system

Abstract

A system is provided.SOLUTION: A system comprising: means for a user to upload an article; means for a server to parse the uploaded article; means for the server to automatically translate the parsed article into multiple languages; means for the server to extract and embed SEO keywords for the translated article; means for the server to generate and link relevant images and video to the article; and means for the server to distribute the processed article to platforms in each country.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] Many companies and individuals today disseminate information via the Internet, but because it is limited to a specific language, it is difficult for that information to reach audiences in other regions. Furthermore, language barriers hinder revenue growth, and the labor and costs required for language translation are a significant burden for small and medium-sized enterprises and freelancers. Furthermore, SEO strategies must be implemented individually in multiple languages, requiring additional effort. This invention solves these problems, removes language barriers, and provides a system that allows anyone to easily disseminate information globally. [Means for solving the problem]

[0005] The present invention provides a system including the following means: a means for users to upload articles; a means for a server to analyze the uploaded articles; a means for the server to automatically translate the analyzed articles into multiple languages; a means for the server to extract and embed SEO keywords into the translated articles; a means for the server to generate related images and videos and link them to the articles; and a means for the server to distribute the processed articles to platforms in each country. The system also includes a means for users to preview the articles and issue a distribution command, and a means for the server to analyze and translate the content of the articles using a natural language processing engine. This system significantly reduces the labor and cost of language translation and enables effective global information dissemination.

[0006] A "user" is an entity that accesses the system and uploads articles and issues distribution instructions.

[0007] The "server" is a device that controls the entire system and performs article analysis, translation, SEO keyword extraction and embedding, media generation, and article distribution.

[0008] An "article" is a collection of information uploaded by a user, which has specific content in text format.

[0009] "Means for uploading" refers to the means by which a user sends an article to the system and the article is received by the server.

[0010] "Means of analysis" refers to the procedure for understanding the content of an article, interpreting its grammar and meaning, and preparing for further processing.

[0011] "Means for automatic translation" is the process of converting the analyzed articles into multiple target languages.

[0012] "SEO keywords" are words or phrases that are easily recognized by search engines and are embedded in articles for search engine optimization.

[0013] "Extract and embed" is a method of finding appropriate SEO keywords from the content of an article and incorporating them into the translated article in a natural way.

[0014] "Means for generating images and videos" refers to procedures for automatically creating visual media related to the article content.

[0015] "Linking means" refers to the method by which generated media is linked and stored with the corresponding article.

[0016] The "means of distribution" refers to the method by which the final processed article is sent to each country's platform and made public.

[0017] "Means for checking the preview" refers to a procedure that allows users to see the final form of the translated article and related media in advance and check for any problems.

[0018] A "natural language processing engine" is a software technology that analyzes the grammar and meaning of a language and translates it into other languages. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention is a system for creating articles in multiple languages ​​and implementing SEO measures. In this system, users upload articles, and the server automatically translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media, ultimately distributing them to platforms in each country.

[0041] Program processing

[0042] 1. Initial Setup:

[0043] When a user logs into the system using a web browser, they enter their authentication information.

[0044] The server receives the authentication information sent by the user and performs authentication.

[0045] 2. Upload your article:

[0046] The user selects an article file written in Japanese and uploads it to the system.

[0047] The server receives the uploaded article files and stores them in an internal database.

[0048] 3. Article analysis and translation:

[0049] The server sends the uploaded article to a natural language processing engine (NLP engine) to analyze the article's content.

[0050] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[0051] Translated articles are stored on a server for each target language.

[0052] 4. SEO:

[0053] The server automatically extracts keywords necessary for SEO from the original Japanese article.

[0054] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[0055] 5. Media Generation:

[0056] The server automatically generates related images and videos based on the content of the article.

[0057] The generated media files are associated with the translated article and saved.

[0058] 6. Preview the article:

[0059] Users preview translated articles and auto-generated media on the system.

[0060] The user checks that there are no problems with the content and then issues a command to distribute it.

[0061] 7. Article Distribution:

[0062] The server delivers translated articles to platforms in each country according to the user's instructions.

[0063] Specific examples

[0064] 1. Initial Setup:

[0065] A user logs into the system and uploads the article file "NewTech.txt."

[0066] 2. Article analysis and translation:

[0067] The server receives "NewTech.txt" and performs text analysis.

[0068] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[0069] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[0070] 3. SEO:

[0071] The server extracts the SEO keyword "new technology" from the original Japanese article.

[0072] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[0073] 4. Media Generation:

[0074] The server automatically generates technical images related to the article content.

[0075] For example, create an image related to "introducing new technology" and link it to the article.

[0076] 5. Article Preview and Distribution:

[0077] Users can view articles and related media translated into each language on the system.

[0078] After confirmation, if you issue a distribution command, the server will distribute the article to platforms in each country.

[0079] In this way, by implementing the system of the present invention, users can quickly and effectively create and distribute articles in multiple languages, significantly reducing the man-hours and costs involved in language translation and facilitating the global dissemination of information.

[0080] The processing flow will be explained below.

[0081] Step 1: User logs into the system

[0082] The user opens a web browser and accesses the system's login page.

[0083] The user enters their authentication information (username and password) and clicks the "Login" button.

[0084] The server receives the authentication information entered and checks it against information in a database.

[0085] If the authentication is successful, the server displays the dashboard screen to the user.

[0086] Step 2: User uploads article file

[0087] The user clicks the "Upload article" button on the dashboard screen.

[0088] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[0089] The user clicks the "Upload" button.

[0090] The server receives the uploaded files and stores them in the system's storage.

[0091] Step 3: The server parses the article

[0092] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[0093] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[0094] Step 4: The server automatically translates the article into multiple languages

[0095] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[0096] Articles translated into each language are stored in a database on the server.

[0097] Step 5: The server extracts SEO keywords

[0098] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[0099] For example, detect keywords such as "new technology."

[0100] Step 6: The server translates the extracted keywords into each language and embeds them

[0101] The server translates the extracted keywords into keywords appropriate for the target language.

[0102] Translated keywords are embedded naturally into translated articles in each language.

[0103] Step 7: The server generates the relevant images and videos

[0104] The server automatically generates related images and videos based on the content of the article.

[0105] For example, create a technical image related to "introducing new technology."

[0106] Step 8: The server associates the generated media with the article

[0107] The server links the generated images and videos to the corresponding translated articles.

[0108] The media files are stored in a database on the server along with the articles.

[0109] Step 9: User Previews Article

[0110] Users can preview translated articles and related media in their language on the system.

[0111] The preview screen checks the accuracy of the content and the relevance of the media.

[0112] Step 10: User directs distribution

[0113] After checking the preview, the user clicks the "Distribute" button.

[0114] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[0115] Step 11: The server delivers the article

[0116] The server then sends the translated articles to pre-designated platforms in each country for publication.

[0117] Articles are published on each platform and become accessible to users.

[0118] Example 1

[0119] 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."

[0120] Currently, there are only a limited number of systems that can effectively generate multilingual articles and implement SEO measures. The automatic translation of articles into multiple languages ​​and the appropriate embedding of SEO keywords are particularly time-consuming. There is also a lack of technology to automatically generate related media files and link them to articles. This creates challenges for users, as it requires a lot of time, effort, and costs when distributing articles globally.

[0121] 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.

[0122] In this invention, the server includes means for users to upload articles using a computer terminal, means for the server to analyze the uploaded articles using a natural language processing engine, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to automatically generate related images and videos using a generative AI model and link them to the articles, and means for the server to distribute the processed articles to web platforms in each country. This enables users to quickly and effectively generate and distribute articles in multiple languages, significantly reducing the labor and cost of language translation and facilitating global information dissemination.

[0123] "User" means an individual or legal entity that uses the System to generate, translate, and distribute articles.

[0124] A "computer terminal" is a device that allows a user to access and operate the system, and includes, for example, a personal computer, a smartphone, a tablet, etc.

[0125] The "server" is a central processing unit that processes the entire system, receiving articles, analyzing them, translating them, generating media, and distributing them.

[0126] A "natural language processing engine" is software or a system that analyzes the content of articles and performs grammatical analysis and keyword extraction.

[0127] "Translation API" means an external service or interface that a server uses to automatically translate articles into multiple languages.

[0128] "SEO keywords" are important keywords for search engine optimization (SEO), and are words that are embedded in articles to help them appear higher in search engines.

[0129] A "generative AI model" is an artificial intelligence model that automatically generates related images and videos based on the content of an article.

[0130] "Web platform" refers to the online services and media to which articles are distributed, including, for example, blog sites, news portals, and social media.

[0131] In this way, the above definitions can be used to make the claims more specific and clear.

[0132] This invention is a system in which users upload articles, the server automatically translates them into multiple languages, extracts and embeds SEO keywords, generates and links related media, and finally distributes them to web platforms in each country. This system is implemented using the following steps and components:

[0133] First, a user accesses the system using a web browser. The user enters their authentication information on the login screen and logs into the system. The authentication information is received by the server and compared with the information stored in the internal database. If this authentication is successful, the user is redirected to the dashboard screen.

[0134] Next, the user selects an article file written in Japanese and clicks the upload button. The device sends the selected file to the server, which then verifies the received file. Once verification is complete, the file is saved in the internal database.

[0135] The server then sends the saved article file to a natural language processing engine (NLP engine). The NLP engine performs grammatical analysis and keyword extraction, and returns the analysis results to the server. Based on these analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, and Spanish). A common translation API is used for the translation.

[0136] For translated articles, the server automatically extracts SEO keywords, translates them into the target language, and embeds them. Extracted keywords are inserted into each article in a natural context to minimize unnecessary manual work.

[0137] In addition, the server uses a generative AI model to automatically generate images and videos related to the article content. For example, if there is an article titled "Introduction of New Technology," technology-related images will be automatically generated by the generative AI model. These media files are linked to the translated article and stored in an internal database.

[0138] Users can preview articles and related media translated into each language from the system's dashboard. After confirming that there are no problems with the content, they issue a distribution command, and the server distributes the article to each country's web platform. This uses each platform's API to post the article and media files appropriately.

[0139] Examples and prompts

[0140] 1. Upload your article:

[0141] A user logs into the system and uploads the article file "NewTech.txt."

[0142] 2. Article analysis and translation:

[0143] The server receives "NewTech.txt" and performs text analysis.

[0144] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[0145] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[0146] 3. SEO:

[0147] The server extracts the SEO keyword "new technology" from Japanese articles.

[0148] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[0149] 4. Media Generation:

[0150] The server automatically generates technical images related to the article content.

[0151] For example, create an image related to "introducing new technology" and link it to the article.

[0152] Example prompt sentence:

[0153] "Write an article in Japanese announcing the introduction of a new technology. Also, translate this article into English, French, and Spanish, embedding appropriate SEO keywords in each language article and generating relevant images."

[0154] Using this system, users can quickly and efficiently create and distribute articles in multiple languages, significantly reducing the effort and cost of language translation and making it easier to disseminate information globally.

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

[0156] Step 1:

[0157] Initial Setup

[0158] A user accesses the system using a web browser and enters authentication information (username and password) on the login screen.

[0159] Input: Username, Password

[0160] The server receives the entered authentication information, checks it against the correct authentication information stored in its internal database, and if authentication is successful, displays the dashboard screen to the user.

[0161] Output: Login success / failure message, dashboard screen or error message

[0162] Step 2:

[0163] Article Upload

[0164] The user selects the Japanese article file from the dashboard screen and clicks the "Upload" button.

[0165] Input: Article file (e.g. NewTech.txt)

[0166] The terminal sends the selected file to the server, which then verifies the file, including checking the file format and virus checks.

[0167] The server stores the verified files in an internal database.

[0168] Output: File save success / failure message

[0169] Step 3:

[0170] Article analysis and translation

[0171] The server sends article files stored in an internal database to a natural language processing engine (NLP engine) to analyze the content.

[0172] Input: Article file (e.g. NewTech.txt)

[0173] The server extracts the article content from the analysis results and automatically translates it into multiple target languages. The translation process uses an external translation API (e.g., a general translation API).

[0174] Output: Translated article (English, French, Spanish, etc.)

[0175] Step 4:

[0176] SEO measures

[0177] The server uses a natural language processing engine to extract SEO keywords from the original article.

[0178] Input: Original article (e.g. "We introduced new technology")

[0179] The server translates the extracted keywords into multiple target languages.

[0180] The server embeds the translated keywords naturally into the translated articles in each target language.

[0181] Output: SEO-optimized translated article

[0182] Step 5:

[0183] Media Generation

[0184] The server uses a generative AI model to automatically generate relevant images and videos based on the article's content.

[0185] Input: Article content (e.g., "Introduction of new technology")

[0186] The server associates the automatically generated media files (images, videos) with the translated articles and stores them in a database.

[0187] Output: Translated articles with related media

[0188] Step 6:

[0189] Article Preview

[0190] Users preview translated articles and auto-generated media on the system.

[0191] Input: Preview request

[0192] The server generates a temporary preview and displays it to the user, who can then view each language version of the article and its associated media.

[0193] Output: Preview screen, user requests for corrections or confirmation

[0194] Step 7:

[0195] Article distribution

[0196] The user checks the preview content and clicks the "Distribute" button.

[0197] Input: Delivery instructions

[0198] The server distributes the translated articles to web platforms in each country using their respective APIs (e.g. blog site API, news portal API).

[0199] Output: Articles distributed to each country's web platform, distribution success / failure message

[0200] (Application example 1)

[0201] 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."

[0202] While existing multilingual article generation and SEO systems allow users to easily translate and distribute articles, they do not support real-time visual recognition-based advertisement generation and display. Furthermore, they lack the ability to instantly generate multilingual advertising content and overlay it on visual devices. There is a particular need for a method to improve the efficiency of inbound marketing in tourist destinations and shopping malls.

[0203] 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.

[0204] In this invention, the server includes: means for users to upload articles; means for the server to analyze the uploaded articles; means for the server to automatically translate the analyzed articles into multiple languages; means for the server to extract and embed SEO keywords for the translated articles; means for the server to generate related images and videos and link them to the articles; means for the server to distribute the processed articles to platforms in various countries; means for users to detect visual targets using a content browsing device and automatically generate advertising content based on the targets; means for the server to translate the generated advertising content into multiple languages ​​and apply SEO measures; and means for users to check the translated advertising content on the content browsing device and draw it in a specified visual area. This enables users to generate and display multilingual advertisements in real time based on visual recognition, significantly improving the efficiency of inbound marketing.

[0205] "User" means any entity, including individuals or corporations, that uses this system to upload articles and generate, review, and distribute content.

[0206] "Article" means a text document containing information that can be uploaded, analyzed, translated, search engine optimized, and associated with related media by the server.

[0207] "Uploading" refers to the act of a user transferring their own digital data to a server.

[0208] "Analysis" is the process by which the server uses a natural language processing engine to understand the content of the uploaded article and extract information.

[0209] "Translation" is a server function that converts analyzed articles into multiple target languages.

[0210] "SEO keywords" are specific words or phrases that are embedded in articles for search engine optimization.

[0211] "Media" refers to visual and audio supplementary information such as images and videos related to the content of the article.

[0212] A "viewed object" is an object or scene that a user visually recognizes through a content browsing device.

[0213] "Advertising content" refers to promotional text and multimedia material that is automatically generated based on the viewed object.

[0214] A "content viewing device" is a device such as smart glasses or a head-mounted display worn or used by a user, which overlays advertising content in the visual field.

[0215] "Overlay display" is a technique for displaying additional information overlaid on top of existing visual information.

[0216] "Distribution" refers to the act of delivering processed articles and advertising content to platforms in each country via the Internet.

[0217] A "natural language processing engine" is a type of software that the server uses to understand the content of an article and extract and translate the appropriate information.

[0218] In order to put the present invention into practice, the following specific system is constructed.

[0219] The server analyzes articles uploaded by users, translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media.It also has the function of automatically generating advertising content in real time based on the objects the user sees using their visual device, translating and implementing SEO measures, and overlaying it in the visual area.

[0220] Specifically, the server does the following:

[0221] 1. User authentication and article upload: A user logs into the system via a web browser and uploads an article file. The server processes the authentication information and stores the uploaded article in an internal database.

[0222] 2. Natural language processing and translation: The server uses an internal natural language processing engine (e.g., nltk, spaCy) to analyze the content of the uploaded article and automatically translate it into multiple target languages ​​(e.g., English, French, Spanish, etc.). This can be done using the Google Translate API, etc.

[0223] 3. Extracting and embedding SEO keywords: Automatically extract keywords necessary for SEO from the original article, translate them into the target language, and embed them appropriately in the article in each language.

[0224] 4. Related Media Generation: The server automatically generates related images and videos based on the article content and links them to the article. This can be done using a generative AI model (e.g., DALL-E, Stable Diffusion).

[0225] 5. Real-time ad generation: When a user wears smart glasses or a head-mounted display, the device uses a visual recognition engine (e.g., OpenCV, Google Cloud Vision API) to detect the object being viewed. Based on the detected object, ad content is automatically generated, translated, and optimized for SEO.

[0226] Through these steps, users can efficiently deliver multilingual articles and real-time generated advertisements. A specific example of use is when a user wearing smart glasses sees a cafe in a tourist spot, multilingual advertisement content based on that cafe is displayed in front of the user's eyes.

[0227] Prompt Sentence Examples

[0228] Please explain the structure of the object-based real-time multilingual advertisement generation system. Please explain in detail how it uses Google Cloud Vision API to detect the visual object, retrieves relevant advertisements from the advertisement database, performs multilingual translation using Google Trans, and displays the advertisements on smart glasses.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1:

[0231] A user logs in to the system through a web browser and uploads an article file. The server receives the authentication information and authenticates the user. If authentication is successful, the uploaded article file is stored in the internal database.

[0232] Input: User credentials, article file

[0233] Output: Articles stored in the internal database

[0234] Step 2:

[0235] The server sends the uploaded article to a natural language processing engine, which analyzes the article's content, including its sentence structure, topic, and important keywords.

[0236] Input: Articles stored in the internal database

[0237] Output: Analyzed article content (topics, keywords, etc.)

[0238] Step 3:

[0239] Based on the analysis results, the server automatically translates the article into multiple target languages ​​using a translation engine (e.g., Google Translate API). The translated articles are stored in an internal database for each language.

[0240] Input: Parsed article content, list of target languages

[0241] Output: Article translated into multiple languages

[0242] Step 4:

[0243] The server automatically extracts keywords necessary for SEO from the original Japanese article, translates the extracted keywords into the target language, and embeds them appropriately in the translated article in each language.

[0244] Input: Japanese article, list of target languages

[0245] Output: Translated articles with embedded SEO keywords

[0246] Step 5:

[0247] The server generates relevant images and videos based on the article content, automatically generating media using generative AI models (e.g., DALL-E, Stable Diffusion), and connecting them to translated articles in each language.

[0248] Input: Translation article content

[0249] Output: Related media (images, videos)

[0250] Step 6:

[0251] The user wears smart glasses or a head-mounted display, and the device detects the visual object. The device then identifies the object using a visual recognition engine (e.g., Google Cloud Vision API).

[0252] Input: Visual information captured on the device

[0253] Output: Detected objects

[0254] Step 7:

[0255] The server automatically generates advertising content based on the detected objects, retrieving relevant promotional text and multimedia materials from an advertising database and customizing them with a generative AI model.

[0256] Input: Detected object

[0257] Output: Generated ad content

[0258] Step 8:

[0259] The server translates the generated advertising content into multiple target languages ​​and implements SEO measures. It translates into multiple languages ​​using a translation engine and embeds SEO keywords.

[0260] Input: Generated ad content, list of target languages

[0261] Output: Translated ad content

[0262] Step 9:

[0263] The user checks the translated advertising content on the content viewing device, and the terminal overlays it in the designated visual area, where the advertising content is displayed together with the user's visual information.

[0264] Input: translated ad content

[0265] Output: Overlaid ad content

[0266] 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.

[0267] This invention is a system that generates articles in multiple languages, implements SEO measures, and recognizes user emotions and reflects them in articles and related media. In this system, users upload articles, and the server automatically analyzes and translates the articles, extracts and embeds SEO keywords, generates related media, and adjusts the content based on user emotion data before distributing it to platforms in each country.

[0268] Program processing

[0269] 1. Initial Setup:

[0270] A user logs into the system using a web browser and enters their authentication information.

[0271] The server receives the entered authentication information and performs authentication by comparing it with information in a database.

[0272] 2. Upload your article:

[0273] The user selects an article file written in Japanese and uploads it to the system.

[0274] The server receives the uploaded files and stores them in an internal database.

[0275] 3. Article analysis and translation:

[0276] The server reads the saved article file, sends it to a natural language processing engine (NLP engine), and analyzes the article content.

[0277] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[0278] The translated articles are stored on a server for each target language.

[0279] 4. SEO:

[0280] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[0281] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[0282] 5. Media Generation:

[0283] The server automatically generates related images and videos based on the article content.

[0284] The generated media files are saved and linked to the corresponding translated article.

[0285] 6. Acquiring and analyzing emotion data:

[0286] Users enter their emotional data when uploading articles, which can be done using a simple questionnaire or facial expression recognition, for example.

[0287] The server sends the acquired emotion data to the emotion engine for analysis.

[0288] 7. Reflecting emotional data:

[0289] The server adjusts the content of translated articles and related media based on the analyzed emotional data.

[0290] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[0291] 8. Article Preview:

[0292] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[0293] The user checks that there are no problems with the content and then issues a command to distribute it.

[0294] 9. Article Distribution:

[0295] The server follows the user's instructions and distributes the article to relevant platforms in each country.

[0296] Articles will be published on each platform, making them accessible to a diverse audience.

[0297] Specific examples

[0298] 1. Initial Setup:

[0299] A user logs into the system and uploads an article file called "TechNews.txt".

[0300] 2. Article analysis and translation:

[0301] The server reads "TechNews.txt" and the NLP engine analyzes the article content.

[0302] The article "We have introduced new technology" is translated into English "We have introduced new technology", French "Nous avons introduit une nouvelle technologie" and Spanish "Hemos introducido nueva tecnología".

[0303] 3. SEO:

[0304] The server extracts the SEO keyword "new technology," translates it into each target language, and embeds it in the article.

[0305] 4. Media Generation:

[0306] The server generates images related to the article content and links them to each translated article.

[0307] 5. Acquiring and analyzing emotion data:

[0308] A user enters emotional data such as "excited" in a survey.

[0309] The server sends this emotional data to the emotion engine, and adjusts media and articles based on the analysis results.

[0310] 6. Preview and distribute your article:

[0311] The user checks the preview and instructs distribution.

[0312] The server distributes the adjusted articles to platforms in each country and makes them public.

[0313] This system allows users to quickly generate and distribute multilingual articles that reflect emotional data, enabling more personalized and effective information dissemination to readers.

[0314] The processing flow will be explained below.

[0315] Step 1: User logs into the system

[0316] A user accesses the system's login page using a web browser.

[0317] The user enters their authentication information (username and password) and clicks the "Login" button.

[0318] The server receives the entered authentication information and performs authentication by comparing it with information in its internal database.

[0319] If the authentication is successful, the server displays the dashboard screen to the user.

[0320] Step 2: User uploads article file

[0321] The user clicks the "Upload article" button on the dashboard screen.

[0322] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[0323] The user clicks the "Upload" button.

[0324] The server receives the uploaded files and stores them in an internal database.

[0325] Step 3: The server retrieves the emotion data

[0326] Users enter their emotional data using a simple questionnaire or a facial expression recognition system.

[0327] For example, the user inputs the emotion "excited."

[0328] The server receives the emotion data and sends it to the emotion engine.

[0329] Step 4: The server parses the article

[0330] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[0331] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[0332] Step 5: The server automatically translates the article into multiple languages

[0333] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[0334] Articles translated into each language are stored in a database on the server.

[0335] Step 6: The server extracts and embeds SEO keywords

[0336] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[0337] For example, extract the keyword "new technology."

[0338] The server translates this into the target language and embeds it in a natural way into the translated article in each language.

[0339] Step 7: The server generates the relevant images and videos

[0340] The server automatically generates related images and videos based on the content of the article.

[0341] For example, create an image related to "introduction of new technology."

[0342] Step 8: The server adjusts the media and article content based on the sentiment data.

[0343] The server receives the analysis results from the emotion engine and adjusts the content of translated articles and related media.

[0344] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[0345] Step 9: Server associates generated media with article

[0346] The server links the generated images and videos to the corresponding translated articles.

[0347] The media files are stored in a database on the server along with the articles.

[0348] Step 10: User sees article preview

[0349] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[0350] The preview screen checks the accuracy of the content, the relevance of the media, and the effectiveness of reflecting emotions.

[0351] Step 11: User directs distribution

[0352] After checking the preview, the user clicks the "Distribute" button.

[0353] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[0354] Step 12: The server delivers the article

[0355] The server then sends the translated articles to pre-designated platforms in each country for publication.

[0356] Articles are published on each platform and become accessible to users.

[0357] Example 2

[0358] 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."

[0359] Conventional multilingual article generation systems have difficulty reflecting user sentiment data in addition to article translation and SEO measures, resulting in insufficient and effective personalization. Furthermore, there is a need to streamline the overall processing flow, including improving translation accuracy and adding features such as automatic generation of related media.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0361] In this invention, the server includes: a means for a user to log in to the system using authentication information; a means for the user to upload articles; a means for the server to save the uploaded articles; a means for the server to analyze the articles using a natural language processing engine; a means for the server to automatically translate the analyzed articles into multiple languages; a means for the server to save the translated articles; a means for the server to extract SEO keywords and embed them in the translated articles; a means for the server to generate images and videos based on the article content; a means for the server to link related images and videos to the articles; a means for the user to input emotional data; a means for the server to analyze the emotional data and adjust the translated articles and related media; and a means for the server to distribute the processed articles to platforms in each country. This enables efficient generation of multilingual articles that reflect user emotional data, SEO measures, and the automatic generation and distribution of related media.

[0362] "User" means any person or entity that accesses the System and uploads and manipulates Articles.

[0363] "Authentication information" refers to information such as a username and password used by a user to log in to a system.

[0364] "System" refers to a platform where users can upload articles and have them translated, search engine optimized, media generated, and sentiment data reflected.

[0365] "Server" refers to a computing device that handles the overall processing of the system and is responsible for data storage, analysis, translation, media generation, and delivery.

[0366] A "natural language processing engine" refers to software technology that analyzes text data and performs semantic understanding and translation.

[0367] "Analysis" refers to the process of breaking down the content of an uploaded article and understanding its meaning and grammatical structure.

[0368] "Translation" refers to the process of converting the content of the analyzed article into another language.

[0369] "SEO keywords" refers to embedding specific words or phrases within an article for search engine optimization.

[0370] "Generating images and videos" refers to automatically creating relevant visual content based on article content.

[0371] "Emotional data" refers to the emotional feedback and reactions to articles entered by users.

[0372] "Parse and translate" refers to the process of using a natural language processing engine to understand article content and translate it into multiple languages.

[0373] "Platform" refers to the website or service on which articles are published, and the medium through which users provide information to a diverse audience.

[0374] This invention relates to a system that generates and distributes articles and related media in multiple languages, reflecting user emotional data, in addition to providing SEO support. This system is realized through the cooperation of users, terminals, and a server.

[0375] A user logs into a system using a web browser (e.g., Google Chrome), enters authentication information (username and password), and the server receives the information using Apache HTTP Server or Nginx and authenticates the user by checking it against a MySQL or PostgreSQL database.

[0376] After logging in, the user selects an article file written in Japanese (e.g., "TechNews.txt") and uploads it to the system. The server receives the uploaded article file via FastAPI or the Django framework and stores it in cloud storage such as Amazon S3.

[0377] The server then analyzes the article content using Python and natural language processing libraries such as NLTK and spaCy. The analysis results are saved in JSON format. The server then uses the Google Translate API and Microsoft Translator API to automatically translate the analyzed article into multiple languages. The translation results are also saved in a database on the server.

[0378] The server uses libraries like BeautifulSoup or Scrapy to extract SEO-friendly keywords from the original article, which are then translated into the target language and embedded appropriately into each translated article.

[0379] The server also uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content, and the generated media files are saved and linked to each translated article.

[0380] When uploading an article, users enter their emotional data (e.g., "excited") through a questionnaire or a facial recognition camera. The server analyzes the emotional data using Microsoft Azure's emotion API or IBM Watson's emotion recognition API, and uses the results to adjust the content of the translated article and related media. For example, if positive emotional data is entered, brighter images and optimistic text will be added to the article.

[0381] Users can preview articles and related media translated into various languages ​​and with sentiment data reflected in the content on the system, and if there are no problems, they can issue a distribution command.

[0382] Finally, the server distributes the articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API, allowing the processed articles to be published on platforms in various countries and made accessible to readers.

[0383] As a concrete example, a user accesses the system using Google Chrome and logs in. They upload an article file called TechNews.txt. This file is analyzed using Python and spaCy and translated into English, French, and Spanish using the Google Translate API. The extracted SEO keyword "new technology" is then translated into each language and embedded in the article. The server uses DALL-E to generate technology-related images and link them to the translated article. The user inputs emotional data such as "excited," and the server analyzes the emotional data and adjusts the article and images accordingly. Once the user checks the preview and requests distribution, the server publishes the article via WordPress' XML-RPC API.

[0384] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0385] Step 1: Authenticate the user

[0386] Input: The user enters their authentication information (username and password) using a web browser.

[0387] Processing: The server receives the authentication information via Apache HTTP Server or Nginx and authenticates the user against a MySQL or PostgreSQL database.

[0388] Output: If authentication is successful, the user is granted access to the system.

[0389] Step 2: Upload your article

[0390] Input: The user selects an article file (e.g. TechNews.txt) from the terminal and clicks the upload button.

[0391] Processing: The server receives files uploaded via FastAPI or Django and stores them in cloud storage such as Amazon S3.

[0392] Output: Article files are securely stored on the server.

[0393] Step 3: Analyzing the article

[0394] Input: The server reads the saved article file.

[0395] Processing: The server uses Python and natural language processing libraries such as NLTK and spaCy to analyze the article content, for example by tokenizing the sentences and performing morphological analysis.

[0396] Output: The analysis results are converted to JSON format and saved in the database.

[0397] Step 4: Translate the article

[0398] Input: Parsed article content

[0399] Processing: The server calls the Google Translate API or Microsoft Translator API to translate the parsed content into multiple languages ​​(English, French, Spanish, etc.).

[0400] Output: The translated article is saved in the database.

[0401] Step 5: Extract and embed SEO keywords

[0402] Input: Original article content

[0403] Processing: The server uses libraries such as BeautifulSoup or Scrapy to extract SEO-friendly keywords, translates the extracted keywords into the target language, and embeds them appropriately in each translated article.

[0404] Output: The translated article with embedded SEO keywords is saved in the database.

[0405] Step 6: Generate related media

[0406] Input: Article content

[0407] Processing: The server uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content.

[0408] Output: The generated media files are linked to each translated article and stored in a database.

[0409] Step 7: Acquire and analyze emotion data

[0410] Input: The user inputs emotion data through a questionnaire or facial recognition camera.

[0411] Processing: The server analyzes the emotion data using Microsoft Azure's emotion API and IBM Watson's emotion recognition API.

[0412] Output: The analyzed emotion data is stored in a database.

[0413] Step 8: Reflecting emotional data

[0414] Input: Parsed sentiment data and translated article content

[0415] Processing: The server adjusts the content of the translated article and related media based on the sentiment data. For example, if there is positive sentiment data, it adds brighter colors and more positive expressions to the article.

[0416] Output: The adjusted articles and media are stored in a database.

[0417] Step 9: Preview your article

[0418] Input: Articles and related media translated into various languages ​​and updated with sentiment data

[0419] Processing: The user previews these contents on the system, visually checks them, and makes corrections if necessary.

[0420] Output: If the user is satisfied with the content, he / she issues a distribution instruction.

[0421] Step 10: Article Distribution

[0422] Input: Articles and related media for which distribution instructions have been issued

[0423] Processing: The server delivers articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API.

[0424] Output: The processed articles are published on national platforms and made accessible to readers.

[0425] (Application example 2)

[0426] 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."

[0427] Conventional content distribution systems required users to manually translate articles into multiple languages, implement SEO measures, and generate related media. Furthermore, there was a lack of technology to automatically generate and distribute content that reflected user sentiment. This made the article generation and distribution process time-consuming and labor-intensive, making it difficult to disseminate personalized information.

[0428] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for users to upload articles, means for the server to analyze the uploaded articles, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to generate related images and videos and link them to the articles, means for the server to acquire and analyze user emotion data, means for the server to adjust the content of the articles and related media based on the emotion data, and means for the server to distribute the processed articles to platforms in each country. This enables users to quickly generate and distribute content that is multilingual and reflects emotions.

[0429] A "user" is a person or entity that uploads articles to the system and issues previews and distribution instructions.

[0430] The "server" is a computer system that analyzes articles, translates them, implements SEO measures, generates media, acquires and analyzes emotional data, and adjusts the content, before distributing the articles to platforms in each country.

[0431] "Articles" refer to text content uploaded by users and are subject to translation into various languages.

[0432] "Analysis" is the process of understanding the content of the uploaded article and extracting the necessary information.

[0433] "Machine translation" is the process of mechanically converting analyzed articles into multiple target languages.

[0434] "SEO keywords" are specific important words or phrases used to rank articles in search engines.

[0435] "Related images and videos" are visual media files generated based on the article content and presented together with the article.

[0436] "Emotion data" is information that represents the user's emotional state, and is obtained through questionnaires or facial expression recognition.

[0437] A "platform" is an online medium or site that exists in each country and is the place where articles are distributed and published.

[0438] "Preview" refers to the display confirmation performed by the user as a final check of the article and related media.

[0439] An "emotion engine" is a software tool that analyzes acquired emotional data and adjusts content based on the results.

[0440] This invention is a system that significantly simplifies the user article creation process and efficiently delivers more personalized content by supporting multiple languages ​​and reflecting emotional data. This system allows users to upload articles and automatically performs each step of article analysis, translation, SEO measures, media generation, emotional data acquisition and analysis, content adjustment, and distribution.

[0441] Hardware and software used

[0442] Hardware: Smartphones, smart glasses, head-mounted displays, cloud servers

[0443] Software: Python, Google Cloud Translation API, Elasticsearch, AWS Rekognition, MySQL, WordPress CMS

[0444] User actions

[0445] Users log in to the system using their smartphones, smart glasses, or head-mounted displays to upload articles. When uploading, users can also provide their own emotional data, which can be done through a questionnaire or facial recognition using the smartphone camera.

[0446] Server operations

[0447] The server processes the uploaded articles and sentiment data through the following process:

[0448] 1. Receiving and saving articles

[0449] The server receives the uploaded article files and stores them in a MySQL database.

[0450] 2. Article analysis and translation

[0451] A Python script is used to run an NLP engine (natural language processing engine) to analyze the article content.

[0452] Use the Google Cloud Translation API to automatically translate articles into multiple target languages.

[0453] 3. SEO

[0454] Using Elasticsearch, we automatically extract keywords that are effective for SEO from the original Japanese article.

[0455] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[0456] 4. Generate related media

[0457] Use AWS Rekognition to generate relevant images and videos based on the article content.

[0458] The generated media files are linked to the corresponding translated articles and stored in the WordPress CMS.

[0459] 5. Acquiring and Reflecting Emotional Data

[0460] The emotion acquisition module is used to collect emotion data provided by users (survey results and facial expression recognition data).

[0461] The server sends this emotional data to the emotion engine and adjusts the content of the translated article and related media based on the analysis results.

[0462] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[0463] Article preview and distribution

[0464] The server provides the adjusted article to the user for preview, and once the user confirms the distribution instructions, the server distributes the adjusted article to platforms in each country and makes it public.

[0465] Examples of prompt statements

[0466] Example prompts to input to a generative AI model:

[0467] "This article talks about the introduction of innovative technology. Your SEO keywords are 'new technology,' 'innovation,' and 'introduction.' Use 'excitement' as your emotional data and write the article in a bright, optimistic tone."

[0468] In this way, users can create and distribute multilingual content efficiently and personalizedly.

[0469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0470] Step 1:

[0471] Users log in to the system using their smartphone, smart glasses, or head-mounted display. When logging in, authentication information is entered, which is received by the server and verified against information in a MySQL database. If authentication is successful, the user can proceed to the article upload screen.

[0472] Step 2:

[0473] The user selects an article file and uploads it to the system. The uploaded file is sent to the server, which receives it and stores it in a MySQL database. The input is the article file uploaded by the user, and the output is the article data stored in the database.

[0474] Step 3:

[0475] The server reads the article file and sends it to an NLP engine (natural language processing engine) using a Python script to analyze the article content. The analysis results include the article structure and key points of the content. The input is the saved article data, and the output is the analyzed article content.

[0476] Step 4:

[0477] Based on the analysis results, the server uses the Google Cloud Translation API to automatically translate the article into multiple target languages ​​(e.g., English, French, Spanish, etc.) The input is the analysis results, and the output is the article data translated into each target language.

[0478] Step 5:

[0479] The server uses Elasticsearch to automatically extract important SEO keywords from the original Japanese article. The extracted keywords are also translated into the target language and appropriately embedded in the translated article in each language. The input is the original article data and the translated article data, and the output is the translated article with SEO measures applied.

[0480] Step 6:

[0481] The server uses AWS Rekognition to automatically generate related images and videos based on the article content. The generated media files are linked to the corresponding translated article and saved in the WordPress CMS. The input is the translated article data, and the output is a media file containing related images and videos.

[0482] Step 7:

[0483] When uploading an article, users provide their own emotional data. This can be done through a questionnaire or facial recognition using a smartphone camera. The server acquires this emotional data and sends it to the emotion engine for analysis. The input is the user's emotional data, and the output is the analyzed emotional data.

[0484] Step 8:

[0485] The server adjusts the content of the translated article and related media based on the emotional data. For example, if positive emotional data is recognized, it will use a brighter or more optimistic tone for the article or media. The input is the analyzed emotional data and the translated article and media data, and the output is the adjusted content.

[0486] Step 9:

[0487] The server provides the adjusted article and media to the user for preview. The user checks the content and, if there are no problems, issues a distribution command. The input is the adjusted content, and the output is the user's distribution command.

[0488] Step 10:

[0489] The server follows the user's instructions and distributes the adjusted article to the relevant platforms in each country. The article is then published and made accessible to a diverse audience. The input is the distribution instructions and adjusted content, and the output is the article published on each platform in each country.

[0490] 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.

[0491] 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.

[0492] 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.

[0493] [Second embodiment]

[0494] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0495] 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.

[0496] 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).

[0497] 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.

[0498] 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.

[0499] 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).

[0500] 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.

[0501] 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.

[0502] 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.

[0503] 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.

[0504] In the smart glasses 214, 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.

[0505] 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."

[0506] This invention is a system for creating articles in multiple languages ​​and implementing SEO measures. In this system, users upload articles, and the server automatically translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media, ultimately distributing them to platforms in each country.

[0507] Program processing

[0508] 1. Initial Setup:

[0509] When a user logs into the system using a web browser, they enter their authentication information.

[0510] The server receives the authentication information sent by the user and performs authentication.

[0511] 2. Upload your article:

[0512] The user selects an article file written in Japanese and uploads it to the system.

[0513] The server receives the uploaded article files and stores them in an internal database.

[0514] 3. Article analysis and translation:

[0515] The server sends the uploaded article to a natural language processing engine (NLP engine) to analyze the article's content.

[0516] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[0517] Translated articles are stored on a server for each target language.

[0518] 4. SEO:

[0519] The server automatically extracts keywords necessary for SEO from the original Japanese article.

[0520] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[0521] 5. Media Generation:

[0522] The server automatically generates related images and videos based on the content of the article.

[0523] The generated media files are associated with the translated article and saved.

[0524] 6. Preview the article:

[0525] Users preview translated articles and auto-generated media on the system.

[0526] The user checks that there are no problems with the content and then issues a command to distribute it.

[0527] 7. Article Distribution:

[0528] The server delivers translated articles to platforms in each country according to the user's instructions.

[0529] Specific examples

[0530] 1. Initial Setup:

[0531] A user logs into the system and uploads the article file "NewTech.txt."

[0532] 2. Article analysis and translation:

[0533] The server receives "NewTech.txt" and performs text analysis.

[0534] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[0535] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[0536] 3. SEO:

[0537] The server extracts the SEO keyword "new technology" from the original Japanese article.

[0538] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[0539] 4. Media Generation:

[0540] The server automatically generates technical images related to the article content.

[0541] For example, create an image related to "introducing new technology" and link it to the article.

[0542] 5. Article Preview and Distribution:

[0543] Users can view articles and related media translated into each language on the system.

[0544] After confirmation, if you issue a distribution command, the server will distribute the article to platforms in each country.

[0545] In this way, by implementing the system of the present invention, users can quickly and effectively create and distribute articles in multiple languages, significantly reducing the man-hours and costs involved in language translation and facilitating the global dissemination of information.

[0546] The processing flow will be explained below.

[0547] Step 1: User logs into the system

[0548] The user opens a web browser and accesses the system's login page.

[0549] The user enters their authentication information (username and password) and clicks the "Login" button.

[0550] The server receives the authentication information entered and checks it against information in a database.

[0551] If the authentication is successful, the server displays the dashboard screen to the user.

[0552] Step 2: User uploads article file

[0553] The user clicks the "Upload article" button on the dashboard screen.

[0554] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[0555] The user clicks the "Upload" button.

[0556] The server receives the uploaded files and stores them in the system's storage.

[0557] Step 3: The server parses the article

[0558] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[0559] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[0560] Step 4: The server automatically translates the article into multiple languages

[0561] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[0562] Articles translated into each language are stored in a database on the server.

[0563] Step 5: The server extracts SEO keywords

[0564] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[0565] For example, detect keywords such as "new technology."

[0566] Step 6: The server translates the extracted keywords into each language and embeds them

[0567] The server translates the extracted keywords into keywords appropriate for the target language.

[0568] Translated keywords are embedded naturally into translated articles in each language.

[0569] Step 7: The server generates the relevant images and videos

[0570] The server automatically generates related images and videos based on the content of the article.

[0571] For example, create a technical image related to "introducing new technology."

[0572] Step 8: The server associates the generated media with the article

[0573] The server links the generated images and videos to the corresponding translated articles.

[0574] The media files are stored in a database on the server along with the articles.

[0575] Step 9: User Previews Article

[0576] Users can preview translated articles and related media in their language on the system.

[0577] The preview screen checks the accuracy of the content and the relevance of the media.

[0578] Step 10: User directs distribution

[0579] After checking the preview, the user clicks the "Distribute" button.

[0580] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[0581] Step 11: The server delivers the article

[0582] The server then sends the translated articles to pre-designated platforms in each country for publication.

[0583] Articles are published on each platform and become accessible to users.

[0584] Example 1

[0585] 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."

[0586] Currently, there are only a limited number of systems that can effectively generate multilingual articles and implement SEO measures. The automatic translation of articles into multiple languages ​​and the appropriate embedding of SEO keywords are particularly time-consuming. There is also a lack of technology to automatically generate related media files and link them to articles. This creates challenges for users, as it requires a lot of time, effort, and costs when distributing articles globally.

[0587] 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.

[0588] In this invention, the server includes means for users to upload articles using a computer terminal, means for the server to analyze the uploaded articles using a natural language processing engine, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to automatically generate related images and videos using a generative AI model and link them to the articles, and means for the server to distribute the processed articles to web platforms in each country. This enables users to quickly and effectively generate and distribute articles in multiple languages, significantly reducing the labor and cost of language translation and facilitating global information dissemination.

[0589] "User" means an individual or legal entity that uses the System to generate, translate, and distribute articles.

[0590] A "computer terminal" is a device that allows a user to access and operate the system, and includes, for example, a personal computer, a smartphone, a tablet, etc.

[0591] The "server" is a central processing unit that processes the entire system, receiving articles, analyzing them, translating them, generating media, and distributing them.

[0592] A "natural language processing engine" is software or a system that analyzes the content of articles and performs grammatical analysis and keyword extraction.

[0593] "Translation API" means an external service or interface that a server uses to automatically translate articles into multiple languages.

[0594] "SEO keywords" are important keywords for search engine optimization (SEO), and are words that are embedded in articles to help them appear higher in search engines.

[0595] A "generative AI model" is an artificial intelligence model that automatically generates related images and videos based on the content of an article.

[0596] "Web platform" refers to the online services and media to which articles are distributed, including, for example, blog sites, news portals, and social media.

[0597] In this way, the above definitions can be used to make the claims more specific and clear.

[0598] This invention is a system in which users upload articles, the server automatically translates them into multiple languages, extracts and embeds SEO keywords, generates and links related media, and finally distributes them to web platforms in each country. This system is implemented using the following steps and components:

[0599] First, a user accesses the system using a web browser. The user enters their authentication information on the login screen and logs into the system. The authentication information is received by the server and compared with the information stored in the internal database. If this authentication is successful, the user is redirected to the dashboard screen.

[0600] Next, the user selects an article file written in Japanese and clicks the upload button. The device sends the selected file to the server, which then verifies the received file. Once verification is complete, the file is saved in the internal database.

[0601] The server then sends the saved article file to a natural language processing engine (NLP engine). The NLP engine performs grammatical analysis and keyword extraction, and returns the analysis results to the server. Based on these analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, and Spanish). A common translation API is used for the translation.

[0602] For translated articles, the server automatically extracts SEO keywords, translates them into the target language, and embeds them. Extracted keywords are inserted into each article in a natural context to minimize unnecessary manual work.

[0603] In addition, the server uses a generative AI model to automatically generate images and videos related to the article content. For example, if there is an article titled "Introduction of New Technology," technology-related images will be automatically generated by the generative AI model. These media files are linked to the translated article and stored in an internal database.

[0604] Users can preview articles and related media translated into each language from the system's dashboard. After confirming that there are no problems with the content, they issue a distribution command, and the server distributes the article to each country's web platform. This uses each platform's API to post the article and media files appropriately.

[0605] Examples and prompts

[0606] 1. Upload your article:

[0607] A user logs into the system and uploads the article file "NewTech.txt."

[0608] 2. Article analysis and translation:

[0609] The server receives "NewTech.txt" and performs text analysis.

[0610] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[0611] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[0612] 3. SEO:

[0613] The server extracts the SEO keyword "new technology" from Japanese articles.

[0614] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[0615] 4. Media Generation:

[0616] The server automatically generates technical images related to the article content.

[0617] For example, create an image related to "introducing new technology" and link it to the article.

[0618] Example prompt sentence:

[0619] "Write an article in Japanese announcing the introduction of a new technology. Also, translate this article into English, French, and Spanish, embedding appropriate SEO keywords in each language article and generating relevant images."

[0620] Using this system, users can quickly and efficiently create and distribute articles in multiple languages, significantly reducing the effort and cost of language translation and making it easier to disseminate information globally.

[0621] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0622] Step 1:

[0623] Initial Setup

[0624] A user accesses the system using a web browser and enters authentication information (username and password) on the login screen.

[0625] Input: Username, Password

[0626] The server receives the entered authentication information, checks it against the correct authentication information stored in its internal database, and if authentication is successful, displays the dashboard screen to the user.

[0627] Output: Login success / failure message, dashboard screen or error message

[0628] Step 2:

[0629] Article Upload

[0630] The user selects the Japanese article file from the dashboard screen and clicks the "Upload" button.

[0631] Input: Article file (e.g. NewTech.txt)

[0632] The terminal sends the selected file to the server, which then verifies the file, including checking the file format and virus checks.

[0633] The server stores the verified files in an internal database.

[0634] Output: File save success / failure message

[0635] Step 3:

[0636] Article analysis and translation

[0637] The server sends article files stored in an internal database to a natural language processing engine (NLP engine) to analyze the content.

[0638] Input: Article file (e.g. NewTech.txt)

[0639] The server extracts the article content from the analysis results and automatically translates it into multiple target languages. The translation process uses an external translation API (e.g., a general translation API).

[0640] Output: Translated article (English, French, Spanish, etc.)

[0641] Step 4:

[0642] SEO measures

[0643] The server uses a natural language processing engine to extract SEO keywords from the original article.

[0644] Input: Original article (e.g. "We introduced new technology")

[0645] The server translates the extracted keywords into multiple target languages.

[0646] The server embeds the translated keywords naturally into the translated articles in each target language.

[0647] Output: SEO-optimized translated article

[0648] Step 5:

[0649] Media Generation

[0650] The server uses a generative AI model to automatically generate relevant images and videos based on the article's content.

[0651] Input: Article content (e.g., "Introduction of new technology")

[0652] The server associates the automatically generated media files (images, videos) with the translated articles and stores them in a database.

[0653] Output: Translated articles with related media

[0654] Step 6:

[0655] Article Preview

[0656] Users preview translated articles and auto-generated media on the system.

[0657] Input: Preview request

[0658] The server generates a temporary preview and displays it to the user, who can then view each language version of the article and its associated media.

[0659] Output: Preview screen, user requests for corrections or confirmation

[0660] Step 7:

[0661] Article distribution

[0662] The user checks the preview content and clicks the "Distribute" button.

[0663] Input: Delivery instructions

[0664] The server distributes the translated articles to web platforms in each country using their respective APIs (e.g. blog site API, news portal API).

[0665] Output: Articles distributed to each country's web platform, distribution success / failure message

[0666] (Application example 1)

[0667] 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."

[0668] While existing multilingual article generation and SEO systems allow users to easily translate and distribute articles, they do not support real-time visual recognition-based advertisement generation and display. Furthermore, they lack the ability to instantly generate multilingual advertising content and overlay it on visual devices. There is a particular need for a method to improve the efficiency of inbound marketing in tourist destinations and shopping malls.

[0669] 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.

[0670] In this invention, the server includes: means for users to upload articles; means for the server to analyze the uploaded articles; means for the server to automatically translate the analyzed articles into multiple languages; means for the server to extract and embed SEO keywords for the translated articles; means for the server to generate related images and videos and link them to the articles; means for the server to distribute the processed articles to platforms in various countries; means for users to detect visual targets using a content browsing device and automatically generate advertising content based on the targets; means for the server to translate the generated advertising content into multiple languages ​​and apply SEO measures; and means for users to check the translated advertising content on the content browsing device and draw it in a specified visual area. This enables users to generate and display multilingual advertisements in real time based on visual recognition, significantly improving the efficiency of inbound marketing.

[0671] "User" means any entity, including individuals or corporations, that uses this system to upload articles and generate, review, and distribute content.

[0672] "Article" means a text document containing information that can be uploaded, analyzed, translated, search engine optimized, and associated with related media by the server.

[0673] "Uploading" refers to the act of a user transferring their own digital data to a server.

[0674] "Analysis" is the process by which the server uses a natural language processing engine to understand the content of the uploaded article and extract information.

[0675] "Translation" is a server function that converts analyzed articles into multiple target languages.

[0676] "SEO keywords" are specific words or phrases that are embedded in articles for search engine optimization.

[0677] "Media" refers to visual and audio supplementary information such as images and videos related to the content of the article.

[0678] A "viewed object" is an object or scene that a user visually recognizes through a content browsing device.

[0679] "Advertising content" refers to promotional text and multimedia material that is automatically generated based on the viewed object.

[0680] A "content viewing device" is a device such as smart glasses or a head-mounted display worn or used by a user, which overlays advertising content in the visual field.

[0681] "Overlay display" is a technique for displaying additional information overlaid on top of existing visual information.

[0682] "Distribution" refers to the act of delivering processed articles and advertising content to platforms in each country via the Internet.

[0683] A "natural language processing engine" is a type of software that the server uses to understand the content of an article and extract and translate the appropriate information.

[0684] In order to put the present invention into practice, the following specific system is constructed.

[0685] The server analyzes articles uploaded by users, translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media.It also has the function of automatically generating advertising content in real time based on the objects the user sees using their visual device, translating and implementing SEO measures, and overlaying it in the visual area.

[0686] Specifically, the server does the following:

[0687] 1. User authentication and article upload: A user logs into the system via a web browser and uploads an article file. The server processes the authentication information and stores the uploaded article in an internal database.

[0688] 2. Natural language processing and translation: The server uses an internal natural language processing engine (e.g., nltk, spaCy) to analyze the content of the uploaded article and automatically translate it into multiple target languages ​​(e.g., English, French, Spanish, etc.). This can be done using the Google Translate API, etc.

[0689] 3. Extracting and embedding SEO keywords: Automatically extract keywords necessary for SEO from the original article, translate them into the target language, and embed them appropriately in the article in each language.

[0690] 4. Related Media Generation: The server automatically generates related images and videos based on the article content and links them to the article. This can be done using a generative AI model (e.g., DALL-E, Stable Diffusion).

[0691] 5. Real-time ad generation: When a user wears smart glasses or a head-mounted display, the device uses a visual recognition engine (e.g., OpenCV, Google Cloud Vision API) to detect the object being viewed. Based on the detected object, ad content is automatically generated, translated, and optimized for SEO.

[0692] Through these steps, users can efficiently deliver multilingual articles and real-time generated advertisements. A specific example of use is when a user wearing smart glasses sees a cafe in a tourist spot, multilingual advertisement content based on that cafe is displayed in front of the user's eyes.

[0693] Prompt Sentence Examples

[0694] Please explain the structure of the object-based real-time multilingual advertisement generation system. Please explain in detail how it uses Google Cloud Vision API to detect the visual object, retrieves relevant advertisements from the advertisement database, performs multilingual translation using Google Trans, and displays the advertisements on smart glasses.

[0695] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0696] Step 1:

[0697] A user logs in to the system through a web browser and uploads an article file. The server receives the authentication information and authenticates the user. If authentication is successful, the uploaded article file is stored in the internal database.

[0698] Input: User credentials, article file

[0699] Output: Articles stored in the internal database

[0700] Step 2:

[0701] The server sends the uploaded article to a natural language processing engine, which analyzes the article's content, including its sentence structure, topic, and important keywords.

[0702] Input: Articles stored in the internal database

[0703] Output: Analyzed article content (topics, keywords, etc.)

[0704] Step 3:

[0705] Based on the analysis results, the server automatically translates the article into multiple target languages ​​using a translation engine (e.g., Google Translate API). The translated articles are stored in an internal database for each language.

[0706] Input: Parsed article content, list of target languages

[0707] Output: Article translated into multiple languages

[0708] Step 4:

[0709] The server automatically extracts keywords necessary for SEO from the original Japanese article, translates the extracted keywords into the target language, and embeds them appropriately in the translated article in each language.

[0710] Input: Japanese article, list of target languages

[0711] Output: Translated articles with embedded SEO keywords

[0712] Step 5:

[0713] The server generates relevant images and videos based on the article content, automatically generating media using generative AI models (e.g., DALL-E, Stable Diffusion), and connecting them to translated articles in each language.

[0714] Input: Translation article content

[0715] Output: Related media (images, videos)

[0716] Step 6:

[0717] The user wears smart glasses or a head-mounted display, and the device detects the visual object. The device then identifies the object using a visual recognition engine (e.g., Google Cloud Vision API).

[0718] Input: Visual information captured on the device

[0719] Output: Detected objects

[0720] Step 7:

[0721] The server automatically generates advertising content based on the detected objects, retrieving relevant promotional text and multimedia materials from an advertising database and customizing them with a generative AI model.

[0722] Input: Detected object

[0723] Output: Generated ad content

[0724] Step 8:

[0725] The server translates the generated advertising content into multiple target languages ​​and implements SEO measures. It translates into multiple languages ​​using a translation engine and embeds SEO keywords.

[0726] Input: Generated ad content, list of target languages

[0727] Output: Translated ad content

[0728] Step 9:

[0729] The user checks the translated advertising content on the content viewing device, and the terminal overlays it in the designated visual area, where the advertising content is displayed together with the user's visual information.

[0730] Input: translated ad content

[0731] Output: Overlaid ad content

[0732] 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.

[0733] This invention is a system that generates articles in multiple languages, implements SEO measures, and recognizes user emotions and reflects them in articles and related media. In this system, users upload articles, and the server automatically analyzes and translates the articles, extracts and embeds SEO keywords, generates related media, and adjusts the content based on user emotion data before distributing it to platforms in each country.

[0734] Program processing

[0735] 1. Initial Setup:

[0736] A user logs into the system using a web browser and enters their authentication information.

[0737] The server receives the entered authentication information and performs authentication by comparing it with information in a database.

[0738] 2. Upload your article:

[0739] The user selects an article file written in Japanese and uploads it to the system.

[0740] The server receives the uploaded files and stores them in an internal database.

[0741] 3. Article analysis and translation:

[0742] The server reads the saved article file, sends it to a natural language processing engine (NLP engine), and analyzes the article content.

[0743] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[0744] The translated articles are stored on a server for each target language.

[0745] 4. SEO:

[0746] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[0747] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[0748] 5. Media Generation:

[0749] The server automatically generates related images and videos based on the article content.

[0750] The generated media files are saved and linked to the corresponding translated article.

[0751] 6. Acquiring and analyzing emotion data:

[0752] Users enter their emotional data when uploading articles, which can be done using a simple questionnaire or facial expression recognition, for example.

[0753] The server sends the acquired emotion data to the emotion engine for analysis.

[0754] 7. Reflecting emotional data:

[0755] The server adjusts the content of translated articles and related media based on the analyzed emotional data.

[0756] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[0757] 8. Article Preview:

[0758] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[0759] The user checks that there are no problems with the content and then issues a command to distribute it.

[0760] 9. Article Distribution:

[0761] The server follows the user's instructions and distributes the article to relevant platforms in each country.

[0762] Articles will be published on each platform, making them accessible to a diverse audience.

[0763] Specific examples

[0764] 1. Initial Setup:

[0765] A user logs into the system and uploads an article file called "TechNews.txt".

[0766] 2. Article analysis and translation:

[0767] The server reads "TechNews.txt" and the NLP engine analyzes the article content.

[0768] The article "We have introduced new technology" is translated into English "We have introduced new technology", French "Nous avons introduit une nouvelle technologie" and Spanish "Hemos introducido nueva tecnología".

[0769] 3. SEO:

[0770] The server extracts the SEO keyword "new technology," translates it into each target language, and embeds it in the article.

[0771] 4. Media Generation:

[0772] The server generates images related to the article content and links them to each translated article.

[0773] 5. Acquiring and analyzing emotion data:

[0774] A user enters emotional data such as "excited" in a survey.

[0775] The server sends this emotional data to the emotion engine, and adjusts media and articles based on the analysis results.

[0776] 6. Preview and distribute your article:

[0777] The user checks the preview and instructs distribution.

[0778] The server distributes the adjusted articles to platforms in each country and makes them public.

[0779] This system allows users to quickly generate and distribute multilingual articles that reflect emotional data, enabling more personalized and effective information dissemination to readers.

[0780] The processing flow will be explained below.

[0781] Step 1: User logs into the system

[0782] A user accesses the system's login page using a web browser.

[0783] The user enters their authentication information (username and password) and clicks the "Login" button.

[0784] The server receives the entered authentication information and performs authentication by comparing it with information in its internal database.

[0785] If the authentication is successful, the server displays the dashboard screen to the user.

[0786] Step 2: User uploads article file

[0787] The user clicks the "Upload article" button on the dashboard screen.

[0788] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[0789] The user clicks the "Upload" button.

[0790] The server receives the uploaded files and stores them in an internal database.

[0791] Step 3: The server retrieves the emotion data

[0792] Users enter their emotional data using a simple questionnaire or a facial expression recognition system.

[0793] For example, the user inputs the emotion "excited."

[0794] The server receives the emotion data and sends it to the emotion engine.

[0795] Step 4: The server parses the article

[0796] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[0797] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[0798] Step 5: The server automatically translates the article into multiple languages

[0799] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[0800] Articles translated into each language are stored in a database on the server.

[0801] Step 6: The server extracts and embeds SEO keywords

[0802] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[0803] For example, extract the keyword "new technology."

[0804] The server translates this into the target language and embeds it in a natural way into the translated article in each language.

[0805] Step 7: The server generates the relevant images and videos

[0806] The server automatically generates related images and videos based on the content of the article.

[0807] For example, create an image related to "introduction of new technology."

[0808] Step 8: The server adjusts the media and article content based on the sentiment data.

[0809] The server receives the analysis results from the emotion engine and adjusts the content of translated articles and related media.

[0810] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[0811] Step 9: Server associates generated media with article

[0812] The server links the generated images and videos to the corresponding translated articles.

[0813] The media files are stored in a database on the server along with the articles.

[0814] Step 10: User sees article preview

[0815] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[0816] The preview screen checks the accuracy of the content, the relevance of the media, and the effectiveness of reflecting emotions.

[0817] Step 11: User directs distribution

[0818] After checking the preview, the user clicks the "Distribute" button.

[0819] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[0820] Step 12: The server delivers the article

[0821] The server then sends the translated articles to pre-designated platforms in each country for publication.

[0822] Articles are published on each platform and become accessible to users.

[0823] Example 2

[0824] 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."

[0825] Conventional multilingual article generation systems have difficulty reflecting user sentiment data in addition to article translation and SEO measures, resulting in insufficient and effective personalization. Furthermore, there is a need to streamline the overall processing flow, including improving translation accuracy and adding features such as automatic generation of related media.

[0826] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0827] In this invention, the server includes: a means for a user to log in to the system using authentication information; a means for the user to upload articles; a means for the server to save the uploaded articles; a means for the server to analyze the articles using a natural language processing engine; a means for the server to automatically translate the analyzed articles into multiple languages; a means for the server to save the translated articles; a means for the server to extract SEO keywords and embed them in the translated articles; a means for the server to generate images and videos based on the article content; a means for the server to link related images and videos to the articles; a means for the user to input emotional data; a means for the server to analyze the emotional data and adjust the translated articles and related media; and a means for the server to distribute the processed articles to platforms in each country. This enables efficient generation of multilingual articles that reflect user emotional data, SEO measures, and the automatic generation and distribution of related media.

[0828] "User" means any person or entity that accesses the System and uploads and manipulates Articles.

[0829] "Authentication information" refers to information such as a username and password used by a user to log in to a system.

[0830] "System" refers to a platform where users can upload articles and have them translated, search engine optimized, media generated, and sentiment data reflected.

[0831] "Server" refers to a computing device that handles the overall processing of the system and is responsible for data storage, analysis, translation, media generation, and delivery.

[0832] A "natural language processing engine" refers to software technology that analyzes text data and performs semantic understanding and translation.

[0833] "Analysis" refers to the process of breaking down the content of an uploaded article and understanding its meaning and grammatical structure.

[0834] "Translation" refers to the process of converting the content of the analyzed article into another language.

[0835] "SEO keywords" refers to embedding specific words or phrases within an article for search engine optimization.

[0836] "Generating images and videos" refers to automatically creating relevant visual content based on article content.

[0837] "Emotional data" refers to the emotional feedback and reactions to articles entered by users.

[0838] "Parse and translate" refers to the process of using a natural language processing engine to understand article content and translate it into multiple languages.

[0839] "Platform" refers to the website or service on which articles are published, and the medium through which users provide information to a diverse audience.

[0840] This invention relates to a system that generates and distributes articles and related media in multiple languages, reflecting user emotional data, in addition to providing SEO support. This system is realized through the cooperation of users, terminals, and a server.

[0841] A user logs into a system using a web browser (e.g., Google Chrome), enters authentication information (username and password), and the server receives the information using Apache HTTP Server or Nginx and authenticates the user by checking it against a MySQL or PostgreSQL database.

[0842] After logging in, the user selects an article file written in Japanese (e.g., "TechNews.txt") and uploads it to the system. The server receives the uploaded article file via FastAPI or the Django framework and stores it in cloud storage such as Amazon S3.

[0843] The server then analyzes the article content using Python and natural language processing libraries such as NLTK and spaCy. The analysis results are saved in JSON format. The server then uses the Google Translate API and Microsoft Translator API to automatically translate the analyzed article into multiple languages. The translation results are also saved in a database on the server.

[0844] The server uses libraries like BeautifulSoup or Scrapy to extract SEO-friendly keywords from the original article, which are then translated into the target language and embedded appropriately into each translated article.

[0845] The server also uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content, and the generated media files are saved and linked to each translated article.

[0846] When uploading an article, users enter their emotional data (e.g., "excited") through a questionnaire or a facial recognition camera. The server analyzes the emotional data using Microsoft Azure's emotion API or IBM Watson's emotion recognition API, and uses the results to adjust the content of the translated article and related media. For example, if positive emotional data is entered, brighter images and optimistic text will be added to the article.

[0847] Users can preview articles and related media translated into various languages ​​and with sentiment data reflected in the content on the system, and if there are no problems, they can issue a distribution command.

[0848] Finally, the server distributes the articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API, allowing the processed articles to be published on platforms in various countries and made accessible to readers.

[0849] As a concrete example, a user accesses the system using Google Chrome and logs in. They upload an article file called TechNews.txt. This file is analyzed using Python and spaCy and translated into English, French, and Spanish using the Google Translate API. The extracted SEO keyword "new technology" is then translated into each language and embedded in the article. The server uses DALL-E to generate technology-related images and link them to the translated article. The user inputs emotional data such as "excited," and the server analyzes the emotional data and adjusts the article and images accordingly. Once the user checks the preview and requests distribution, the server publishes the article via WordPress' XML-RPC API.

[0850] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0851] Step 1: Authenticate the user

[0852] Input: The user enters their authentication information (username and password) using a web browser.

[0853] Processing: The server receives the authentication information via Apache HTTP Server or Nginx and authenticates the user against a MySQL or PostgreSQL database.

[0854] Output: If authentication is successful, the user is granted access to the system.

[0855] Step 2: Upload your article

[0856] Input: The user selects an article file (e.g. TechNews.txt) from the terminal and clicks the upload button.

[0857] Processing: The server receives files uploaded via FastAPI or Django and stores them in cloud storage such as Amazon S3.

[0858] Output: Article files are securely stored on the server.

[0859] Step 3: Analyzing the article

[0860] Input: The server reads the saved article file.

[0861] Processing: The server uses Python and natural language processing libraries such as NLTK and spaCy to analyze the article content, for example by tokenizing the sentences and performing morphological analysis.

[0862] Output: The analysis results are converted to JSON format and saved in the database.

[0863] Step 4: Translate the article

[0864] Input: Parsed article content

[0865] Processing: The server calls the Google Translate API or Microsoft Translator API to translate the parsed content into multiple languages ​​(English, French, Spanish, etc.).

[0866] Output: The translated article is saved in the database.

[0867] Step 5: Extract and embed SEO keywords

[0868] Input: Original article content

[0869] Processing: The server uses libraries such as BeautifulSoup or Scrapy to extract SEO-friendly keywords, translates the extracted keywords into the target language, and embeds them appropriately in each translated article.

[0870] Output: The translated article with embedded SEO keywords is saved in the database.

[0871] Step 6: Generate related media

[0872] Input: Article content

[0873] Processing: The server uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content.

[0874] Output: The generated media files are linked to each translated article and stored in a database.

[0875] Step 7: Acquire and analyze emotion data

[0876] Input: The user inputs emotion data through a questionnaire or facial recognition camera.

[0877] Processing: The server analyzes the emotion data using Microsoft Azure's emotion API and IBM Watson's emotion recognition API.

[0878] Output: The analyzed emotion data is stored in a database.

[0879] Step 8: Reflecting emotional data

[0880] Input: Parsed sentiment data and translated article content

[0881] Processing: The server adjusts the content of the translated article and related media based on the sentiment data. For example, if there is positive sentiment data, it adds brighter colors and more positive expressions to the article.

[0882] Output: The adjusted articles and media are stored in a database.

[0883] Step 9: Preview your article

[0884] Input: Articles and related media translated into various languages ​​and updated with sentiment data

[0885] Processing: The user previews these contents on the system, visually checks them, and makes corrections if necessary.

[0886] Output: If the user is satisfied with the content, he / she issues a distribution instruction.

[0887] Step 10: Article Distribution

[0888] Input: Articles and related media for which distribution instructions have been issued

[0889] Processing: The server delivers articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API.

[0890] Output: The processed articles are published on national platforms and made accessible to readers.

[0891] (Application example 2)

[0892] 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."

[0893] Conventional content distribution systems required users to manually translate articles into multiple languages, implement SEO measures, and generate related media. Furthermore, there was a lack of technology to automatically generate and distribute content that reflected user sentiment. This made the article generation and distribution process time-consuming and labor-intensive, making it difficult to disseminate personalized information.

[0894] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for users to upload articles, means for the server to analyze the uploaded articles, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to generate related images and videos and link them to the articles, means for the server to acquire and analyze user emotion data, means for the server to adjust the content of the articles and related media based on the emotion data, and means for the server to distribute the processed articles to platforms in each country. This enables users to quickly generate and distribute content that is multilingual and reflects emotions.

[0895] A "user" is a person or entity that uploads articles to the system and issues previews and distribution instructions.

[0896] The "server" is a computer system that analyzes articles, translates them, implements SEO measures, generates media, acquires and analyzes emotional data, and adjusts the content, before distributing the articles to platforms in each country.

[0897] "Articles" refer to text content uploaded by users and are subject to translation into various languages.

[0898] "Analysis" is the process of understanding the content of the uploaded article and extracting the necessary information.

[0899] "Machine translation" is the process of mechanically converting analyzed articles into multiple target languages.

[0900] "SEO keywords" are specific important words or phrases used to rank articles in search engines.

[0901] "Related images and videos" are visual media files generated based on the article content and presented together with the article.

[0902] "Emotion data" is information that represents the user's emotional state, and is obtained through questionnaires or facial expression recognition.

[0903] A "platform" is an online medium or site that exists in each country and is the place where articles are distributed and published.

[0904] "Preview" refers to the display confirmation performed by the user as a final check of the article and related media.

[0905] An "emotion engine" is a software tool that analyzes acquired emotional data and adjusts content based on the results.

[0906] This invention is a system that significantly simplifies the user article creation process and efficiently delivers more personalized content by supporting multiple languages ​​and reflecting emotional data. This system allows users to upload articles and automatically performs each step of article analysis, translation, SEO measures, media generation, emotional data acquisition and analysis, content adjustment, and distribution.

[0907] Hardware and software used

[0908] Hardware: Smartphones, smart glasses, head-mounted displays, cloud servers

[0909] Software: Python, Google Cloud Translation API, Elasticsearch, AWS Rekognition, MySQL, WordPress CMS

[0910] User actions

[0911] Users log in to the system using their smartphones, smart glasses, or head-mounted displays to upload articles. When uploading, users can also provide their own emotional data, which can be done through a questionnaire or facial recognition using the smartphone camera.

[0912] Server operations

[0913] The server processes the uploaded articles and sentiment data through the following process:

[0914] 1. Receiving and saving articles

[0915] The server receives the uploaded article files and stores them in a MySQL database.

[0916] 2. Article analysis and translation

[0917] A Python script is used to run an NLP engine (natural language processing engine) to analyze the article content.

[0918] Use the Google Cloud Translation API to automatically translate articles into multiple target languages.

[0919] 3. SEO

[0920] Using Elasticsearch, we automatically extract keywords that are effective for SEO from the original Japanese article.

[0921] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[0922] 4. Generate related media

[0923] Use AWS Rekognition to generate relevant images and videos based on the article content.

[0924] The generated media files are linked to the corresponding translated articles and stored in the WordPress CMS.

[0925] 5. Acquiring and Reflecting Emotional Data

[0926] The emotion acquisition module is used to collect emotion data provided by users (survey results and facial expression recognition data).

[0927] The server sends this emotional data to the emotion engine and adjusts the content of the translated article and related media based on the analysis results.

[0928] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[0929] Article preview and distribution

[0930] The server provides the adjusted article to the user for preview, and once the user confirms the distribution instructions, the server distributes the adjusted article to platforms in each country and makes it public.

[0931] Examples of prompt statements

[0932] Example prompts to input to a generative AI model:

[0933] "This article talks about the introduction of innovative technology. Your SEO keywords are 'new technology,' 'innovation,' and 'introduction.' Use 'excitement' as your emotional data and write the article in a bright, optimistic tone."

[0934] In this way, users can create and distribute multilingual content efficiently and personalizedly.

[0935] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0936] Step 1:

[0937] Users log in to the system using their smartphone, smart glasses, or head-mounted display. When logging in, authentication information is entered, which is received by the server and verified against information in a MySQL database. If authentication is successful, the user can proceed to the article upload screen.

[0938] Step 2:

[0939] The user selects an article file and uploads it to the system. The uploaded file is sent to the server, which receives it and stores it in a MySQL database. The input is the article file uploaded by the user, and the output is the article data stored in the database.

[0940] Step 3:

[0941] The server reads the article file and sends it to an NLP engine (natural language processing engine) using a Python script to analyze the article content. The analysis results include the article structure and key points of the content. The input is the saved article data, and the output is the analyzed article content.

[0942] Step 4:

[0943] Based on the analysis results, the server uses the Google Cloud Translation API to automatically translate the article into multiple target languages ​​(e.g., English, French, Spanish, etc.) The input is the analysis results, and the output is the article data translated into each target language.

[0944] Step 5:

[0945] The server uses Elasticsearch to automatically extract important SEO keywords from the original Japanese article. The extracted keywords are also translated into the target language and appropriately embedded in the translated article in each language. The input is the original article data and the translated article data, and the output is the translated article with SEO measures applied.

[0946] Step 6:

[0947] The server uses AWS Rekognition to automatically generate related images and videos based on the article content. The generated media files are linked to the corresponding translated article and saved in the WordPress CMS. The input is the translated article data, and the output is a media file containing related images and videos.

[0948] Step 7:

[0949] When uploading an article, users provide their own emotional data. This can be done through a questionnaire or facial recognition using a smartphone camera. The server acquires this emotional data and sends it to the emotion engine for analysis. The input is the user's emotional data, and the output is the analyzed emotional data.

[0950] Step 8:

[0951] The server adjusts the content of the translated article and related media based on the emotional data. For example, if positive emotional data is recognized, it will use a brighter or more optimistic tone for the article or media. The input is the analyzed emotional data and the translated article and media data, and the output is the adjusted content.

[0952] Step 9:

[0953] The server provides the adjusted article and media to the user for preview. The user checks the content and, if there are no problems, issues a distribution command. The input is the adjusted content, and the output is the user's distribution command.

[0954] Step 10:

[0955] The server follows the user's instructions and distributes the adjusted article to the relevant platforms in each country. The article is then published and made accessible to a diverse audience. The input is the distribution instructions and adjusted content, and the output is the article published on each platform in each country.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] [Third embodiment]

[0960] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0961] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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).

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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."

[0972] This invention is a system for creating articles in multiple languages ​​and implementing SEO measures. In this system, users upload articles, and the server automatically translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media, ultimately distributing them to platforms in each country.

[0973] Program processing

[0974] 1. Initial Setup:

[0975] When a user logs into the system using a web browser, they enter their authentication information.

[0976] The server receives the authentication information sent by the user and performs authentication.

[0977] 2. Upload your article:

[0978] The user selects an article file written in Japanese and uploads it to the system.

[0979] The server receives the uploaded article files and stores them in an internal database.

[0980] 3. Article analysis and translation:

[0981] The server sends the uploaded article to a natural language processing engine (NLP engine) to analyze the article's content.

[0982] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[0983] Translated articles are stored on a server for each target language.

[0984] 4. SEO:

[0985] The server automatically extracts keywords necessary for SEO from the original Japanese article.

[0986] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[0987] 5. Media Generation:

[0988] The server automatically generates related images and videos based on the content of the article.

[0989] The generated media files are associated with the translated article and saved.

[0990] 6. Preview the article:

[0991] Users preview translated articles and auto-generated media on the system.

[0992] The user checks that there are no problems with the content and then issues a command to distribute it.

[0993] 7. Article Distribution:

[0994] The server delivers translated articles to platforms in each country according to the user's instructions.

[0995] Specific examples

[0996] 1. Initial Setup:

[0997] A user logs into the system and uploads the article file "NewTech.txt."

[0998] 2. Article analysis and translation:

[0999] The server receives "NewTech.txt" and performs text analysis.

[1000] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[1001] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[1002] 3. SEO:

[1003] The server extracts the SEO keyword "new technology" from the original Japanese article.

[1004] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[1005] 4. Media Generation:

[1006] The server automatically generates technical images related to the article content.

[1007] For example, create an image related to "introducing new technology" and link it to the article.

[1008] 5. Article Preview and Distribution:

[1009] Users can view articles and related media translated into each language on the system.

[1010] After confirmation, if you issue a distribution command, the server will distribute the article to platforms in each country.

[1011] In this way, by implementing the system of the present invention, users can quickly and effectively create and distribute articles in multiple languages, significantly reducing the man-hours and costs involved in language translation and facilitating the global dissemination of information.

[1012] The processing flow will be explained below.

[1013] Step 1: User logs into the system

[1014] The user opens a web browser and accesses the system's login page.

[1015] The user enters their authentication information (username and password) and clicks the "Login" button.

[1016] The server receives the authentication information entered and checks it against information in a database.

[1017] If the authentication is successful, the server displays the dashboard screen to the user.

[1018] Step 2: User uploads article file

[1019] The user clicks the "Upload article" button on the dashboard screen.

[1020] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[1021] The user clicks the "Upload" button.

[1022] The server receives the uploaded files and stores them in the system's storage.

[1023] Step 3: The server parses the article

[1024] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[1025] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[1026] Step 4: The server automatically translates the article into multiple languages

[1027] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[1028] Articles translated into each language are stored in a database on the server.

[1029] Step 5: The server extracts SEO keywords

[1030] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[1031] For example, detect keywords such as "new technology."

[1032] Step 6: The server translates the extracted keywords into each language and embeds them

[1033] The server translates the extracted keywords into keywords appropriate for the target language.

[1034] Translated keywords are embedded naturally into translated articles in each language.

[1035] Step 7: The server generates the relevant images and videos

[1036] The server automatically generates related images and videos based on the content of the article.

[1037] For example, create a technical image related to "introducing new technology."

[1038] Step 8: The server associates the generated media with the article

[1039] The server links the generated images and videos to the corresponding translated articles.

[1040] The media files are stored in a database on the server along with the articles.

[1041] Step 9: User Previews Article

[1042] Users can preview translated articles and related media in their language on the system.

[1043] The preview screen checks the accuracy of the content and the relevance of the media.

[1044] Step 10: User directs distribution

[1045] After checking the preview, the user clicks the "Distribute" button.

[1046] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[1047] Step 11: The server delivers the article

[1048] The server then sends the translated articles to pre-designated platforms in each country for publication.

[1049] Articles are published on each platform and become accessible to users.

[1050] Example 1

[1051] 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."

[1052] Currently, there are only a limited number of systems that can effectively generate multilingual articles and implement SEO measures. The automatic translation of articles into multiple languages ​​and the appropriate embedding of SEO keywords are particularly time-consuming. There is also a lack of technology to automatically generate related media files and link them to articles. This creates challenges for users, as it requires a lot of time, effort, and costs when distributing articles globally.

[1053] 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.

[1054] In this invention, the server includes means for users to upload articles using a computer terminal, means for the server to analyze the uploaded articles using a natural language processing engine, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to automatically generate related images and videos using a generative AI model and link them to the articles, and means for the server to distribute the processed articles to web platforms in each country. This enables users to quickly and effectively generate and distribute articles in multiple languages, significantly reducing the labor and cost of language translation and facilitating global information dissemination.

[1055] "User" means an individual or legal entity that uses the System to generate, translate, and distribute articles.

[1056] A "computer terminal" is a device that allows a user to access and operate the system, and includes, for example, a personal computer, a smartphone, a tablet, etc.

[1057] The "server" is a central processing unit that processes the entire system, receiving articles, analyzing them, translating them, generating media, and distributing them.

[1058] A "natural language processing engine" is software or a system that analyzes the content of articles and performs grammatical analysis and keyword extraction.

[1059] "Translation API" means an external service or interface that a server uses to automatically translate articles into multiple languages.

[1060] "SEO keywords" are important keywords for search engine optimization (SEO), and are words that are embedded in articles to help them appear higher in search engines.

[1061] A "generative AI model" is an artificial intelligence model that automatically generates related images and videos based on the content of an article.

[1062] "Web platform" refers to the online services and media to which articles are distributed, including, for example, blog sites, news portals, and social media.

[1063] In this way, the above definitions can be used to make the claims more specific and clear.

[1064] This invention is a system in which users upload articles, the server automatically translates them into multiple languages, extracts and embeds SEO keywords, generates and links related media, and finally distributes them to web platforms in each country. This system is implemented using the following steps and components:

[1065] First, a user accesses the system using a web browser. The user enters their authentication information on the login screen and logs into the system. The authentication information is received by the server and compared with the information stored in the internal database. If this authentication is successful, the user is redirected to the dashboard screen.

[1066] Next, the user selects an article file written in Japanese and clicks the upload button. The device sends the selected file to the server, which then verifies the received file. Once verification is complete, the file is saved in the internal database.

[1067] The server then sends the saved article file to a natural language processing engine (NLP engine). The NLP engine performs grammatical analysis and keyword extraction, and returns the analysis results to the server. Based on these analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, and Spanish). A common translation API is used for the translation.

[1068] For translated articles, the server automatically extracts SEO keywords, translates them into the target language, and embeds them. Extracted keywords are inserted into each article in a natural context to minimize unnecessary manual work.

[1069] In addition, the server uses a generative AI model to automatically generate images and videos related to the article content. For example, if there is an article titled "Introduction of New Technology," technology-related images will be automatically generated by the generative AI model. These media files are linked to the translated article and stored in an internal database.

[1070] Users can preview articles and related media translated into each language from the system's dashboard. After confirming that there are no problems with the content, they issue a distribution command, and the server distributes the article to each country's web platform. This uses each platform's API to post the article and media files appropriately.

[1071] Examples and prompts

[1072] 1. Upload your article:

[1073] A user logs into the system and uploads the article file "NewTech.txt."

[1074] 2. Article analysis and translation:

[1075] The server receives "NewTech.txt" and performs text analysis.

[1076] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[1077] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[1078] 3. SEO:

[1079] The server extracts the SEO keyword "new technology" from Japanese articles.

[1080] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[1081] 4. Media Generation:

[1082] The server automatically generates technical images related to the article content.

[1083] For example, create an image related to "introducing new technology" and link it to the article.

[1084] Example prompt sentence:

[1085] "Write an article in Japanese announcing the introduction of a new technology. Also, translate this article into English, French, and Spanish, embedding appropriate SEO keywords in each language article and generating relevant images."

[1086] Using this system, users can quickly and efficiently create and distribute articles in multiple languages, significantly reducing the effort and cost of language translation and making it easier to disseminate information globally.

[1087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1088] Step 1:

[1089] Initial Setup

[1090] A user accesses the system using a web browser and enters authentication information (username and password) on the login screen.

[1091] Input: Username, Password

[1092] The server receives the entered authentication information, checks it against the correct authentication information stored in its internal database, and if authentication is successful, displays the dashboard screen to the user.

[1093] Output: Login success / failure message, dashboard screen or error message

[1094] Step 2:

[1095] Article Upload

[1096] The user selects the Japanese article file from the dashboard screen and clicks the "Upload" button.

[1097] Input: Article file (e.g. NewTech.txt)

[1098] The terminal sends the selected file to the server, which then verifies the file, including checking the file format and virus checks.

[1099] The server stores the verified files in an internal database.

[1100] Output: File save success / failure message

[1101] Step 3:

[1102] Article analysis and translation

[1103] The server sends article files stored in an internal database to a natural language processing engine (NLP engine) to analyze the content.

[1104] Input: Article file (e.g. NewTech.txt)

[1105] The server extracts the article content from the analysis results and automatically translates it into multiple target languages. The translation process uses an external translation API (e.g., a general translation API).

[1106] Output: Translated article (English, French, Spanish, etc.)

[1107] Step 4:

[1108] SEO measures

[1109] The server uses a natural language processing engine to extract SEO keywords from the original article.

[1110] Input: Original article (e.g. "We introduced new technology")

[1111] The server translates the extracted keywords into multiple target languages.

[1112] The server embeds the translated keywords naturally into the translated articles in each target language.

[1113] Output: SEO-optimized translated article

[1114] Step 5:

[1115] Media Generation

[1116] The server uses a generative AI model to automatically generate relevant images and videos based on the article's content.

[1117] Input: Article content (e.g., "Introduction of new technology")

[1118] The server associates the automatically generated media files (images, videos) with the translated articles and stores them in a database.

[1119] Output: Translated articles with related media

[1120] Step 6:

[1121] Article Preview

[1122] Users preview translated articles and auto-generated media on the system.

[1123] Input: Preview request

[1124] The server generates a temporary preview and displays it to the user, who can then view each language version of the article and its associated media.

[1125] Output: Preview screen, user requests for corrections or confirmation

[1126] Step 7:

[1127] Article distribution

[1128] The user checks the preview content and clicks the "Distribute" button.

[1129] Input: Delivery instructions

[1130] The server distributes the translated articles to web platforms in each country using their respective APIs (e.g. blog site API, news portal API).

[1131] Output: Articles distributed to each country's web platform, distribution success / failure message

[1132] (Application example 1)

[1133] 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."

[1134] While existing multilingual article generation and SEO systems allow users to easily translate and distribute articles, they do not support real-time visual recognition-based advertisement generation and display. Furthermore, they lack the ability to instantly generate multilingual advertising content and overlay it on visual devices. There is a particular need for a method to improve the efficiency of inbound marketing in tourist destinations and shopping malls.

[1135] 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.

[1136] In this invention, the server includes: means for users to upload articles; means for the server to analyze the uploaded articles; means for the server to automatically translate the analyzed articles into multiple languages; means for the server to extract and embed SEO keywords for the translated articles; means for the server to generate related images and videos and link them to the articles; means for the server to distribute the processed articles to platforms in various countries; means for users to detect visual targets using a content browsing device and automatically generate advertising content based on the targets; means for the server to translate the generated advertising content into multiple languages ​​and apply SEO measures; and means for users to check the translated advertising content on the content browsing device and draw it in a specified visual area. This enables users to generate and display multilingual advertisements in real time based on visual recognition, significantly improving the efficiency of inbound marketing.

[1137] "User" means any entity, including individuals or corporations, that uses this system to upload articles and generate, review, and distribute content.

[1138] "Article" means a text document containing information that can be uploaded, analyzed, translated, search engine optimized, and associated with related media by the server.

[1139] "Uploading" refers to the act of a user transferring their own digital data to a server.

[1140] "Analysis" is the process by which the server uses a natural language processing engine to understand the content of the uploaded article and extract information.

[1141] "Translation" is a server function that converts analyzed articles into multiple target languages.

[1142] "SEO keywords" are specific words or phrases that are embedded in articles for search engine optimization.

[1143] "Media" refers to visual and audio supplementary information such as images and videos related to the content of the article.

[1144] A "viewed object" is an object or scene that a user visually recognizes through a content browsing device.

[1145] "Advertising content" refers to promotional text and multimedia material that is automatically generated based on the viewed object.

[1146] A "content viewing device" is a device such as smart glasses or a head-mounted display worn or used by a user, which overlays advertising content in the visual field.

[1147] "Overlay display" is a technique for displaying additional information overlaid on top of existing visual information.

[1148] "Distribution" refers to the act of delivering processed articles and advertising content to platforms in each country via the Internet.

[1149] A "natural language processing engine" is a type of software that the server uses to understand the content of an article and extract and translate the appropriate information.

[1150] In order to put the present invention into practice, the following specific system is constructed.

[1151] The server analyzes articles uploaded by users, translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media.It also has the function of automatically generating advertising content in real time based on the objects the user sees using their visual device, translating and implementing SEO measures, and overlaying it in the visual area.

[1152] Specifically, the server does the following:

[1153] 1. User authentication and article upload: A user logs into the system via a web browser and uploads an article file. The server processes the authentication information and stores the uploaded article in an internal database.

[1154] 2. Natural language processing and translation: The server uses an internal natural language processing engine (e.g., nltk, spaCy) to analyze the content of the uploaded article and automatically translate it into multiple target languages ​​(e.g., English, French, Spanish, etc.). This can be done using the Google Translate API, etc.

[1155] 3. Extracting and embedding SEO keywords: Automatically extract keywords necessary for SEO from the original article, translate them into the target language, and embed them appropriately in the article in each language.

[1156] 4. Related Media Generation: The server automatically generates related images and videos based on the article content and links them to the article. This can be done using a generative AI model (e.g., DALL-E, Stable Diffusion).

[1157] 5. Real-time ad generation: When a user wears smart glasses or a head-mounted display, the device uses a visual recognition engine (e.g., OpenCV, Google Cloud Vision API) to detect the object being viewed. Based on the detected object, ad content is automatically generated, translated, and optimized for SEO.

[1158] Through these steps, users can efficiently deliver multilingual articles and real-time generated advertisements. A specific example of use is when a user wearing smart glasses sees a cafe in a tourist spot, multilingual advertisement content based on that cafe is displayed in front of the user's eyes.

[1159] Prompt Sentence Examples

[1160] Please explain the structure of the object-based real-time multilingual advertisement generation system. Please explain in detail how it uses Google Cloud Vision API to detect the visual object, retrieves relevant advertisements from the advertisement database, performs multilingual translation using Google Trans, and displays the advertisements on smart glasses.

[1161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1162] Step 1:

[1163] A user logs in to the system through a web browser and uploads an article file. The server receives the authentication information and authenticates the user. If authentication is successful, the uploaded article file is stored in the internal database.

[1164] Input: User credentials, article file

[1165] Output: Articles stored in the internal database

[1166] Step 2:

[1167] The server sends the uploaded article to a natural language processing engine, which analyzes the article's content, including its sentence structure, topic, and important keywords.

[1168] Input: Articles stored in the internal database

[1169] Output: Analyzed article content (topics, keywords, etc.)

[1170] Step 3:

[1171] Based on the analysis results, the server automatically translates the article into multiple target languages ​​using a translation engine (e.g., Google Translate API). The translated articles are stored in an internal database for each language.

[1172] Input: Parsed article content, list of target languages

[1173] Output: Article translated into multiple languages

[1174] Step 4:

[1175] The server automatically extracts keywords necessary for SEO from the original Japanese article, translates the extracted keywords into the target language, and embeds them appropriately in the translated article in each language.

[1176] Input: Japanese article, list of target languages

[1177] Output: Translated articles with embedded SEO keywords

[1178] Step 5:

[1179] The server generates relevant images and videos based on the article content, automatically generating media using generative AI models (e.g., DALL-E, Stable Diffusion), and connecting them to translated articles in each language.

[1180] Input: Translation article content

[1181] Output: Related media (images, videos)

[1182] Step 6:

[1183] The user wears smart glasses or a head-mounted display, and the device detects the visual object. The device then identifies the object using a visual recognition engine (e.g., Google Cloud Vision API).

[1184] Input: Visual information captured on the device

[1185] Output: Detected objects

[1186] Step 7:

[1187] The server automatically generates advertising content based on the detected objects, retrieving relevant promotional text and multimedia materials from an advertising database and customizing them with a generative AI model.

[1188] Input: Detected object

[1189] Output: Generated ad content

[1190] Step 8:

[1191] The server translates the generated advertising content into multiple target languages ​​and implements SEO measures. It translates into multiple languages ​​using a translation engine and embeds SEO keywords.

[1192] Input: Generated ad content, list of target languages

[1193] Output: Translated ad content

[1194] Step 9:

[1195] The user checks the translated advertising content on the content viewing device, and the terminal overlays it in the designated visual area, where the advertising content is displayed together with the user's visual information.

[1196] Input: translated ad content

[1197] Output: Overlaid ad content

[1198] 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.

[1199] This invention is a system that generates articles in multiple languages, implements SEO measures, and recognizes user emotions and reflects them in articles and related media. In this system, users upload articles, and the server automatically analyzes and translates the articles, extracts and embeds SEO keywords, generates related media, and adjusts the content based on user emotion data before distributing it to platforms in each country.

[1200] Program processing

[1201] 1. Initial Setup:

[1202] A user logs into the system using a web browser and enters their authentication information.

[1203] The server receives the entered authentication information and performs authentication by comparing it with information in a database.

[1204] 2. Upload your article:

[1205] The user selects an article file written in Japanese and uploads it to the system.

[1206] The server receives the uploaded files and stores them in an internal database.

[1207] 3. Article analysis and translation:

[1208] The server reads the saved article file, sends it to a natural language processing engine (NLP engine), and analyzes the article content.

[1209] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[1210] The translated articles are stored on a server for each target language.

[1211] 4. SEO:

[1212] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[1213] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[1214] 5. Media Generation:

[1215] The server automatically generates related images and videos based on the article content.

[1216] The generated media files are saved and linked to the corresponding translated article.

[1217] 6. Acquiring and analyzing emotion data:

[1218] Users enter their emotional data when uploading articles, which can be done using a simple questionnaire or facial expression recognition, for example.

[1219] The server sends the acquired emotion data to the emotion engine for analysis.

[1220] 7. Reflecting emotional data:

[1221] The server adjusts the content of translated articles and related media based on the analyzed emotional data.

[1222] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[1223] 8. Article Preview:

[1224] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[1225] The user checks that there are no problems with the content and then issues a command to distribute it.

[1226] 9. Article Distribution:

[1227] The server follows the user's instructions and distributes the article to relevant platforms in each country.

[1228] Articles will be published on each platform, making them accessible to a diverse audience.

[1229] Specific examples

[1230] 1. Initial Setup:

[1231] A user logs into the system and uploads an article file called "TechNews.txt".

[1232] 2. Article analysis and translation:

[1233] The server reads "TechNews.txt" and the NLP engine analyzes the article content.

[1234] The article "We have introduced new technology" is translated into English "We have introduced new technology", French "Nous avons introduit une nouvelle technologie" and Spanish "Hemos introducido nueva tecnología".

[1235] 3. SEO:

[1236] The server extracts the SEO keyword "new technology," translates it into each target language, and embeds it in the article.

[1237] 4. Media Generation:

[1238] The server generates images related to the article content and links them to each translated article.

[1239] 5. Acquiring and analyzing emotion data:

[1240] A user enters emotional data such as "excited" in a survey.

[1241] The server sends this emotional data to the emotion engine, and adjusts media and articles based on the analysis results.

[1242] 6. Preview and distribute your article:

[1243] The user checks the preview and instructs distribution.

[1244] The server distributes the adjusted articles to platforms in each country and makes them public.

[1245] This system allows users to quickly generate and distribute multilingual articles that reflect emotional data, enabling more personalized and effective information dissemination to readers.

[1246] The processing flow will be explained below.

[1247] Step 1: User logs into the system

[1248] A user accesses the system's login page using a web browser.

[1249] The user enters their authentication information (username and password) and clicks the "Login" button.

[1250] The server receives the entered authentication information and performs authentication by comparing it with information in its internal database.

[1251] If the authentication is successful, the server displays the dashboard screen to the user.

[1252] Step 2: User uploads article file

[1253] The user clicks the "Upload article" button on the dashboard screen.

[1254] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[1255] The user clicks the "Upload" button.

[1256] The server receives the uploaded files and stores them in an internal database.

[1257] Step 3: The server retrieves the emotion data

[1258] Users enter their emotional data using a simple questionnaire or a facial expression recognition system.

[1259] For example, the user inputs the emotion "excited."

[1260] The server receives the emotion data and sends it to the emotion engine.

[1261] Step 4: The server parses the article

[1262] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[1263] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[1264] Step 5: The server automatically translates the article into multiple languages

[1265] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[1266] Articles translated into each language are stored in a database on the server.

[1267] Step 6: The server extracts and embeds SEO keywords

[1268] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[1269] For example, extract the keyword "new technology."

[1270] The server translates this into the target language and embeds it in a natural way into the translated article in each language.

[1271] Step 7: The server generates the relevant images and videos

[1272] The server automatically generates related images and videos based on the content of the article.

[1273] For example, create an image related to "introduction of new technology."

[1274] Step 8: The server adjusts the media and article content based on the sentiment data.

[1275] The server receives the analysis results from the emotion engine and adjusts the content of translated articles and related media.

[1276] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[1277] Step 9: Server associates generated media with article

[1278] The server links the generated images and videos to the corresponding translated articles.

[1279] The media files are stored in a database on the server along with the articles.

[1280] Step 10: User sees article preview

[1281] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[1282] The preview screen checks the accuracy of the content, the relevance of the media, and the effectiveness of reflecting emotions.

[1283] Step 11: User directs distribution

[1284] After checking the preview, the user clicks the "Distribute" button.

[1285] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[1286] Step 12: The server delivers the article

[1287] The server then sends the translated articles to pre-designated platforms in each country for publication.

[1288] Articles are published on each platform and become accessible to users.

[1289] Example 2

[1290] 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."

[1291] Conventional multilingual article generation systems have difficulty reflecting user sentiment data in addition to article translation and SEO measures, resulting in insufficient and effective personalization. Furthermore, there is a need to streamline the overall processing flow, including improving translation accuracy and adding features such as automatic generation of related media.

[1292] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1293] In this invention, the server includes: a means for a user to log in to the system using authentication information; a means for the user to upload articles; a means for the server to save the uploaded articles; a means for the server to analyze the articles using a natural language processing engine; a means for the server to automatically translate the analyzed articles into multiple languages; a means for the server to save the translated articles; a means for the server to extract SEO keywords and embed them in the translated articles; a means for the server to generate images and videos based on the article content; a means for the server to link related images and videos to the articles; a means for the user to input emotional data; a means for the server to analyze the emotional data and adjust the translated articles and related media; and a means for the server to distribute the processed articles to platforms in each country. This enables efficient generation of multilingual articles that reflect user emotional data, SEO measures, and the automatic generation and distribution of related media.

[1294] "User" means any person or entity that accesses the System and uploads and manipulates Articles.

[1295] "Authentication information" refers to information such as a username and password used by a user to log in to a system.

[1296] "System" refers to a platform where users can upload articles and have them translated, search engine optimized, media generated, and sentiment data reflected.

[1297] "Server" refers to a computing device that handles the overall processing of the system and is responsible for data storage, analysis, translation, media generation, and delivery.

[1298] A "natural language processing engine" refers to software technology that analyzes text data and performs semantic understanding and translation.

[1299] "Analysis" refers to the process of breaking down the content of an uploaded article and understanding its meaning and grammatical structure.

[1300] "Translation" refers to the process of converting the content of the analyzed article into another language.

[1301] "SEO keywords" refers to embedding specific words or phrases within an article for search engine optimization.

[1302] "Generating images and videos" refers to automatically creating relevant visual content based on article content.

[1303] "Emotional data" refers to the emotional feedback and reactions to articles entered by users.

[1304] "Parse and translate" refers to the process of using a natural language processing engine to understand article content and translate it into multiple languages.

[1305] "Platform" refers to the website or service on which articles are published, and the medium through which users provide information to a diverse audience.

[1306] This invention relates to a system that generates and distributes articles and related media in multiple languages, reflecting user emotional data, in addition to providing SEO support. This system is realized through the cooperation of users, terminals, and a server.

[1307] A user logs into a system using a web browser (e.g., Google Chrome), enters authentication information (username and password), and the server receives the information using Apache HTTP Server or Nginx and authenticates the user by checking it against a MySQL or PostgreSQL database.

[1308] After logging in, the user selects an article file written in Japanese (e.g., "TechNews.txt") and uploads it to the system. The server receives the uploaded article file via FastAPI or the Django framework and stores it in cloud storage such as Amazon S3.

[1309] The server then analyzes the article content using Python and natural language processing libraries such as NLTK and spaCy. The analysis results are saved in JSON format. The server then uses the Google Translate API and Microsoft Translator API to automatically translate the analyzed article into multiple languages. The translation results are also saved in a database on the server.

[1310] The server uses libraries like BeautifulSoup or Scrapy to extract SEO-friendly keywords from the original article, which are then translated into the target language and embedded appropriately into each translated article.

[1311] The server also uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content, and the generated media files are saved and linked to each translated article.

[1312] When uploading an article, users enter their emotional data (e.g., "excited") through a questionnaire or a facial recognition camera. The server analyzes the emotional data using Microsoft Azure's emotion API or IBM Watson's emotion recognition API, and uses the results to adjust the content of the translated article and related media. For example, if positive emotional data is entered, brighter images and optimistic text will be added to the article.

[1313] Users can preview articles and related media translated into various languages ​​and with sentiment data reflected in the content on the system, and if there are no problems, they can issue a distribution command.

[1314] Finally, the server distributes the articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API, allowing the processed articles to be published on platforms in various countries and made accessible to readers.

[1315] As a concrete example, a user accesses the system using Google Chrome and logs in. They upload an article file called TechNews.txt. This file is analyzed using Python and spaCy and translated into English, French, and Spanish using the Google Translate API. The extracted SEO keyword "new technology" is then translated into each language and embedded in the article. The server uses DALL-E to generate technology-related images and link them to the translated article. The user inputs emotional data such as "excited," and the server analyzes the emotional data and adjusts the article and images accordingly. Once the user checks the preview and requests distribution, the server publishes the article via WordPress' XML-RPC API.

[1316] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1317] Step 1: Authenticate the user

[1318] Input: The user enters their authentication information (username and password) using a web browser.

[1319] Processing: The server receives the authentication information via Apache HTTP Server or Nginx and authenticates the user against a MySQL or PostgreSQL database.

[1320] Output: If authentication is successful, the user is granted access to the system.

[1321] Step 2: Upload your article

[1322] Input: The user selects an article file (e.g. TechNews.txt) from the terminal and clicks the upload button.

[1323] Processing: The server receives files uploaded via FastAPI or Django and stores them in cloud storage such as Amazon S3.

[1324] Output: Article files are securely stored on the server.

[1325] Step 3: Analyzing the article

[1326] Input: The server reads the saved article file.

[1327] Processing: The server uses Python and natural language processing libraries such as NLTK and spaCy to analyze the article content, for example by tokenizing the sentences and performing morphological analysis.

[1328] Output: The analysis results are converted to JSON format and saved in the database.

[1329] Step 4: Translate the article

[1330] Input: Parsed article content

[1331] Processing: The server calls the Google Translate API or Microsoft Translator API to translate the parsed content into multiple languages ​​(English, French, Spanish, etc.).

[1332] Output: The translated article is saved in the database.

[1333] Step 5: Extract and embed SEO keywords

[1334] Input: Original article content

[1335] Processing: The server uses libraries such as BeautifulSoup or Scrapy to extract SEO-friendly keywords, translates the extracted keywords into the target language, and embeds them appropriately in each translated article.

[1336] Output: The translated article with embedded SEO keywords is saved in the database.

[1337] Step 6: Generate related media

[1338] Input: Article content

[1339] Processing: The server uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content.

[1340] Output: The generated media files are linked to each translated article and stored in a database.

[1341] Step 7: Acquire and analyze emotion data

[1342] Input: The user inputs emotion data through a questionnaire or facial recognition camera.

[1343] Processing: The server analyzes the emotion data using Microsoft Azure's emotion API and IBM Watson's emotion recognition API.

[1344] Output: The analyzed emotion data is stored in a database.

[1345] Step 8: Reflecting emotional data

[1346] Input: Parsed sentiment data and translated article content

[1347] Processing: The server adjusts the content of the translated article and related media based on the sentiment data. For example, if there is positive sentiment data, it adds brighter colors and more positive expressions to the article.

[1348] Output: The adjusted articles and media are stored in a database.

[1349] Step 9: Preview your article

[1350] Input: Articles and related media translated into various languages ​​and updated with sentiment data

[1351] Processing: The user previews these contents on the system, visually checks them, and makes corrections if necessary.

[1352] Output: If the user is satisfied with the content, he / she issues a distribution instruction.

[1353] Step 10: Article Distribution

[1354] Input: Articles and related media for which distribution instructions have been issued

[1355] Processing: The server delivers articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API.

[1356] Output: The processed articles are published on national platforms and made accessible to readers.

[1357] (Application example 2)

[1358] 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."

[1359] Conventional content distribution systems required users to manually translate articles into multiple languages, implement SEO measures, and generate related media. Furthermore, there was a lack of technology to automatically generate and distribute content that reflected user sentiment. This made the article generation and distribution process time-consuming and labor-intensive, making it difficult to disseminate personalized information.

[1360] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for users to upload articles, means for the server to analyze the uploaded articles, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to generate related images and videos and link them to the articles, means for the server to acquire and analyze user emotion data, means for the server to adjust the content of the articles and related media based on the emotion data, and means for the server to distribute the processed articles to platforms in each country. This enables users to quickly generate and distribute content that is multilingual and reflects emotions.

[1361] A "user" is a person or entity that uploads articles to the system and issues previews and distribution instructions.

[1362] The "server" is a computer system that analyzes articles, translates them, implements SEO measures, generates media, acquires and analyzes emotional data, and adjusts the content, before distributing the articles to platforms in each country.

[1363] "Articles" refer to text content uploaded by users and are subject to translation into various languages.

[1364] "Analysis" is the process of understanding the content of the uploaded article and extracting the necessary information.

[1365] "Machine translation" is the process of mechanically converting analyzed articles into multiple target languages.

[1366] "SEO keywords" are specific important words or phrases used to rank articles in search engines.

[1367] "Related images and videos" are visual media files generated based on the article content and presented together with the article.

[1368] "Emotion data" is information that represents the user's emotional state, and is obtained through questionnaires or facial expression recognition.

[1369] A "platform" is an online medium or site that exists in each country and is the place where articles are distributed and published.

[1370] "Preview" refers to the display confirmation performed by the user as a final check of the article and related media.

[1371] An "emotion engine" is a software tool that analyzes acquired emotional data and adjusts content based on the results.

[1372] This invention is a system that significantly simplifies the user article creation process and efficiently delivers more personalized content by supporting multiple languages ​​and reflecting emotional data. This system allows users to upload articles and automatically performs each step of article analysis, translation, SEO measures, media generation, emotional data acquisition and analysis, content adjustment, and distribution.

[1373] Hardware and software used

[1374] Hardware: Smartphones, smart glasses, head-mounted displays, cloud servers

[1375] Software: Python, Google Cloud Translation API, Elasticsearch, AWS Rekognition, MySQL, WordPress CMS

[1376] User actions

[1377] Users log in to the system using their smartphones, smart glasses, or head-mounted displays to upload articles. When uploading, users can also provide their own emotional data, which can be done through a questionnaire or facial recognition using the smartphone camera.

[1378] Server operations

[1379] The server processes the uploaded articles and sentiment data through the following process:

[1380] 1. Receiving and saving articles

[1381] The server receives the uploaded article files and stores them in a MySQL database.

[1382] 2. Article analysis and translation

[1383] A Python script is used to run an NLP engine (natural language processing engine) to analyze the article content.

[1384] Use the Google Cloud Translation API to automatically translate articles into multiple target languages.

[1385] 3. SEO

[1386] Using Elasticsearch, we automatically extract keywords that are effective for SEO from the original Japanese article.

[1387] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[1388] 4. Generate related media

[1389] Use AWS Rekognition to generate relevant images and videos based on the article content.

[1390] The generated media files are linked to the corresponding translated articles and stored in the WordPress CMS.

[1391] 5. Acquiring and Reflecting Emotional Data

[1392] The emotion acquisition module is used to collect emotion data provided by users (survey results and facial expression recognition data).

[1393] The server sends this emotional data to the emotion engine and adjusts the content of the translated article and related media based on the analysis results.

[1394] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[1395] Article preview and distribution

[1396] The server provides the adjusted article to the user for preview, and once the user confirms the distribution instructions, the server distributes the adjusted article to platforms in each country and makes it public.

[1397] Examples of prompt statements

[1398] Example prompts to input to a generative AI model:

[1399] "This article talks about the introduction of innovative technology. Your SEO keywords are 'new technology,' 'innovation,' and 'introduction.' Use 'excitement' as your emotional data and write the article in a bright, optimistic tone."

[1400] In this way, users can create and distribute multilingual content efficiently and personalizedly.

[1401] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1402] Step 1:

[1403] Users log in to the system using their smartphone, smart glasses, or head-mounted display. When logging in, authentication information is entered, which is received by the server and verified against information in a MySQL database. If authentication is successful, the user can proceed to the article upload screen.

[1404] Step 2:

[1405] The user selects an article file and uploads it to the system. The uploaded file is sent to the server, which receives it and stores it in a MySQL database. The input is the article file uploaded by the user, and the output is the article data stored in the database.

[1406] Step 3:

[1407] The server reads the article file and sends it to an NLP engine (natural language processing engine) using a Python script to analyze the article content. The analysis results include the article structure and key points of the content. The input is the saved article data, and the output is the analyzed article content.

[1408] Step 4:

[1409] Based on the analysis results, the server uses the Google Cloud Translation API to automatically translate the article into multiple target languages ​​(e.g., English, French, Spanish, etc.) The input is the analysis results, and the output is the article data translated into each target language.

[1410] Step 5:

[1411] The server uses Elasticsearch to automatically extract important SEO keywords from the original Japanese article. The extracted keywords are also translated into the target language and appropriately embedded in the translated article in each language. The input is the original article data and the translated article data, and the output is the translated article with SEO measures applied.

[1412] Step 6:

[1413] The server uses AWS Rekognition to automatically generate related images and videos based on the article content. The generated media files are linked to the corresponding translated article and saved in the WordPress CMS. The input is the translated article data, and the output is a media file containing related images and videos.

[1414] Step 7:

[1415] When uploading an article, users provide their own emotional data. This can be done through a questionnaire or facial recognition using a smartphone camera. The server acquires this emotional data and sends it to the emotion engine for analysis. The input is the user's emotional data, and the output is the analyzed emotional data.

[1416] Step 8:

[1417] The server adjusts the content of the translated article and related media based on the emotional data. For example, if positive emotional data is recognized, it will use a brighter or more optimistic tone for the article or media. The input is the analyzed emotional data and the translated article and media data, and the output is the adjusted content.

[1418] Step 9:

[1419] The server provides the adjusted article and media to the user for preview. The user checks the content and, if there are no problems, issues a distribution command. The input is the adjusted content, and the output is the user's distribution command.

[1420] Step 10:

[1421] The server follows the user's instructions and distributes the adjusted article to the relevant platforms in each country. The article is then published and made accessible to a diverse audience. The input is the distribution instructions and adjusted content, and the output is the article published on each platform in each country.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] [Fourth embodiment]

[1426] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1427] 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.

[1428] 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).

[1429] 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.

[1430] 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.

[1431] 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).

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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."

[1439] This invention is a system for creating articles in multiple languages ​​and implementing SEO measures. In this system, users upload articles, and the server automatically translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media, ultimately distributing them to platforms in each country.

[1440] Program processing

[1441] 1. Initial Setup:

[1442] When a user logs into the system using a web browser, they enter their authentication information.

[1443] The server receives the authentication information sent by the user and performs authentication.

[1444] 2. Upload your article:

[1445] The user selects an article file written in Japanese and uploads it to the system.

[1446] The server receives the uploaded article files and stores them in an internal database.

[1447] 3. Article analysis and translation:

[1448] The server sends the uploaded article to a natural language processing engine (NLP engine) to analyze the article's content.

[1449] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[1450] Translated articles are stored on a server for each target language.

[1451] 4. SEO:

[1452] The server automatically extracts keywords necessary for SEO from the original Japanese article.

[1453] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[1454] 5. Media Generation:

[1455] The server automatically generates related images and videos based on the content of the article.

[1456] The generated media files are associated with the translated article and saved.

[1457] 6. Preview the article:

[1458] Users preview translated articles and auto-generated media on the system.

[1459] The user checks that there are no problems with the content and then issues a command to distribute it.

[1460] 7. Article Distribution:

[1461] The server delivers translated articles to platforms in each country according to the user's instructions.

[1462] Specific examples

[1463] 1. Initial Setup:

[1464] A user logs into the system and uploads the article file "NewTech.txt."

[1465] 2. Article analysis and translation:

[1466] The server receives "NewTech.txt" and performs text analysis.

[1467] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[1468] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[1469] 3. SEO:

[1470] The server extracts the SEO keyword "new technology" from the original Japanese article.

[1471] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[1472] 4. Media Generation:

[1473] The server automatically generates technical images related to the article content.

[1474] For example, create an image related to "introducing new technology" and link it to the article.

[1475] 5. Article Preview and Distribution:

[1476] Users can view articles and related media translated into each language on the system.

[1477] After confirmation, if you issue a distribution command, the server will distribute the article to platforms in each country.

[1478] In this way, by implementing the system of the present invention, users can quickly and effectively create and distribute articles in multiple languages, significantly reducing the man-hours and costs involved in language translation and facilitating the global dissemination of information.

[1479] The processing flow will be explained below.

[1480] Step 1: User logs into the system

[1481] The user opens a web browser and accesses the system's login page.

[1482] The user enters their authentication information (username and password) and clicks the "Login" button.

[1483] The server receives the authentication information entered and checks it against information in a database.

[1484] If the authentication is successful, the server displays the dashboard screen to the user.

[1485] Step 2: User uploads article file

[1486] The user clicks the "Upload article" button on the dashboard screen.

[1487] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[1488] The user clicks the "Upload" button.

[1489] The server receives the uploaded files and stores them in the system's storage.

[1490] Step 3: The server parses the article

[1491] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[1492] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[1493] Step 4: The server automatically translates the article into multiple languages

[1494] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[1495] Articles translated into each language are stored in a database on the server.

[1496] Step 5: The server extracts SEO keywords

[1497] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[1498] For example, detect keywords such as "new technology."

[1499] Step 6: The server translates the extracted keywords into each language and embeds them

[1500] The server translates the extracted keywords into keywords appropriate for the target language.

[1501] Translated keywords are embedded naturally into translated articles in each language.

[1502] Step 7: The server generates the relevant images and videos

[1503] The server automatically generates related images and videos based on the content of the article.

[1504] For example, create a technical image related to "introducing new technology."

[1505] Step 8: The server associates the generated media with the article

[1506] The server links the generated images and videos to the corresponding translated articles.

[1507] The media files are stored in a database on the server along with the articles.

[1508] Step 9: User Previews Article

[1509] Users can preview translated articles and related media in their language on the system.

[1510] The preview screen checks the accuracy of the content and the relevance of the media.

[1511] Step 10: User directs distribution

[1512] After checking the preview, the user clicks the "Distribute" button.

[1513] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[1514] Step 11: The server delivers the article

[1515] The server then sends the translated articles to pre-designated platforms in each country for publication.

[1516] Articles are published on each platform and become accessible to users.

[1517] Example 1

[1518] 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."

[1519] Currently, there are only a limited number of systems that can effectively generate multilingual articles and implement SEO measures. The automatic translation of articles into multiple languages ​​and the appropriate embedding of SEO keywords are particularly time-consuming. There is also a lack of technology to automatically generate related media files and link them to articles. This creates challenges for users, as it requires a lot of time, effort, and costs when distributing articles globally.

[1520] 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.

[1521] In this invention, the server includes means for users to upload articles using a computer terminal, means for the server to analyze the uploaded articles using a natural language processing engine, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to automatically generate related images and videos using a generative AI model and link them to the articles, and means for the server to distribute the processed articles to web platforms in each country. This enables users to quickly and effectively generate and distribute articles in multiple languages, significantly reducing the labor and cost of language translation and facilitating global information dissemination.

[1522] "User" means an individual or legal entity that uses the System to generate, translate, and distribute articles.

[1523] A "computer terminal" is a device that allows a user to access and operate the system, and includes, for example, a personal computer, a smartphone, a tablet, etc.

[1524] The "server" is a central processing unit that processes the entire system, receiving articles, analyzing them, translating them, generating media, and distributing them.

[1525] A "natural language processing engine" is software or a system that analyzes the content of articles and performs grammatical analysis and keyword extraction.

[1526] "Translation API" means an external service or interface that a server uses to automatically translate articles into multiple languages.

[1527] "SEO keywords" are important keywords for search engine optimization (SEO), and are words that are embedded in articles to help them appear higher in search engines.

[1528] A "generative AI model" is an artificial intelligence model that automatically generates related images and videos based on the content of an article.

[1529] "Web platform" refers to the online services and media to which articles are distributed, including, for example, blog sites, news portals, and social media.

[1530] In this way, the above definitions can be used to make the claims more specific and clear.

[1531] This invention is a system in which users upload articles, the server automatically translates them into multiple languages, extracts and embeds SEO keywords, generates and links related media, and finally distributes them to web platforms in each country. This system is implemented using the following steps and components:

[1532] First, a user accesses the system using a web browser. The user enters their authentication information on the login screen and logs into the system. The authentication information is received by the server and compared with the information stored in the internal database. If this authentication is successful, the user is redirected to the dashboard screen.

[1533] Next, the user selects an article file written in Japanese and clicks the upload button. The device sends the selected file to the server, which then verifies the received file. Once verification is complete, the file is saved in the internal database.

[1534] The server then sends the saved article file to a natural language processing engine (NLP engine). The NLP engine performs grammatical analysis and keyword extraction, and returns the analysis results to the server. Based on these analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, and Spanish). A common translation API is used for the translation.

[1535] For translated articles, the server automatically extracts SEO keywords, translates them into the target language, and embeds them. Extracted keywords are inserted into each article in a natural context to minimize unnecessary manual work.

[1536] In addition, the server uses a generative AI model to automatically generate images and videos related to the article content. For example, if there is an article titled "Introduction of New Technology," technology-related images will be automatically generated by the generative AI model. These media files are linked to the translated article and stored in an internal database.

[1537] Users can preview articles and related media translated into each language from the system's dashboard. After confirming that there are no problems with the content, they issue a distribution command, and the server distributes the article to each country's web platform. This uses each platform's API to post the article and media files appropriately.

[1538] Examples and prompts

[1539] 1. Upload your article:

[1540] A user logs into the system and uploads the article file "NewTech.txt."

[1541] 2. Article analysis and translation:

[1542] The server receives "NewTech.txt" and performs text analysis.

[1543] Article content: "We have introduced new technology" is analyzed by an NLP engine.

[1544] Based on the analysis results, the server translates the article into English: "We have introduced new technology," French: "Nous avons introduit une nouvelle technologie," and Spanish: "Hemos introducido nueva tecnología."

[1545] 3. SEO:

[1546] The server extracts the SEO keyword "new technology" from Japanese articles.

[1547] The server translates this into English "new technology," French "nouvelle technologie," and Spanish "nueva tecnología," and embeds them naturally into each translated article.

[1548] 4. Media Generation:

[1549] The server automatically generates technical images related to the article content.

[1550] For example, create an image related to "introducing new technology" and link it to the article.

[1551] Example prompt sentence:

[1552] "Write an article in Japanese announcing the introduction of a new technology. Also, translate this article into English, French, and Spanish, embedding appropriate SEO keywords in each language article and generating relevant images."

[1553] Using this system, users can quickly and efficiently create and distribute articles in multiple languages, significantly reducing the effort and cost of language translation and making it easier to disseminate information globally.

[1554] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1555] Step 1:

[1556] Initial Setup

[1557] A user accesses the system using a web browser and enters authentication information (username and password) on the login screen.

[1558] Input: Username, Password

[1559] The server receives the entered authentication information, checks it against the correct authentication information stored in its internal database, and if authentication is successful, displays the dashboard screen to the user.

[1560] Output: Login success / failure message, dashboard screen or error message

[1561] Step 2:

[1562] Article Upload

[1563] The user selects the Japanese article file from the dashboard screen and clicks the "Upload" button.

[1564] Input: Article file (e.g. NewTech.txt)

[1565] The terminal sends the selected file to the server, which then verifies the file, including checking the file format and virus checks.

[1566] The server stores the verified files in an internal database.

[1567] Output: File save success / failure message

[1568] Step 3:

[1569] Article analysis and translation

[1570] The server sends article files stored in an internal database to a natural language processing engine (NLP engine) to analyze the content.

[1571] Input: Article file (e.g. NewTech.txt)

[1572] The server extracts the article content from the analysis results and automatically translates it into multiple target languages. The translation process uses an external translation API (e.g., a general translation API).

[1573] Output: Translated article (English, French, Spanish, etc.)

[1574] Step 4:

[1575] SEO measures

[1576] The server uses a natural language processing engine to extract SEO keywords from the original article.

[1577] Input: Original article (e.g. "We introduced new technology")

[1578] The server translates the extracted keywords into multiple target languages.

[1579] The server embeds the translated keywords naturally into the translated articles in each target language.

[1580] Output: SEO-optimized translated article

[1581] Step 5:

[1582] Media Generation

[1583] The server uses a generative AI model to automatically generate relevant images and videos based on the article's content.

[1584] Input: Article content (e.g., "Introduction of new technology")

[1585] The server associates the automatically generated media files (images, videos) with the translated articles and stores them in a database.

[1586] Output: Translated articles with related media

[1587] Step 6:

[1588] Article Preview

[1589] Users preview translated articles and auto-generated media on the system.

[1590] Input: Preview request

[1591] The server generates a temporary preview and displays it to the user, who can then view each language version of the article and its associated media.

[1592] Output: Preview screen, user requests for corrections or confirmation

[1593] Step 7:

[1594] Article distribution

[1595] The user checks the preview content and clicks the "Distribute" button.

[1596] Input: Delivery instructions

[1597] The server distributes the translated articles to web platforms in each country using their respective APIs (e.g. blog site API, news portal API).

[1598] Output: Articles distributed to each country's web platform, distribution success / failure message

[1599] (Application example 1)

[1600] 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."

[1601] While existing multilingual article generation and SEO systems allow users to easily translate and distribute articles, they do not support real-time visual recognition-based advertisement generation and display. Furthermore, they lack the ability to instantly generate multilingual advertising content and overlay it on visual devices. There is a particular need for a method to improve the efficiency of inbound marketing in tourist destinations and shopping malls.

[1602] 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.

[1603] In this invention, the server includes: means for users to upload articles; means for the server to analyze the uploaded articles; means for the server to automatically translate the analyzed articles into multiple languages; means for the server to extract and embed SEO keywords for the translated articles; means for the server to generate related images and videos and link them to the articles; means for the server to distribute the processed articles to platforms in various countries; means for users to detect visual targets using a content browsing device and automatically generate advertising content based on the targets; means for the server to translate the generated advertising content into multiple languages ​​and apply SEO measures; and means for users to check the translated advertising content on the content browsing device and draw it in a specified visual area. This enables users to generate and display multilingual advertisements in real time based on visual recognition, significantly improving the efficiency of inbound marketing.

[1604] "User" means any entity, including individuals or corporations, that uses this system to upload articles and generate, review, and distribute content.

[1605] "Article" means a text document containing information that can be uploaded, analyzed, translated, search engine optimized, and associated with related media by the server.

[1606] "Uploading" refers to the act of a user transferring their own digital data to a server.

[1607] "Analysis" is the process by which the server uses a natural language processing engine to understand the content of the uploaded article and extract information.

[1608] "Translation" is a server function that converts analyzed articles into multiple target languages.

[1609] "SEO keywords" are specific words or phrases that are embedded in articles for search engine optimization.

[1610] "Media" refers to visual and audio supplementary information such as images and videos related to the content of the article.

[1611] A "viewed object" is an object or scene that a user visually recognizes through a content browsing device.

[1612] "Advertising content" refers to promotional text and multimedia material that is automatically generated based on the viewed object.

[1613] A "content viewing device" is a device such as smart glasses or a head-mounted display worn or used by a user, which overlays advertising content in the visual field.

[1614] "Overlay display" is a technique for displaying additional information overlaid on top of existing visual information.

[1615] "Distribution" refers to the act of delivering processed articles and advertising content to platforms in each country via the Internet.

[1616] A "natural language processing engine" is a type of software that the server uses to understand the content of an article and extract and translate the appropriate information.

[1617] In order to put the present invention into practice, the following specific system is constructed.

[1618] The server analyzes articles uploaded by users, translates them into multiple languages, extracts and embeds SEO keywords, and generates and links related media.It also has the function of automatically generating advertising content in real time based on the objects the user sees using their visual device, translating and implementing SEO measures, and overlaying it in the visual area.

[1619] Specifically, the server does the following:

[1620] 1. User authentication and article upload: A user logs into the system via a web browser and uploads an article file. The server processes the authentication information and stores the uploaded article in an internal database.

[1621] 2. Natural language processing and translation: The server uses an internal natural language processing engine (e.g., nltk, spaCy) to analyze the content of the uploaded article and automatically translate it into multiple target languages ​​(e.g., English, French, Spanish, etc.). This can be done using the Google Translate API, etc.

[1622] 3. Extracting and embedding SEO keywords: Automatically extract keywords necessary for SEO from the original article, translate them into the target language, and embed them appropriately in the article in each language.

[1623] 4. Related Media Generation: The server automatically generates related images and videos based on the article content and links them to the article. This can be done using a generative AI model (e.g., DALL-E, Stable Diffusion).

[1624] 5. Real-time ad generation: When a user wears smart glasses or a head-mounted display, the device uses a visual recognition engine (e.g., OpenCV, Google Cloud Vision API) to detect the object being viewed. Based on the detected object, ad content is automatically generated, translated, and optimized for SEO.

[1625] Through these steps, users can efficiently deliver multilingual articles and real-time generated advertisements. A specific example of use is when a user wearing smart glasses sees a cafe in a tourist spot, multilingual advertisement content based on that cafe is displayed in front of the user's eyes.

[1626] Prompt Sentence Examples

[1627] Please explain the structure of the object-based real-time multilingual advertisement generation system. Please explain in detail how it uses Google Cloud Vision API to detect the visual object, retrieves relevant advertisements from the advertisement database, performs multilingual translation using Google Trans, and displays the advertisements on smart glasses.

[1628] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1629] Step 1:

[1630] A user logs in to the system through a web browser and uploads an article file. The server receives the authentication information and authenticates the user. If authentication is successful, the uploaded article file is stored in the internal database.

[1631] Input: User credentials, article file

[1632] Output: Articles stored in the internal database

[1633] Step 2:

[1634] The server sends the uploaded article to a natural language processing engine, which analyzes the article's content, including its sentence structure, topic, and important keywords.

[1635] Input: Articles stored in the internal database

[1636] Output: Analyzed article content (topics, keywords, etc.)

[1637] Step 3:

[1638] Based on the analysis results, the server automatically translates the article into multiple target languages ​​using a translation engine (e.g., Google Translate API). The translated articles are stored in an internal database for each language.

[1639] Input: Parsed article content, list of target languages

[1640] Output: Article translated into multiple languages

[1641] Step 4:

[1642] The server automatically extracts keywords necessary for SEO from the original Japanese article, translates the extracted keywords into the target language, and embeds them appropriately in the translated article in each language.

[1643] Input: Japanese article, list of target languages

[1644] Output: Translated articles with embedded SEO keywords

[1645] Step 5:

[1646] The server generates relevant images and videos based on the article content, automatically generating media using generative AI models (e.g., DALL-E, Stable Diffusion), and connecting them to translated articles in each language.

[1647] Input: Translation article content

[1648] Output: Related media (images, videos)

[1649] Step 6:

[1650] The user wears smart glasses or a head-mounted display, and the device detects the visual object. The device then identifies the object using a visual recognition engine (e.g., Google Cloud Vision API).

[1651] Input: Visual information captured on the device

[1652] Output: Detected objects

[1653] Step 7:

[1654] The server automatically generates advertising content based on the detected objects, retrieving relevant promotional text and multimedia materials from an advertising database and customizing them with a generative AI model.

[1655] Input: Detected object

[1656] Output: Generated ad content

[1657] Step 8:

[1658] The server translates the generated advertising content into multiple target languages ​​and implements SEO measures. It translates into multiple languages ​​using a translation engine and embeds SEO keywords.

[1659] Input: Generated ad content, list of target languages

[1660] Output: Translated ad content

[1661] Step 9:

[1662] The user checks the translated advertising content on the content viewing device, and the terminal overlays it in the designated visual area, where the advertising content is displayed together with the user's visual information.

[1663] Input: translated ad content

[1664] Output: Overlaid ad content

[1665] 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.

[1666] This invention is a system that generates articles in multiple languages, implements SEO measures, and recognizes user emotions and reflects them in articles and related media. In this system, users upload articles, and the server automatically analyzes and translates the articles, extracts and embeds SEO keywords, generates related media, and adjusts the content based on user emotion data before distributing it to platforms in each country.

[1667] Program processing

[1668] 1. Initial Setup:

[1669] A user logs into the system using a web browser and enters their authentication information.

[1670] The server receives the entered authentication information and performs authentication by comparing it with information in a database.

[1671] 2. Upload your article:

[1672] The user selects an article file written in Japanese and uploads it to the system.

[1673] The server receives the uploaded files and stores them in an internal database.

[1674] 3. Article analysis and translation:

[1675] The server reads the saved article file, sends it to a natural language processing engine (NLP engine), and analyzes the article content.

[1676] Based on the analysis results, the server automatically translates the article into multiple target languages ​​(e.g., English, French, Spanish, etc.).

[1677] The translated articles are stored on a server for each target language.

[1678] 4. SEO:

[1679] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[1680] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[1681] 5. Media Generation:

[1682] The server automatically generates related images and videos based on the article content.

[1683] The generated media files are saved and linked to the corresponding translated article.

[1684] 6. Acquiring and analyzing emotion data:

[1685] Users enter their emotional data when uploading articles, which can be done using a simple questionnaire or facial expression recognition, for example.

[1686] The server sends the acquired emotion data to the emotion engine for analysis.

[1687] 7. Reflecting emotional data:

[1688] The server adjusts the content of translated articles and related media based on the analyzed emotional data.

[1689] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[1690] 8. Article Preview:

[1691] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[1692] The user checks that there are no problems with the content and then issues a command to distribute it.

[1693] 9. Article Distribution:

[1694] The server follows the user's instructions and distributes the article to relevant platforms in each country.

[1695] Articles will be published on each platform, making them accessible to a diverse audience.

[1696] Specific examples

[1697] 1. Initial Setup:

[1698] A user logs into the system and uploads an article file called "TechNews.txt".

[1699] 2. Article analysis and translation:

[1700] The server reads "TechNews.txt" and the NLP engine analyzes the article content.

[1701] The article "We have introduced new technology" is translated into English "We have introduced new technology", French "Nous avons introduit une nouvelle technologie" and Spanish "Hemos introducido nueva tecnología".

[1702] 3. SEO:

[1703] The server extracts the SEO keyword "new technology," translates it into each target language, and embeds it in the article.

[1704] 4. Media Generation:

[1705] The server generates images related to the article content and links them to each translated article.

[1706] 5. Acquiring and analyzing emotion data:

[1707] A user enters emotional data such as "excited" in a survey.

[1708] The server sends this emotional data to the emotion engine, and adjusts media and articles based on the analysis results.

[1709] 6. Preview and distribute your article:

[1710] The user checks the preview and instructs distribution.

[1711] The server distributes the adjusted articles to platforms in each country and makes them public.

[1712] This system allows users to quickly generate and distribute multilingual articles that reflect emotional data, enabling more personalized and effective information dissemination to readers.

[1713] The processing flow will be explained below.

[1714] Step 1: User logs into the system

[1715] A user accesses the system's login page using a web browser.

[1716] The user enters their authentication information (username and password) and clicks the "Login" button.

[1717] The server receives the entered authentication information and performs authentication by comparing it with information in its internal database.

[1718] If the authentication is successful, the server displays the dashboard screen to the user.

[1719] Step 2: User uploads article file

[1720] The user clicks the "Upload article" button on the dashboard screen.

[1721] A file selection dialog will appear and the user can select the Japanese text file they wish to upload.

[1722] The user clicks the "Upload" button.

[1723] The server receives the uploaded files and stores them in an internal database.

[1724] Step 3: The server retrieves the emotion data

[1725] Users enter their emotional data using a simple questionnaire or a facial expression recognition system.

[1726] For example, the user inputs the emotion "excited."

[1727] The server receives the emotion data and sends it to the emotion engine.

[1728] Step 4: The server parses the article

[1729] The server reads the saved article files and sends them to a natural language processing engine (NLP engine).

[1730] The NLP engine analyzes the grammar, structure, and semantics of the article and returns the analysis results to the server.

[1731] Step 5: The server automatically translates the article into multiple languages

[1732] Based on the analysis results, the server automatically translates the article into the target language (e.g., English, French, Spanish, etc.).

[1733] Articles translated into each language are stored in a database on the server.

[1734] Step 6: The server extracts and embeds SEO keywords

[1735] The server automatically extracts keywords that are effective for SEO from the original Japanese article.

[1736] For example, extract the keyword "new technology."

[1737] The server translates this into the target language and embeds it in a natural way into the translated article in each language.

[1738] Step 7: The server generates the relevant images and videos

[1739] The server automatically generates related images and videos based on the content of the article.

[1740] For example, create an image related to "introduction of new technology."

[1741] Step 8: The server adjusts the media and article content based on the sentiment data.

[1742] The server receives the analysis results from the emotion engine and adjusts the content of translated articles and related media.

[1743] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[1744] Step 9: Server associates generated media with article

[1745] The server links the generated images and videos to the corresponding translated articles.

[1746] The media files are stored in a database on the server along with the articles.

[1747] Step 10: User sees article preview

[1748] Users can preview articles and related media in the system, which have been translated into various languages ​​and have sentiment data reflected.

[1749] The preview screen checks the accuracy of the content, the relevance of the media, and the effectiveness of reflecting emotions.

[1750] Step 11: User directs distribution

[1751] After checking the preview, the user clicks the "Distribute" button.

[1752] The server receives the distribution instructions and begins the process of distributing the article to relevant platforms in each country.

[1753] Step 12: The server delivers the article

[1754] The server then sends the translated articles to pre-designated platforms in each country for publication.

[1755] Articles are published on each platform and become accessible to users.

[1756] Example 2

[1757] 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."

[1758] Conventional multilingual article generation systems have difficulty reflecting user sentiment data in addition to article translation and SEO measures, resulting in insufficient and effective personalization. Furthermore, there is a need to streamline the overall processing flow, including improving translation accuracy and adding features such as automatic generation of related media.

[1759] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1760] In this invention, the server includes: a means for a user to log in to the system using authentication information; a means for the user to upload articles; a means for the server to save the uploaded articles; a means for the server to analyze the articles using a natural language processing engine; a means for the server to automatically translate the analyzed articles into multiple languages; a means for the server to save the translated articles; a means for the server to extract SEO keywords and embed them in the translated articles; a means for the server to generate images and videos based on the article content; a means for the server to link related images and videos to the articles; a means for the user to input emotional data; a means for the server to analyze the emotional data and adjust the translated articles and related media; and a means for the server to distribute the processed articles to platforms in each country. This enables efficient generation of multilingual articles that reflect user emotional data, SEO measures, and the automatic generation and distribution of related media.

[1761] "User" means any person or entity that accesses the System and uploads and manipulates Articles.

[1762] "Authentication information" refers to information such as a username and password used by a user to log in to a system.

[1763] "System" refers to a platform where users can upload articles and have them translated, search engine optimized, media generated, and sentiment data reflected.

[1764] "Server" refers to a computing device that handles the overall processing of the system and is responsible for data storage, analysis, translation, media generation, and delivery.

[1765] A "natural language processing engine" refers to software technology that analyzes text data and performs semantic understanding and translation.

[1766] "Analysis" refers to the process of breaking down the content of an uploaded article and understanding its meaning and grammatical structure.

[1767] "Translation" refers to the process of converting the content of the analyzed article into another language.

[1768] "SEO keywords" refers to embedding specific words or phrases within an article for search engine optimization.

[1769] "Generating images and videos" refers to automatically creating relevant visual content based on article content.

[1770] "Emotional data" refers to the emotional feedback and reactions to articles entered by users.

[1771] "Parse and translate" refers to the process of using a natural language processing engine to understand article content and translate it into multiple languages.

[1772] "Platform" refers to the website or service on which articles are published, and the medium through which users provide information to a diverse audience.

[1773] This invention relates to a system that generates and distributes articles and related media in multiple languages, reflecting user emotional data, in addition to providing SEO support. This system is realized through the cooperation of users, terminals, and a server.

[1774] A user logs into a system using a web browser (e.g., Google Chrome), enters authentication information (username and password), and the server receives the information using Apache HTTP Server or Nginx and authenticates the user by checking it against a MySQL or PostgreSQL database.

[1775] After logging in, the user selects an article file written in Japanese (e.g., "TechNews.txt") and uploads it to the system. The server receives the uploaded article file via FastAPI or the Django framework and stores it in cloud storage such as Amazon S3.

[1776] The server then analyzes the article content using Python and natural language processing libraries such as NLTK and spaCy. The analysis results are saved in JSON format. The server then uses the Google Translate API and Microsoft Translator API to automatically translate the analyzed article into multiple languages. The translation results are also saved in a database on the server.

[1777] The server uses libraries like BeautifulSoup or Scrapy to extract SEO-friendly keywords from the original article, which are then translated into the target language and embedded appropriately into each translated article.

[1778] The server also uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content, and the generated media files are saved and linked to each translated article.

[1779] When uploading an article, users enter their emotional data (e.g., "excited") through a questionnaire or a facial recognition camera. The server analyzes the emotional data using Microsoft Azure's emotion API or IBM Watson's emotion recognition API, and uses the results to adjust the content of the translated article and related media. For example, if positive emotional data is entered, brighter images and optimistic text will be added to the article.

[1780] Users can preview articles and related media translated into various languages ​​and with sentiment data reflected in the content on the system, and if there are no problems, they can issue a distribution command.

[1781] Finally, the server distributes the articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API, allowing the processed articles to be published on platforms in various countries and made accessible to readers.

[1782] As a concrete example, a user accesses the system using Google Chrome and logs in. They upload an article file called TechNews.txt. This file is analyzed using Python and spaCy and translated into English, French, and Spanish using the Google Translate API. The extracted SEO keyword "new technology" is then translated into each language and embedded in the article. The server uses DALL-E to generate technology-related images and link them to the translated article. The user inputs emotional data such as "excited," and the server analyzes the emotional data and adjusts the article and images accordingly. Once the user checks the preview and requests distribution, the server publishes the article via WordPress' XML-RPC API.

[1783] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1784] Step 1: Authenticate the user

[1785] Input: The user enters their authentication information (username and password) using a web browser.

[1786] Processing: The server receives the authentication information via Apache HTTP Server or Nginx and authenticates the user against a MySQL or PostgreSQL database.

[1787] Output: If authentication is successful, the user is granted access to the system.

[1788] Step 2: Upload your article

[1789] Input: The user selects an article file (e.g. TechNews.txt) from the terminal and clicks the upload button.

[1790] Processing: The server receives files uploaded via FastAPI or Django and stores them in cloud storage such as Amazon S3.

[1791] Output: Article files are securely stored on the server.

[1792] Step 3: Analyzing the article

[1793] Input: The server reads the saved article file.

[1794] Processing: The server uses Python and natural language processing libraries such as NLTK and spaCy to analyze the article content, for example by tokenizing the sentences and performing morphological analysis.

[1795] Output: The analysis results are converted to JSON format and saved in the database.

[1796] Step 4: Translate the article

[1797] Input: Parsed article content

[1798] Processing: The server calls the Google Translate API or Microsoft Translator API to translate the parsed content into multiple languages ​​(English, French, Spanish, etc.).

[1799] Output: The translated article is saved in the database.

[1800] Step 5: Extract and embed SEO keywords

[1801] Input: Original article content

[1802] Processing: The server uses libraries such as BeautifulSoup or Scrapy to extract SEO-friendly keywords, translates the extracted keywords into the target language, and embeds them appropriately in each translated article.

[1803] Output: The translated article with embedded SEO keywords is saved in the database.

[1804] Step 6: Generate related media

[1805] Input: Article content

[1806] Processing: The server uses generative AI models such as OpenAI's DALL-E and DeepArt to automatically generate images and videos based on the article content.

[1807] Output: The generated media files are linked to each translated article and stored in a database.

[1808] Step 7: Acquire and analyze emotion data

[1809] Input: The user inputs emotion data through a questionnaire or facial recognition camera.

[1810] Processing: The server analyzes the emotion data using Microsoft Azure's emotion API and IBM Watson's emotion recognition API.

[1811] Output: The analyzed emotion data is stored in a database.

[1812] Step 8: Reflecting emotional data

[1813] Input: Parsed sentiment data and translated article content

[1814] Processing: The server adjusts the content of the translated article and related media based on the sentiment data. For example, if there is positive sentiment data, it adds brighter colors and more positive expressions to the article.

[1815] Output: The adjusted articles and media are stored in a database.

[1816] Step 9: Preview your article

[1817] Input: Articles and related media translated into various languages ​​and updated with sentiment data

[1818] Processing: The user previews these contents on the system, visually checks them, and makes corrections if necessary.

[1819] Output: If the user is satisfied with the content, he / she issues a distribution instruction.

[1820] Step 10: Article Distribution

[1821] Input: Articles and related media for which distribution instructions have been issued

[1822] Processing: The server delivers articles to platforms such as WordPress, Medium, and Wix via XML-RPC API or JSON API.

[1823] Output: The processed articles are published on national platforms and made accessible to readers.

[1824] (Application example 2)

[1825] 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."

[1826] Conventional content distribution systems required users to manually translate articles into multiple languages, implement SEO measures, and generate related media. Furthermore, there was a lack of technology to automatically generate and distribute content that reflected user sentiment. This made the article generation and distribution process time-consuming and labor-intensive, making it difficult to disseminate personalized information.

[1827] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for users to upload articles, means for the server to analyze the uploaded articles, means for the server to automatically translate the analyzed articles into multiple languages, means for the server to extract and embed SEO keywords into the translated articles, means for the server to generate related images and videos and link them to the articles, means for the server to acquire and analyze user emotion data, means for the server to adjust the content of the articles and related media based on the emotion data, and means for the server to distribute the processed articles to platforms in each country. This enables users to quickly generate and distribute content that is multilingual and reflects emotions.

[1828] A "user" is a person or entity that uploads articles to the system and issues previews and distribution instructions.

[1829] The "server" is a computer system that analyzes articles, translates them, implements SEO measures, generates media, acquires and analyzes emotional data, and adjusts the content, before distributing the articles to platforms in each country.

[1830] "Articles" refer to text content uploaded by users and are subject to translation into various languages.

[1831] "Analysis" is the process of understanding the content of the uploaded article and extracting the necessary information.

[1832] "Machine translation" is the process of mechanically converting analyzed articles into multiple target languages.

[1833] "SEO keywords" are specific important words or phrases used to rank articles in search engines.

[1834] "Related images and videos" are visual media files generated based on the article content and presented together with the article.

[1835] "Emotion data" is information that represents the user's emotional state, and is obtained through questionnaires or facial expression recognition.

[1836] A "platform" is an online medium or site that exists in each country and is the place where articles are distributed and published.

[1837] "Preview" refers to the display confirmation performed by the user as a final check of the article and related media.

[1838] An "emotion engine" is a software tool that analyzes acquired emotional data and adjusts content based on the results.

[1839] This invention is a system that significantly simplifies the user article creation process and efficiently delivers more personalized content by supporting multiple languages ​​and reflecting emotional data. This system allows users to upload articles and automatically performs each step of article analysis, translation, SEO measures, media generation, emotional data acquisition and analysis, content adjustment, and distribution.

[1840] Hardware and software used

[1841] Hardware: Smartphones, smart glasses, head-mounted displays, cloud servers

[1842] Software: Python, Google Cloud Translation API, Elasticsearch, AWS Rekognition, MySQL, WordPress CMS

[1843] User actions

[1844] Users log in to the system using their smartphones, smart glasses, or head-mounted displays to upload articles. When uploading, users can also provide their own emotional data, which can be done through a questionnaire or facial recognition using the smartphone camera.

[1845] Server operations

[1846] The server processes the uploaded articles and sentiment data through the following process:

[1847] 1. Receiving and saving articles

[1848] The server receives the uploaded article files and stores them in a MySQL database.

[1849] 2. Article analysis and translation

[1850] A Python script is used to run an NLP engine (natural language processing engine) to analyze the article content.

[1851] Use the Google Cloud Translation API to automatically translate articles into multiple target languages.

[1852] 3. SEO

[1853] Using Elasticsearch, we automatically extract keywords that are effective for SEO from the original Japanese article.

[1854] The extracted keywords are translated into the target language and embedded appropriately into the translated articles in each language.

[1855] 4. Generate related media

[1856] Use AWS Rekognition to generate relevant images and videos based on the article content.

[1857] The generated media files are linked to the corresponding translated articles and stored in the WordPress CMS.

[1858] 5. Acquiring and Reflecting Emotional Data

[1859] The emotion acquisition module is used to collect emotion data provided by users (survey results and facial expression recognition data).

[1860] The server sends this emotional data to the emotion engine and adjusts the content of the translated article and related media based on the analysis results.

[1861] For example, if positive sentiment data is identified, use a brighter or more optimistic tone for the article or media.

[1862] Article preview and distribution

[1863] The server provides the adjusted article to the user for preview, and once the user confirms the distribution instructions, the server distributes the adjusted article to platforms in each country and makes it public.

[1864] Examples of prompt statements

[1865] Example prompts to input to a generative AI model:

[1866] "This article talks about the introduction of innovative technology. Your SEO keywords are 'new technology,' 'innovation,' and 'introduction.' Use 'excitement' as your emotional data and write the article in a bright, optimistic tone."

[1867] In this way, users can create and distribute multilingual content efficiently and personalizedly.

[1868] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1869] Step 1:

[1870] Users log in to the system using their smartphone, smart glasses, or head-mounted display. When logging in, authentication information is entered, which is received by the server and verified against information in a MySQL database. If authentication is successful, the user can proceed to the article upload screen.

[1871] Step 2:

[1872] The user selects an article file and uploads it to the system. The uploaded file is sent to the server, which receives it and stores it in a MySQL database. The input is the article file uploaded by the user, and the output is the article data stored in the database.

[1873] Step 3:

[1874] The server reads the article file and sends it to an NLP engine (natural language processing engine) using a Python script to analyze the article content. The analysis results include the article structure and key points of the content. The input is the saved article data, and the output is the analyzed article content.

[1875] Step 4:

[1876] Based on the analysis results, the server uses the Google Cloud Translation API to automatically translate the article into multiple target languages ​​(e.g., English, French, Spanish, etc.) The input is the analysis results, and the output is the article data translated into each target language.

[1877] Step 5:

[1878] The server uses Elasticsearch to automatically extract important SEO keywords from the original Japanese article. The extracted keywords are also translated into the target language and appropriately embedded in the translated article in each language. The input is the original article data and the translated article data, and the output is the translated article with SEO measures applied.

[1879] Step 6:

[1880] The server uses AWS Rekognition to automatically generate related images and videos based on the article content. The generated media files are linked to the corresponding translated article and saved in the WordPress CMS. The input is the translated article data, and the output is a media file containing related images and videos.

[1881] Step 7:

[1882] When uploading an article, users provide their own emotional data. This can be done through a questionnaire or facial recognition using a smartphone camera. The server acquires this emotional data and sends it to the emotion engine for analysis. The input is the user's emotional data, and the output is the analyzed emotional data.

[1883] Step 8:

[1884] The server adjusts the content of the translated article and related media based on the emotional data. For example, if positive emotional data is recognized, it will use a brighter or more optimistic tone for the article or media. The input is the analyzed emotional data and the translated article and media data, and the output is the adjusted content.

[1885] Step 9:

[1886] The server provides the adjusted article and media to the user for preview. The user checks the content and, if there are no problems, issues a distribution command. The input is the adjusted content, and the output is the user's distribution command.

[1887] Step 10:

[1888] The server follows the user's instructions and distributes the adjusted article to the relevant platforms in each country. The article is then published and made accessible to a diverse audience. The input is the distribution instructions and adjusted content, and the output is the article published on each platform in each country.

[1889] 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.

[1890] 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.

[1891] 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.

[1892] 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.

[1893] 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.

[1894] 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.

[1895] 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).

[1896] 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.

[1897] 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."

[1898] 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.

[1899] 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).

[1900] 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.

[1901] 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.

[1902] 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.

[1903] 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.

[1904] 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.

[1905] 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.

[1906] 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.

[1907] 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.

[1908] 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.

[1909] 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.

[1910] The following is further disclosed regarding the above embodiment.

[1911] (Claim 1)

[1912] a means for users to upload articles;

[1913] a means for the server to analyze the uploaded articles;

[1914] A means for the server to automatically translate the analyzed articles into multiple languages;

[1915] The server extracts and embeds SEO keywords into the translated articles.

[1916] A means for the server to generate relevant images and videos and link them to articles;

[1917] The system includes a means for the server to distribute the processed articles to platforms in each country.

[1918] (Claim 2)

[1919] 10. The system of claim 1, further comprising means for a user to preview an article and instruct distribution.

[1920] (Claim 3)

[1921] 10. The system of claim 1, wherein the server includes means for analyzing and translating article content using a natural language processing engine.

[1922] "Example 1"

[1923] (Claim 1)

[1924] a means for a user to upload articles using a computer terminal;

[1925] a means for the server to analyze the uploaded articles using a natural language processing engine;

[1926] A means for the server to automatically translate the analyzed articles into multiple languages;

[1927] The server extracts and embeds SEO keywords into the translated articles.

[1928] The server uses a generative AI model to automatically generate related images and videos and link them to articles.

[1929] The system includes a means for the server to distribute the processed articles to web platforms in each country.

[1930] (Claim 2)

[1931] 10. The system of claim 1, further comprising means for a user to preview an article and instruct distribution.

[1932] (Claim 3)

[1933] 10. The system of claim 1, wherein the server includes means for analyzing and translating article content using a natural language processing engine.

[1934] "Application Example 1"

[1935] (Claim 1)

[1936] a means for users to upload articles;

[1937] a means for the server to analyze the uploaded articles;

[1938] A means for the server to automatically translate the analyzed articles into multiple languages;

[1939] The server extracts and embeds SEO keywords into the translated articles.

[1940] A means for the server to generate relevant images and videos and link them to articles;

[1941] The server distributes the processed articles to platforms in each country.

[1942] a means for detecting a visually recognized object by a user using a content browsing device and automatically generating advertising content based on the object;

[1943] A means for translating the server-generated advertising content into multiple languages ​​and implementing SEO measures;

[1944] The system includes means for a user to view the translated advertising content on a content viewing device and render it in a designated visual area.

[1945] (Claim 2)

[1946] 10. The system of claim 1, further comprising means for a user to preview an article and instruct distribution.

[1947] (Claim 3)

[1948] 10. The system of claim 1, wherein the server includes means for analyzing and translating article content using a natural language processing engine.

[1949] "Example 2: Combining Emotion Engines"

[1950] (Claim 1)

[1951] a means for a user to log into the system using authentication information;

[1952] a means for users to upload articles;

[1953] a means for the server to store the uploaded articles;

[1954] a means for the server to analyze the article using a natural language processing engine;

[1955] A means for the server to automatically translate the analyzed articles into multiple languages;

[1956] a means for the server to store the translated articles;

[1957] The server extracts SEO keywords and embeds them in the translated article.

[1958] A means for the server to generate images and videos based on the article content;

[1959] A way for the server to link relevant images and videos to articles,

[1960] a means for a user to input emotion data;

[1961] a means for the server to analyze the sentiment data and adjust the translated articles and related media;

[1962] The system includes a means for the server to distribute the processed articles to platforms in each country.

[1963] (Claim 2)

[1964] 10. The system of claim 1, further comprising means for a user to preview and instruct distribution of articles and related media translated into each language and reflecting the sentiment data.

[1965] (Claim 3)

[1966] 10. The system of claim 1, wherein the server includes means for analyzing and translating article content using a natural language processing engine.

[1967] "Application example 2 when combining emotion engines"

[1968] (Claim 1)

[1969] a means for users to upload articles;

[1970] a means for the server to analyze the uploaded articles;

[1971] A means for the server to automatically translate the analyzed articles into multiple languages;

[1972] The server extracts and embeds SEO keywords into the translated articles.

[1973] A means for the server to generate relevant images and videos and link them to the article;

[1974] A means for the server to acquire and analyze user emotion data;

[1975] A means for the server to adjust the content of articles and related media based on emotion data;

[1976] The system includes a means for the server to distribute the processed articles to platforms in each country.

[1977] (Claim 2)

[1978] 10. The system of claim 1, further comprising means for a user to preview an article and instruct distribution.

[1979] (Claim 3)

[1980] 10. The system of claim 1, wherein the server includes means for analyzing and translating article content using a natural language processing engine. [Explanation of symbols]

[1981] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for users to upload articles; a means for the server to analyze the uploaded articles; A means for the server to automatically translate the analyzed articles into multiple languages; The server extracts and embeds SEO keywords into the translated articles. A means for the server to generate relevant images and videos and link them to articles; The system includes a means for the server to distribute the processed articles to platforms in each country.

2. 2. The system of claim 1, further comprising means for a user to check a preview of an article and to instruct distribution.

3. 10. The system of claim 1, wherein the server includes means for analyzing and translating the content of the article using a natural language processing engine.

Images