes the key points.

[1682] Output: A summary for each article.

[1683] Step 3:

[1684] The server extracts keywords from the generated summary.

[1685] Input: The summary text generated in step 2.

[1686] Data processing: The server again uses natural language processing technology to extract important keywords from the summary text, using a generative AI model.

[1687] Output: A list of extracted keywords.

[1688] Step 4:

[1689] The server generates a prompt sentence based on the extracted keywords and generates a link to related information.

[1690] Input: The list of keywords extracted in step 3.

[1691] Data processing: A generative AI model generates prompts based on keywords, identifies related information from the prompts, and generates links based on this identified information.

[1692] Output: A list of the generated prompt statements and associated links.

[1693] Step 5:

[1694] The server delivers the summary, keywords and related links to the user device.

[1695] Input: Abstract generated in step 2, keywords extracted in step 3, links generated in step 4.

[1696] Data processing: The server combines these data, formats them appropriately, and sends them to the user's device.

[1697] Output: Abstract, keywords, and related links delivered to the user's device.

[1698] Step 6:

[1699] The terminal displays the delivered summary and keywords.

[1700] Input: Abstract, keywords, and related links delivered in Step 5.

[1701] Data processing: The application receives the distributed data and displays it on the user interface, which the user can view.

[1702] Output: Abstract, keywords, and related links displayed in the user interface.

[1703] Step 7:

[1704] The user selects a displayed keyword.

[1705] Input: The keyword displayed in step 6.

[1706] Data processing: The user selects a keyword, which is then sent to the server.

[1707] Output: The selected keywords sent to the server.

[1708] Step 8:

[1709] The server retrieves relevant information based on the selected keywords.

[1710] Input: The selected keyword submitted in step 7.

[1711] Data processing: The server searches and retrieves relevant information based on the selected keywords from databases and the Internet.

[1712] Output: The relevant information retrieved.

[1713] Step 9:

[1714] The server distributes the retrieved relevant information to the user device.

[1715] Input: Relevant information obtained in step 8.

[1716] Data processing: The server formats the retrieved information and sends it to the user device.

[1717] Output: Relevant information delivered to user device.

[1718] Step 10:

[1719] The terminal displays the retrieved related information.

[1720] Input: Relevant information delivered in Step 9.

[1721] Data processing: The received relevant information is processed and displayed on the user interface.

[1722] Output: Relevant information displayed on the user interface.

[1723] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1724] This invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system dynamically adjusts the news content and related information according to the user's emotions, providing a personalized experience.

[1725] Basic configuration

[1726] This system collects news articles, analyzes them using natural language processing technology to generate summaries, extracts keywords from them, generates links to related information, and delivers and displays them to users' devices. Furthermore, by combining it with an emotion engine, it recognizes the user's emotions and optimizes the information displayed based on those emotions.

[1727] Program processing

[1728] The program processing of this system will be explained in natural language below.

[1729] News article collection and analysis

[1730] 1. Collecting news articles

[1731] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, thereby obtaining article data from a wide range of news sources.

[1732] 2. Analysis of article content

[1733] The server analyzes the text of collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating summaries.

[1734] 3. Summary Generation

[1735] The server generates a summary from the analyzed article content. The summary is concisely summarized in a few lines and conveys the essence of the article.

[1736] Keyword extraction and distribution

[1737] 4. Keyword extraction

[1738] The server extracts keywords from the abstract using natural language processing techniques such as TF-IDF and Word2Vec, thereby identifying keywords related to the main themes of the article.

[1739] 5. Generating Related Links

[1740] The server generates links to related information based on the extracted keywords, including links to product pages, official websites, review articles, etc.

[1741] 6. Summary Article and Keyword Distribution

[1742] The server delivers the generated summary article and keywords to the user's device, providing information in real time via API.

[1743] Acquisition and display of user operations and related information

[1744] 7. Keyword Selection

[1745] The user selects keywords that interest them from those displayed on the device, and performs operations by tapping or clicking.

[1746] 8. Obtaining related information

[1747] The server retrieves relevant information based on user-selected keywords, providing up-to-date information using internet searches and database queries.

[1748] 9. Display of related information

[1749] The device displays relevant information to the user, including product details, reviews, official websites, and more.

[1750] Combining Emotion Engines

[1751] One of the features of the present invention is that it incorporates an emotion engine that recognizes the user's emotions, which adds the following processing:

[1752] 10. Emotional Recognition

[1753] The device recognizes emotions from the user's facial expressions, voice, input, etc. The emotion engine uses machine learning algorithms to identify emotional states.

[1754] 11. Information Optimization

[1755] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, it provides more detailed information and related news. On the other hand, if the user is in a negative emotional state, it prioritizes the display of concise information and relaxing content.

[1756] Specific examples

[1757] For example, if a user is viewing a news article titled "New Smartphone Announcement," the following processing will occur:

[1758] 1. The server collects news articles.

[1759] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[1760] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[1761] 4. The server generates links to relevant product pages and review articles.

[1762] 5. The server delivers the summary and keywords to the user's device.

[1763] 6. The user selects the keyword "smartphone."

[1764] 7. The server retrieves the relevant information and displays the details page to the user.

[1765] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[1766] In this way, information provision can be optimized according to the user's emotions, resulting in a more personalized news viewing experience.

[1767] The processing flow will be explained below.

[1768] Step 1:

[1769] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping technology, allowing for the rapid acquisition of new articles from a wide range of news sources.

[1770] Step 2:

[1771] The server analyzes the collected news article text using natural language processing (NLP) techniques, tokenizing the sentences in the article, performing morphological analysis, and assigning an importance score to each sentence.

[1772] Step 3:

[1773] The server generates a summary based on the analyzed article content. The summary is usually a few lines long and succinctly conveys the main points of the article.

[1774] Step 4:

[1775] The server extracts keywords from the summary using natural language processing techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec to determine keywords that reflect the main themes of the article.

[1776] Step 5:

[1777] The server generates links to related information based on the extracted keywords, including links to related product pages, official websites, review articles, etc.

[1778] Step 6:

[1779] The server delivers the generated summary article and keywords to the user's device, using an API to send data in real time so that the user can receive the information immediately.

[1780] Step 7:

[1781] The terminal displays the received summary article and keywords on the screen in a visually easy-to-read format so that the user can easily grasp the article's outline.

[1782] Step 8:

[1783] The user selects the keyword they are interested in from the displayed keywords, and performs selection operations through the interface, such as tapping and clicking.

[1784] Step 9:

[1785] The server retrieves relevant information based on user-selected keywords, using database queries and internet searches to gather the latest information.

[1786] Step 10:

[1787] The device displays the retrieved relevant information to the user, including product detail pages, reviews, official websites, and more, allowing users to quickly access the information they are looking for.

[1788] Step 11:

[1789] The device uses an emotion engine to recognize emotions from the user's facial expressions, voice, input, etc. Machine learning algorithms are used to identify the user's emotional state.

[1790] Step 12:

[1791] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a negative emotional state, it will prioritize displaying concise information and relaxing content to optimize the user experience.

[1792] Specific examples

[1793] For example, when processing a news article titled "New Smartphone Announced," the process would proceed as follows:

[1794] 1. The server collects news articles.

[1795] 2. The server analyzes the article and generates a summary: "A new smartphone model has been announced."

[1796] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[1797] 4. The server generates links to relevant product pages and review articles.

[1798] 5. The server delivers the summary and keywords to the user's terminal.

[1799] 6. The device will display the summary article and keywords.

[1800] 7. The user selects the keyword "smartphone."

[1801] 8. The server retrieves the relevant information and displays a details page to the user.

[1802] 9. The device recognizes the user's emotions.

[1803] 10. The server optimizes and displays relevant information such as detailed reviews and purchase links based on the user's sentiment.

[1804] This series of processes allows users to efficiently grasp the news and quickly obtain relevant information that matches their emotional state.

[1805] Example 2

[1806] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1807] In recent years, information overload has made it difficult for users to quickly and efficiently obtain the information they need. With the vast amount of news articles being generated daily, it takes a great deal of time and effort for users to grasp the important content. Furthermore, there is a lack of information provided that is tailored to the user's emotional state, creating a need for improved user experience. Current technology faces the challenge of achieving a continuous flow of news article collection, analysis, and distribution, as well as information optimization through user emotion recognition. To address these challenges, an information delivery system that combines immediacy and personalization to meet user needs is needed.

[1808] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1809] In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for recognizing a user's emotion, and means for optimizing display information based on the recognized user's emotion. This allows users to efficiently understand daily news articles and quickly obtain related information based on keywords extracted from the articles. Furthermore, information is dynamically adjusted according to the user's emotional state, providing a more personalized experience.

[1810] A "news article aggregator" is a software and hardware mechanism for aggregating news articles from multiple sources on the Internet.

[1811] "Means of analyzing the content of collected news articles and generating summaries" refers to the technology and process of using natural language processing technology to understand and analyze the content of news articles and generate a concise summary.

[1812] "Means for extracting keywords from the generated summaries" refers to algorithms and techniques for identifying major themes and important words from the generated summaries and extracting them as keywords.

[1813] The "means for generating links to related information based on extracted keywords" is a mechanism for dynamically generating links to related information or web pages based on extracted keywords.

[1814] "Means for delivering the generated summary and keywords to the user's terminal" refers to the communication technology and infrastructure for transmitting and delivering the generated summary and keywords to the user's terminal in real time.

[1815] "Means for recognizing user emotions" refers to emotion recognition technology and sensor devices for detecting and identifying emotions from the user's facial expressions, voice, input content, etc.

[1816] "Means for optimizing display information based on recognized user emotions" refers to a technology that dynamically changes the content and format of the information to be displayed based on the detected emotional state of the user, thereby providing information that more appropriately meets the user's needs and situation.

[1817] The present invention relates to a system that enables users to efficiently understand daily news articles and navigate to related information based on keywords extracted from those articles. Furthermore, the present invention is characterized by combining an emotion engine that recognizes the user's emotions, dynamically adjusting the news content and related information according to the user's emotions, providing a personalized experience.

[1818] Basic configuration

[1819] The system of the present invention includes the following components:

[1820] News article collection method

[1821] News article analysis methods

[1822] Summary generation means

[1823] Keyword extraction method

[1824] Related link generation method

[1825] Abstract and Keyword Distribution Methods

[1826] A means of recognizing user emotions

[1827] How to optimize the information displayed

[1828] News article collection and analysis

[1829] The server collects the latest news articles from multiple news sites using RSS feeds, APIs, and web scraping. This is done using Python's "Requests" library, among other tools. The collected article text is then analyzed using natural language processing (NLP) techniques. NLP libraries such as "SpaCy" and "NLTK" are used. This identifies the important parts and main themes of the article and generates a concise summary.

[1830] Keyword extraction and link generation for related information

[1831] The server uses techniques such as TF-IDF and Word2Vec to extract keywords from the generated summary. Based on the extracted keywords, the server generates links to related information, including product pages, official websites, and review articles. An API is then used to deliver the generated summary and keywords to the user's device.

[1832] User interaction and emotion recognition

[1833] Users can obtain relevant information of interest by selecting keywords displayed on their device. Based on the selected keywords, the server retrieves relevant information using Internet searches and database queries and displays it on the device. In addition, the device recognizes emotions from the user's facial expressions, voice, and input content. Software such as "OpenFace" and "Affectiva" is used as the emotion engine.

[1834] Information Optimization

[1835] The server optimizes the displayed information based on the user's recognized emotions. For example, if the user is excited, it will prioritize detailed spec reviews and purchase links, but if the user is in a negative emotional state, it will display relaxing content.

[1836] Specific examples

[1837] For example, if a user is looking at a news article about a new smartphone being announced, the following happens:

[1838] 1. The server collects news articles.

[1839] 2. The server parses the article and generates a summary: "A new smartphone model has been announced."

[1840] 3. The server extracts the keywords "smartphone," "model," and "announcement."

[1841] 4. The server generates links to relevant product pages and review articles.

[1842] 5. The server delivers the summary and keywords to the user's terminal.

[1843] 6. The user selects the keyword "smartphone."

[1844] 7. The server retrieves the relevant information and displays the details page to the user.

[1845] 8. The device recognizes the user's emotions. For example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[1846] Example prompts for generative AI models

[1847] An example of a prompt to input to a generative AI model is as follows:

[1848] Imagine a user is reading an article about a new smartphone. This system collects and analyzes news articles to generate summaries. It then extracts keywords from the summaries and generates links to related information. It then uses an emotion engine to recognize the user's emotions and dynamically adjusts the information displayed based on those emotions. If the user selects the keyword "smartphone," the server retrieves related information and the device displays detailed information. Please explain this process in detail, along with the system's processing steps.

[1849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1850] Step 1: Gather news articles

[1851] Input: RSS feed URL of the news site, API endpoint, website URL to be scraped.

[1852] How it works: The server collects news articles using RSS feeds, APIs, and web scraping. Specifically, it uses the Python "Requests" library to send requests to news site APIs and parses the JSON data it receives.

[1853] Output: JSON or text data of collected news articles.

[1854] Step 2: Analyzing the article content

[1855] Input: Collected text data of news articles.

[1856] How it works: The server analyzes the content of articles using NLP libraries like SpaCy and NLTK to identify important parts and major themes of the article. The analysis includes morphological and contextual analysis.

[1857] Output: Information on the main themes and key parts of the analyzed articles.

[1858] Step 3: Generate a summary

[1859] Input: Parsed article content.

[1860] How it works: The server generates a summary based on the analysis results. The summary is concisely summarized in a few lines and conveys the essence of the article. The server uses an extractive summarization algorithm to extract sentences that are deemed particularly important.

[1861] Output: The generated summary.

[1862] Step 4: Keyword extraction

[1863] Input: The generated summary sentence.

[1864] How it works: The server extracts keywords from the abstract using techniques such as TF-IDF and Word2Vec, which identifies important keywords related to the main theme of the article.

[1865] Output: Extracted keyword list.

[1866] Step 5: Generate related links

[1867] Input: Extracted keyword list.

[1868] How it works: The server generates links to related information based on keywords. This includes URLs to product pages, official websites, review articles, etc. Link generation is done using search engine APIs and pre-collected databases.

[1869] Output: A list of generated related links.

[1870] Step 6: Summary and Keyword Distribution

[1871] Input: Generated abstract and keyword list.

[1872] How it works: The server delivers the generated summary and keywords to the user's device, providing real-time information via API and sending data to the device application.

[1873] Output: Summary and keywords delivered to the user's terminal.

[1874] Step 7: Selecting Keywords

[1875] Input: Keyword list delivered to the device.

[1876] How it works: The user selects keywords that interest them from those displayed on the device, and performs the action by tapping or clicking. This selection action is detected by the device and triggers the next step.

[1877] Output: The selected keywords.

[1878] Step 8: Obtain related information

[1879] Input: A keyword selected by the user.

[1880] How it works: The server retrieves relevant information based on the selected keywords, specifically using internet searches and database queries to gather the latest information.

[1881] Output: The relevant information retrieved.

[1882] Step 9: View related information

[1883] Input: The relevant information retrieved.

[1884] Operation: The device displays the retrieved related information to the user. This may include product detail pages, review articles, official websites, etc. The related information is displayed through a user interface.

[1885] Output: Relevant information displayed on the terminal.

[1886] Step 10: Recognize emotions

[1887] Input: User facial expressions, voice, input, etc.

[1888] How it works: The device recognizes emotions from the user's facial expressions, voice, and input. The emotion engine uses machine learning algorithms to identify emotional states, specifically software like "OpenFace" and "Affectiva."

[1889] Output: Perceived emotional state.

[1890] Step 11: Information optimization

[1891] Input: The perceived emotional state of the user.

[1892] How it works: The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. For example, if the user is in a positive emotional state, detailed spec reviews and purchase links will be prioritized. Conversely, if the user is in a negative emotional state, concise information and relaxing content will be prioritized.

[1893] Output: Information display optimized for the user's emotional state.

[1894] (Application example 2)

[1895] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1896] In today's information society, users are required to efficiently and quickly obtain the information they need from a vast amount of news articles. Furthermore, if the content of news articles and related information is provided to users without taking into account the user's emotional state, information receptivity may be reduced. Conventional news delivery systems are unable to dynamically adjust information to reflect the individual user's emotional state, limiting the improvement of usability. A new approach to solving this problem is needed.

[1897] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting news articles, means for analyzing the contents of the collected news articles to generate summaries, means for extracting keywords from the generated summaries, means for generating links to related information based on the extracted keywords, means for delivering the generated summaries and keywords to a user terminal, means for acquiring related information when a keyword displayed on the user terminal is selected, means for displaying the acquired related information on the user terminal, emotion recognition means for recognizing the user's emotion, and means for dynamically changing the related information and keywords to be displayed based on the recognized user emotion. This enables a user to efficiently grasp and select related information and news content in a manner appropriate to their emotional state.

[1898] "Means for collecting news articles" is a function that automatically obtains the latest news articles from multiple news sources on the Internet.

[1899] "Means for analyzing the content of news articles and generating summaries" refers to a function that uses natural language processing technology to identify important parts and main themes of collected news articles and generate concise summaries.

[1900] The "means for extracting keywords from summaries" is a function for identifying and extracting highly relevant keywords from the generated summaries.

[1901] The "means for generating links to related information" is a function that automatically generates links to related information or web pages based on the extracted keywords.

[1902] The "means for delivering the summary and keywords to the user terminal" is a function for transmitting the generated summary and keywords to the user terminal and displaying them.

[1903] "Means for obtaining related information when a keyword displayed by a user terminal is selected" is a function for obtaining information related to a keyword when the user selects the keyword displayed on the terminal.

[1904] The "means for displaying the acquired related information on the user terminal" is a function for displaying the acquired related information on the user terminal.

[1905] The "emotion recognition means for recognizing the user's emotions" is a function for identifying the user's emotional state from the user's facial expressions, voice, and input contents.

[1906] The "means for dynamically changing the related information and keywords to be displayed" is a function for changing the content of the information and keywords to be displayed in real time based on the recognized user's emotions.

[1907] The present invention provides a system and method for efficiently understanding news articles, and further provides the ability to dynamically adjust news and related information based on user sentiment. The present invention has the following system configuration.

[1908] 1. Collecting news articles

[1909] The server collects the latest news articles from multiple news sources (news websites, RSS feeds, etc.). This can be achieved by subscribing to RSS feeds, using API integration, or using web scraping techniques. This aggregation consolidates news articles from a wide range of sources.

[1910] 2. News article analysis and summary generation

[1911] The server analyzes the collected news articles using natural language processing (NLP) techniques, identifying the important parts and main themes of the articles and generating concise summaries. This summary generation is achieved using, for example, the nltk library and various machine learning techniques.

[1912] 3. Keyword extraction

[1913] The server uses natural language processing techniques such as Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec to extract key keywords from the generated summary, thereby identifying the main themes and relevant words of the article.

[1914] 4. Linking to related information

[1915] Based on the extracted keywords, it generates links to relevant web pages and databases, including product pages, official websites, and review articles, allowing users to access more detailed information.

[1916] 5. Summary and Keyword Distribution

[1917] The server delivers the generated summary and keywords to the user's device. This information is provided in real time via an API and can be viewed on the user's device.

[1918] 6. User operations and display of related information

[1919] Users can obtain detailed related information by tapping on keywords they are interested in from those displayed on their device. The server retrieves further related information based on the keywords selected by the user and displays it on the user's device.

[1920] 7. Emotion Recognition and Information Optimization

[1921] The device analyzes the user's facial expressions, voice, and input content to identify their emotional state using an emotion recognition engine. This emotion recognition uses machine learning algorithms such as EmotionEngine. The server dynamically adjusts the news articles and related information displayed based on the user's recognized emotion. For example, if the user is in a positive emotional state, more detailed information will be displayed first, while if the user is in a negative emotional state, brief information will be displayed first.

[1922] Specific examples

[1923] For example, if a user is viewing a news article titled "Announcement of a new smart device," the following process takes place: The server collects news articles, analyzes them, and generates summaries. Keywords such as "smart device" and "announcement" are extracted from the generated summaries. The server generates links to related product pages and review articles and delivers the summaries and keywords to the user's device. When the user selects the keyword "smart device," the server retrieves related information and displays a detailed page to the user. At this time, the device recognizes the user's emotions; for example, if the user is excited, it will prioritize displaying detailed spec reviews and purchase links.

[1924] Prompt Sentence Examples

[1925] Prompt: "Design a system that helps users efficiently keep up with breaking news and delivers information accordingly. Additionally, add the ability to recognize the user's emotions and adjust the content accordingly."

[1926] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1927] Step 1:

[1928] The server collects news articles. Specifically, it obtains article data from multiple news sources using RSS feeds, news site APIs, and web scraping technology. It uses a list of URLs as input and obtains a list of collected text data as output.

[1929] Step 2:

[1930] The server analyzes the content of collected news articles and generates summaries. Specifically, it uses natural language processing (NLP) techniques to analyze articles and identify important parts and main themes. The article text is used as input, and a summary is obtained as output.

[1931] Step 3:

[1932] The server extracts keywords from the generated summary. In this step, it uses natural language processing techniques such as TF-IDF and Word2Vec to identify keywords. It uses the summary sentence as input and obtains a list of keywords as output.

[1933] Step 4:

[1934] The server generates links to related information based on the extracted keywords, including related product pages, official websites, review articles, etc. It uses a list of keywords as input and obtains a list of related links as output.

[1935] Step 5:

[1936] The server delivers the generated summary and keywords to the user's device, transmitting information in real time via an API. The server uses the generated summary, keywords, and a list of related links as input, and delivers data to the user's device as output.

[1937] Step 6:

[1938] The user selects keywords displayed on the device by tapping or clicking on the keyword of interest. The input is the keyword selection, and the output is the selected keyword.

[1939] Step 7:

[1940] The server retrieves relevant information based on the selected keywords. It uses internet searches and database queries to gather up-to-date relevant information. It uses the selected keywords as input and gets relevant information as output.

[1941] Step 8:

[1942] The device displays the retrieved related information to the user, including product detail pages and review articles. The retrieved related information is used as input, and the display on the user device is used as output.

[1943] Step 9:

[1944] The device uses an emotion recognition engine to recognize the user's emotions. It identifies emotions from the user's facial expressions, voice, and input content. It uses the user's facial expression data and voice data as input and obtains the user's emotional state as output.

[1945] Step 10:

[1946] The server dynamically changes the relevant information and keywords displayed based on the user's recognized emotions. If the user is in a positive emotional state, detailed information is displayed, and if the user is in a negative emotional state, brief information is displayed preferentially. Using the emotional state and relevant information as input, tailored information is obtained as output.

[1947] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1948] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1949] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1950] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1951] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1952] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1953] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1954] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1955] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1956] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1957] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1958] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1959] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1960] 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.

[1961] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1962] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1963] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1964] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1965] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1966] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1967] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1968] The following is further disclosed regarding the above embodiment.

[1969] (Claim 1)

[1970] a means of collecting news articles;

[1971] a means for analyzing the content of collected news articles and generating summaries;

[1972] means for extracting keywords from the generated summaries;

[1973] a means for generating links to related information based on the extracted keywords;

[1974] means for delivering the generated summary and keywords to a user terminal;

[1975] means for acquiring related information when a displayed keyword is selected by a user terminal;

[1976] means for displaying the acquired related information on a user terminal;

[1977] A system including:

[1978] (Claim 2)

[1979] 10. The system of claim 1, wherein the news articles are analyzed using natural language processing techniques.

[1980] (Claim 3)

[1981] 10. The system of claim 1, wherein the abstracts and keywords are stored in a database.

[1982] "Example 1"

[1983] (Claim 1)

[1984] a means for collecting news content;

[1985] a means for analyzing the collected news content and generating a summary;

[1986] means for extracting keywords from the generated summaries;

[1987] a means for generating links to related information based on the extracted keywords;

[1988] means for delivering the generated summary and keywords to a user device;

[1989] means for acquiring related information when a displayed keyword is selected by a user device;

[1990] means for displaying the retrieved related information on the user device;

[1991] A means for using natural language processing techniques to generate summaries and extract keywords;

[1992] means for converting news content, summaries and keywords into an analyzable format;

[1993] means for retrieving and distributing relevant information over a digital network;

[1994] A system including:

[1995] (Claim 2)

[1996] 10. The system of claim 1, wherein the collected news content is analyzed using a natural language processing engine to extract important sentences and phrases.

[1997] (Claim 3)

[1998] 10. The system of claim 1, wherein the abstracts and keywords are stored in a database maintained on a server.

[1999] "Application Example 1"

[2000] (Claim 1)

[2001] a means of collecting news articles;

[2002] a means for analyzing the content of collected news articles and generating summaries;

[2003] means for extracting keywords from the generated summaries;

[2004] a means for generating links to related information based on the extracted keywords;

[2005] means for delivering the generated summary and keywords to a user device;

[2006] means for acquiring related information when a displayed keyword is selected by a user device;

[2007] means for displaying the acquired related information on a user device;

[2008] a means for generating a summary using natural language processing techniques and extracting keywords from the summary using a generative AI model;

[2009] a means for generating a prompt sentence based on the extracted keywords and further identifying related information using the prompt sentence;

[2010] A system including:

[2011] (Claim 2)

[2012] 2. The system according to claim 1, wherein the news article is analyzed using natural language processing technology, and a prompt sentence is generated from the generated summary and keywords.

[2013] (Claim 3)

[2014] 10. The system of claim 1, wherein the abstracts and keywords are stored in a database and the generated prompt sentences are used to search for related information.

[2015] "Example 2: Combining Emotion Engines"

[2016] (Claim 1)

[2017] a means of collecting news articles;

[2018] a means for analyzing the content of collected news articles and generating summaries;

[2019] means for extracting keywords from the generated summaries;

[2020] a means for generating links to related information based on the extracted keywords;

[2021] means for delivering the generated summary and keywords to a user terminal;

[2022] means for acquiring related information when a displayed keyword is selected by a user terminal;

[2023] means for displaying the acquired related information on a user terminal;

[2024] means for recognizing a user's emotion;

[2025] means for optimizing the displayed information based on the recognized user emotion;

[2026] A system including:

[2027] (Claim 2)

[2028] 10. The system of claim 1, wherein the news articles are analyzed using natural language processing techniques.

[2029] (Claim 3)

[2030] 10. The system of claim 1, wherein the abstracts and keywords are stored in a database.

[2031] "Application example 2 when combining emotion engines"

[2032] (Claim 1)

[2033] a means of collecting news articles;

[2034] a means for analyzing the content of collected news articles and generating summaries;

[2035] means for extracting keywords from the generated summaries;

[2036] a means for generating links to related information based on the extracted keywords;

[2037] means for delivering the generated summary and keywords to a user terminal;

[2038] means for acquiring related information when a displayed keyword is selected by a user terminal;

[2039] means for displaying the acquired related information on a user terminal;

[2040] emotion recognition means for recognizing an emotion of a user;

[2041] A means for dynamically changing related information and keywords to be displayed based on the recognized user's emotions;

[2042] A system including:

[2043] (Claim 2)

[2044] 10. The system of claim 1, wherein the news articles are analyzed using natural language processing techniques.

[2045] (Claim 3)

[2046] 10. The system of claim 1, wherein the abstracts and keywords are stored in a database. [Explanation of symbols]

[2047] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting news articles; a means for analyzing the content of collected news articles and generating summaries; means for extracting keywords from the generated summaries; a means for generating links to related information based on the extracted keywords; means for delivering the generated summary and keywords to a user terminal; means for acquiring related information when a displayed keyword is selected by a user terminal; means for displaying the acquired related information on a user terminal; A system including:

2. 10. The system of claim 1, wherein the news articles are analyzed using natural language processing techniques.

3. 10. The system of claim 1, wherein the abstracts and keywords are stored in a database.

Images