System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information; means for generating an article using a natural language processing engine based on the collected information; means for confirming grammar and content of the generated article using a proofreading engine; means for translating the generated and updated article using a multilingual translation engine; means for storing and publishing the translated article in a database; and means for inserting a paid advertisement into the article based on a condition specified by a user.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] Problems with conventional Wikipedia include slow article updates due to its reliance on volunteer contributors, which can result in inaccurate information, and insufficient multilingual support. Furthermore, limited monetization options make sustainable operation difficult. The present invention aims to solve these problems by providing a system for creating and updating articles that is fast, accurate, and multilingual. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by using the following means. The system includes a means for collecting information, a means for generating articles using a natural language processing engine based on the collected information, a means for checking the grammar and content of the generated articles using a proofreading engine, a means for translating the generated and updated articles using a multilingual translation engine, a means for storing and publishing the translated articles in a database, and a means for inserting paid advertisements into the articles based on user-specified conditions. This improves the speed and accuracy of article updates, making it possible to support multiple languages ​​and generate advertising revenue. Furthermore, by including a means for updating existing articles based on collected information, a means for reconfirming the appropriateness of generated and updated articles, and a means for correcting mistranslations and grammatical errors in translated articles, the system can provide higher-quality information.

[0006] The "means of collecting information" is a component that has the function of automatically gathering reliable information from news sites, paper databases, government agency pages, etc. on the Internet.

[0007] A "natural language processing engine" is an algorithm or system that analyzes collected text data and extracts and summarizes meaningful information.

[0008] The "means for generating articles" is a component that has the function of automatically creating new articles based on information summarized by the natural language processing engine.

[0009] A "proofreading engine" is an algorithm or system that checks generated articles for grammatical errors and content consistency and makes any necessary corrections.

[0010] A "multilingual translation engine" is an algorithm or system capable of translating generated and updated articles into multiple languages.

[0011] The "means for storing and publishing in a database" is a component that has the function of storing translated articles in a database and publishing them in a state that can be displayed to the user when necessary.

[0012] The "means for inserting paid advertisements into articles" is a component that has a function for placing paid advertisements in appropriate locations within articles based on conditions specified by the user.

[0013] A "means for updating existing articles" is a component that has the functionality to automatically update existing articles in the database based on new information collected.

[0014] The "means for reconfirming the appropriateness of articles" is a component that has a mechanism for reconfirming whether the content of generated or updated articles is accurate and appropriate.

[0015] "Means for correcting mistranslations and grammatical errors" refers to a system that has the functionality to detect and correct mistranslations and grammatical errors in translated articles. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] overview

[0038] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include placing paid advertisements. Below, we will explain the operation of the system in detail from the perspectives of the server, terminal, and user.

[0039] Basic configuration

[0040] The system consists of the following main components:

[0041] 1. Information gathering engine

[0042] 2. Generation AI

[0043] 3. Proofreading Engine

[0044] 4. Multilingual Translation Engine

[0045] 5. Database

[0046] 6. Ad Management System

[0047] Program processing flow

[0048] Information gathering

[0049] The server periodically collects data from reliable sources such as news sites, academic paper databases, and government agency pages on the web.

[0050] Article Generation

[0051] The server passes the collected information to a natural language processing engine for summarization and categorization.

[0052] The summarized information is then passed to a generative AI to create a new article.

[0053] The server sends the generated article to a proofreading engine for grammatical and content checking and correction.

[0054] Update an existing article

[0055] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information.

[0056] To incorporate new information into existing articles, generative AI is used to regenerate articles.

[0057] The text is passed to a proofreading engine for rechecking and correction if necessary.

[0058] Translation Processing

[0059] The server sends the generated or updated article to a multilingual translation engine for translation into multiple languages.

[0060] The server then double-checks the translated article and corrects any mistranslations or grammatical errors.

[0061] Article Publication

[0062] The server stores the final articles (original and translated) in a database and prepares them for display when accessed by a user.

[0063] The device (user's browser or app) accesses the article, retrieves it from the database, and displays it.

[0064] Paid advertising placement

[0065] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) via the advertising management system.

[0066] The server identifies suitable articles based on specified criteria and inserts advertisements within the articles.

[0067] The terminal appropriately displays the designated advertisement when displaying the final article to the user.

[0068] Specific examples

[0069] Example 1: Creating and updating articles

[0070] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[0071] Generative AI generates articles based on new information.

[0072] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[0073] Example 2: Translation processing

[0074] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine and translated into English, French, Spanish, and other languages.

[0075] The translated content is rechecked on the server and finally saved in the database.

[0076] Example 3: Paid advertising

[0077] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[0078] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[0079] In this way, the system automatically processes everything from information collection to article creation, translation, updates, and the insertion of paid advertisements, providing efficient and accurate information.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[0083] Step 2:

[0084] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[0085] Step 3:

[0086] The server passes the summarized data to the AI ​​generator, which then creates a new article based on the data it receives, automatically generating a structure for the article, including a headline, introduction, main content, and conclusion.

[0087] Step 4:

[0088] The server then sends the generated article to a proofreading engine, which checks for grammatical errors and consistency of content. The proofreading engine uses AI technology to correct the article for correct grammar and appropriate expressions.

[0089] Step 5:

[0090] The server sends the generated and proofread article to a multilingual translation engine, where the article is translated into multiple languages ​​(e.g., English, French, Spanish, etc.).

[0091] Step 6:

[0092] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[0093] Step 7:

[0094] The server stores the final article in a database, which contains both the original and the translation.

[0095] Step 8:

[0096] The device (user's browser or app) requests an article, the server retrieves the article from the database, and displays it to the user, often in a translated version based on the user's language settings.

[0097] Step 9:

[0098] Users (advertiser sponsors) set the conditions for the ads they want to run (such as topics, keywords, and target areas) through a dedicated interface.

[0099] Step 10:

[0100] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[0101] Step 11:

[0102] When the device finally displays the article to the user, it embeds the specified advertisement appropriately within the article and displays it, so that the user can view the advertisement together with the article.

[0103] These steps enable the system to automatically provide fast and accurate information, multilingual support, and advertising monetization.

[0104] Example 1

[0105] 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."

[0106] In today's information society, there is a need to efficiently and accurately collect large amounts of information and generate valuable digital content. However, manually collecting information and generating articles requires a lot of time and effort, and there is also the risk of grammatical errors and mistranslations. Furthermore, providing the generated content in multiple languages ​​and effectively incorporating paid promotions requires advanced technology, making this a challenging task.

[0107] 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.

[0108] In this invention, the server includes a means for collecting information, a means for generating digital content using a natural language processing engine based on the collected information, and a means for checking the grammar and content of the generated digital content using a proofreading engine, thereby enabling efficient and accurate information collection, generation, and proofreading.

[0109] The server further includes means for translating the generated and updated digital content using a multilingual translation engine, means for storing and publishing the translated digital content in a data storage, and means for inserting paid promotions into the digital content based on conditions specified by a user, thereby enabling the generated digital content to be provided in multiple languages ​​and for inserting paid promotions in appropriate locations to maximize revenue.

[0110] "Means of collecting information" refers to a mechanism for regularly obtaining data from reliable sources.

[0111] "Natural language processing engine" refers to software or a system for analyzing, summarizing, and categorizing text.

[0112] "Means for generating digital content" refers to a system that uses artificial intelligence technology to automatically create new articles and content based on collected information.

[0113] "Proofreading Engine" means software or a system for checking and correcting the grammatical and content accuracy of generated digital content.

[0114] "Multilingual translation engine" refers to software or a system for translating generated digital content into multiple languages.

[0115] "Data storage" refers to databases and storage systems that store collected and generated digital content and make it available for retrieval as needed.

[0116] "User-specified conditions" refers to the advertising sponsor setting the promotion targets and conditions (keywords, categories, target countries, etc.).

[0117] "Paid Promotion" refers to advertisements or promotions that are inserted into digital content in exchange for a fee paid by advertising sponsors.

[0118] overview

[0119] The present invention relates to a system that utilizes artificial intelligence technology to automatically collect, generate, translate, and update information, as well as insert paid advertisements. The system includes the following main components:

[0120] Information Gathering Engine

[0121] Natural Language Processing Engine

[0122] Generative AI Models

[0123] Proofreading Engine

[0124] Multilingual Translation Engine

[0125] Data Storage

[0126] Ad Management System

[0127] Explaining program processing in natural language

[0128] Information gathering

[0129] The server periodically collects data from reliable sources, such as news sites, academic paper databases, and government pages, using web scraping tools such as BeautifulSoup and Scrapy. This ensures reliable and comprehensive collection of information.

[0130] Article Generation

[0131] The server passes the collected information to a natural language processing engine (e.g., spaCy, NLTK) for summarization and categorization. Then, based on the summarized information, a generative AI model (e.g., GPT-4) is used to create a new article. For example, the following prompt sentence is input to the generative AI model:

[0132] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[0133] The generated article is sent to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) to correct and check grammar and content.

[0134] Update an existing article

[0135] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information. To incorporate the new information into the identified articles, it regenerates the articles, again using the generative AI model. For example, it uses prompts like this:

[0136] Prompt: Please update this article with the latest information.

[0137] The generated article is then passed back to the proofreading engine, where corrections are made as needed.

[0138] Translation Processing

[0139] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) for translation into multiple languages. The translated article is then checked again by the server, where mistranslations and grammatical errors are corrected.

[0140] Article Publication

[0141] The server stores the final articles (original and translated) in data storage and prepares them for display when accessed by the user. The device (user's browser or app) accesses these articles, retrieves them from data storage, and displays them.

[0142] Paid advertising placement

[0143] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) through the advertising management system. The server identifies appropriate articles based on the specified conditions and inserts advertisements into those articles. When the terminal displays the final article to the user, it includes the appropriate advertisements.

[0144] Specific examples

[0145] Example 1: Creating and updating articles

[0146] When new information about the "COVID-19 variant" is updated, the server uses BeautifulSoup to collect relevant information from the web, then uses a generative AI model to generate a new article, checks the grammar of the article using the Grammarly API, saves it in data storage, and publishes it.

[0147] Example 2: Translation processing

[0148] The newly generated article "New coronavirus variant" is sent to DeepL for translation into English, French, Spanish, etc. The translated content is then rechecked on the server and saved in data storage.

[0149] Example 3: Paid advertising

[0150] If a health company wants to advertise "antivirus products," the user sets the conditions in the ad management system, and the server inserts the ad in the appropriate place within the relevant article and displays it when it is displayed to the user.

[0151] In this way, the system of the present invention automates the entire process from information collection to content creation, translation, updating, and advertising, thereby realizing efficient and accurate information provision.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1: Regularly scan your sources

[0154] The server periodically scans designated sources (news sites, academic paper databases, government pages, etc.) and executes a script to periodically retrieve information using a web scraping tool such as BeautifulSoup or Scrapy. For example, the scraping task can be run at 2:00 AM every day using AWS Lambda or Google Cloud Functions.

[0155] Input: Source of information (URL, etc.)

[0156] Output: Raw data obtained (HTML, JSON, etc.)

[0157] Step 2: Acquire and store data

[0158] The server analyzes the raw data obtained by scraping and extracts the necessary information. This process uses an analysis library such as BeautifulSoup. The extracted information is stored in a temporary database (e.g., Redis or MongoDB).

[0159] Input: Raw data obtained by scraping

[0160] Output: Parsed extracted data (text format)

[0161] Step 3: Preprocessing and summarizing data

[0162] The server passes the stored extracted data to a natural language processing engine (e.g., spaCy, NLTK), which cleans the data (removes unnecessary symbols and spaces), summarizes it, and categorizes it, generating structured data that is easy to analyze.

[0163] Input: Extracted data stored in a temporary database

[0164] Output: Cleaned and summarized data

[0165] Step 4: Create a new article

[0166] The server uses the summary data generated in the previous step to input data into a generative AI model (e.g., GPT-4) to generate a new article, using the following prompt:

[0167] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[0168] As a result, a new article is generated.

[0169] Input: summarized data, prompt statement

[0170] Output: New article generated

[0171] Step 5: Proofread your article

[0172] The server sends the generated new article to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) for grammatical and content checking and correction. The proofread article is then stored in a temporary database.

[0173] Input: New article generated

[0174] Output: Proofread and revised article

[0175] Step 6: Scan and update existing articles

[0176] The server periodically scans the existing articles in the data storage and identifies those that need to be updated. This is done using a backend script (e.g., a Python script). To incorporate the new information into the identified articles, the server regenerates them, again using the generative AI model, with a prompt like this:

[0177] Prompt: Please update this article with the latest information.

[0178] Input: Existing articles in data storage, prompt text

[0179] Output: Updated article

[0180] Step 7: Recalibrate and save

[0181] The server passes the regenerated article to the proofreading engine for further checking and necessary corrections, and finally saves the updated article to data storage.

[0182] Input: Regenerated article

[0183] Output: Proofread and updated article

[0184] Step 8: Translation Request and Confirmation

[0185] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) to translate it into multiple languages, then double-checks the translated content to correct mistranslations and grammatical errors.

[0186] Input: Proofread and updated article

[0187] Output: Translated article

[0188] Step 9: Save the translated article

[0189] The server stores the reconfirmed and corrected translated articles in data storage, and the stored articles are provided to users in real time.

[0190] Input: Reviewed and corrected translation

[0191] Output: Articles saved in data storage

[0192] Step 10: Display to the User

[0193] When a user accesses an article, the device (user's browser or app) retrieves the article from data storage and displays it. The article is dynamically rendered using a front-end framework (e.g., React, Vue.js).

[0194] Input: A request from the user

[0195] Output: Articles displayed

[0196] Step 11: Setting ad conditions

[0197] Users (advertising sponsors) specify the conditions (keywords, category, target country, etc.) of the advertisements they wish to place via the advertising management system.

[0198] Input: Conditions specified by the advertiser

[0199] Output: Set advertising conditions

[0200] Step 12: Inserting Ads into Articles

[0201] The server identifies suitable articles based on the advertising criteria you set and inserts ads into those articles, optimizing the ad position and format using A / B testing.

[0202] Input: Set advertising conditions, target article

[0203] Output: Article with ad inserted

[0204] Step 13: Displaying articles with ads

[0205] The device displays the article with the advertisement inserted to the user, which increases the visibility of the advertisement and improves the click-through rate (CTR).

[0206] Input: Article with ad inserted

[0207] Output: Article with ads displayed to the user

[0208] (Application example 1)

[0209] 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."

[0210] Modern online shopping sites are required to provide content such as product descriptions and user reviews in multiple languages ​​quickly and accurately, while also inserting appropriate paid advertisements. However, doing this manually requires a significant amount of time and effort, and there is a high risk of updating information, mistranslations, and grammatical errors. Furthermore, providing information in multiple languages ​​requires specialized knowledge and is extremely difficult. Therefore, an automated system is needed to solve these challenges.

[0211] 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.

[0212] In this invention, the server includes means for collecting information, means for generating content using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated content using a proofreading engine, means for translating the generated and updated content using a multilingual translation engine, means for storing and publishing the translated content in a database, means for inserting paid advertisements into the content based on conditions set by a user, means for automatically generating product descriptions using a generative AI model based on the collected information, and means for translating the generated product descriptions into multiple languages. This makes it possible to quickly and accurately provide content such as product descriptions and user reviews in multiple languages, and to insert appropriate paid advertisements while ensuring the quality of information updates and translations.

[0213] "Means for collecting information" refers to technology for automatically collecting necessary data from multiple sources on the Internet.

[0214] A "natural language processing engine" refers to an algorithm or program that analyzes collected information and generates sentences in a format that humans can understand.

[0215] "Means for generating content" refers to technology that automatically creates new articles and descriptions based on collected information.

[0216] A "proofreading engine" is a program that checks the grammar and content of the generated text and corrects it if necessary.

[0217] A "multilingual translation engine" is a technology for translating generated and updated content into multiple languages.

[0218] "Means for storing and publishing in a database" refers to the system that stores the final content and publishes it for users to access.

[0219] "Means for inserting paid advertisements into content based on conditions set by the user" refers to a technology that embeds advertisements in appropriate locations according to conditions specified by the user.

[0220] A "generative AI model" refers to an algorithm that uses artificial intelligence to automatically generate new sentences and descriptions.

[0221] "Means for automatically generating product descriptions" refers to technology that uses a generative AI model to automatically create product descriptions.

[0222] The "means for multilingual translation" is a technique for translating the generated product description into multiple languages.

[0223] A system for implementing the present invention comprises the following major components:

[0224] 1. Information gathering engine

[0225] 2. Generative AI Models

[0226] 3. Proofreading Engine

[0227] 4. Multilingual Translation Engine

[0228] 5. Database

[0229] 6. Ad Management System

[0230] The server integrates these components and automates a series of processes, from information collection to generation, translation, proofreading, publication, and advertisement insertion. The specific process is explained below.

[0231] Information gathering

[0232] The server periodically collects data from news sites, official pages, user reviews, specialized blogs, etc. on the Internet. The collected information is first stored in a database for use in the next step. The main software used is the requests library and BeautifulSoup.

[0233] Product description generation

[0234] The server passes the collected information to a generative AI model, which generates a new product description based on the product's features and benefits. The generative AI model is built using OpenAI APIs and other tools.

[0235] proofreading

[0236] The generated product description is sent to a proofreading engine for grammatical and content checking and correction. A natural language processing engine is used as the grammar checker.

[0237] Multilingual Translation

[0238] The generated product description is sent to a multilingual translation engine, where it is translated into multiple languages. The translation engine uses the Google Translate API, among others. The translated content is then passed back to a proofreading engine to correct mistranslations and grammatical errors.

[0239] Database storage and publication

[0240] Finally, the generated and translated product descriptions are stored in a database and can be accessed via user devices (such as smartphones or robots).

[0241] Paid advertising insertion

[0242] Users set the ad criteria (keywords, category, target market, etc.) through the ad management system, and the server inserts the ad into the appropriate product description, which is then displayed when the final product page is published.

[0243] Specific examples

[0244] For example, to generate a product description for a new pair of noise-canceling headphones, the following prompts are fed into the generative AI model:

[0245] Prompt statement:

[0246] Please use the following information to describe your product:

[0247] Product Name: High-quality noise-canceling headphones

[0248] Features: Long battery life, comfortable fit

[0249] ...

[0250] This system automates the process from generating product descriptions to translating them into multiple languages ​​and inserting advertisements, enabling fast and accurate information provision. The specific hardware used includes a Linux-based server, and the software includes the OpenAI API, Google Translation API, requests, and BeautifulSoup.

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1: Gather information

[0253] The server collects data from news sites, official pages, user reviews, specialized blogs, etc. It uses the requests library and BeautifulSoup to retrieve the text data of web pages and store it in a database. The input is a list of URLs to be collected, and the output is the collected text data.

[0254] Step 2: Product description generation

[0255] The server passes the collected text data to a natural language processing engine for summarization and categorization. It then sends product description generation prompts to a generative AI model to create a new product description. The input is the collected text data, and the output is the generated product description.

[0256] Step 3: Proofreading

[0257] The server sends the generated product description to a proofreading engine for grammatical and content checking and correction. The input is the generated product description, and the output is the proofread product description. A grammar checker is used to improve accuracy.

[0258] Step 4: Multilingual Translation

[0259] The server passes the proofread product description to a multilingual translation engine, which translates it into multiple specified languages. The engine used is the Google Translate API. The input is the proofread product description, and the output is the product description translated into multiple languages.

[0260] Step 5: Translation confirmation

[0261] The server then passes the translated product description back to the proofreading engine, which checks for and corrects mistranslations and grammatical errors. The input is the translated product description, and the output is the corrected multilingual product description.

[0262] Step 6: Save and publish the database

[0263] The server saves the modified multilingual product description in a database and makes it publicly available for access by user terminals. The input is the modified multilingual product description, and the output is the product description saved in the database.

[0264] Step 7: Inserting Paid Ads

[0265] Users set the ad conditions (keywords, category, target market, etc.) through the ad management system. The server inserts the ad into the appropriate product description based on the set conditions. The input is the ad conditions set by the user, and the output is the product description with the ad inserted.

[0266] This efficiently automates the process from creating product descriptions to translating them into multiple languages ​​and inserting advertisements, making it possible to provide users with fast and accurate information.

[0267] 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.

[0268] overview

[0269] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include posting paid advertisements. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and adjust the display content and advertisements based on those emotions. Below, we will explain the operation of the system in detail from the perspectives of the server, the terminal, and the user.

[0270] Basic configuration

[0271] The system consists of the following main components:

[0272] 1. Information gathering engine

[0273] 2. Generation AI

[0274] 3. Proofreading Engine

[0275] 4. Multilingual Translation Engine

[0276] 5. Emotion Engine

[0277] 6. Database

[0278] 7. Advertising Management System

[0279] Program processing flow

[0280] Information gathering

[0281] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[0282] Article Generation

[0283] The server sends the collected information to a natural language processing engine, which categorizes and summarizes it. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[0284] The server passes the summarized data to the generation AI, which then creates a new article, automatically generating the article structure, including a headline, introduction, main content, and conclusion.

[0285] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency.

[0286] Translation processing and publishing

[0287] The server sends the generated and proofread articles to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[0288] The server checks the translated article and corrects mistranslations and grammatical errors using a correction engine.

[0289] The server stores the final article in a database and prepares it for display when accessed by a user.

[0290] The device requests an article, the server retrieves it from the database, and displays it to the user, often in a translated version based on the user's language settings.

[0291] Emotion recognition and article adjustment

[0292] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[0293] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[0294] Paid advertising placement

[0295] Users (advertiser sponsors) set the conditions for the ads they want to run (e.g., topics, keywords, target countries) through a dedicated interface.

[0296] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[0297] When the terminal finally displays the article to the user, it embeds the specified advertisement in the article appropriately and displays it in a way that is likely to interest the user.

[0298] Specific examples

[0299] Example 1: Creating and updating articles

[0300] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[0301] Generative AI generates articles based on new information.

[0302] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[0303] Example 2: Translation processing

[0304] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine, where it is translated into English, French, Spanish, and other languages.

[0305] The translated content is rechecked on the server and finally saved in the database.

[0306] Example 3: Emotion-based display adjustment

[0307] When a user of a device views an article, the emotion engine analyzes the user's reactions (e.g., click history, viewing time, comments) and determines that the user is expressing positive emotions.

[0308] The server suggests articles tailored to the user and displays articles that are encouraging and hopeful.

[0309] Example 4: Paid advertising

[0310] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[0311] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[0312] This system automatically handles everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, ensuring efficient and accurate information provision.

[0313] The processing flow will be explained below.

[0314] Step 1:

[0315] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is done automatically according to the set interval.

[0316] Step 2:

[0317] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information about "mutant strains of the new coronavirus" is collected, the information is summarized to extract key points.

[0318] Step 3:

[0319] The server passes the summarized data to the generation AI, which then creates a new article based on the data received. For example, it automatically generates an article structure, such as a headline, introduction, main content, and conclusion.

[0320] Step 4:

[0321] The server sends the generated article to a proofreading engine, which checks it for grammatical errors and content consistency and makes corrections as needed.

[0322] Step 5:

[0323] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[0324] Step 6:

[0325] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[0326] Step 7:

[0327] The server stores the final article in a database, which contains both the original and the translation.

[0328] Step 8:

[0329] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[0330] Step 9:

[0331] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[0332] Step 10:

[0333] The server inserts advertisements provided through the advertisement management system into articles in an optimal manner based on the user's emotions analyzed by the emotion engine.

[0334] Step 11:

[0335] The device (user's browser or app) requests the final article, the server retrieves it from the database and displays it to the user, including any optimized ads.

[0336] Step 12:

[0337] Users (advertiser sponsors) can view feedback reports provided through the system, which show how effective their ads were for users.

[0338] Through these steps, the system can automatically provide fast and accurate information, support multiple languages, customize based on user sentiment, and monetize advertising.

[0339] Example 2

[0340] 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."

[0341] In conventional systems, various processes such as information gathering, article generation, translation, and ad insertion were performed separately, making it difficult to efficiently execute a series of processes. Furthermore, the system was unable to provide content that took user emotions into consideration, which resulted in a lack of improvement in the user experience. Furthermore, the accuracy of ad targeting was low, limiting the effectiveness of advertising.

[0342] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting information; means for generating articles using a natural language processing engine based on the collected information; means for checking the grammar and content of the generated articles using a proofreading engine; means for translating the generated and updated articles using a multilingual translation engine; means for storing and publishing the translated articles in a database; means for inserting paid advertisements into articles based on user-specified conditions; and means for analyzing user responses to recognize emotions and adjusting display content based on the recognized emotions. This enables the efficient execution of a series of processes and the provision of optimal content based on user emotions. Furthermore, highly targeted advertisement display is expected to improve advertising effectiveness.

[0343] "Means for collecting information" refers to the ability to execute a process that automatically retrieves the latest data from designated websites and databases on the Internet.

[0344] A "natural language processing engine" is an artificial intelligence technology that analyzes collected information and performs processes such as classifying and summarizing the information and generating text.

[0345] "Means for generating articles" refers to the process of automatically creating new articles based on collected information using a natural language processing engine.

[0346] A "proofreading engine" is an artificial intelligence technology that checks the grammatical and content accuracy of generated text and makes any necessary corrections.

[0347] "Multilingual Translation Engine" means a translation technology that performs the process of translating generated and proofread articles into multiple languages.

[0348] "Means for storing and publishing articles in a database" refers to the process of storing the final generated articles in a database and publishing them for users to access.

[0349] "Means for inserting paid advertisements into articles" refers to the process of adding advertising content to applicable articles based on advertising criteria set by a user.

[0350] "Means for analyzing user responses and recognizing emotions" refers to artificial intelligence technology that analyzes user input and behavioral data to identify the user's emotional state.

[0351] "Means for tailoring display content" refers to the process of optimizing the content and format of displayed articles based on perceived user sentiment.

[0352] The system of the present invention uses generative AI to automatically collect, generate, translate, and update information, and automates a series of processes including the placement of paid advertisements. This system is composed of the following main components: an information collection engine, a natural language processing engine, generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertisement management system.

[0353] Information gathering

[0354] The server runs an information gathering engine that gathers the latest data from selected news sites, academic paper databases, and government agency pages using Python's Beautiful Soup library, and stores the data in a MySQL database.

[0355] Article Generation

[0356] The server sends the collected information to a natural language processing engine, which uses the BERT model to categorize and summarize the information. The summarized data is then passed to a generative AI (based on GPT-4) that generates a new article based on a prompt. For example, the prompt could be, "Based on information about the latest variants of the new coronavirus, please create an article with a headline, introduction, main content, and conclusion."

[0357] The generated articles are checked for grammar and content using a proofreading engine (Grammarly API), and any necessary corrections are made.

[0358] Translation processing and publishing

[0359] The server translates the generated and proofread articles into multiple languages ​​using the Google Translate API. The translated articles are then checked again with the Grammarly API to correct any mistranslations or grammatical errors. The final articles are stored in a database and prepared for display when accessed by users.

[0360] The device requests an article, the server retrieves it from the database and displays it to the user, with the appropriate translation depending on the user's language settings.

[0361] Emotion recognition and display content adjustment

[0362] The server uses an emotion engine (Text Analytics for sentiment analysis API) to analyze the user's input and reactions obtained from the device and identify the user's emotional state. Based on the results of this analysis, the server adjusts the content displayed, for example, displaying articles that inspire hope to users with positive emotions.

[0363] Paid advertising placement

[0364] Users (advertising sponsors) use the advertising management system interface (built with Ruby on Rails) to set the conditions for the advertisements they wish to display.

[0365] The server identifies appropriate articles based on the criteria and inserts paid advertisements into the articles at designated locations. When the device finally displays the articles to the user, it embeds the designated advertisements appropriately and displays them in a way that is likely to attract the user's attention.

[0366] In this way, the system of the present invention automatically processes everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, thereby providing efficient and accurate information.

[0367] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0368] Step 1: Gather information

[0369] The server starts an information collection engine and prepares a list of specified news sites, academic paper databases, government agency pages, etc. The server then uses Python's Beautiful Soup library to scrape each website and collect the latest information. The input is the URL of the target website, and the output is the collected text data. This data is saved in temporary storage (for example, a MySQL database).

[0370] Step 2: Categorize and summarize

[0371] The server sends the collected text data to a natural language processing engine. Here, Hugging Face's BERT model is used to categorize and summarize the data. The input is scraped text data, and the output is categorized summary text. For example, if information about mutated strains of the new coronavirus is collected, the data is summarized to extract the main point, "mutated strains of the new coronavirus are increasing concerns about the spread of infection."

[0372] Step 3: Article generation

[0373] The server passes the summarized data to the generation AI and sends a request including a prompt. The generation AI uses the GPT-4 model. The input is the summarized text and the prompt, and the output is a new article. For example, the prompt is sent as follows: "Based on information about the latest variants of the new coronavirus, please write an article that includes a headline, introduction, main content, and conclusion." The generated article will be structured text that includes a headline, introduction, main content, and conclusion.

[0374] Step 4: Proofreading

[0375] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency. Here, we use Grammarly's API. The input is the generated article, and the output is the proofread and corrected article. Specifically, it detects grammatical errors and corrects them to make the sentence grammatically correct.

[0376] Step 5: Translation

[0377] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages. This uses the Google Translate API. The input is the proofread article, and the output is the translated article. For example, it can be translated into English, French, Spanish, or other languages. The translated article is then checked again with the Grammarly API to correct any mistranslations or grammatical errors.

[0378] Step 6: Save and publish your article

[0379] The server stores the final article in a database, ready to display when accessed by the user. The input is the translated and proofread article, and the output is the article stored in the database. The device requests the article, the server retrieves it from the database, and displays it to the user. For example, depending on the user's language preference, the appropriate translation might be displayed: English, French, Spanish, etc.

[0380] Step 7: Emotion recognition and display adjustment

[0381] The server uses an emotion engine to analyze user input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions. Here, the Text Analytics for sentiment analysis API is used. The input is the user's reaction data, and the output is the user's emotional state. Based on the recognized emotions, the server adjusts the content and format of the articles to be displayed. For example, for a user who shows positive emotions, it displays articles that are encouraging and instill hope.

[0382] Step 8: Place Paid Ads

[0383] Users (advertising sponsors) set the conditions for the ads they want to run (e.g., topic, keywords, target country) through the ad management system. This interface is built using Ruby on Rails. The input is the ad conditions set by the user, and the output is the ad case generated based on those conditions. The server identifies appropriate articles based on the conditions received from the ad management system and inserts paid ads into the specified locations within the articles. When the device finally displays the article to the user, it embeds the specified ads within the article appropriately and displays them in a way that is likely to interest the user.

[0384] Through these steps, the system provides efficient and accurate information, displays optimal content based on the user's emotions, and places advertisements with high targeting accuracy.

[0385] (Application example 2)

[0386] 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."

[0387] Conventional news distribution systems are unable to display news optimally based on user sentiment, even when they rapidly generate, proofread, and translate collected information, making it difficult to improve the user experience. They also have difficulty increasing revenue through appropriate advertising placement. Therefore, there is a need for a system that automatically displays articles that reflect user sentiment and places paid advertisements according to user interests.

[0388] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0389] In this invention, the server includes means for collecting information, means for generating articles using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated articles using a proofreading engine, means for translating the generated and updated articles using a multilingual translation engine, means for storing and publishing the translated articles in a database, means for inserting paid advertisements into articles based on conditions specified by the user, and means for analyzing user emotions and adjusting display content based thereon, thereby enabling article display optimized to user emotions and effective advertisement placement.

[0390] The "means of collecting information" is an engine that automatically retrieves the latest information from news sites and academic paper databases on the Internet.

[0391] A "natural language processing engine" is an AI technology that analyzes collected information and generates articles.

[0392] The "means for generating articles" is a system that utilizes a natural language processing engine to execute the process of creating text.

[0393] A "proofreading engine" is an engine that has the function of checking and correcting the consistency of grammar and content of generated articles.

[0394] A "multilingual translation engine" is an AI technology for translating articles into multiple languages.

[0395] "Means for storing and publishing in a database" refers to a system for storing translated articles and providing them to users when they access them.

[0396] The "means for inserting paid advertisements into articles" is a system that places appropriate advertisements within articles based on conditions set by the user.

[0397] "Means for analyzing user emotions" refers to a system that analyzes the user's input and reactions to recognize emotions and adjusts the display content based on those emotions.

[0398] The system for implementing this invention consists of the following main components: an information gathering engine, a generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertising management system. The role and processing flow of each component will be explained in detail.

[0399] Information Gathering Engine

[0400] The information collection engine is used to scrape the latest data from specific news sites and academic paper databases. It uses AWS EC2 as the hardware and Python and the Scrapy library as the software. The collected data is stored on the server in a structured format.

[0401] Generation AI

[0402] The collected information is then generated into new articles by a generative AI. The generative AI uses OpenAI's GPT-4 and Hugging Face Transformers. This automatically generates article structures such as a headline, introduction, main content, and conclusion. A GPU server (equipped with NVIDIA A100) is used to achieve high-speed processing.

[0403] Proofreading Engine

[0404] The generated articles are then checked for grammar and content by a proofreading engine, using the Grammarly API and LanguageTool, ensuring accuracy and consistency of the generated text.

[0405] Multilingual Translation Engine

[0406] The proofread articles are then translated into multiple languages ​​using a multilingual translation engine, including the Google Cloud Translation API and DeepL API. A GPU server is also used to speed up the translation process.

[0407] Emotion Engine

[0408] Articles stored in the database are optimized by a sentiment engine that analyzes user input and reactions, using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, to display the best articles based on the user's sentiment.

[0409] Ad Management System

[0410] The ad management system inserts appropriate ads into articles based on the conditions set by the user. This system uses the Google Ads API and Facebook Ads API. Appropriate ad placement can maximize the effectiveness of ads.

[0411] Specific examples

[0412] Example 1: Generating news articles

[0413] Data collected: "Latest information on COVID-19 variants"

[0414] Example prompt for generative AI: "Please extract key points about the new coronavirus variant and generate a new news article."

[0415] Example 2: Translation processing

[0416] Example prompt: "Translate the following news article into English, French, and Spanish."

[0417] Example 3: Emotion-based display adjustment

[0418] Sample prompt: "Users are expressing positive emotions, so please tailor your article to be encouraging and uplifting."

[0419] Example 4: Paid Ad Insertion

[0420] Example ad: "New antivirus product"

[0421] Example prompt: "Insert an advertisement into a news article based on the following criteria."

[0422] In this way, the system of the present invention automatically performs all processes from information collection to article creation, translation, emotion recognition, and advertisement insertion, thereby realizing optimal information provision and advertisement display for the user.

[0423] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0424] Step 1: Gather information

[0425] Specific operation: The server periodically scrapes the latest information from specified news sites and academic paper databases.

[0426] Input: URL of the specified website or database

[0427] Output: Information collected by scraping

[0428] Data processing: Use Python and the Scrapy library to extract the necessary data from the web page and save it in a structured format (e.g., JSON format).

[0429] Step 2: Article generation

[0430] Specific operation: The server generates news articles using generative AI based on the collected information.

[0431] Input: Collected information (JSON format)

[0432] Output: Generated news article (text format)

[0433] Data processing: Using OpenAI's GPT-4 model on a GPU server, the collected data is analyzed and summarized, and a structured article is automatically generated, including a headline, introduction, main content, and conclusion.

[0434] Step 3: Proofread your article

[0435] What it does: The generated article is sent to a proofreading engine where it is checked and corrected for grammar and content consistency.

[0436] Input: Generated news article (text format)

[0437] Output: Proofread news article (text format)

[0438] Data processing: Use Grammarly API and LanguageTool to check for grammatical errors and stylistic consistency and make any necessary corrections.

[0439] Step 4: Multilingual Translation

[0440] What it does: The proofread article is sent to a multilingual translation engine and translated into multiple languages.

[0441] Input: Proofread news article (text format)

[0442] Output: Translated news articles (multilingual text format)

[0443] Data processing: Using the Google Cloud Translation API or DeepL API, articles are translated into the specified language (e.g., English, French, Spanish). The translated text is then checked for grammar again and corrected if necessary.

[0444] Step 5: Save and publish the database

[0445] What it does: The translated articles are stored in a database and made publicly available for users to access.

[0446] Input: Translated news article (multilingual text format)

[0447] Output: Published news article (text on a web page or application)

[0448] Data processing: The translated text is stored in a database and news articles in the appropriate language are provided upon user request.

[0449] Step 6: Inserting Paid Ads

[0450] What it does: Places appropriate ads within news articles based on user-specified criteria.

[0451] Input: User-specified advertising conditions (target demographic, keywords, etc.)

[0452] Output: News article with ads inserted (text format)

[0453] Data processing: Advertisements are inserted into the appropriate positions within articles based on the specified conditions using the ad management system (Google Ads API, Facebook Ads API).

[0454] Step 7: Sentiment analysis and display optimization

[0455] How it works: When a user browses an article, the emotion engine analyzes the user's input and reactions and optimizes the content displayed based on that.

[0456] Input: User response data (click history, viewing time, comments)

[0457] Output: Optimized display content (text format)

[0458] Data processing: Using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, we analyze user sentiment and tailor articles to encourage and inspire positive responses.

[0459] The above steps ensure that the entire process, from information gathering to article creation, proofreading, multilingual translation, database storage, paid advertising insertion, and display optimization based on sentiment analysis, proceeds smoothly, resulting in a system that provides users with the best possible news experience.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] [Second embodiment]

[0464] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0465] 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.

[0466] 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).

[0467] 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.

[0468] 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.

[0469] 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).

[0470] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] 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.

[0475] 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."

[0476] overview

[0477] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include placing paid advertisements. Below, we will explain the operation of the system in detail from the perspectives of the server, terminal, and user.

[0478] Basic configuration

[0479] The system consists of the following main components:

[0480] 1. Information gathering engine

[0481] 2. Generation AI

[0482] 3. Proofreading Engine

[0483] 4. Multilingual Translation Engine

[0484] 5. Database

[0485] 6. Ad Management System

[0486] Program processing flow

[0487] Information gathering

[0488] The server periodically collects data from reliable sources such as news sites, academic paper databases, and government agency pages on the web.

[0489] Article Generation

[0490] The server passes the collected information to a natural language processing engine for summarization and categorization.

[0491] The summarized information is then passed to a generative AI to create a new article.

[0492] The server sends the generated article to a proofreading engine for grammatical and content checking and correction.

[0493] Update an existing article

[0494] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information.

[0495] To incorporate new information into existing articles, generative AI is used to regenerate articles.

[0496] The text is passed to a proofreading engine for rechecking and correction if necessary.

[0497] Translation Processing

[0498] The server sends the generated or updated article to a multilingual translation engine for translation into multiple languages.

[0499] The server then double-checks the translated article and corrects any mistranslations or grammatical errors.

[0500] Article Publication

[0501] The server stores the final articles (original and translated) in a database and prepares them for display when accessed by a user.

[0502] The device (user's browser or app) accesses the article, retrieves it from the database, and displays it.

[0503] Paid advertising placement

[0504] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) via the advertising management system.

[0505] The server identifies suitable articles based on specified criteria and inserts advertisements within the articles.

[0506] The terminal appropriately displays the designated advertisement when displaying the final article to the user.

[0507] Specific examples

[0508] Example 1: Creating and updating articles

[0509] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[0510] Generative AI generates articles based on new information.

[0511] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[0512] Example 2: Translation processing

[0513] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine and translated into English, French, Spanish, and other languages.

[0514] The translated content is rechecked on the server and finally saved in the database.

[0515] Example 3: Paid advertising

[0516] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[0517] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[0518] In this way, the system automatically processes everything from information collection to article creation, translation, updates, and the insertion of paid advertisements, providing efficient and accurate information.

[0519] The processing flow will be explained below.

[0520] Step 1:

[0521] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[0522] Step 2:

[0523] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[0524] Step 3:

[0525] The server passes the summarized data to the AI ​​generator, which then creates a new article based on the data it receives, automatically generating a structure for the article, including a headline, introduction, main content, and conclusion.

[0526] Step 4:

[0527] The server then sends the generated article to a proofreading engine, which checks for grammatical errors and consistency of content. The proofreading engine uses AI technology to correct the article for correct grammar and appropriate expressions.

[0528] Step 5:

[0529] The server sends the generated and proofread article to a multilingual translation engine, where the article is translated into multiple languages ​​(e.g., English, French, Spanish, etc.).

[0530] Step 6:

[0531] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[0532] Step 7:

[0533] The server stores the final article in a database, which contains both the original and the translation.

[0534] Step 8:

[0535] The device (user's browser or app) requests an article, the server retrieves the article from the database, and displays it to the user, often in a translated version based on the user's language settings.

[0536] Step 9:

[0537] Users (advertiser sponsors) set the conditions for the ads they want to run (such as topics, keywords, and target areas) through a dedicated interface.

[0538] Step 10:

[0539] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[0540] Step 11:

[0541] When the device finally displays the article to the user, it embeds the specified advertisement appropriately within the article and displays it, so that the user can view the advertisement together with the article.

[0542] These steps enable the system to automatically provide fast and accurate information, multilingual support, and advertising monetization.

[0543] Example 1

[0544] 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."

[0545] In today's information society, there is a need to efficiently and accurately collect large amounts of information and generate valuable digital content. However, manually collecting information and generating articles requires a lot of time and effort, and there is also the risk of grammatical errors and mistranslations. Furthermore, providing the generated content in multiple languages ​​and effectively incorporating paid promotions requires advanced technology, making this a challenging task.

[0546] 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.

[0547] In this invention, the server includes a means for collecting information, a means for generating digital content using a natural language processing engine based on the collected information, and a means for checking the grammar and content of the generated digital content using a proofreading engine, thereby enabling efficient and accurate information collection, generation, and proofreading.

[0548] The server further includes means for translating the generated and updated digital content using a multilingual translation engine, means for storing and publishing the translated digital content in a data storage, and means for inserting paid promotions into the digital content based on conditions specified by a user, thereby enabling the generated digital content to be provided in multiple languages ​​and for inserting paid promotions in appropriate locations to maximize revenue.

[0549] "Means of collecting information" refers to a mechanism for regularly obtaining data from reliable sources.

[0550] "Natural language processing engine" refers to software or a system for analyzing, summarizing, and categorizing text.

[0551] "Means for generating digital content" refers to a system that uses artificial intelligence technology to automatically create new articles and content based on collected information.

[0552] "Proofreading Engine" means software or a system for checking and correcting the grammatical and content accuracy of generated digital content.

[0553] "Multilingual translation engine" refers to software or a system for translating generated digital content into multiple languages.

[0554] "Data storage" refers to databases and storage systems that store collected and generated digital content and make it available for retrieval as needed.

[0555] "User-specified conditions" refers to the advertising sponsor setting the promotion targets and conditions (keywords, categories, target countries, etc.).

[0556] "Paid Promotion" refers to advertisements or promotions that are inserted into digital content in exchange for a fee paid by advertising sponsors.

[0557] overview

[0558] The present invention relates to a system that utilizes artificial intelligence technology to automatically collect, generate, translate, and update information, as well as insert paid advertisements. The system includes the following main components:

[0559] Information Gathering Engine

[0560] Natural Language Processing Engine

[0561] Generative AI Models

[0562] Proofreading Engine

[0563] Multilingual Translation Engine

[0564] Data Storage

[0565] Ad Management System

[0566] Explaining program processing in natural language

[0567] Information gathering

[0568] The server periodically collects data from reliable sources, such as news sites, academic paper databases, and government pages, using web scraping tools such as BeautifulSoup and Scrapy. This ensures reliable and comprehensive collection of information.

[0569] Article Generation

[0570] The server passes the collected information to a natural language processing engine (e.g., spaCy, NLTK) for summarization and categorization. Then, based on the summarized information, a generative AI model (e.g., GPT-4) is used to create a new article. For example, the following prompt sentence is input to the generative AI model:

[0571] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[0572] The generated article is sent to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) to correct and check grammar and content.

[0573] Update an existing article

[0574] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information. To incorporate the new information into the identified articles, it regenerates the articles, again using the generative AI model. For example, it uses prompts like this:

[0575] Prompt: Please update this article with the latest information.

[0576] The generated article is then passed back to the proofreading engine, where corrections are made as needed.

[0577] Translation Processing

[0578] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) for translation into multiple languages. The translated article is then checked again by the server, where mistranslations and grammatical errors are corrected.

[0579] Article Publication

[0580] The server stores the final articles (original and translated) in data storage and prepares them for display when accessed by the user. The device (user's browser or app) accesses these articles, retrieves them from data storage, and displays them.

[0581] Paid advertising placement

[0582] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) through the advertising management system. The server identifies appropriate articles based on the specified conditions and inserts advertisements into those articles. When the terminal displays the final article to the user, it includes the appropriate advertisements.

[0583] Specific examples

[0584] Example 1: Creating and updating articles

[0585] When new information about the "COVID-19 variant" is updated, the server uses BeautifulSoup to collect relevant information from the web, then uses a generative AI model to generate a new article, checks the grammar of the article using the Grammarly API, saves it in data storage, and publishes it.

[0586] Example 2: Translation processing

[0587] The newly generated article "New coronavirus variant" is sent to DeepL for translation into English, French, Spanish, etc. The translated content is then rechecked on the server and saved in data storage.

[0588] Example 3: Paid advertising

[0589] If a health company wants to advertise "antivirus products," the user sets the conditions in the ad management system, and the server inserts the ad in the appropriate place within the relevant article and displays it when it is displayed to the user.

[0590] In this way, the system of the present invention automates the entire process from information collection to content creation, translation, updating, and advertising, thereby realizing efficient and accurate information provision.

[0591] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0592] Step 1: Regularly scan your sources

[0593] The server periodically scans designated sources (news sites, academic paper databases, government pages, etc.) and executes a script to periodically retrieve information using a web scraping tool such as BeautifulSoup or Scrapy. For example, the scraping task can be run at 2:00 AM every day using AWS Lambda or Google Cloud Functions.

[0594] Input: Source of information (URL, etc.)

[0595] Output: Raw data obtained (HTML, JSON, etc.)

[0596] Step 2: Acquire and store data

[0597] The server analyzes the raw data obtained by scraping and extracts the necessary information. This process uses an analysis library such as BeautifulSoup. The extracted information is stored in a temporary database (e.g., Redis or MongoDB).

[0598] Input: Raw data obtained by scraping

[0599] Output: Parsed extracted data (text format)

[0600] Step 3: Preprocessing and summarizing data

[0601] The server passes the stored extracted data to a natural language processing engine (e.g., spaCy, NLTK), which cleans the data (removes unnecessary symbols and spaces), summarizes it, and categorizes it, generating structured data that is easy to analyze.

[0602] Input: Extracted data stored in a temporary database

[0603] Output: Cleaned and summarized data

[0604] Step 4: Create a new article

[0605] The server uses the summary data generated in the previous step to input data into a generative AI model (e.g., GPT-4) to generate a new article, using the following prompt:

[0606] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[0607] As a result, a new article is generated.

[0608] Input: summarized data, prompt statement

[0609] Output: New article generated

[0610] Step 5: Proofread your article

[0611] The server sends the generated new article to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) for grammatical and content checking and correction. The proofread article is then stored in a temporary database.

[0612] Input: New article generated

[0613] Output: Proofread and revised article

[0614] Step 6: Scan and update existing articles

[0615] The server periodically scans the existing articles in the data storage and identifies those that need to be updated. This is done using a backend script (e.g., a Python script). To incorporate the new information into the identified articles, the server regenerates them, again using the generative AI model, with a prompt like this:

[0616] Prompt: Please update this article with the latest information.

[0617] Input: Existing articles in data storage, prompt text

[0618] Output: Updated article

[0619] Step 7: Recalibrate and save

[0620] The server passes the regenerated article to the proofreading engine for further checking and necessary corrections, and finally saves the updated article to data storage.

[0621] Input: Regenerated article

[0622] Output: Proofread and updated article

[0623] Step 8: Translation Request and Confirmation

[0624] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) to translate it into multiple languages, then double-checks the translated content to correct mistranslations and grammatical errors.

[0625] Input: Proofread and updated article

[0626] Output: Translated article

[0627] Step 9: Save the translated article

[0628] The server stores the reconfirmed and corrected translated articles in data storage, and the stored articles are provided to users in real time.

[0629] Input: Reviewed and corrected translation

[0630] Output: Articles saved in data storage

[0631] Step 10: Display to the User

[0632] When a user accesses an article, the device (user's browser or app) retrieves the article from data storage and displays it. The article is dynamically rendered using a front-end framework (e.g., React, Vue.js).

[0633] Input: A request from the user

[0634] Output: Articles displayed

[0635] Step 11: Setting ad conditions

[0636] Users (advertising sponsors) specify the conditions (keywords, category, target country, etc.) of the advertisements they wish to place via the advertising management system.

[0637] Input: Conditions specified by the advertiser

[0638] Output: Set advertising conditions

[0639] Step 12: Inserting Ads into Articles

[0640] The server identifies suitable articles based on the advertising criteria you set and inserts ads into those articles, optimizing the ad position and format using A / B testing.

[0641] Input: Set advertising conditions, target article

[0642] Output: Article with ad inserted

[0643] Step 13: Displaying articles with ads

[0644] The device displays the article with the advertisement inserted to the user, which increases the visibility of the advertisement and improves the click-through rate (CTR).

[0645] Input: Article with ad inserted

[0646] Output: Article with ads displayed to the user

[0647] (Application example 1)

[0648] 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."

[0649] Modern online shopping sites are required to provide content such as product descriptions and user reviews in multiple languages ​​quickly and accurately, while also inserting appropriate paid advertisements. However, doing this manually requires a significant amount of time and effort, and there is a high risk of updating information, mistranslations, and grammatical errors. Furthermore, providing information in multiple languages ​​requires specialized knowledge and is extremely difficult. Therefore, an automated system is needed to solve these challenges.

[0650] 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.

[0651] In this invention, the server includes means for collecting information, means for generating content using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated content using a proofreading engine, means for translating the generated and updated content using a multilingual translation engine, means for storing and publishing the translated content in a database, means for inserting paid advertisements into the content based on conditions set by a user, means for automatically generating product descriptions using a generative AI model based on the collected information, and means for translating the generated product descriptions into multiple languages. This makes it possible to quickly and accurately provide content such as product descriptions and user reviews in multiple languages, and to insert appropriate paid advertisements while ensuring the quality of information updates and translations.

[0652] "Means for collecting information" refers to technology for automatically collecting necessary data from multiple sources on the Internet.

[0653] A "natural language processing engine" refers to an algorithm or program that analyzes collected information and generates sentences in a format that humans can understand.

[0654] "Means for generating content" refers to technology that automatically creates new articles and descriptions based on collected information.

[0655] A "proofreading engine" is a program that checks the grammar and content of the generated text and corrects it if necessary.

[0656] A "multilingual translation engine" is a technology for translating generated and updated content into multiple languages.

[0657] "Means for storing and publishing in a database" refers to the system that stores the final content and publishes it for users to access.

[0658] "Means for inserting paid advertisements into content based on conditions set by the user" refers to a technology that embeds advertisements in appropriate locations according to conditions specified by the user.

[0659] A "generative AI model" refers to an algorithm that uses artificial intelligence to automatically generate new sentences and descriptions.

[0660] "Means for automatically generating product descriptions" refers to technology that uses a generative AI model to automatically create product descriptions.

[0661] The "means for multilingual translation" is a technique for translating the generated product description into multiple languages.

[0662] A system for implementing the present invention comprises the following major components:

[0663] 1. Information gathering engine

[0664] 2. Generative AI Models

[0665] 3. Proofreading Engine

[0666] 4. Multilingual Translation Engine

[0667] 5. Database

[0668] 6. Ad Management System

[0669] The server integrates these components and automates a series of processes, from information collection to generation, translation, proofreading, publication, and advertisement insertion. The specific process is explained below.

[0670] Information gathering

[0671] The server periodically collects data from news sites, official pages, user reviews, specialized blogs, etc. on the Internet. The collected information is first stored in a database for use in the next step. The main software used is the requests library and BeautifulSoup.

[0672] Product description generation

[0673] The server passes the collected information to a generative AI model, which generates a new product description based on the product's features and benefits. The generative AI model is built using OpenAI APIs and other tools.

[0674] proofreading

[0675] The generated product description is sent to a proofreading engine for grammatical and content checking and correction. A natural language processing engine is used as the grammar checker.

[0676] Multilingual Translation

[0677] The generated product description is sent to a multilingual translation engine, where it is translated into multiple languages. The translation engine uses the Google Translate API, among others. The translated content is then passed back to a proofreading engine to correct mistranslations and grammatical errors.

[0678] Database storage and publication

[0679] Finally, the generated and translated product descriptions are stored in a database and can be accessed via user devices (such as smartphones or robots).

[0680] Paid advertising insertion

[0681] Users set the ad criteria (keywords, category, target market, etc.) through the ad management system, and the server inserts the ad into the appropriate product description, which is then displayed when the final product page is published.

[0682] Specific examples

[0683] For example, to generate a product description for a new pair of noise-canceling headphones, the following prompts are fed into the generative AI model:

[0684] Prompt statement:

[0685] Please use the following information to describe your product:

[0686] Product Name: High-quality noise-canceling headphones

[0687] Features: Long battery life, comfortable fit

[0688] ...

[0689] This system automates the process from generating product descriptions to translating them into multiple languages ​​and inserting advertisements, enabling fast and accurate information provision. The specific hardware used includes a Linux-based server, and the software includes the OpenAI API, Google Translation API, requests, and BeautifulSoup.

[0690] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0691] Step 1: Gather information

[0692] The server collects data from news sites, official pages, user reviews, specialized blogs, etc. It uses the requests library and BeautifulSoup to retrieve the text data of web pages and store it in a database. The input is a list of URLs to be collected, and the output is the collected text data.

[0693] Step 2: Product description generation

[0694] The server passes the collected text data to a natural language processing engine for summarization and categorization. It then sends product description generation prompts to a generative AI model to create a new product description. The input is the collected text data, and the output is the generated product description.

[0695] Step 3: Proofreading

[0696] The server sends the generated product description to a proofreading engine for grammatical and content checking and correction. The input is the generated product description, and the output is the proofread product description. A grammar checker is used to improve accuracy.

[0697] Step 4: Multilingual Translation

[0698] The server passes the proofread product description to a multilingual translation engine, which translates it into multiple specified languages. The engine used is the Google Translate API. The input is the proofread product description, and the output is the product description translated into multiple languages.

[0699] Step 5: Translation confirmation

[0700] The server then passes the translated product description back to the proofreading engine, which checks for and corrects mistranslations and grammatical errors. The input is the translated product description, and the output is the corrected multilingual product description.

[0701] Step 6: Save and publish the database

[0702] The server saves the modified multilingual product description in a database and makes it publicly available for access by user terminals. The input is the modified multilingual product description, and the output is the product description saved in the database.

[0703] Step 7: Inserting Paid Ads

[0704] Users set the ad conditions (keywords, category, target market, etc.) through the ad management system. The server inserts the ad into the appropriate product description based on the set conditions. The input is the ad conditions set by the user, and the output is the product description with the ad inserted.

[0705] This efficiently automates the process from creating product descriptions to translating them into multiple languages ​​and inserting advertisements, making it possible to provide users with fast and accurate information.

[0706] 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.

[0707] overview

[0708] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include posting paid advertisements. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and adjust the display content and advertisements based on those emotions. Below, we will explain the operation of the system in detail from the perspectives of the server, the terminal, and the user.

[0709] Basic configuration

[0710] The system consists of the following main components:

[0711] 1. Information gathering engine

[0712] 2. Generation AI

[0713] 3. Proofreading Engine

[0714] 4. Multilingual Translation Engine

[0715] 5. Emotion Engine

[0716] 6. Database

[0717] 7. Advertising Management System

[0718] Program processing flow

[0719] Information gathering

[0720] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[0721] Article Generation

[0722] The server sends the collected information to a natural language processing engine, which categorizes and summarizes it. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[0723] The server passes the summarized data to the generation AI, which then creates a new article, automatically generating the article structure, including a headline, introduction, main content, and conclusion.

[0724] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency.

[0725] Translation processing and publishing

[0726] The server sends the generated and proofread articles to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[0727] The server checks the translated article and corrects mistranslations and grammatical errors using a correction engine.

[0728] The server stores the final article in a database and prepares it for display when accessed by a user.

[0729] The device requests an article, the server retrieves it from the database, and displays it to the user, often in a translated version based on the user's language settings.

[0730] Emotion recognition and article adjustment

[0731] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[0732] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[0733] Paid advertising placement

[0734] Users (advertiser sponsors) set the conditions for the ads they want to run (e.g., topics, keywords, target countries) through a dedicated interface.

[0735] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[0736] When the terminal finally displays the article to the user, it embeds the specified advertisement in the article appropriately and displays it in a way that is likely to interest the user.

[0737] Specific examples

[0738] Example 1: Creating and updating articles

[0739] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[0740] Generative AI generates articles based on new information.

[0741] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[0742] Example 2: Translation processing

[0743] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine, where it is translated into English, French, Spanish, and other languages.

[0744] The translated content is rechecked on the server and finally saved in the database.

[0745] Example 3: Emotion-based display adjustment

[0746] When a user of a device views an article, the emotion engine analyzes the user's reactions (e.g., click history, viewing time, comments) and determines that the user is expressing positive emotions.

[0747] The server suggests articles tailored to the user and displays articles that are encouraging and hopeful.

[0748] Example 4: Paid advertising

[0749] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[0750] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[0751] This system automatically handles everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, ensuring efficient and accurate information provision.

[0752] The processing flow will be explained below.

[0753] Step 1:

[0754] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is done automatically according to the set interval.

[0755] Step 2:

[0756] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information about "mutant strains of the new coronavirus" is collected, the information is summarized to extract key points.

[0757] Step 3:

[0758] The server passes the summarized data to the generation AI, which then creates a new article based on the data received. For example, it automatically generates an article structure, such as a headline, introduction, main content, and conclusion.

[0759] Step 4:

[0760] The server sends the generated article to a proofreading engine, which checks it for grammatical errors and content consistency and makes corrections as needed.

[0761] Step 5:

[0762] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[0763] Step 6:

[0764] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[0765] Step 7:

[0766] The server stores the final article in a database, which contains both the original and the translation.

[0767] Step 8:

[0768] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[0769] Step 9:

[0770] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[0771] Step 10:

[0772] The server inserts advertisements provided through the advertisement management system into articles in an optimal manner based on the user's emotions analyzed by the emotion engine.

[0773] Step 11:

[0774] The device (user's browser or app) requests the final article, the server retrieves it from the database and displays it to the user, including any optimized ads.

[0775] Step 12:

[0776] Users (advertiser sponsors) can view feedback reports provided through the system, which show how effective their ads were for users.

[0777] Through these steps, the system can automatically provide fast and accurate information, support multiple languages, customize based on user sentiment, and monetize advertising.

[0778] Example 2

[0779] 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."

[0780] In conventional systems, various processes such as information gathering, article generation, translation, and ad insertion were performed separately, making it difficult to efficiently execute a series of processes. Furthermore, the system was unable to provide content that took user emotions into consideration, which resulted in a lack of improvement in the user experience. Furthermore, the accuracy of ad targeting was low, limiting the effectiveness of advertising.

[0781] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting information; means for generating articles using a natural language processing engine based on the collected information; means for checking the grammar and content of the generated articles using a proofreading engine; means for translating the generated and updated articles using a multilingual translation engine; means for storing and publishing the translated articles in a database; means for inserting paid advertisements into articles based on user-specified conditions; and means for analyzing user responses to recognize emotions and adjusting display content based on the recognized emotions. This enables the efficient execution of a series of processes and the provision of optimal content based on user emotions. Furthermore, highly targeted advertisement display is expected to improve advertising effectiveness.

[0782] "Means for collecting information" refers to the ability to execute a process that automatically retrieves the latest data from designated websites and databases on the Internet.

[0783] A "natural language processing engine" is an artificial intelligence technology that analyzes collected information and performs processes such as classifying and summarizing the information and generating text.

[0784] "Means for generating articles" refers to the process of automatically creating new articles based on collected information using a natural language processing engine.

[0785] A "proofreading engine" is an artificial intelligence technology that checks the grammatical and content accuracy of generated text and makes any necessary corrections.

[0786] "Multilingual Translation Engine" means a translation technology that performs the process of translating generated and proofread articles into multiple languages.

[0787] "Means for storing and publishing articles in a database" refers to the process of storing the final generated articles in a database and publishing them for users to access.

[0788] "Means for inserting paid advertisements into articles" refers to the process of adding advertising content to applicable articles based on advertising criteria set by a user.

[0789] "Means for analyzing user responses and recognizing emotions" refers to artificial intelligence technology that analyzes user input and behavioral data to identify the user's emotional state.

[0790] "Means for tailoring display content" refers to the process of optimizing the content and format of displayed articles based on perceived user sentiment.

[0791] The system of the present invention uses generative AI to automatically collect, generate, translate, and update information, and automates a series of processes including the placement of paid advertisements. This system is composed of the following main components: an information collection engine, a natural language processing engine, generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertisement management system.

[0792] Information gathering

[0793] The server runs an information gathering engine that gathers the latest data from selected news sites, academic paper databases, and government agency pages using Python's Beautiful Soup library, and stores the data in a MySQL database.

[0794] Article Generation

[0795] The server sends the collected information to a natural language processing engine, which uses the BERT model to categorize and summarize the information. The summarized data is then passed to a generative AI (based on GPT-4) that generates a new article based on a prompt. For example, the prompt could be, "Based on information about the latest variants of the new coronavirus, please create an article with a headline, introduction, main content, and conclusion."

[0796] The generated articles are checked for grammar and content using a proofreading engine (Grammarly API), and any necessary corrections are made.

[0797] Translation processing and publishing

[0798] The server translates the generated and proofread articles into multiple languages ​​using the Google Translate API. The translated articles are then checked again with the Grammarly API to correct any mistranslations or grammatical errors. The final articles are stored in a database and prepared for display when accessed by users.

[0799] The device requests an article, the server retrieves it from the database and displays it to the user, with the appropriate translation depending on the user's language settings.

[0800] Emotion recognition and display content adjustment

[0801] The server uses an emotion engine (Text Analytics for sentiment analysis API) to analyze the user's input and reactions obtained from the device and identify the user's emotional state. Based on the results of this analysis, the server adjusts the content displayed, for example, displaying articles that inspire hope to users with positive emotions.

[0802] Paid advertising placement

[0803] Users (advertising sponsors) use the advertising management system interface (built with Ruby on Rails) to set the conditions for the advertisements they wish to display.

[0804] The server identifies appropriate articles based on the criteria and inserts paid advertisements into the articles at designated locations. When the device finally displays the articles to the user, it embeds the designated advertisements appropriately and displays them in a way that is likely to attract the user's attention.

[0805] In this way, the system of the present invention automatically processes everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, thereby providing efficient and accurate information.

[0806] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0807] Step 1: Gather information

[0808] The server starts an information collection engine and prepares a list of specified news sites, academic paper databases, government agency pages, etc. The server then uses Python's Beautiful Soup library to scrape each website and collect the latest information. The input is the URL of the target website, and the output is the collected text data. This data is saved in temporary storage (for example, a MySQL database).

[0809] Step 2: Categorize and summarize

[0810] The server sends the collected text data to a natural language processing engine. Here, Hugging Face's BERT model is used to categorize and summarize the data. The input is scraped text data, and the output is categorized summary text. For example, if information about mutated strains of the new coronavirus is collected, the data is summarized to extract the main point, "mutated strains of the new coronavirus are increasing concerns about the spread of infection."

[0811] Step 3: Article generation

[0812] The server passes the summarized data to the generation AI and sends a request including a prompt. The generation AI uses the GPT-4 model. The input is the summarized text and the prompt, and the output is a new article. For example, the prompt is sent as follows: "Based on information about the latest variants of the new coronavirus, please write an article that includes a headline, introduction, main content, and conclusion." The generated article will be structured text that includes a headline, introduction, main content, and conclusion.

[0813] Step 4: Proofreading

[0814] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency. Here, we use Grammarly's API. The input is the generated article, and the output is the proofread and corrected article. Specifically, it detects grammatical errors and corrects them to make the sentence grammatically correct.

[0815] Step 5: Translation

[0816] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages. This uses the Google Translate API. The input is the proofread article, and the output is the translated article. For example, it can be translated into English, French, Spanish, or other languages. The translated article is then checked again with the Grammarly API to correct any mistranslations or grammatical errors.

[0817] Step 6: Save and publish your article

[0818] The server stores the final article in a database, ready to display when accessed by the user. The input is the translated and proofread article, and the output is the article stored in the database. The device requests the article, the server retrieves it from the database, and displays it to the user. For example, depending on the user's language preference, the appropriate translation might be displayed: English, French, Spanish, etc.

[0819] Step 7: Emotion recognition and display adjustment

[0820] The server uses an emotion engine to analyze user input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions. Here, the Text Analytics for sentiment analysis API is used. The input is the user's reaction data, and the output is the user's emotional state. Based on the recognized emotions, the server adjusts the content and format of the articles to be displayed. For example, for a user who shows positive emotions, it displays articles that are encouraging and instill hope.

[0821] Step 8: Place Paid Ads

[0822] Users (advertising sponsors) set the conditions for the ads they want to run (e.g., topic, keywords, target country) through the ad management system. This interface is built using Ruby on Rails. The input is the ad conditions set by the user, and the output is the ad case generated based on those conditions. The server identifies appropriate articles based on the conditions received from the ad management system and inserts paid ads into the specified locations within the articles. When the device finally displays the article to the user, it embeds the specified ads within the article appropriately and displays them in a way that is likely to interest the user.

[0823] Through these steps, the system provides efficient and accurate information, displays optimal content based on the user's emotions, and places advertisements with high targeting accuracy.

[0824] (Application example 2)

[0825] 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."

[0826] Conventional news distribution systems are unable to display news optimally based on user sentiment, even when they rapidly generate, proofread, and translate collected information, making it difficult to improve the user experience. They also have difficulty increasing revenue through appropriate advertising placement. Therefore, there is a need for a system that automatically displays articles that reflect user sentiment and places paid advertisements according to user interests.

[0827] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0828] In this invention, the server includes means for collecting information, means for generating articles using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated articles using a proofreading engine, means for translating the generated and updated articles using a multilingual translation engine, means for storing and publishing the translated articles in a database, means for inserting paid advertisements into articles based on conditions specified by the user, and means for analyzing user emotions and adjusting display content based thereon, thereby enabling article display optimized to user emotions and effective advertisement placement.

[0829] The "means of collecting information" is an engine that automatically retrieves the latest information from news sites and academic paper databases on the Internet.

[0830] A "natural language processing engine" is an AI technology that analyzes collected information and generates articles.

[0831] The "means for generating articles" is a system that utilizes a natural language processing engine to execute the process of creating text.

[0832] A "proofreading engine" is an engine that has the function of checking and correcting the consistency of grammar and content of generated articles.

[0833] A "multilingual translation engine" is an AI technology for translating articles into multiple languages.

[0834] "Means for storing and publishing in a database" refers to a system for storing translated articles and providing them to users when they access them.

[0835] The "means for inserting paid advertisements into articles" is a system that places appropriate advertisements within articles based on conditions set by the user.

[0836] "Means for analyzing user emotions" refers to a system that analyzes the user's input and reactions to recognize emotions and adjusts the display content based on those emotions.

[0837] The system for implementing this invention consists of the following main components: an information gathering engine, a generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertising management system. The role and processing flow of each component will be explained in detail.

[0838] Information Gathering Engine

[0839] The information collection engine is used to scrape the latest data from specific news sites and academic paper databases. It uses AWS EC2 as the hardware and Python and the Scrapy library as the software. The collected data is stored on the server in a structured format.

[0840] Generation AI

[0841] The collected information is then generated into new articles by a generative AI. The generative AI uses OpenAI's GPT-4 and Hugging Face Transformers. This automatically generates article structures such as a headline, introduction, main content, and conclusion. A GPU server (equipped with NVIDIA A100) is used to achieve high-speed processing.

[0842] Proofreading Engine

[0843] The generated articles are then checked for grammar and content by a proofreading engine, using the Grammarly API and LanguageTool, ensuring accuracy and consistency of the generated text.

[0844] Multilingual Translation Engine

[0845] The proofread articles are then translated into multiple languages ​​using a multilingual translation engine, including the Google Cloud Translation API and DeepL API. A GPU server is also used to speed up the translation process.

[0846] Emotion Engine

[0847] Articles stored in the database are optimized by a sentiment engine that analyzes user input and reactions, using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, to display the best articles based on the user's sentiment.

[0848] Ad Management System

[0849] The ad management system inserts appropriate ads into articles based on the conditions set by the user. This system uses the Google Ads API and Facebook Ads API. Appropriate ad placement can maximize the effectiveness of ads.

[0850] Specific examples

[0851] Example 1: Generating news articles

[0852] Data collected: "Latest information on COVID-19 variants"

[0853] Example prompt for generative AI: "Please extract key points about the new coronavirus variant and generate a new news article."

[0854] Example 2: Translation processing

[0855] Example prompt: "Translate the following news article into English, French, and Spanish."

[0856] Example 3: Emotion-based display adjustment

[0857] Sample prompt: "Users are expressing positive emotions, so please tailor your article to be encouraging and uplifting."

[0858] Example 4: Paid Ad Insertion

[0859] Example ad: "New antivirus product"

[0860] Example prompt: "Insert an advertisement into a news article based on the following criteria."

[0861] In this way, the system of the present invention automatically performs all processes from information collection to article creation, translation, emotion recognition, and advertisement insertion, thereby realizing optimal information provision and advertisement display for the user.

[0862] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0863] Step 1: Gather information

[0864] Specific operation: The server periodically scrapes the latest information from specified news sites and academic paper databases.

[0865] Input: URL of the specified website or database

[0866] Output: Information collected by scraping

[0867] Data processing: Use Python and the Scrapy library to extract the necessary data from the web page and save it in a structured format (e.g., JSON format).

[0868] Step 2: Article generation

[0869] Specific operation: The server generates news articles using generative AI based on the collected information.

[0870] Input: Collected information (JSON format)

[0871] Output: Generated news article (text format)

[0872] Data processing: Using OpenAI's GPT-4 model on a GPU server, the collected data is analyzed and summarized, and a structured article is automatically generated, including a headline, introduction, main content, and conclusion.

[0873] Step 3: Proofread your article

[0874] What it does: The generated article is sent to a proofreading engine where it is checked and corrected for grammar and content consistency.

[0875] Input: Generated news article (text format)

[0876] Output: Proofread news article (text format)

[0877] Data processing: Use Grammarly API and LanguageTool to check for grammatical errors and stylistic consistency and make any necessary corrections.

[0878] Step 4: Multilingual Translation

[0879] What it does: The proofread article is sent to a multilingual translation engine and translated into multiple languages.

[0880] Input: Proofread news article (text format)

[0881] Output: Translated news articles (multilingual text format)

[0882] Data processing: Using the Google Cloud Translation API or DeepL API, articles are translated into the specified language (e.g., English, French, Spanish). The translated text is then checked for grammar again and corrected if necessary.

[0883] Step 5: Save and publish the database

[0884] What it does: The translated articles are stored in a database and made publicly available for users to access.

[0885] Input: Translated news article (multilingual text format)

[0886] Output: Published news article (text on a web page or application)

[0887] Data processing: The translated text is stored in a database and news articles in the appropriate language are provided upon user request.

[0888] Step 6: Inserting Paid Ads

[0889] What it does: Places appropriate ads within news articles based on user-specified criteria.

[0890] Input: User-specified advertising conditions (target demographic, keywords, etc.)

[0891] Output: News article with ads inserted (text format)

[0892] Data processing: Advertisements are inserted into the appropriate positions within articles based on the specified conditions using the ad management system (Google Ads API, Facebook Ads API).

[0893] Step 7: Sentiment analysis and display optimization

[0894] How it works: When a user browses an article, the emotion engine analyzes the user's input and reactions and optimizes the content displayed based on that.

[0895] Input: User response data (click history, viewing time, comments)

[0896] Output: Optimized display content (text format)

[0897] Data processing: Using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, we analyze user sentiment and tailor articles to encourage and inspire positive responses.

[0898] The above steps ensure that the entire process, from information gathering to article creation, proofreading, multilingual translation, database storage, paid advertising insertion, and display optimization based on sentiment analysis, proceeds smoothly, resulting in a system that provides users with the best possible news experience.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] [Third embodiment]

[0903] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0904] 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.

[0905] 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).

[0906] 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.

[0907] 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.

[0908] 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).

[0909] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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."

[0915] overview

[0916] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include placing paid advertisements. Below, we will explain the operation of the system in detail from the perspectives of the server, terminal, and user.

[0917] Basic configuration

[0918] The system consists of the following main components:

[0919] 1. Information gathering engine

[0920] 2. Generation AI

[0921] 3. Proofreading Engine

[0922] 4. Multilingual Translation Engine

[0923] 5. Database

[0924] 6. Ad Management System

[0925] Program processing flow

[0926] Information gathering

[0927] The server periodically collects data from reliable sources such as news sites, academic paper databases, and government agency pages on the web.

[0928] Article Generation

[0929] The server passes the collected information to a natural language processing engine for summarization and categorization.

[0930] The summarized information is then passed to a generative AI to create a new article.

[0931] The server sends the generated article to a proofreading engine for grammatical and content checking and correction.

[0932] Update an existing article

[0933] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information.

[0934] To incorporate new information into existing articles, generative AI is used to regenerate articles.

[0935] The text is passed to a proofreading engine for rechecking and correction if necessary.

[0936] Translation Processing

[0937] The server sends the generated or updated article to a multilingual translation engine for translation into multiple languages.

[0938] The server then double-checks the translated article and corrects any mistranslations or grammatical errors.

[0939] Article Publication

[0940] The server stores the final articles (original and translated) in a database and prepares them for display when accessed by a user.

[0941] The device (user's browser or app) accesses the article, retrieves it from the database, and displays it.

[0942] Paid advertising placement

[0943] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) via the advertising management system.

[0944] The server identifies suitable articles based on specified criteria and inserts advertisements within the articles.

[0945] The terminal appropriately displays the designated advertisement when displaying the final article to the user.

[0946] Specific examples

[0947] Example 1: Creating and updating articles

[0948] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[0949] Generative AI generates articles based on new information.

[0950] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[0951] Example 2: Translation processing

[0952] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine and translated into English, French, Spanish, and other languages.

[0953] The translated content is rechecked on the server and finally saved in the database.

[0954] Example 3: Paid advertising

[0955] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[0956] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[0957] In this way, the system automatically processes everything from information collection to article creation, translation, updates, and the insertion of paid advertisements, providing efficient and accurate information.

[0958] The processing flow will be explained below.

[0959] Step 1:

[0960] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[0961] Step 2:

[0962] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[0963] Step 3:

[0964] The server passes the summarized data to the AI ​​generator, which then creates a new article based on the data it receives, automatically generating a structure for the article, including a headline, introduction, main content, and conclusion.

[0965] Step 4:

[0966] The server then sends the generated article to a proofreading engine, which checks for grammatical errors and consistency of content. The proofreading engine uses AI technology to correct the article for correct grammar and appropriate expressions.

[0967] Step 5:

[0968] The server sends the generated and proofread article to a multilingual translation engine, where the article is translated into multiple languages ​​(e.g., English, French, Spanish, etc.).

[0969] Step 6:

[0970] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[0971] Step 7:

[0972] The server stores the final article in a database, which contains both the original and the translation.

[0973] Step 8:

[0974] The device (user's browser or app) requests an article, the server retrieves the article from the database, and displays it to the user, often in a translated version based on the user's language settings.

[0975] Step 9:

[0976] Users (advertiser sponsors) set the conditions for the ads they want to run (such as topics, keywords, and target areas) through a dedicated interface.

[0977] Step 10:

[0978] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[0979] Step 11:

[0980] When the device finally displays the article to the user, it embeds the specified advertisement appropriately within the article and displays it, so that the user can view the advertisement together with the article.

[0981] These steps enable the system to automatically provide fast and accurate information, multilingual support, and advertising monetization.

[0982] Example 1

[0983] 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."

[0984] In today's information society, there is a need to efficiently and accurately collect large amounts of information and generate valuable digital content. However, manually collecting information and generating articles requires a lot of time and effort, and there is also the risk of grammatical errors and mistranslations. Furthermore, providing the generated content in multiple languages ​​and effectively incorporating paid promotions requires advanced technology, making this a challenging task.

[0985] 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.

[0986] In this invention, the server includes a means for collecting information, a means for generating digital content using a natural language processing engine based on the collected information, and a means for checking the grammar and content of the generated digital content using a proofreading engine, thereby enabling efficient and accurate information collection, generation, and proofreading.

[0987] The server further includes means for translating the generated and updated digital content using a multilingual translation engine, means for storing and publishing the translated digital content in a data storage, and means for inserting paid promotions into the digital content based on conditions specified by a user, thereby enabling the generated digital content to be provided in multiple languages ​​and for inserting paid promotions in appropriate locations to maximize revenue.

[0988] "Means of collecting information" refers to a mechanism for regularly obtaining data from reliable sources.

[0989] "Natural language processing engine" refers to software or a system for analyzing, summarizing, and categorizing text.

[0990] "Means for generating digital content" refers to a system that uses artificial intelligence technology to automatically create new articles and content based on collected information.

[0991] "Proofreading Engine" means software or a system for checking and correcting the grammatical and content accuracy of generated digital content.

[0992] "Multilingual translation engine" refers to software or a system for translating generated digital content into multiple languages.

[0993] "Data storage" refers to databases and storage systems that store collected and generated digital content and make it available for retrieval as needed.

[0994] "User-specified conditions" refers to the advertising sponsor setting the promotion targets and conditions (keywords, categories, target countries, etc.).

[0995] "Paid Promotion" refers to advertisements or promotions that are inserted into digital content in exchange for a fee paid by advertising sponsors.

[0996] overview

[0997] The present invention relates to a system that utilizes artificial intelligence technology to automatically collect, generate, translate, and update information, as well as insert paid advertisements. The system includes the following main components:

[0998] Information Gathering Engine

[0999] Natural Language Processing Engine

[1000] Generative AI Models

[1001] Proofreading Engine

[1002] Multilingual Translation Engine

[1003] Data Storage

[1004] Ad Management System

[1005] Explaining program processing in natural language

[1006] Information gathering

[1007] The server periodically collects data from reliable sources, such as news sites, academic paper databases, and government pages, using web scraping tools such as BeautifulSoup and Scrapy. This ensures reliable and comprehensive collection of information.

[1008] Article Generation

[1009] The server passes the collected information to a natural language processing engine (e.g., spaCy, NLTK) for summarization and categorization. Then, based on the summarized information, a generative AI model (e.g., GPT-4) is used to create a new article. For example, the following prompt sentence is input to the generative AI model:

[1010] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[1011] The generated article is sent to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) to correct and check grammar and content.

[1012] Update an existing article

[1013] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information. To incorporate the new information into the identified articles, it regenerates the articles, again using the generative AI model. For example, it uses prompts like this:

[1014] Prompt: Please update this article with the latest information.

[1015] The generated article is then passed back to the proofreading engine, where corrections are made as needed.

[1016] Translation Processing

[1017] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) for translation into multiple languages. The translated article is then checked again by the server, where mistranslations and grammatical errors are corrected.

[1018] Article Publication

[1019] The server stores the final articles (original and translated) in data storage and prepares them for display when accessed by the user. The device (user's browser or app) accesses these articles, retrieves them from data storage, and displays them.

[1020] Paid advertising placement

[1021] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) through the advertising management system. The server identifies appropriate articles based on the specified conditions and inserts advertisements into those articles. When the terminal displays the final article to the user, it includes the appropriate advertisements.

[1022] Specific examples

[1023] Example 1: Creating and updating articles

[1024] When new information about the "COVID-19 variant" is updated, the server uses BeautifulSoup to collect relevant information from the web, then uses a generative AI model to generate a new article, checks the grammar of the article using the Grammarly API, saves it in data storage, and publishes it.

[1025] Example 2: Translation processing

[1026] The newly generated article "New coronavirus variant" is sent to DeepL for translation into English, French, Spanish, etc. The translated content is then rechecked on the server and saved in data storage.

[1027] Example 3: Paid advertising

[1028] If a health company wants to advertise "antivirus products," the user sets the conditions in the ad management system, and the server inserts the ad in the appropriate place within the relevant article and displays it when it is displayed to the user.

[1029] In this way, the system of the present invention automates the entire process from information collection to content creation, translation, updating, and advertising, thereby realizing efficient and accurate information provision.

[1030] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1031] Step 1: Regularly scan your sources

[1032] The server periodically scans designated sources (news sites, academic paper databases, government pages, etc.) and executes a script to periodically retrieve information using a web scraping tool such as BeautifulSoup or Scrapy. For example, the scraping task can be run at 2:00 AM every day using AWS Lambda or Google Cloud Functions.

[1033] Input: Source of information (URL, etc.)

[1034] Output: Raw data obtained (HTML, JSON, etc.)

[1035] Step 2: Acquire and store data

[1036] The server analyzes the raw data obtained by scraping and extracts the necessary information. This process uses an analysis library such as BeautifulSoup. The extracted information is stored in a temporary database (e.g., Redis or MongoDB).

[1037] Input: Raw data obtained by scraping

[1038] Output: Parsed extracted data (text format)

[1039] Step 3: Preprocessing and summarizing data

[1040] The server passes the stored extracted data to a natural language processing engine (e.g., spaCy, NLTK), which cleans the data (removes unnecessary symbols and spaces), summarizes it, and categorizes it, generating structured data that is easy to analyze.

[1041] Input: Extracted data stored in a temporary database

[1042] Output: Cleaned and summarized data

[1043] Step 4: Create a new article

[1044] The server uses the summary data generated in the previous step to input data into a generative AI model (e.g., GPT-4) to generate a new article, using the following prompt:

[1045] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[1046] As a result, a new article is generated.

[1047] Input: summarized data, prompt statement

[1048] Output: New article generated

[1049] Step 5: Proofread your article

[1050] The server sends the generated new article to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) for grammatical and content checking and correction. The proofread article is then stored in a temporary database.

[1051] Input: New article generated

[1052] Output: Proofread and revised article

[1053] Step 6: Scan and update existing articles

[1054] The server periodically scans the existing articles in the data storage and identifies those that need to be updated. This is done using a backend script (e.g., a Python script). To incorporate the new information into the identified articles, the server regenerates them, again using the generative AI model, with a prompt like this:

[1055] Prompt: Please update this article with the latest information.

[1056] Input: Existing articles in data storage, prompt text

[1057] Output: Updated article

[1058] Step 7: Recalibrate and save

[1059] The server passes the regenerated article to the proofreading engine for further checking and necessary corrections, and finally saves the updated article to data storage.

[1060] Input: Regenerated article

[1061] Output: Proofread and updated article

[1062] Step 8: Translation Request and Confirmation

[1063] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) to translate it into multiple languages, then double-checks the translated content to correct mistranslations and grammatical errors.

[1064] Input: Proofread and updated article

[1065] Output: Translated article

[1066] Step 9: Save the translated article

[1067] The server stores the reconfirmed and corrected translated articles in data storage, and the stored articles are provided to users in real time.

[1068] Input: Reviewed and corrected translation

[1069] Output: Articles saved in data storage

[1070] Step 10: Display to the User

[1071] When a user accesses an article, the device (user's browser or app) retrieves the article from data storage and displays it. The article is dynamically rendered using a front-end framework (e.g., React, Vue.js).

[1072] Input: A request from the user

[1073] Output: Articles displayed

[1074] Step 11: Setting ad conditions

[1075] Users (advertising sponsors) specify the conditions (keywords, category, target country, etc.) of the advertisements they wish to place via the advertising management system.

[1076] Input: Conditions specified by the advertiser

[1077] Output: Set advertising conditions

[1078] Step 12: Inserting Ads into Articles

[1079] The server identifies suitable articles based on the advertising criteria you set and inserts ads into those articles, optimizing the ad position and format using A / B testing.

[1080] Input: Set advertising conditions, target article

[1081] Output: Article with ad inserted

[1082] Step 13: Displaying articles with ads

[1083] The device displays the article with the advertisement inserted to the user, which increases the visibility of the advertisement and improves the click-through rate (CTR).

[1084] Input: Article with ad inserted

[1085] Output: Article with ads displayed to the user

[1086] (Application example 1)

[1087] 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."

[1088] Modern online shopping sites are required to provide content such as product descriptions and user reviews in multiple languages ​​quickly and accurately, while also inserting appropriate paid advertisements. However, doing this manually requires a significant amount of time and effort, and there is a high risk of updating information, mistranslations, and grammatical errors. Furthermore, providing information in multiple languages ​​requires specialized knowledge and is extremely difficult. Therefore, an automated system is needed to solve these challenges.

[1089] 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.

[1090] In this invention, the server includes means for collecting information, means for generating content using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated content using a proofreading engine, means for translating the generated and updated content using a multilingual translation engine, means for storing and publishing the translated content in a database, means for inserting paid advertisements into the content based on conditions set by a user, means for automatically generating product descriptions using a generative AI model based on the collected information, and means for translating the generated product descriptions into multiple languages. This makes it possible to quickly and accurately provide content such as product descriptions and user reviews in multiple languages, and to insert appropriate paid advertisements while ensuring the quality of information updates and translations.

[1091] "Means for collecting information" refers to technology for automatically collecting necessary data from multiple sources on the Internet.

[1092] A "natural language processing engine" refers to an algorithm or program that analyzes collected information and generates sentences in a format that humans can understand.

[1093] "Means for generating content" refers to technology that automatically creates new articles and descriptions based on collected information.

[1094] A "proofreading engine" is a program that checks the grammar and content of the generated text and corrects it if necessary.

[1095] A "multilingual translation engine" is a technology for translating generated and updated content into multiple languages.

[1096] "Means for storing and publishing in a database" refers to the system that stores the final content and publishes it for users to access.

[1097] "Means for inserting paid advertisements into content based on conditions set by the user" refers to a technology that embeds advertisements in appropriate locations according to conditions specified by the user.

[1098] A "generative AI model" refers to an algorithm that uses artificial intelligence to automatically generate new sentences and descriptions.

[1099] "Means for automatically generating product descriptions" refers to technology that uses a generative AI model to automatically create product descriptions.

[1100] The "means for multilingual translation" is a technique for translating the generated product description into multiple languages.

[1101] A system for implementing the present invention comprises the following major components:

[1102] 1. Information gathering engine

[1103] 2. Generative AI Models

[1104] 3. Proofreading Engine

[1105] 4. Multilingual Translation Engine

[1106] 5. Database

[1107] 6. Ad Management System

[1108] The server integrates these components and automates a series of processes, from information collection to generation, translation, proofreading, publication, and advertisement insertion. The specific process is explained below.

[1109] Information gathering

[1110] The server periodically collects data from news sites, official pages, user reviews, specialized blogs, etc. on the Internet. The collected information is first stored in a database for use in the next step. The main software used is the requests library and BeautifulSoup.

[1111] Product description generation

[1112] The server passes the collected information to a generative AI model, which generates a new product description based on the product's features and benefits. The generative AI model is built using OpenAI APIs and other tools.

[1113] proofreading

[1114] The generated product description is sent to a proofreading engine for grammatical and content checking and correction. A natural language processing engine is used as the grammar checker.

[1115] Multilingual Translation

[1116] The generated product description is sent to a multilingual translation engine, where it is translated into multiple languages. The translation engine uses the Google Translate API, among others. The translated content is then passed back to a proofreading engine to correct mistranslations and grammatical errors.

[1117] Database storage and publication

[1118] Finally, the generated and translated product descriptions are stored in a database and can be accessed via user devices (such as smartphones or robots).

[1119] Paid advertising insertion

[1120] Users set the ad criteria (keywords, category, target market, etc.) through the ad management system, and the server inserts the ad into the appropriate product description, which is then displayed when the final product page is published.

[1121] Specific examples

[1122] For example, to generate a product description for a new pair of noise-canceling headphones, the following prompts are fed into the generative AI model:

[1123] Prompt statement:

[1124] Please use the following information to describe your product:

[1125] Product Name: High-quality noise-canceling headphones

[1126] Features: Long battery life, comfortable fit

[1127] ...

[1128] This system automates the process from generating product descriptions to translating them into multiple languages ​​and inserting advertisements, enabling fast and accurate information provision. The specific hardware used includes a Linux-based server, and the software includes the OpenAI API, Google Translation API, requests, and BeautifulSoup.

[1129] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1130] Step 1: Gather information

[1131] The server collects data from news sites, official pages, user reviews, specialized blogs, etc. It uses the requests library and BeautifulSoup to retrieve the text data of web pages and store it in a database. The input is a list of URLs to be collected, and the output is the collected text data.

[1132] Step 2: Product description generation

[1133] The server passes the collected text data to a natural language processing engine for summarization and categorization. It then sends product description generation prompts to a generative AI model to create a new product description. The input is the collected text data, and the output is the generated product description.

[1134] Step 3: Proofreading

[1135] The server sends the generated product description to a proofreading engine for grammatical and content checking and correction. The input is the generated product description, and the output is the proofread product description. A grammar checker is used to improve accuracy.

[1136] Step 4: Multilingual Translation

[1137] The server passes the proofread product description to a multilingual translation engine, which translates it into multiple specified languages. The engine used is the Google Translate API. The input is the proofread product description, and the output is the product description translated into multiple languages.

[1138] Step 5: Translation confirmation

[1139] The server then passes the translated product description back to the proofreading engine, which checks for and corrects mistranslations and grammatical errors. The input is the translated product description, and the output is the corrected multilingual product description.

[1140] Step 6: Save and publish the database

[1141] The server saves the modified multilingual product description in a database and makes it publicly available for access by user terminals. The input is the modified multilingual product description, and the output is the product description saved in the database.

[1142] Step 7: Inserting Paid Ads

[1143] Users set the ad conditions (keywords, category, target market, etc.) through the ad management system. The server inserts the ad into the appropriate product description based on the set conditions. The input is the ad conditions set by the user, and the output is the product description with the ad inserted.

[1144] This efficiently automates the process from creating product descriptions to translating them into multiple languages ​​and inserting advertisements, making it possible to provide users with fast and accurate information.

[1145] 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.

[1146] overview

[1147] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include posting paid advertisements. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and adjust the display content and advertisements based on those emotions. Below, we will explain the operation of the system in detail from the perspectives of the server, the terminal, and the user.

[1148] Basic configuration

[1149] The system consists of the following main components:

[1150] 1. Information gathering engine

[1151] 2. Generation AI

[1152] 3. Proofreading Engine

[1153] 4. Multilingual Translation Engine

[1154] 5. Emotion Engine

[1155] 6. Database

[1156] 7. Advertising Management System

[1157] Program processing flow

[1158] Information gathering

[1159] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[1160] Article Generation

[1161] The server sends the collected information to a natural language processing engine, which categorizes and summarizes it. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[1162] The server passes the summarized data to the generation AI, which then creates a new article, automatically generating the article structure, including a headline, introduction, main content, and conclusion.

[1163] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency.

[1164] Translation processing and publishing

[1165] The server sends the generated and proofread articles to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[1166] The server checks the translated article and corrects mistranslations and grammatical errors using a correction engine.

[1167] The server stores the final article in a database and prepares it for display when accessed by a user.

[1168] The device requests an article, the server retrieves it from the database, and displays it to the user, often in a translated version based on the user's language settings.

[1169] Emotion recognition and article adjustment

[1170] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[1171] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[1172] Paid advertising placement

[1173] Users (advertiser sponsors) set the conditions for the ads they want to run (e.g., topics, keywords, target countries) through a dedicated interface.

[1174] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[1175] When the terminal finally displays the article to the user, it embeds the specified advertisement in the article appropriately and displays it in a way that is likely to interest the user.

[1176] Specific examples

[1177] Example 1: Creating and updating articles

[1178] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[1179] Generative AI generates articles based on new information.

[1180] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[1181] Example 2: Translation processing

[1182] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine, where it is translated into English, French, Spanish, and other languages.

[1183] The translated content is rechecked on the server and finally saved in the database.

[1184] Example 3: Emotion-based display adjustment

[1185] When a user of a device views an article, the emotion engine analyzes the user's reactions (e.g., click history, viewing time, comments) and determines that the user is expressing positive emotions.

[1186] The server suggests articles tailored to the user and displays articles that are encouraging and hopeful.

[1187] Example 4: Paid advertising

[1188] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[1189] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[1190] This system automatically handles everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, ensuring efficient and accurate information provision.

[1191] The processing flow will be explained below.

[1192] Step 1:

[1193] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is done automatically according to the set interval.

[1194] Step 2:

[1195] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information about "mutant strains of the new coronavirus" is collected, the information is summarized to extract key points.

[1196] Step 3:

[1197] The server passes the summarized data to the generation AI, which then creates a new article based on the data received. For example, it automatically generates an article structure, such as a headline, introduction, main content, and conclusion.

[1198] Step 4:

[1199] The server sends the generated article to a proofreading engine, which checks it for grammatical errors and content consistency and makes corrections as needed.

[1200] Step 5:

[1201] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[1202] Step 6:

[1203] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[1204] Step 7:

[1205] The server stores the final article in a database, which contains both the original and the translation.

[1206] Step 8:

[1207] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[1208] Step 9:

[1209] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[1210] Step 10:

[1211] The server inserts advertisements provided through the advertisement management system into articles in an optimal manner based on the user's emotions analyzed by the emotion engine.

[1212] Step 11:

[1213] The device (user's browser or app) requests the final article, the server retrieves it from the database and displays it to the user, including any optimized ads.

[1214] Step 12:

[1215] Users (advertiser sponsors) can view feedback reports provided through the system, which show how effective their ads were for users.

[1216] Through these steps, the system can automatically provide fast and accurate information, support multiple languages, customize based on user sentiment, and monetize advertising.

[1217] Example 2

[1218] 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."

[1219] In conventional systems, various processes such as information gathering, article generation, translation, and ad insertion were performed separately, making it difficult to efficiently execute a series of processes. Furthermore, the system was unable to provide content that took user emotions into consideration, which resulted in a lack of improvement in the user experience. Furthermore, the accuracy of ad targeting was low, limiting the effectiveness of advertising.

[1220] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting information; means for generating articles using a natural language processing engine based on the collected information; means for checking the grammar and content of the generated articles using a proofreading engine; means for translating the generated and updated articles using a multilingual translation engine; means for storing and publishing the translated articles in a database; means for inserting paid advertisements into articles based on user-specified conditions; and means for analyzing user responses to recognize emotions and adjusting display content based on the recognized emotions. This enables the efficient execution of a series of processes and the provision of optimal content based on user emotions. Furthermore, highly targeted advertisement display is expected to improve advertising effectiveness.

[1221] "Means for collecting information" refers to the ability to execute a process that automatically retrieves the latest data from designated websites and databases on the Internet.

[1222] A "natural language processing engine" is an artificial intelligence technology that analyzes collected information and performs processes such as classifying and summarizing the information and generating text.

[1223] "Means for generating articles" refers to the process of automatically creating new articles based on collected information using a natural language processing engine.

[1224] A "proofreading engine" is an artificial intelligence technology that checks the grammatical and content accuracy of generated text and makes any necessary corrections.

[1225] "Multilingual Translation Engine" means a translation technology that performs the process of translating generated and proofread articles into multiple languages.

[1226] "Means for storing and publishing articles in a database" refers to the process of storing the final generated articles in a database and publishing them for users to access.

[1227] "Means for inserting paid advertisements into articles" refers to the process of adding advertising content to applicable articles based on advertising criteria set by a user.

[1228] "Means for analyzing user responses and recognizing emotions" refers to artificial intelligence technology that analyzes user input and behavioral data to identify the user's emotional state.

[1229] "Means for tailoring display content" refers to the process of optimizing the content and format of displayed articles based on perceived user sentiment.

[1230] The system of the present invention uses generative AI to automatically collect, generate, translate, and update information, and automates a series of processes including the placement of paid advertisements. This system is composed of the following main components: an information collection engine, a natural language processing engine, generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertisement management system.

[1231] Information gathering

[1232] The server runs an information gathering engine that gathers the latest data from selected news sites, academic paper databases, and government agency pages using Python's Beautiful Soup library, and stores the data in a MySQL database.

[1233] Article Generation

[1234] The server sends the collected information to a natural language processing engine, which uses the BERT model to categorize and summarize the information. The summarized data is then passed to a generative AI (based on GPT-4) that generates a new article based on a prompt. For example, the prompt could be, "Based on information about the latest variants of the new coronavirus, please create an article with a headline, introduction, main content, and conclusion."

[1235] The generated articles are checked for grammar and content using a proofreading engine (Grammarly API), and any necessary corrections are made.

[1236] Translation processing and publishing

[1237] The server translates the generated and proofread articles into multiple languages ​​using the Google Translate API. The translated articles are then checked again with the Grammarly API to correct any mistranslations or grammatical errors. The final articles are stored in a database and prepared for display when accessed by users.

[1238] The device requests an article, the server retrieves it from the database and displays it to the user, with the appropriate translation depending on the user's language settings.

[1239] Emotion recognition and display content adjustment

[1240] The server uses an emotion engine (Text Analytics for sentiment analysis API) to analyze the user's input and reactions obtained from the device and identify the user's emotional state. Based on the results of this analysis, the server adjusts the content displayed, for example, displaying articles that inspire hope to users with positive emotions.

[1241] Paid advertising placement

[1242] Users (advertising sponsors) use the advertising management system interface (built with Ruby on Rails) to set the conditions for the advertisements they wish to display.

[1243] The server identifies appropriate articles based on the criteria and inserts paid advertisements into the articles at designated locations. When the device finally displays the articles to the user, it embeds the designated advertisements appropriately and displays them in a way that is likely to attract the user's attention.

[1244] In this way, the system of the present invention automatically processes everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, thereby providing efficient and accurate information.

[1245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1246] Step 1: Gather information

[1247] The server starts an information collection engine and prepares a list of specified news sites, academic paper databases, government agency pages, etc. The server then uses Python's Beautiful Soup library to scrape each website and collect the latest information. The input is the URL of the target website, and the output is the collected text data. This data is saved in temporary storage (for example, a MySQL database).

[1248] Step 2: Categorize and summarize

[1249] The server sends the collected text data to a natural language processing engine. Here, Hugging Face's BERT model is used to categorize and summarize the data. The input is scraped text data, and the output is categorized summary text. For example, if information about mutated strains of the new coronavirus is collected, the data is summarized to extract the main point, "mutated strains of the new coronavirus are increasing concerns about the spread of infection."

[1250] Step 3: Article generation

[1251] The server passes the summarized data to the generation AI and sends a request including a prompt. The generation AI uses the GPT-4 model. The input is the summarized text and the prompt, and the output is a new article. For example, the prompt is sent as follows: "Based on information about the latest variants of the new coronavirus, please write an article that includes a headline, introduction, main content, and conclusion." The generated article will be structured text that includes a headline, introduction, main content, and conclusion.

[1252] Step 4: Proofreading

[1253] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency. Here, we use Grammarly's API. The input is the generated article, and the output is the proofread and corrected article. Specifically, it detects grammatical errors and corrects them to make the sentence grammatically correct.

[1254] Step 5: Translation

[1255] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages. This uses the Google Translate API. The input is the proofread article, and the output is the translated article. For example, it can be translated into English, French, Spanish, or other languages. The translated article is then checked again with the Grammarly API to correct any mistranslations or grammatical errors.

[1256] Step 6: Save and publish your article

[1257] The server stores the final article in a database, ready to display when accessed by the user. The input is the translated and proofread article, and the output is the article stored in the database. The device requests the article, the server retrieves it from the database, and displays it to the user. For example, depending on the user's language preference, the appropriate translation might be displayed: English, French, Spanish, etc.

[1258] Step 7: Emotion recognition and display adjustment

[1259] The server uses an emotion engine to analyze user input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions. Here, the Text Analytics for sentiment analysis API is used. The input is the user's reaction data, and the output is the user's emotional state. Based on the recognized emotions, the server adjusts the content and format of the articles to be displayed. For example, for a user who shows positive emotions, it displays articles that are encouraging and instill hope.

[1260] Step 8: Place Paid Ads

[1261] Users (advertising sponsors) set the conditions for the ads they want to run (e.g., topic, keywords, target country) through the ad management system. This interface is built using Ruby on Rails. The input is the ad conditions set by the user, and the output is the ad case generated based on those conditions. The server identifies appropriate articles based on the conditions received from the ad management system and inserts paid ads into the specified locations within the articles. When the device finally displays the article to the user, it embeds the specified ads within the article appropriately and displays them in a way that is likely to interest the user.

[1262] Through these steps, the system provides efficient and accurate information, displays optimal content based on the user's emotions, and places advertisements with high targeting accuracy.

[1263] (Application example 2)

[1264] 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."

[1265] Conventional news distribution systems are unable to display news optimally based on user sentiment, even when they rapidly generate, proofread, and translate collected information, making it difficult to improve the user experience. They also have difficulty increasing revenue through appropriate advertising placement. Therefore, there is a need for a system that automatically displays articles that reflect user sentiment and places paid advertisements according to user interests.

[1266] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1267] In this invention, the server includes means for collecting information, means for generating articles using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated articles using a proofreading engine, means for translating the generated and updated articles using a multilingual translation engine, means for storing and publishing the translated articles in a database, means for inserting paid advertisements into articles based on conditions specified by the user, and means for analyzing user emotions and adjusting display content based thereon, thereby enabling article display optimized to user emotions and effective advertisement placement.

[1268] The "means of collecting information" is an engine that automatically retrieves the latest information from news sites and academic paper databases on the Internet.

[1269] A "natural language processing engine" is an AI technology that analyzes collected information and generates articles.

[1270] The "means for generating articles" is a system that utilizes a natural language processing engine to execute the process of creating text.

[1271] A "proofreading engine" is an engine that has the function of checking and correcting the consistency of grammar and content of generated articles.

[1272] A "multilingual translation engine" is an AI technology for translating articles into multiple languages.

[1273] "Means for storing and publishing in a database" refers to a system for storing translated articles and providing them to users when they access them.

[1274] The "means for inserting paid advertisements into articles" is a system that places appropriate advertisements within articles based on conditions set by the user.

[1275] "Means for analyzing user emotions" refers to a system that analyzes the user's input and reactions to recognize emotions and adjusts the display content based on those emotions.

[1276] The system for implementing this invention consists of the following main components: an information gathering engine, a generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertising management system. The role and processing flow of each component will be explained in detail.

[1277] Information Gathering Engine

[1278] The information collection engine is used to scrape the latest data from specific news sites and academic paper databases. It uses AWS EC2 as the hardware and Python and the Scrapy library as the software. The collected data is stored on the server in a structured format.

[1279] Generation AI

[1280] The collected information is then generated into new articles by a generative AI. The generative AI uses OpenAI's GPT-4 and Hugging Face Transformers. This automatically generates article structures such as a headline, introduction, main content, and conclusion. A GPU server (equipped with NVIDIA A100) is used to achieve high-speed processing.

[1281] Proofreading Engine

[1282] The generated articles are then checked for grammar and content by a proofreading engine, using the Grammarly API and LanguageTool, ensuring accuracy and consistency of the generated text.

[1283] Multilingual Translation Engine

[1284] The proofread articles are then translated into multiple languages ​​using a multilingual translation engine, including the Google Cloud Translation API and DeepL API. A GPU server is also used to speed up the translation process.

[1285] Emotion Engine

[1286] Articles stored in the database are optimized by a sentiment engine that analyzes user input and reactions, using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, to display the best articles based on the user's sentiment.

[1287] Ad Management System

[1288] The ad management system inserts appropriate ads into articles based on the conditions set by the user. This system uses the Google Ads API and Facebook Ads API. Appropriate ad placement can maximize the effectiveness of ads.

[1289] Specific examples

[1290] Example 1: Generating news articles

[1291] Data collected: "Latest information on COVID-19 variants"

[1292] Example prompt for generative AI: "Please extract key points about the new coronavirus variant and generate a new news article."

[1293] Example 2: Translation processing

[1294] Example prompt: "Translate the following news article into English, French, and Spanish."

[1295] Example 3: Emotion-based display adjustment

[1296] Sample prompt: "Users are expressing positive emotions, so please tailor your article to be encouraging and uplifting."

[1297] Example 4: Paid Ad Insertion

[1298] Example ad: "New antivirus product"

[1299] Example prompt: "Insert an advertisement into a news article based on the following criteria."

[1300] In this way, the system of the present invention automatically performs all processes from information collection to article creation, translation, emotion recognition, and advertisement insertion, thereby realizing optimal information provision and advertisement display for the user.

[1301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1302] Step 1: Gather information

[1303] Specific operation: The server periodically scrapes the latest information from specified news sites and academic paper databases.

[1304] Input: URL of the specified website or database

[1305] Output: Information collected by scraping

[1306] Data processing: Use Python and the Scrapy library to extract the necessary data from the web page and save it in a structured format (e.g., JSON format).

[1307] Step 2: Article generation

[1308] Specific operation: The server generates news articles using generative AI based on the collected information.

[1309] Input: Collected information (JSON format)

[1310] Output: Generated news article (text format)

[1311] Data processing: Using OpenAI's GPT-4 model on a GPU server, the collected data is analyzed and summarized, and a structured article is automatically generated, including a headline, introduction, main content, and conclusion.

[1312] Step 3: Proofread your article

[1313] What it does: The generated article is sent to a proofreading engine where it is checked and corrected for grammar and content consistency.

[1314] Input: Generated news article (text format)

[1315] Output: Proofread news article (text format)

[1316] Data processing: Use Grammarly API and LanguageTool to check for grammatical errors and stylistic consistency and make any necessary corrections.

[1317] Step 4: Multilingual Translation

[1318] What it does: The proofread article is sent to a multilingual translation engine and translated into multiple languages.

[1319] Input: Proofread news article (text format)

[1320] Output: Translated news articles (multilingual text format)

[1321] Data processing: Using the Google Cloud Translation API or DeepL API, articles are translated into the specified language (e.g., English, French, Spanish). The translated text is then checked for grammar again and corrected if necessary.

[1322] Step 5: Save and publish the database

[1323] What it does: The translated articles are stored in a database and made publicly available for users to access.

[1324] Input: Translated news article (multilingual text format)

[1325] Output: Published news article (text on a web page or application)

[1326] Data processing: The translated text is stored in a database and news articles in the appropriate language are provided upon user request.

[1327] Step 6: Inserting Paid Ads

[1328] What it does: Places appropriate ads within news articles based on user-specified criteria.

[1329] Input: User-specified advertising conditions (target demographic, keywords, etc.)

[1330] Output: News article with ads inserted (text format)

[1331] Data processing: Advertisements are inserted into the appropriate positions within articles based on the specified conditions using the ad management system (Google Ads API, Facebook Ads API).

[1332] Step 7: Sentiment analysis and display optimization

[1333] How it works: When a user browses an article, the emotion engine analyzes the user's input and reactions and optimizes the content displayed based on that.

[1334] Input: User response data (click history, viewing time, comments)

[1335] Output: Optimized display content (text format)

[1336] Data processing: Using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, we analyze user sentiment and tailor articles to encourage and inspire positive responses.

[1337] The above steps ensure that the entire process, from information gathering to article creation, proofreading, multilingual translation, database storage, paid advertising insertion, and display optimization based on sentiment analysis, proceeds smoothly, resulting in a system that provides users with the best possible news experience.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] [Fourth embodiment]

[1342] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1343] 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.

[1344] 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).

[1345] 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.

[1346] 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.

[1347] 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).

[1348] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] 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."

[1355] overview

[1356] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include placing paid advertisements. Below, we will explain the operation of the system in detail from the perspectives of the server, terminal, and user.

[1357] Basic configuration

[1358] The system consists of the following main components:

[1359] 1. Information gathering engine

[1360] 2. Generation AI

[1361] 3. Proofreading Engine

[1362] 4. Multilingual Translation Engine

[1363] 5. Database

[1364] 6. Ad Management System

[1365] Program processing flow

[1366] Information gathering

[1367] The server periodically collects data from reliable sources such as news sites, academic paper databases, and government agency pages on the web.

[1368] Article Generation

[1369] The server passes the collected information to a natural language processing engine for summarization and categorization.

[1370] The summarized information is then passed to a generative AI to create a new article.

[1371] The server sends the generated article to a proofreading engine for grammatical and content checking and correction.

[1372] Update an existing article

[1373] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information.

[1374] To incorporate new information into existing articles, generative AI is used to regenerate articles.

[1375] The text is passed to a proofreading engine for rechecking and correction if necessary.

[1376] Translation Processing

[1377] The server sends the generated or updated article to a multilingual translation engine for translation into multiple languages.

[1378] The server then double-checks the translated article and corrects any mistranslations or grammatical errors.

[1379] Article Publication

[1380] The server stores the final articles (original and translated) in a database and prepares them for display when accessed by a user.

[1381] The device (user's browser or app) accesses the article, retrieves it from the database, and displays it.

[1382] Paid advertising placement

[1383] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) via the advertising management system.

[1384] The server identifies suitable articles based on specified criteria and inserts advertisements within the articles.

[1385] The terminal appropriately displays the designated advertisement when displaying the final article to the user.

[1386] Specific examples

[1387] Example 1: Creating and updating articles

[1388] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[1389] Generative AI generates articles based on new information.

[1390] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[1391] Example 2: Translation processing

[1392] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine and translated into English, French, Spanish, and other languages.

[1393] The translated content is rechecked on the server and finally saved in the database.

[1394] Example 3: Paid advertising

[1395] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[1396] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[1397] In this way, the system automatically processes everything from information collection to article creation, translation, updates, and the insertion of paid advertisements, providing efficient and accurate information.

[1398] The processing flow will be explained below.

[1399] Step 1:

[1400] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[1401] Step 2:

[1402] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[1403] Step 3:

[1404] The server passes the summarized data to the AI ​​generator, which then creates a new article based on the data it receives, automatically generating a structure for the article, including a headline, introduction, main content, and conclusion.

[1405] Step 4:

[1406] The server then sends the generated article to a proofreading engine, which checks for grammatical errors and consistency of content. The proofreading engine uses AI technology to correct the article for correct grammar and appropriate expressions.

[1407] Step 5:

[1408] The server sends the generated and proofread article to a multilingual translation engine, where the article is translated into multiple languages ​​(e.g., English, French, Spanish, etc.).

[1409] Step 6:

[1410] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[1411] Step 7:

[1412] The server stores the final article in a database, which contains both the original and the translation.

[1413] Step 8:

[1414] The device (user's browser or app) requests an article, the server retrieves the article from the database, and displays it to the user, often in a translated version based on the user's language settings.

[1415] Step 9:

[1416] Users (advertiser sponsors) set the conditions for the ads they want to run (such as topics, keywords, and target areas) through a dedicated interface.

[1417] Step 10:

[1418] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[1419] Step 11:

[1420] When the device finally displays the article to the user, it embeds the specified advertisement appropriately within the article and displays it, so that the user can view the advertisement together with the article.

[1421] These steps enable the system to automatically provide fast and accurate information, multilingual support, and advertising monetization.

[1422] Example 1

[1423] 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."

[1424] In today's information society, there is a need to efficiently and accurately collect large amounts of information and generate valuable digital content. However, manually collecting information and generating articles requires a lot of time and effort, and there is also the risk of grammatical errors and mistranslations. Furthermore, providing the generated content in multiple languages ​​and effectively incorporating paid promotions requires advanced technology, making this a challenging task.

[1425] 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.

[1426] In this invention, the server includes a means for collecting information, a means for generating digital content using a natural language processing engine based on the collected information, and a means for checking the grammar and content of the generated digital content using a proofreading engine, thereby enabling efficient and accurate information collection, generation, and proofreading.

[1427] The server further includes means for translating the generated and updated digital content using a multilingual translation engine, means for storing and publishing the translated digital content in a data storage, and means for inserting paid promotions into the digital content based on conditions specified by a user, thereby enabling the generated digital content to be provided in multiple languages ​​and for inserting paid promotions in appropriate locations to maximize revenue.

[1428] "Means of collecting information" refers to a mechanism for regularly obtaining data from reliable sources.

[1429] "Natural language processing engine" refers to software or a system for analyzing, summarizing, and categorizing text.

[1430] "Means for generating digital content" refers to a system that uses artificial intelligence technology to automatically create new articles and content based on collected information.

[1431] "Proofreading Engine" means software or a system for checking and correcting the grammatical and content accuracy of generated digital content.

[1432] "Multilingual translation engine" refers to software or a system for translating generated digital content into multiple languages.

[1433] "Data storage" refers to databases and storage systems that store collected and generated digital content and make it available for retrieval as needed.

[1434] "User-specified conditions" refers to the advertising sponsor setting the promotion targets and conditions (keywords, categories, target countries, etc.).

[1435] "Paid Promotion" refers to advertisements or promotions that are inserted into digital content in exchange for a fee paid by advertising sponsors.

[1436] overview

[1437] The present invention relates to a system that utilizes artificial intelligence technology to automatically collect, generate, translate, and update information, as well as insert paid advertisements. The system includes the following main components:

[1438] Information Gathering Engine

[1439] Natural Language Processing Engine

[1440] Generative AI Models

[1441] Proofreading Engine

[1442] Multilingual Translation Engine

[1443] Data Storage

[1444] Ad Management System

[1445] Explaining program processing in natural language

[1446] Information gathering

[1447] The server periodically collects data from reliable sources, such as news sites, academic paper databases, and government pages, using web scraping tools such as BeautifulSoup and Scrapy. This ensures reliable and comprehensive collection of information.

[1448] Article Generation

[1449] The server passes the collected information to a natural language processing engine (e.g., spaCy, NLTK) for summarization and categorization. Then, based on the summarized information, a generative AI model (e.g., GPT-4) is used to create a new article. For example, the following prompt sentence is input to the generative AI model:

[1450] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[1451] The generated article is sent to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) to correct and check grammar and content.

[1452] Update an existing article

[1453] The server periodically scans the existing articles in the database to identify those that need to be updated to reflect new information. To incorporate the new information into the identified articles, it regenerates the articles, again using the generative AI model. For example, it uses prompts like this:

[1454] Prompt: Please update this article with the latest information.

[1455] The generated article is then passed back to the proofreading engine, where corrections are made as needed.

[1456] Translation Processing

[1457] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) for translation into multiple languages. The translated article is then checked again by the server, where mistranslations and grammatical errors are corrected.

[1458] Article Publication

[1459] The server stores the final articles (original and translated) in data storage and prepares them for display when accessed by the user. The device (user's browser or app) accesses these articles, retrieves them from data storage, and displays them.

[1460] Paid advertising placement

[1461] Users (advertising sponsors) specify the conditions for the advertisements they wish to place (keywords, categories, target countries, etc.) through the advertising management system. The server identifies appropriate articles based on the specified conditions and inserts advertisements into those articles. When the terminal displays the final article to the user, it includes the appropriate advertisements.

[1462] Specific examples

[1463] Example 1: Creating and updating articles

[1464] When new information about the "COVID-19 variant" is updated, the server uses BeautifulSoup to collect relevant information from the web, then uses a generative AI model to generate a new article, checks the grammar of the article using the Grammarly API, saves it in data storage, and publishes it.

[1465] Example 2: Translation processing

[1466] The newly generated article "New coronavirus variant" is sent to DeepL for translation into English, French, Spanish, etc. The translated content is then rechecked on the server and saved in data storage.

[1467] Example 3: Paid advertising

[1468] If a health company wants to advertise "antivirus products," the user sets the conditions in the ad management system, and the server inserts the ad in the appropriate place within the relevant article and displays it when it is displayed to the user.

[1469] In this way, the system of the present invention automates the entire process from information collection to content creation, translation, updating, and advertising, thereby realizing efficient and accurate information provision.

[1470] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1471] Step 1: Regularly scan your sources

[1472] The server periodically scans designated sources (news sites, academic paper databases, government pages, etc.) and executes a script to periodically retrieve information using a web scraping tool such as BeautifulSoup or Scrapy. For example, the scraping task can be run at 2:00 AM every day using AWS Lambda or Google Cloud Functions.

[1473] Input: Source of information (URL, etc.)

[1474] Output: Raw data obtained (HTML, JSON, etc.)

[1475] Step 2: Acquire and store data

[1476] The server analyzes the raw data obtained by scraping and extracts the necessary information. This process uses an analysis library such as BeautifulSoup. The extracted information is stored in a temporary database (e.g., Redis or MongoDB).

[1477] Input: Raw data obtained by scraping

[1478] Output: Parsed extracted data (text format)

[1479] Step 3: Preprocessing and summarizing data

[1480] The server passes the stored extracted data to a natural language processing engine (e.g., spaCy, NLTK), which cleans the data (removes unnecessary symbols and spaces), summarizes it, and categorizes it, generating structured data that is easy to analyze.

[1481] Input: Extracted data stored in a temporary database

[1482] Output: Cleaned and summarized data

[1483] Step 4: Create a new article

[1484] The server uses the summary data generated in the previous step to input data into a generative AI model (e.g., GPT-4) to generate a new article, using the following prompt:

[1485] Prompt: Generate an article about the latest variant of the novel coronavirus. Provide detailed information based on recent research and government announcements.

[1486] As a result, a new article is generated.

[1487] Input: summarized data, prompt statement

[1488] Output: New article generated

[1489] Step 5: Proofread your article

[1490] The server sends the generated new article to a proofreading engine (e.g., Grammarly API, DeepL grammar checker) for grammatical and content checking and correction. The proofread article is then stored in a temporary database.

[1491] Input: New article generated

[1492] Output: Proofread and revised article

[1493] Step 6: Scan and update existing articles

[1494] The server periodically scans the existing articles in the data storage and identifies those that need to be updated. This is done using a backend script (e.g., a Python script). To incorporate the new information into the identified articles, the server regenerates them, again using the generative AI model, with a prompt like this:

[1495] Prompt: Please update this article with the latest information.

[1496] Input: Existing articles in data storage, prompt text

[1497] Output: Updated article

[1498] Step 7: Recalibrate and save

[1499] The server passes the regenerated article to the proofreading engine for further checking and necessary corrections, and finally saves the updated article to data storage.

[1500] Input: Regenerated article

[1501] Output: Proofread and updated article

[1502] Step 8: Translation Request and Confirmation

[1503] The server sends the created or updated article to a multilingual translation engine (e.g., DeepL, Google Translate API) to translate it into multiple languages, then double-checks the translated content to correct mistranslations and grammatical errors.

[1504] Input: Proofread and updated article

[1505] Output: Translated article

[1506] Step 9: Save the translated article

[1507] The server stores the reconfirmed and corrected translated articles in data storage, and the stored articles are provided to users in real time.

[1508] Input: Reviewed and corrected translation

[1509] Output: Articles saved in data storage

[1510] Step 10: Display to the User

[1511] When a user accesses an article, the device (user's browser or app) retrieves the article from data storage and displays it. The article is dynamically rendered using a front-end framework (e.g., React, Vue.js).

[1512] Input: A request from the user

[1513] Output: Articles displayed

[1514] Step 11: Setting ad conditions

[1515] Users (advertising sponsors) specify the conditions (keywords, category, target country, etc.) of the advertisements they wish to place via the advertising management system.

[1516] Input: Conditions specified by the advertiser

[1517] Output: Set advertising conditions

[1518] Step 12: Inserting Ads into Articles

[1519] The server identifies suitable articles based on the advertising criteria you set and inserts ads into those articles, optimizing the ad position and format using A / B testing.

[1520] Input: Set advertising conditions, target article

[1521] Output: Article with ad inserted

[1522] Step 13: Displaying articles with ads

[1523] The device displays the article with the advertisement inserted to the user, which increases the visibility of the advertisement and improves the click-through rate (CTR).

[1524] Input: Article with ad inserted

[1525] Output: Article with ads displayed to the user

[1526] (Application example 1)

[1527] 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."

[1528] Modern online shopping sites are required to provide content such as product descriptions and user reviews in multiple languages ​​quickly and accurately, while also inserting appropriate paid advertisements. However, doing this manually requires a significant amount of time and effort, and there is a high risk of updating information, mistranslations, and grammatical errors. Furthermore, providing information in multiple languages ​​requires specialized knowledge and is extremely difficult. Therefore, an automated system is needed to solve these challenges.

[1529] 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.

[1530] In this invention, the server includes means for collecting information, means for generating content using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated content using a proofreading engine, means for translating the generated and updated content using a multilingual translation engine, means for storing and publishing the translated content in a database, means for inserting paid advertisements into the content based on conditions set by a user, means for automatically generating product descriptions using a generative AI model based on the collected information, and means for translating the generated product descriptions into multiple languages. This makes it possible to quickly and accurately provide content such as product descriptions and user reviews in multiple languages, and to insert appropriate paid advertisements while ensuring the quality of information updates and translations.

[1531] "Means for collecting information" refers to technology for automatically collecting necessary data from multiple sources on the Internet.

[1532] A "natural language processing engine" refers to an algorithm or program that analyzes collected information and generates sentences in a format that humans can understand.

[1533] "Means for generating content" refers to technology that automatically creates new articles and descriptions based on collected information.

[1534] A "proofreading engine" is a program that checks the grammar and content of the generated text and corrects it if necessary.

[1535] A "multilingual translation engine" is a technology for translating generated and updated content into multiple languages.

[1536] "Means for storing and publishing in a database" refers to the system that stores the final content and publishes it for users to access.

[1537] "Means for inserting paid advertisements into content based on conditions set by the user" refers to a technology that embeds advertisements in appropriate locations according to conditions specified by the user.

[1538] A "generative AI model" refers to an algorithm that uses artificial intelligence to automatically generate new sentences and descriptions.

[1539] "Means for automatically generating product descriptions" refers to technology that uses a generative AI model to automatically create product descriptions.

[1540] The "means for multilingual translation" is a technique for translating the generated product description into multiple languages.

[1541] A system for implementing the present invention comprises the following major components:

[1542] 1. Information gathering engine

[1543] 2. Generative AI Models

[1544] 3. Proofreading Engine

[1545] 4. Multilingual Translation Engine

[1546] 5. Database

[1547] 6. Ad Management System

[1548] The server integrates these components and automates a series of processes, from information collection to generation, translation, proofreading, publication, and advertisement insertion. The specific process is explained below.

[1549] Information gathering

[1550] The server periodically collects data from news sites, official pages, user reviews, specialized blogs, etc. on the Internet. The collected information is first stored in a database for use in the next step. The main software used is the requests library and BeautifulSoup.

[1551] Product description generation

[1552] The server passes the collected information to a generative AI model, which generates a new product description based on the product's features and benefits. The generative AI model is built using OpenAI APIs and other tools.

[1553] proofreading

[1554] The generated product description is sent to a proofreading engine for grammatical and content checking and correction. A natural language processing engine is used as the grammar checker.

[1555] Multilingual Translation

[1556] The generated product description is sent to a multilingual translation engine, where it is translated into multiple languages. The translation engine uses the Google Translate API, among others. The translated content is then passed back to a proofreading engine to correct mistranslations and grammatical errors.

[1557] Database storage and publication

[1558] Finally, the generated and translated product descriptions are stored in a database and can be accessed via user devices (such as smartphones or robots).

[1559] Paid advertising insertion

[1560] Users set the ad criteria (keywords, category, target market, etc.) through the ad management system, and the server inserts the ad into the appropriate product description, which is then displayed when the final product page is published.

[1561] Specific examples

[1562] For example, to generate a product description for a new pair of noise-canceling headphones, the following prompts are fed into the generative AI model:

[1563] Prompt statement:

[1564] Please use the following information to describe your product:

[1565] Product Name: High-quality noise-canceling headphones

[1566] Features: Long battery life, comfortable fit

[1567] ...

[1568] This system automates the process from generating product descriptions to translating them into multiple languages ​​and inserting advertisements, enabling fast and accurate information provision. The specific hardware used includes a Linux-based server, and the software includes the OpenAI API, Google Translation API, requests, and BeautifulSoup.

[1569] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1570] Step 1: Gather information

[1571] The server collects data from news sites, official pages, user reviews, specialized blogs, etc. It uses the requests library and BeautifulSoup to retrieve the text data of web pages and store it in a database. The input is a list of URLs to be collected, and the output is the collected text data.

[1572] Step 2: Product description generation

[1573] The server passes the collected text data to a natural language processing engine for summarization and categorization. It then sends product description generation prompts to a generative AI model to create a new product description. The input is the collected text data, and the output is the generated product description.

[1574] Step 3: Proofreading

[1575] The server sends the generated product description to a proofreading engine for grammatical and content checking and correction. The input is the generated product description, and the output is the proofread product description. A grammar checker is used to improve accuracy.

[1576] Step 4: Multilingual Translation

[1577] The server passes the proofread product description to a multilingual translation engine, which translates it into multiple specified languages. The engine used is the Google Translate API. The input is the proofread product description, and the output is the product description translated into multiple languages.

[1578] Step 5: Translation confirmation

[1579] The server then passes the translated product description back to the proofreading engine, which checks for and corrects mistranslations and grammatical errors. The input is the translated product description, and the output is the corrected multilingual product description.

[1580] Step 6: Save and publish the database

[1581] The server saves the modified multilingual product description in a database and makes it publicly available for access by user terminals. The input is the modified multilingual product description, and the output is the product description saved in the database.

[1582] Step 7: Inserting Paid Ads

[1583] Users set the ad conditions (keywords, category, target market, etc.) through the ad management system. The server inserts the ad into the appropriate product description based on the set conditions. The input is the ad conditions set by the user, and the output is the product description with the ad inserted.

[1584] This efficiently automates the process from creating product descriptions to translating them into multiple languages ​​and inserting advertisements, making it possible to provide users with fast and accurate information.

[1585] 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.

[1586] overview

[1587] This system uses generative AI to automatically collect, generate, translate, and update information, as well as automate a series of processes that include posting paid advertisements. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and adjust the display content and advertisements based on those emotions. Below, we will explain the operation of the system in detail from the perspectives of the server, the terminal, and the user.

[1588] Basic configuration

[1589] The system consists of the following main components:

[1590] 1. Information gathering engine

[1591] 2. Generation AI

[1592] 3. Proofreading Engine

[1593] 4. Multilingual Translation Engine

[1594] 5. Emotion Engine

[1595] 6. Database

[1596] 7. Advertising Management System

[1597] Program processing flow

[1598] Information gathering

[1599] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is automated at set intervals.

[1600] Article Generation

[1601] The server sends the collected information to a natural language processing engine, which categorizes and summarizes it. For example, if information on the topic of "mutant strains of the new coronavirus" is collected, it will be summarized and key points will be extracted.

[1602] The server passes the summarized data to the generation AI, which then creates a new article, automatically generating the article structure, including a headline, introduction, main content, and conclusion.

[1603] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency.

[1604] Translation processing and publishing

[1605] The server sends the generated and proofread articles to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[1606] The server checks the translated article and corrects mistranslations and grammatical errors using a correction engine.

[1607] The server stores the final article in a database and prepares it for display when accessed by a user.

[1608] The device requests an article, the server retrieves it from the database, and displays it to the user, often in a translated version based on the user's language settings.

[1609] Emotion recognition and article adjustment

[1610] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[1611] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[1612] Paid advertising placement

[1613] Users (advertiser sponsors) set the conditions for the ads they want to run (e.g., topics, keywords, target countries) through a dedicated interface.

[1614] The server identifies appropriate articles based on the criteria received from the advertising management system and inserts paid advertisements into the articles at designated locations, positioning the advertisements for efficient display.

[1615] When the terminal finally displays the article to the user, it embeds the specified advertisement in the article appropriately and displays it in a way that is likely to interest the user.

[1616] Specific examples

[1617] Example 1: Creating and updating articles

[1618] When new information about "new coronavirus variants" is updated, the server collects relevant information from the web.

[1619] Generative AI generates articles based on new information.

[1620] The server uses a proofreading engine to check the accuracy of the article, and finally stores it in a database for publication.

[1621] Example 2: Translation processing

[1622] The newly generated article, "New coronavirus variant," is sent to a multilingual translation engine, where it is translated into English, French, Spanish, and other languages.

[1623] The translated content is rechecked on the server and finally saved in the database.

[1624] Example 3: Emotion-based display adjustment

[1625] When a user of a device views an article, the emotion engine analyzes the user's reactions (e.g., click history, viewing time, comments) and determines that the user is expressing positive emotions.

[1626] The server suggests articles tailored to the user and displays articles that are encouraging and hopeful.

[1627] Example 4: Paid advertising

[1628] If a health-related company wants to advertise "antivirus products," the user sets the conditions in the advertising management system.

[1629] The server inserts the advertisements at appropriate locations within the relevant articles and publishes them together with the articles.

[1630] This system automatically handles everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, ensuring efficient and accurate information provision.

[1631] The processing flow will be explained below.

[1632] Step 1:

[1633] The server periodically scrapes the latest data from designated news sites, academic paper databases, government agency pages, etc. This information collection is done automatically according to the set interval.

[1634] Step 2:

[1635] The server sends the collected text data to a natural language processing engine, which categorizes and summarizes the information. For example, if information about "mutant strains of the new coronavirus" is collected, the information is summarized to extract key points.

[1636] Step 3:

[1637] The server passes the summarized data to the generation AI, which then creates a new article based on the data received. For example, it automatically generates an article structure, such as a headline, introduction, main content, and conclusion.

[1638] Step 4:

[1639] The server sends the generated article to a proofreading engine, which checks it for grammatical errors and content consistency and makes corrections as needed.

[1640] Step 5:

[1641] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages ​​(e.g., English, French, Spanish, etc.).

[1642] Step 6:

[1643] The server receives the translated articles and double-checks the accuracy of each language. If mistranslations or grammatical errors are found, they are corrected using a correction engine.

[1644] Step 7:

[1645] The server stores the final article in a database, which contains both the original and the translation.

[1646] Step 8:

[1647] The server uses an emotion engine to analyze the user's input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions.

[1648] Step 9:

[1649] The server generates or adjusts the content and format of articles optimized for the user based on the recognized emotions. For example, if a user expresses positive emotions, it displays articles with encouraging or hopeful content.

[1650] Step 10:

[1651] The server inserts advertisements provided through the advertisement management system into articles in an optimal manner based on the user's emotions analyzed by the emotion engine.

[1652] Step 11:

[1653] The device (user's browser or app) requests the final article, the server retrieves it from the database and displays it to the user, including any optimized ads.

[1654] Step 12:

[1655] Users (advertiser sponsors) can view feedback reports provided through the system, which show how effective their ads were for users.

[1656] Through these steps, the system can automatically provide fast and accurate information, support multiple languages, customize based on user sentiment, and monetize advertising.

[1657] Example 2

[1658] 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."

[1659] In conventional systems, various processes such as information gathering, article generation, translation, and ad insertion were performed separately, making it difficult to efficiently execute a series of processes. Furthermore, the system was unable to provide content that took user emotions into consideration, which resulted in a lack of improvement in the user experience. Furthermore, the accuracy of ad targeting was low, limiting the effectiveness of advertising.

[1660] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting information; means for generating articles using a natural language processing engine based on the collected information; means for checking the grammar and content of the generated articles using a proofreading engine; means for translating the generated and updated articles using a multilingual translation engine; means for storing and publishing the translated articles in a database; means for inserting paid advertisements into articles based on user-specified conditions; and means for analyzing user responses to recognize emotions and adjusting display content based on the recognized emotions. This enables the efficient execution of a series of processes and the provision of optimal content based on user emotions. Furthermore, highly targeted advertisement display is expected to improve advertising effectiveness.

[1661] "Means for collecting information" refers to the ability to execute a process that automatically retrieves the latest data from designated websites and databases on the Internet.

[1662] A "natural language processing engine" is an artificial intelligence technology that analyzes collected information and performs processes such as classifying and summarizing the information and generating text.

[1663] "Means for generating articles" refers to the process of automatically creating new articles based on collected information using a natural language processing engine.

[1664] A "proofreading engine" is an artificial intelligence technology that checks the grammatical and content accuracy of generated text and makes any necessary corrections.

[1665] "Multilingual Translation Engine" means a translation technology that performs the process of translating generated and proofread articles into multiple languages.

[1666] "Means for storing and publishing articles in a database" refers to the process of storing the final generated articles in a database and publishing them for users to access.

[1667] "Means for inserting paid advertisements into articles" refers to the process of adding advertising content to applicable articles based on advertising criteria set by a user.

[1668] "Means for analyzing user responses and recognizing emotions" refers to artificial intelligence technology that analyzes user input and behavioral data to identify the user's emotional state.

[1669] "Means for tailoring display content" refers to the process of optimizing the content and format of displayed articles based on perceived user sentiment.

[1670] The system of the present invention uses generative AI to automatically collect, generate, translate, and update information, and automates a series of processes including the placement of paid advertisements. This system is composed of the following main components: an information collection engine, a natural language processing engine, generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertisement management system.

[1671] Information gathering

[1672] The server runs an information gathering engine that gathers the latest data from selected news sites, academic paper databases, and government agency pages using Python's Beautiful Soup library, and stores the data in a MySQL database.

[1673] Article Generation

[1674] The server sends the collected information to a natural language processing engine, which uses the BERT model to categorize and summarize the information. The summarized data is then passed to a generative AI (based on GPT-4) that generates a new article based on a prompt. For example, the prompt could be, "Based on information about the latest variants of the new coronavirus, please create an article with a headline, introduction, main content, and conclusion."

[1675] The generated articles are checked for grammar and content using a proofreading engine (Grammarly API), and any necessary corrections are made.

[1676] Translation processing and publishing

[1677] The server translates the generated and proofread articles into multiple languages ​​using the Google Translate API. The translated articles are then checked again with the Grammarly API to correct any mistranslations or grammatical errors. The final articles are stored in a database and prepared for display when accessed by users.

[1678] The device requests an article, the server retrieves it from the database and displays it to the user, with the appropriate translation depending on the user's language settings.

[1679] Emotion recognition and display content adjustment

[1680] The server uses an emotion engine (Text Analytics for sentiment analysis API) to analyze the user's input and reactions obtained from the device and identify the user's emotional state. Based on the results of this analysis, the server adjusts the content displayed, for example, displaying articles that inspire hope to users with positive emotions.

[1681] Paid advertising placement

[1682] Users (advertising sponsors) use the advertising management system interface (built with Ruby on Rails) to set the conditions for the advertisements they wish to display.

[1683] The server identifies appropriate articles based on the criteria and inserts paid advertisements into the articles at designated locations. When the device finally displays the articles to the user, it embeds the designated advertisements appropriately and displays them in a way that is likely to attract the user's attention.

[1684] In this way, the system of the present invention automatically processes everything from information collection to article generation, translation, emotion recognition, updates, and the insertion of paid advertisements, thereby providing efficient and accurate information.

[1685] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1686] Step 1: Gather information

[1687] The server starts an information collection engine and prepares a list of specified news sites, academic paper databases, government agency pages, etc. The server then uses Python's Beautiful Soup library to scrape each website and collect the latest information. The input is the URL of the target website, and the output is the collected text data. This data is saved in temporary storage (for example, a MySQL database).

[1688] Step 2: Categorize and summarize

[1689] The server sends the collected text data to a natural language processing engine. Here, Hugging Face's BERT model is used to categorize and summarize the data. The input is scraped text data, and the output is categorized summary text. For example, if information about mutated strains of the new coronavirus is collected, the data is summarized to extract the main point, "mutated strains of the new coronavirus are increasing concerns about the spread of infection."

[1690] Step 3: Article generation

[1691] The server passes the summarized data to the generation AI and sends a request including a prompt. The generation AI uses the GPT-4 model. The input is the summarized text and the prompt, and the output is a new article. For example, the prompt is sent as follows: "Based on information about the latest variants of the new coronavirus, please write an article that includes a headline, introduction, main content, and conclusion." The generated article will be structured text that includes a headline, introduction, main content, and conclusion.

[1692] Step 4: Proofreading

[1693] The server sends the generated article to a proofreading engine, which checks and corrects grammatical errors and content consistency. Here, we use Grammarly's API. The input is the generated article, and the output is the proofread and corrected article. Specifically, it detects grammatical errors and corrects them to make the sentence grammatically correct.

[1694] Step 5: Translation

[1695] The server sends the generated and proofread article to a multilingual translation engine for translation into multiple languages. This uses the Google Translate API. The input is the proofread article, and the output is the translated article. For example, it can be translated into English, French, Spanish, or other languages. The translated article is then checked again with the Grammarly API to correct any mistranslations or grammatical errors.

[1696] Step 6: Save and publish your article

[1697] The server stores the final article in a database, ready to display when accessed by the user. The input is the translated and proofread article, and the output is the article stored in the database. The device requests the article, the server retrieves it from the database, and displays it to the user. For example, depending on the user's language preference, the appropriate translation might be displayed: English, French, Spanish, etc.

[1698] Step 7: Emotion recognition and display adjustment

[1699] The server uses an emotion engine to analyze user input and reactions (e.g., comments, clicks, viewing time) obtained from the device and recognize the user's emotions. Here, the Text Analytics for sentiment analysis API is used. The input is the user's reaction data, and the output is the user's emotional state. Based on the recognized emotions, the server adjusts the content and format of the articles to be displayed. For example, for a user who shows positive emotions, it displays articles that are encouraging and instill hope.

[1700] Step 8: Place Paid Ads

[1701] Users (advertising sponsors) set the conditions for the ads they want to run (e.g., topic, keywords, target country) through the ad management system. This interface is built using Ruby on Rails. The input is the ad conditions set by the user, and the output is the ad case generated based on those conditions. The server identifies appropriate articles based on the conditions received from the ad management system and inserts paid ads into the specified locations within the articles. When the device finally displays the article to the user, it embeds the specified ads within the article appropriately and displays them in a way that is likely to interest the user.

[1702] Through these steps, the system provides efficient and accurate information, displays optimal content based on the user's emotions, and places advertisements with high targeting accuracy.

[1703] (Application example 2)

[1704] 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."

[1705] Conventional news distribution systems are unable to display news optimally based on user sentiment, even when they rapidly generate, proofread, and translate collected information, making it difficult to improve the user experience. They also have difficulty increasing revenue through appropriate advertising placement. Therefore, there is a need for a system that automatically displays articles that reflect user sentiment and places paid advertisements according to user interests.

[1706] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1707] In this invention, the server includes means for collecting information, means for generating articles using a natural language processing engine based on the collected information, means for checking the grammar and content of the generated articles using a proofreading engine, means for translating the generated and updated articles using a multilingual translation engine, means for storing and publishing the translated articles in a database, means for inserting paid advertisements into articles based on conditions specified by the user, and means for analyzing user emotions and adjusting display content based thereon, thereby enabling article display optimized to user emotions and effective advertisement placement.

[1708] The "means of collecting information" is an engine that automatically retrieves the latest information from news sites and academic paper databases on the Internet.

[1709] A "natural language processing engine" is an AI technology that analyzes collected information and generates articles.

[1710] The "means for generating articles" is a system that utilizes a natural language processing engine to execute the process of creating text.

[1711] A "proofreading engine" is an engine that has the function of checking and correcting the consistency of grammar and content of generated articles.

[1712] A "multilingual translation engine" is an AI technology for translating articles into multiple languages.

[1713] "Means for storing and publishing in a database" refers to a system for storing translated articles and providing them to users when they access them.

[1714] The "means for inserting paid advertisements into articles" is a system that places appropriate advertisements within articles based on conditions set by the user.

[1715] "Means for analyzing user emotions" refers to a system that analyzes the user's input and reactions to recognize emotions and adjusts the display content based on those emotions.

[1716] The system for implementing this invention consists of the following main components: an information gathering engine, a generative AI, a proofreading engine, a multilingual translation engine, an emotion engine, a database, and an advertising management system. The role and processing flow of each component will be explained in detail.

[1717] Information Gathering Engine

[1718] The information collection engine is used to scrape the latest data from specific news sites and academic paper databases. It uses AWS EC2 as the hardware and Python and the Scrapy library as the software. The collected data is stored on the server in a structured format.

[1719] Generation AI

[1720] The collected information is then generated into new articles by a generative AI. The generative AI uses OpenAI's GPT-4 and Hugging Face Transformers. This automatically generates article structures such as a headline, introduction, main content, and conclusion. A GPU server (equipped with NVIDIA A100) is used to achieve high-speed processing.

[1721] Proofreading Engine

[1722] The generated articles are then checked for grammar and content by a proofreading engine, using the Grammarly API and LanguageTool, ensuring accuracy and consistency of the generated text.

[1723] Multilingual Translation Engine

[1724] The proofread articles are then translated into multiple languages ​​using a multilingual translation engine, including the Google Cloud Translation API and DeepL API. A GPU server is also used to speed up the translation process.

[1725] Emotion Engine

[1726] Articles stored in the database are optimized by a sentiment engine that analyzes user input and reactions, using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, to display the best articles based on the user's sentiment.

[1727] Ad Management System

[1728] The ad management system inserts appropriate ads into articles based on the conditions set by the user. This system uses the Google Ads API and Facebook Ads API. Appropriate ad placement can maximize the effectiveness of ads.

[1729] Specific examples

[1730] Example 1: Generating news articles

[1731] Data collected: "Latest information on COVID-19 variants"

[1732] Example prompt for generative AI: "Please extract key points about the new coronavirus variant and generate a new news article."

[1733] Example 2: Translation processing

[1734] Example prompt: "Translate the following news article into English, French, and Spanish."

[1735] Example 3: Emotion-based display adjustment

[1736] Sample prompt: "Users are expressing positive emotions, so please tailor your article to be encouraging and uplifting."

[1737] Example 4: Paid Ad Insertion

[1738] Example ad: "New antivirus product"

[1739] Example prompt: "Insert an advertisement into a news article based on the following criteria."

[1740] In this way, the system of the present invention automatically performs all processes from information collection to article creation, translation, emotion recognition, and advertisement insertion, thereby realizing optimal information provision and advertisement display for the user.

[1741] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1742] Step 1: Gather information

[1743] Specific operation: The server periodically scrapes the latest information from specified news sites and academic paper databases.

[1744] Input: URL of the specified website or database

[1745] Output: Information collected by scraping

[1746] Data processing: Use Python and the Scrapy library to extract the necessary data from the web page and save it in a structured format (e.g., JSON format).

[1747] Step 2: Article generation

[1748] Specific operation: The server generates news articles using generative AI based on the collected information.

[1749] Input: Collected information (JSON format)

[1750] Output: Generated news article (text format)

[1751] Data processing: Using OpenAI's GPT-4 model on a GPU server, the collected data is analyzed and summarized, and a structured article is automatically generated, including a headline, introduction, main content, and conclusion.

[1752] Step 3: Proofread your article

[1753] What it does: The generated article is sent to a proofreading engine where it is checked and corrected for grammar and content consistency.

[1754] Input: Generated news article (text format)

[1755] Output: Proofread news article (text format)

[1756] Data processing: Use Grammarly API and LanguageTool to check for grammatical errors and stylistic consistency and make any necessary corrections.

[1757] Step 4: Multilingual Translation

[1758] What it does: The proofread article is sent to a multilingual translation engine and translated into multiple languages.

[1759] Input: Proofread news article (text format)

[1760] Output: Translated news articles (multilingual text format)

[1761] Data processing: Using the Google Cloud Translation API or DeepL API, articles are translated into the specified language (e.g., English, French, Spanish). The translated text is then checked for grammar again and corrected if necessary.

[1762] Step 5: Save and publish the database

[1763] What it does: The translated articles are stored in a database and made publicly available for users to access.

[1764] Input: Translated news article (multilingual text format)

[1765] Output: Published news article (text on a web page or application)

[1766] Data processing: The translated text is stored in a database and news articles in the appropriate language are provided upon user request.

[1767] Step 6: Inserting Paid Ads

[1768] What it does: Places appropriate ads within news articles based on user-specified criteria.

[1769] Input: User-specified advertising conditions (target demographic, keywords, etc.)

[1770] Output: News article with ads inserted (text format)

[1771] Data processing: Advertisements are inserted into the appropriate positions within articles based on the specified conditions using the ad management system (Google Ads API, Facebook Ads API).

[1772] Step 7: Sentiment analysis and display optimization

[1773] How it works: When a user browses an article, the emotion engine analyzes the user's input and reactions and optimizes the content displayed based on that.

[1774] Input: User response data (click history, viewing time, comments)

[1775] Output: Optimized display content (text format)

[1776] Data processing: Using IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, we analyze user sentiment and tailor articles to encourage and inspire positive responses.

[1777] The above steps ensure that the entire process, from information gathering to article creation, proofreading, multilingual translation, database storage, paid advertising insertion, and display optimization based on sentiment analysis, proceeds smoothly, resulting in a system that provides users with the best possible news experience.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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).

[1785] 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.

[1786] 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."

[1787] 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.

[1788] 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).

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] 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.

[1795] 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.

[1796] 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.

[1797] 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.

[1798] 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.

[1799] The following is further disclosed regarding the above embodiment.

[1800] (Claim 1)

[1801] means of collecting information;

[1802] A method for generating articles using a natural language processing engine based on collected information, and

[1803] A means for checking the grammar and content of the generated articles using a proofreading engine;

[1804] A means for translating the generated and updated articles using a multilingual translation engine;

[1805] A means of storing and publishing translated articles in a database;

[1806] means for inserting paid advertisements into articles based on user-specified criteria;

[1807] A system including:

[1808] (Claim 2)

[1809] 10. The system of claim 1, further comprising: means for updating existing articles based on the collected information; and means for reviewing the appropriateness of the generated and updated articles.

[1810] (Claim 3)

[1811] 10. The system of claim 1, further comprising means for correcting mistranslations and grammatical errors in the translated article.

[1812] "Example 1"

[1813] (Claim 1)

[1814] means of collecting information;

[1815] A means of generating digital content using a natural language processing engine based on the collected information;

[1816] a means for checking the grammar and content of the generated digital content using a proofreading engine;

[1817] a means for translating the generated and updated digital content using a multilingual translation engine;

[1818] a means for storing and publishing the translated digital content in a data storage;

[1819] means for inserting paid promotions into digital content based on user-specified conditions;

[1820] A system including:

[1821] (Claim 2)

[1822] 10. The system of claim 1, further comprising: means for updating existing digital content based on the collected information; and means for reviewing the appropriateness of the generated and updated digital content.

[1823] (Claim 3)

[1824] 10. The system of claim 1, further comprising means for correcting translation errors and grammatical mistakes in the translated digital content.

[1825] "Application Example 1"

[1826] (Claim 1)

[1827] means of collecting information;

[1828] A means of generating content using a natural language processing engine based on the collected information;

[1829] a means for checking the generated content for grammar and content using a proofreading engine;

[1830] means for translating the generated and updated content using a multilingual translation engine;

[1831] A means of storing and publishing the translated content in a database;

[1832] means for inserting paid advertisements into the content based on conditions set by the user;

[1833] A means of automatically generating product descriptions using a generative AI model based on collected information;

[1834] A means for translating the generated product description into multiple languages;

[1835] A system including:

[1836] (Claim 2)

[1837] 10. The system of claim 1, further comprising: means for updating existing content based on the collected information; means for reconfirming the appropriateness of the generated and updated content; and means for reconfirming product descriptions translated into multiple languages.

[1838] (Claim 3)

[1839] 10. The system of claim 1, further comprising means for correcting mistranslations and grammatical errors in the translated content.

[1840] "Example 2: Combining Emotion Engines"

[1841] (Claim 1)

[1842] means of collecting information;

[1843] A method for generating articles using a natural language processing engine based on collected information, and

[1844] A means for checking the grammar and content of the generated articles using a proofreading engine;

[1845] A means for translating the generated and updated articles using a multilingual translation engine;

[1846] A means of storing and publishing translated articles in a database;

[1847] means for inserting paid advertisements into articles based on user-specified criteria;

[1848] means for analyzing a user's reaction to recognize an emotion and adjusting the display content based on the recognized emotion;

[1849] A system including:

[1850] (Claim 2)

[1851] 10. The system of claim 1, further comprising: means for updating existing articles based on the collected information; and means for reviewing the appropriateness of the generated and updated articles.

[1852] (Claim 3)

[1853] 10. The system of claim 1, further comprising means for correcting mistranslations and grammatical errors in the translated article.

[1854] "Application example 2 when combining emotion engines"

[1855] (Claim 1)

[1856] means of collecting information;

[1857] A method for generating articles using a natural language processing engine based on collected information, and

[1858] A means for checking the grammar and content of the generated articles using a proofreading engine;

[1859] A means for translating the generated and updated articles using a multilingual translation engine;

[1860] A means of storing and publishing translated articles in a database;

[1861] means for inserting paid advertisements into articles based on user-specified criteria;

[1862] means for analyzing a user's emotions and adjusting the displayed content based on the emotions;

[1863] A system including:

[1864] (Claim 2)

[1865] 10. The system of claim 1, further comprising: means for updating existing articles based on the collected information; and means for reviewing the appropriateness of the generated and updated articles.

[1866] (Claim 3)

[1867] 10. The system of claim 1, further comprising means for correcting mistranslations and grammatical errors in the translated article. [Explanation of symbols]

[1868] 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. means of collecting information; A method for generating articles using a natural language processing engine based on collected information, and A means for checking the grammar and content of the generated articles using a proofreading engine; A means for translating the generated and updated articles using a multilingual translation engine; A means of storing and publishing translated articles in a database; means for inserting paid advertisements into articles based on user-specified criteria; A system including:

2. 10. The system of claim 1, further comprising: means for updating existing articles based on the collected information; and means for reviewing the appropriateness of generated and updated articles.

3. 10. The system of claim 1, further comprising means for correcting mistranslations and grammatical errors in the translated article.

Images