system

Abstract

Provide a system. [Solution] A means of analyzing search keywords entered by users; A means of extracting related keywords based on the analysis results and collecting information from various databases; A means for automatically generating articles using natural language generation technology based on the collected information; a means for notifying the person in charge of the generated article; A method to check the articles revised by the person in charge again using natural language processing technology, A way to publish the article on the site after the check is complete, A means to monitor and provide feedback on article performance after publication; A system including:

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] Improving website SEO requires a significant amount of time and effort to efficiently gather the information users are looking for and then create and publish articles based on that information. Each process, including research, article creation, proofreading, and post-publication checks and updates, requires a large number of human resources, resulting in delays and issues with information not being kept up to date. Furthermore, to ensure that articles continue to perform well after publication, they must be updated to quickly respond to new trends and service changes, which is also a time-consuming issue. To solve these issues, an efficient, automated system is needed. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. First, a means is provided for analyzing search keywords entered by a user, extracting related keywords based on the analysis results, and collecting information from various databases. The system includes a means for automatically generating articles using natural language generation technology based on the collected information, a means for notifying a person in charge of the generated articles, a means for rechecking articles revised by the person in charge using natural language processing technology, a means for publishing the checked articles on a website, and a means for monitoring the performance of the articles after publication and providing feedback. Furthermore, the system includes a means for periodically checking the articles based on new trends and service changes after publication and proposing updates, and a means for accumulating performance data on published articles and using that data to generate the next article, thereby ensuring the immediacy and quality of information and achieving efficient SEO improvements.

[0006] "Search keywords" are words or phrases that people type into a search engine or website search box to find specific information.

[0007] "Analysis" is the process of breaking down and classifying input data into a computer and extracting essential meanings and relationships.

[0008] "Related keywords" are other keywords or phrases that are highly relevant to the original search keywords and that are extracted through analysis.

[0009] A "database" is a collection of data organized according to specific rules that can be quickly accessed, searched, and updated by a computer.

[0010] "Natural language generation technology" refers to technology that enables computer programs to automatically generate meaningful sentences using human language.

[0011] An "article" is a collection of information about a particular topic expressed as text, and is typically published on websites or in publications.

[0012] A "person in charge" is a human operator who has a designated role and checks, corrects, and updates the content of articles.

[0013] "Natural language processing technology" refers to a set of techniques used by computers to understand, generate, and process human language.

[0014] "Publishing" refers to the process of making an article publicly available on a website or other platform.

[0015] "Performance" is an indicator that shows how much a published article is viewed and how much impact it has on readers.

[0016] "Monitoring" refers to the process by which a computer system regularly observes and records certain performance data and other indicators.

[0017] "Feedback" is the process of returning improvements and corrections based on the results of monitoring, etc.

[0018] An "update proposal" is a specific suggestion for improving or revising the content of an article based on new information or changes.

[0019] A "system" is a collection of devices and software in which multiple elements work together to achieve a specific purpose. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. The program processing of an embodiment of this system will be specifically explained in natural language.

[0042] First, a user enters a specific keyword into a search box on a website. This can be a specific theme, such as "latest SEO trends," or a topic of interest. The server receives the keyword and begins analyzing it. This analysis evaluates the relevance and trendiness of the entered keyword and extracts related keywords.

[0043] Next, the server collects reliable information from various databases and the web based on the extracted related keywords. For example, based on related keywords such as "SEO 2023" and "search engine algorithm changes," it retrieves the latest information from reliable news sites, academic papers, industry blogs, etc.

[0044] Because the collected data is not always consistent, the server filters it and organizes important information, using NLP (natural language processing) technology to evaluate the usefulness of the data and extract only high-quality information.

[0045] The server then uses NLG (Natural Language Generation) technology to generate natural-sounding sentences based on the filtered data, such as a draft article on "The Latest SEO Trends for 2023." This process is fast and automatic.

[0046] The generated draft is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once that is complete, the draft is returned to the server.

[0047] The server then uses NLP technology to check the revised draft again for grammar and consistency. Once this step is complete, the article is finally published by the server. Furthermore, even after publication, the server continues to monitor the article's performance, collecting data such as the number of views and click-through rates.

[0048] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked and published again.

[0049] Through the above process, the present invention provides an efficient system for improving SEO and can quickly provide users with the latest, high-quality information they desire. The system also continuously monitors the performance of published articles and quickly updates them as needed, ensuring that the latest information is always available. In this way, the present invention maximizes SEO effectiveness and enhances the competitiveness of websites.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] A user types specific keywords into a search box on a website, which relate to the information they want to know or the topic that interests them.

[0053] Step 2:

[0054] The server analyzes the keywords entered and evaluates their relevance, using natural language processing technology to interpret the meaning and context of the keywords.

[0055] Step 3:

[0056] The server extracts related keywords based on the analysis results. For example, if the keyword "latest SEO trends" is entered, related keywords such as "SEO 2023" and "search engine algorithm changes" will be extracted.

[0057] Step 4:

[0058] The server gathers reliable information from various databases and the web based on relevant keywords, including news sites, academic papers, industry blogs, and other reliable sources.

[0059] Step 5:

[0060] The server organizes and filters the collected data, using NLP techniques to evaluate the usefulness of the data and extract only the important information.

[0061] Step 6:

[0062] The server uses NLG (Natural Language Generation) technology to generate a draft article based on the filtered data, such as an article about "Latest SEO Trends for 2023."

[0063] Step 7:

[0064] The terminal notifies the person in charge of the generated article draft, including a request to review and revise the draft.

[0065] Step 8:

[0066] The user (person in charge) checks the article draft and makes corrections or additions as necessary. Here, they add missing information and check the accuracy of the content.

[0067] Step 9:

[0068] The device then sends the revised article back to the server, which receives it and again checks its grammar and consistency using NLP technology.

[0069] Step 10:

[0070] Once the server has completed the check, the article is published. This process also includes SEO-friendly settings such as setting metadata and adding internal links.

[0071] Step 11:

[0072] After publishing, the server monitors the performance of the article, including metrics such as views, time spent, and click-through rates.

[0073] Step 12:

[0074] The server periodically checks the articles and determines if they need to be updated based on new trends or changes in the service.

[0075] Step 13:

[0076] If a device is needed, a notification is sent to the person in charge to request that they update the article. Once the user (person in charge) has completed the update, they will republish the article.

[0077] This creates an efficient process for improving SEO and ensures the timeliness and quality of information.

[0078] Example 1

[0079] 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."

[0080] The traditional article generation process for SEO improvement required a lot of manual work, which made it inefficient and time-consuming. Furthermore, updates to keep up with rapidly changing trends were delayed, resulting in outdated information being left behind. Furthermore, insufficient filtering and evaluation of the collected information could result in a decline in the quality of the articles.

[0081] 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.

[0082] In this invention, the server includes means for analyzing search keywords entered by users, means for extracting related keywords based on the analysis results and collecting information from various information sources, means for automatically generating articles based on the collected information using natural language generation technology, means for notifying users of the generated articles, means for rechecking articles revised by users using natural language processing technology, means for publishing the articles on the website after the check is complete, means for monitoring the performance of the articles after publication and providing feedback, means for filtering the collected data to evaluate their usefulness, and means for periodically reviewing published articles and determining whether they need to be updated. This streamlines the article generation process for improving SEO and enables the provision of fast, high-quality information.

[0083] "Analysis" is the process of analyzing the search keywords entered by the user and evaluating their meaning and relevance.

[0084] "Related keywords" are keywords that are related to the keywords entered by the user and are extracted based on search results and trends on search engines.

[0085] "Sources" refers to various databases and websites that provide reliable data.

[0086] "Automatic generation" is the process by which a computer program automatically creates articles based on collected information.

[0087] "Notification" is a communication method for informing users of generated draft articles.

[0088] "Natural language processing technology" is a set of technologies that enable computers to understand, generate, and process human language.

[0089] A "Website" is a collection of information that is publicly available on the Internet and accessible to users.

[0090] "Monitoring" is the process of monitoring the performance of published articles in real time.

[0091] "Feedback" is information used to evaluate the performance of an article based on monitoring results and reflect it in the next steps.

[0092] "Filtering" is the process of selecting useful data from collected information and eliminating unnecessary data.

[0093] "Review" is the process of reevaluating a published article to determine whether the content needs to be updated.

[0094] "Updating" is the process of improving or changing an existing article based on new information or trends.

[0095] The present invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. An embodiment of this system will be described in detail below.

[0096] First, a user enters a specific keyword into a search box on a website, such as a topic like "latest SEO trends." The server receives the keyword and begins analyzing it. Here, it uses tools like Google® Trends API and SEMrush to evaluate the relevance and trendiness of the entered keyword and extract related keywords.

[0097] Next, the server collects reliable information from various sources based on the extracted related keywords, such as Google Scholarly, News API, and RSS feeds, to obtain the latest information based on related keywords such as "SEO 2023" and "search engine algorithm changes."

[0098] Because the collected data is not always consistent, the server filters it and organizes important information using natural language processing (NLP) models such as BERT and GPT-3 (registered trademark) to evaluate the usefulness of the data and extract only high-quality information.

[0099] The server then uses natural language generation (NLG) technology to generate natural-sounding sentences based on the filtered data. Specifically, it uses the GPT-3 API to generate a draft article on "The Latest SEO Trends for 2023." This process is fast and automated.

[0100] The generated draft is notified to the person in charge via their terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once this is complete, the draft is returned to the server.

[0101] The server then checks the revised draft again using NLP techniques to ensure grammar and consistency. Once this step is complete, the article is finally published by the server, for example by publishing the article using the WordPress API.

[0102] After publication, the server monitors the performance of the article and collects data such as the number of views and click-through rates, using the Google Analytics API.

[0103] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked again and published.

[0104] Below are some examples of prompt sentences.

[0105] Generate in-depth articles on the latest SEO trends for 2023.

[0106] When this prompt is input into the generative AI model (GPT-3), the server generates a draft of the "Latest SEO Trends in 2023," and the process proceeds. This system makes it possible to quickly provide users with the latest, high-quality information they desire, maximizing SEO effectiveness.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] A user enters a specific keyword into a search box, for example, "latest SEO trends," and this input is sent to the server.

[0110] Input: The keyword entered by the user (e.g., "latest SEO trends")

[0111] Output: Keyword data for analysis

[0112] Specific operation: The user inputs a keyword through the web interface and submits it. The server receives this input.

[0113] Step 2:

[0114] The server receives the keywords entered by the user and begins analysis, using the Google Trends API and SEMrush to evaluate and extract related keywords and their trending nature.

[0115] Input: Keyword data entered by the user

[0116] Output: List of related keywords

[0117] What it does: The server sends a request to the Google Trends API or SEMrush to retrieve related keywords and their trend data.

[0118] Step 3:

[0119] Based on the extracted related keywords, the server collects reliable information from various sources, such as Google Scholarly, News API, and RSS feeds.

[0120] Input: List of related keywords

[0121] Output: Collected information data

[0122] Specific operation: The server sends requests to multiple information sources based on related keywords and collects the returned information.

[0123] Step 4:

[0124] The server filters the collected data and organizes important information, using NLP models such as BERT and GPT-3 to evaluate the usefulness of the data and extract only high-quality information.

[0125] Input: Collected information data

[0126] Output: Filtered useful information data

[0127] How it works: The server uses NLP models to assess the quality of the information and select important data.

[0128] Step 5:

[0129] The server uses natural language generation (NLG) technology to generate draft articles based on the filtered data. Specifically, it uses the GPT-3 API to create an article on "The Latest SEO Trends in 2023."

[0130] Input: Filtered useful information data

[0131] Output: Generated article draft

[0132] What happens: The server sends a prompt to the NLG model and receives the generated text.

[0133] Step 6:

[0134] The generated draft article is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and modifies the draft.

[0135] Input: Generated article draft

[0136] Output: revised draft article

[0137] Specific operation: The server sends the draft to the terminal, and the user edits the article through a web interface.

[0138] Step 7:

[0139] The server then runs the revised draft through NLP techniques again to check grammar and consistency, and once this step is complete, the article is finally published.

[0140] Input: revised draft article

[0141] Output: Finalized article draft

[0142] What it does: The server uses NLP models to double-check the grammar and consistency of the sentence.

[0143] Step 8:

[0144] The server publishes the finalized article to the website, for example by using the WordPress API to upload the article to the website.

[0145] Input: Finalized article draft

[0146] Output: Published articles

[0147] Specific operation: The server generates and executes an API request for publishing.

[0148] Step 9:

[0149] The server monitors the performance of published articles, for example by collecting data such as views and click-through rates through the Google Analytics API.

[0150] Input: Published article

[0151] Output: Performance data

[0152] Specific operation: The server periodically sends API requests to collect and analyze performance data.

[0153] Step 10:

[0154] The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services, and if necessary, the suggested updates are sent to the user via the terminal.

[0155] Input: Performance data, new trend information

[0156] Output: Notification of whether an update is required

[0157] What it does: The server reviews articles according to a schedule, determines updates based on the latest information, and sends notifications.

[0158] Through these steps, the system provides an efficient way to improve SEO and quickly provide users with the latest, high-quality information they desire.

[0159] (Application example 1)

[0160] 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."

[0161] Providing users with the high-quality information they desire efficiently and quickly is a key challenge for modern content distribution services. In particular, improving SEO and providing content that reflects the latest trends requires automating the creation and updating of articles and content to improve accuracy. However, traditional methods often involve manual processes, from information collection to creation, publication, and feedback, which limits efficiency and accuracy. Furthermore, the lack of a function for intuitively searching and playing content using voice commands poses a challenge for improving the user experience.

[0162] 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.

[0163] In this invention, the server includes means for analyzing search keywords entered by the user, means for presenting related content based on the analyzed voice command, and means for selecting and playing the presented content, thereby efficiently providing high-quality content desired by the user and enabling access to the content through intuitive operations.

[0164] "Search keywords" are words or phrases that users enter to identify the information they are looking for.

[0165] "Natural language generation technology" is a technology that automatically generates natural-sounding sentences that sound like they were written by a human based on collected information.

[0166] "Natural language processing technology" is an artificial intelligence technology for understanding, analyzing, and processing human language.

[0167] "Voice command" is an input method that allows a user to give instructions to a system through voice.

[0168] "Content" means a collection of materials or information made available online or in digital form, including videos, articles, images, etc.

[0169] A "website" is a collection of web pages that provide information on the Internet.

[0170] "Related keywords" are words or phrases that provide additional useful information related to the search keywords entered by the user.

[0171] "Performance data" refers to data that indicates user reactions and behavior, such as the number of views and click rates of published content.

[0172] "Feedback" is the process of providing information for improving and updating content based on data collected by the system and user ratings.

[0173] "Data Source" means an external or internal database or repository used to collect or retrieve information.

[0174] "Contact Person" refers to the person or user responsible for reviewing and correcting the generated articles and content.

[0175] This invention is a content distribution system for efficiently providing users with high-quality content that they desire. This system uses a display device such as a head-mounted display (HMD) to allow users to search for content through voice commands, and automates the process of presenting and playing related content.

[0176] Hardware and software used

[0177] Hardware: Head-mounted display (HMD), server, microphone

[0178] Software: Google Cloud Speech-to-Text API, natural language processing libraries (such as spaCy and Hugging Face's BERT model), database management systems, filtering algorithms, content playback software

[0179] Processing Description

[0180] First, the user puts on the HMD and inputs voice commands into the microphone, which are then sent to a server via the Internet.

[0181] The server converts the audio data to text using the Google Cloud Speech-to-Text API, which is then analyzed using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent.

[0182] Based on the extracted keywords, the server searches the database and filters relevant content (e.g., videos, articles). The filtered content is presented on the HMD display for the user to select.

[0183] Once the user selects the desired content, the server will instruct the HMD to play that content, and feedback and additional instructions during playback can be given via voice commands.

[0184] Examples of concrete examples and prompts

[0185] For example, if a user is looking for a video about the latest SEO trends, the prompt might look something like this:

[0186] Example prompt sentence:

[0187] User: "Show me a video on the latest SEO trends"

[0188] Server: "Searching for videos on the latest SEO trends..."

[0189] / / The search process continues below.

[0190] Server: "The following videos were found:

[0191] 1. "The Latest SEO Trends for 2023"

[0192] 2. "Latest SEO Algorithm Updates"

[0193] 3. "SEO Experts Explain the Latest Trends"

[0194] Begins playing the video selected by the user.

[0195] This allows users to efficiently search for content using voice commands and use it intuitively. This system not only greatly improves user convenience but also provides relevant content quickly and accurately.

[0196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0197] Step 1:

[0198] The user wears the HMD and inputs voice commands into the microphone. This voice data is collected by the HMD microphone and sent to a server via the Internet. The input is a user's voice command such as "Show me a video about the latest SEO trends."

[0199] Step 2:

[0200] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data. The specific process of analyzing voice data (input) and converting it into text data (output) is to break down the voice signal into phonemes and assemble them into a string of characters.

[0201] Step 3:

[0202] The server analyzes the text data using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent. The specific operations for obtaining keywords and user intent (output) from text data (input) involve a process of performing morphological analysis and dependency analysis of the text to identify important words and phrases.

[0203] Step 4:

[0204] The server searches the database based on the extracted keywords and filters relevant content. The specific operations of searching for content in a database using keywords (input) and generating a list of highly relevant content (output) are creating a search query and executing a database query using that query.

[0205] Step 5:

[0206] The server presents the filtered content on the HMD display for user selection. It converts the list of filtered content (input) into a display format for the HMD and displays it on the display (output). Specific operations include setting the display layout and rendering the content.

[0207] Step 6:

[0208] When a user selects a desired content, the selection is sent to the server. The specific operation of sending the content identification information (output) to the server in response to the user's selection operation (input) is to detect the selection operation and send the data.

[0209] Step 7:

[0210] The server issues an instruction to play the selected content on the HMD. Based on the identification information of the content selected by the user (input), the content is loaded and playback begins on the HMD (output). Specific operations include streaming and playback control of the content.

[0211] 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.

[0212] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information, and by combining it with an emotion engine that recognizes user emotions, it realizes more personalized article generation. Detailed embodiments of this system are described below.

[0213] First, a user types a specific keyword into a search box on a website, such as "latest SEO trends," and this typing behavior may reflect the user's emotions and intentions.

[0214] The server then receives the keywords and begins analyzing them. The technology used here is natural language processing (NLP), which analyzes the meaning and context of the keywords. Furthermore, an emotion engine recognizes emotions based on the user's input behavior and browsing history. For example, if a user frequently searches for negative keywords such as "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[0215] The server extracts related keywords based on the recognized emotional information. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. Based on the extracted related keywords, the server collects reliable information from various databases and the web. This collection process includes news sites, academic papers, industry blogs, etc.

[0216] The collected data may be inconsistent, so the server organizes and filters it. NLP technology is used to evaluate the usefulness of the data and extract only the important information. Next, NLG (Natural Language Generation) technology is used to generate an article draft based on the filtered data. The content of this draft reflects the recognized sentiment, and if the user is feeling anxious, for example, the content is adjusted to provide reassurance.

[0217] The generated article draft is notified to the person in charge via the terminal. The user (person in charge) checks the content of the article and makes corrections or additions as necessary. The corrected draft is then returned to the server and checked for grammar and consistency using NLP technology.

[0218] After the check is complete, the server publishes the article on the site. At this point, it also performs SEO-friendly settings such as setting metadata and adding internal links. After publishing, the server monitors the article's performance and collects data such as the number of views, time spent, and click-through rate. This allows it to evaluate how effective the published article is.

[0219] Furthermore, the server periodically checks the articles and determines whether they need to be updated in response to new trends or changes in the service. If an update is necessary, a notification is sent to the person in charge via their device. The user (person in charge) updates the article, and the content is checked again by the server and finally republished.

[0220] In this way, the introduction of an emotion engine in this system enables personalized article generation based on user emotions, achieving further SEO benefits. This allows users to quickly and accurately provide the information they are looking for, improving the competitiveness of websites.

[0221] The processing flow will be explained below.

[0222] Step 1:

[0223] A user types a specific keyword into a search box on a website, for example, a user types "latest SEO trends."

[0224] Step 2:

[0225] The server receives the input keywords and analyzes them using natural language processing (NLP) techniques to understand the meaning and context of the keywords.

[0226] Step 3:

[0227] The server uses an emotion engine to recognize the user's emotions based on their input behavior and browsing history. For example, if a user frequently searches for negative keywords, it can determine that the user is feeling anxious or concerned.

[0228] Step 4:

[0229] The server extracts related keywords based on the results of keyword analysis and emotion recognition. For example, if a user enters "latest SEO trends" and feels anxious, the server extracts positive related keywords such as "SEO success stories" and "effective SEO strategies."

[0230] Step 5:

[0231] The server then uses the extracted related keywords to gather reliable information from various databases and the web, such as news sites, industry blogs, and academic papers, to obtain the latest SEO information.

[0232] Step 6:

[0233] The server organizes and filters the collected information, using NLP technology to evaluate the usefulness of the data and extract only the important information. For example, it prioritizes highly reliable data and the latest information.

[0234] Step 7:

[0235] The server uses NLG (Natural Language Generation) technology to generate article drafts based on the filtered data, which include reassuring content that reflects the perceived user sentiment.

[0236] Step 8:

[0237] The terminal notifies the person in charge of the generated article draft. The user (person in charge) receives the notification and checks the content of the article. For example, he / she checks the corrections and missing information in the draft.

[0238] Step 9:

[0239] The user modifies the draft article and adds additional information, for example adding the latest data or industry insights.

[0240] Step 10:

[0241] The device then sends the revised article back to the server, which receives it and again uses NLP techniques to check for grammar and consistency.

[0242] Step 11:

[0243] After the check is complete, the server publishes the article to the site, and also performs SEO-friendly settings such as setting metadata and adding internal links.

[0244] Step 12:

[0245] The server monitors the performance of the article after it is published, collecting data such as the number of views, time spent on the page, and click-through rate to evaluate its performance.

[0246] Step 13:

[0247] The server periodically checks published articles to determine if they need to be updated to keep up with new trends or changes in the service.

[0248] Step 14:

[0249] If an article needs to be updated, the device will send a notification to the person in charge. The user (person in charge) will receive the notification and update the article.

[0250] Step 15:

[0251] The terminal sends the updated article back to the server, which checks the updated content and republishes it if necessary.

[0252] Through the above process, this system can take user sentiment into consideration and efficiently collect, generate, and publish information, maximizing SEO effectiveness.

[0253] Example 2

[0254] 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."

[0255] The Internet is overflowing with information, making it difficult to efficiently gather and provide the appropriate and useful information users desire. Furthermore, personalized article generation that takes user sentiment into consideration is uncommon, and there is no consistent method for improving user experience. In particular, it is difficult to dynamically update content while maintaining article quality and responding to the latest trends and service changes.

[0256] 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.

[0257] In this invention, the server includes a means for analyzing search keywords entered by users, a means for extracting related keywords based on the analysis results and the user's emotion recognition results, and collecting information from various databases, and a means for automatically generating articles using natural language generation technology based on the collected information. This enables personalized article generation that takes user emotions into consideration. The system also includes a means for notifying a person in charge of the generated article, and after the person in charge has revised the article and checked it again using natural language processing technology, the article is published on the site, and metadata is set and internal links are added. Furthermore, by including a means for monitoring the performance of the article after publication and providing feedback, and a means for periodically checking published articles and notifying the person in charge when updates are necessary, the system can always provide the latest information.

[0258] "Search keywords" are specific words or phrases that users type into a website's search box.

[0259] "Analysis" is the process of using a computer program to understand the meaning and context of the search keywords entered.

[0260] "Emotion recognition" is a technology that determines what emotions a user is feeling based on their input behavior and past browsing history.

[0261] "Related keywords" are other words or phrases that are relevant to the user's interests based on the analysis and emotion recognition results.

[0262] "Information gathering" is the process of obtaining useful data from various databases on the Internet based on the extracted related keywords.

[0263] "Natural language generation technology" is a technology that automatically creates text that humans can understand using collected data.

[0264] An "article draft" is an initial version of an article that is automatically generated using natural language generation technology.

[0265] "Notification" is an action of notifying the person in charge of the generated article draft.

[0266] "Revising" is the process by which the person in charge reviews the contents of the article draft and makes any necessary changes.

[0267] "Natural language processing technology" is a computer program that checks the grammar and consistency of revised articles.

[0268] "Publishing" means making an article that has passed the check available for viewing on the website.

[0269] "Metadata setting" is the process of setting keywords and descriptions to improve SEO effectiveness when publishing an article.

[0270] "Internal linking" is the process of embedding links to related pages within your articles to improve the overall SEO effectiveness of your website.

[0271] "Performance monitoring" involves collecting data such as the number of views, time spent, and click-through rate of published articles to evaluate their effectiveness.

[0272] "Feedback" is the process of identifying areas for improvement based on the results of performance monitoring and communicating them to the person in charge.

[0273] "Regular checks" refer to the process of periodically reviewing published articles to determine whether they need to be updated to keep up with the latest trends or service changes.

[0274] "Update notification" is an action that notifies the person in charge when an article needs to be updated.

[0275] The "person in charge" is a person who is responsible for checking the generated article draft and making any necessary corrections or updates.

[0276] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information. Furthermore, by combining it with an emotion engine that recognizes user emotions, more personalized article generation is realized. Detailed embodiments of the present invention are described below.

[0277] First, a user types a specific keyword into a search box on a website, for example, "latest SEO trends." At this time, the user's typing behavior may reflect emotions and intentions.

[0278] The server then receives the keywords entered by the user and analyzes them. Natural language processing (NLP) technology is used for this analysis, for example, by using the Google Cloud Natural Language API to analyze the meaning and context of the keywords. At the same time, an emotion engine (e.g., IBM Watson® Tone Analyzer) is used to recognize emotions from the user's past search history and input behavior. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will determine that the user is feeling anxious.

[0279] Next, the server extracts related keywords based on the emotion recognition results. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. In this step, the server uses natural language processing and machine learning algorithms.

[0280] The server then uses the extracted related keywords to gather reliable information from various databases, such as news sites, academic papers, industry blogs, etc. For example, it retrieves the latest information on "SEO best practices" from the Google News and Google Scholar databases.

[0281] The server then organizes and filters the collected data, using NLP techniques such as the SpaCy library to remove unnecessary information and extract only the important information.

[0282] The server then uses natural language generation (NLG) technology, such as OpenAI's GPT-3, to generate a draft article based on the filtered data, adjusting the tone and content to reflect the user's emotions and alleviate their anxiety.

[0283] The generated article draft is notified to the person in charge via the terminal, and this notification is done via email or the system's message board.

[0284] Next, the user (person in charge) receives a notification and checks the contents of the article draft, making corrections and additions as necessary to further enhance the content.

[0285] The revised draft is then sent back to the server where it is checked for grammar and consistency using NLP techniques, for example, using the Google Cloud Natural Language API.

[0286] Once the check is complete, the server publishes the article to the website, including setting metadata and adding internal links using tools like Yoast SEO, to maximize SEO effectiveness and help the article rank higher in search engines.

[0287] After publication, the server monitors the article's performance, using tools such as Google Analytics to collect data such as the number of views, time spent, and click-through rate, and displays it on a dashboard to evaluate the article's effectiveness.

[0288] Additionally, the server periodically checks published articles to determine if they need to be updated to reflect new trends or service changes. If an update is required, a notification is sent to the user via the device.

[0289] Finally, the user (person in charge) receives the update notification and updates the article content. The updated article is again checked by the server and finally republished.

[0290] Example prompt sentence:

[0291] "Write an article about the latest SEO trends. Include the following points: 1) Recent developments, 2) Success stories, and 3) Specific ways to improve. Also, be sure to provide reassurance to users, as they may be feeling anxious."

[0292] In this way, the system can generate personalized articles that reflect the user's feelings and always provide the latest information.

[0293] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0294] Step 1:

[0295] A user enters a specific keyword into a search box on a website. For example, they enter the keyword "latest SEO trends" and press the enter key. This input action triggers the system. The input data is "latest SEO trends."

[0296] Step 2:

[0297] The server receives the keywords entered by the user and analyzes them using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to analyze the meaning and context of "latest SEO trends." The input is "latest SEO trends," and the output is the analysis results.

[0298] Step 3:

[0299] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's past search history and input behavior. The input is the user's past search history and input behavior, and the output is the user's emotional state (e.g., anxiety).

[0300] Step 4:

[0301] The server extracts related keywords based on the analysis results and emotion recognition results. For example, if a user is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. The input is the analysis results and the user's emotional state, and the output is the related keywords.

[0302] Step 5:

[0303] The server uses related keywords to collect reliable information from various databases. Specifically, it obtains the latest information on "SEO success stories" from Google News, Google Scholar, etc. The input is related keywords, and the output is the collected information.

[0304] Step 6:

[0305] The server organizes and filters the collected information. It uses NLP techniques (e.g., the SpaCy library) to extract only the important information. The input is the collected information, and the output is the filtered data.

[0306] Step 7:

[0307] The server generates an article draft based on the filtered data using natural language generation (NLG) technology. Specifically, it uses OpenAI's GPT-3 to generate the article draft. The input is the filtered data, and the output is the article draft.

[0308] Step 8:

[0309] The terminal notifies the person in charge of the generated article draft. Notification is done via email or the system's message board. The input is the article draft, and the output is a notification message.

[0310] Step 9:

[0311] The user (person in charge) checks the contents of the article draft and makes corrections or additions as necessary. The input is the article draft, and the output is the corrected draft.

[0312] Step 10:

[0313] The server receives the revised draft again and checks it for grammar and consistency using NLP techniques, specifically the Google Cloud Natural Language API, with the input being the revised draft and the output being the grammar-checked draft.

[0314] Step 11:

[0315] The server publishes the checked article to the website, setting metadata and adding internal links using tools like Yoast SEO. The input is a grammar-checked draft, and the output is the published article.

[0316] Step 12:

[0317] The server monitors the performance of published articles, using tools such as Google Analytics to collect data such as number of views, time spent, click-through rates, etc. The input is the published article, and the output is performance data.

[0318] Step 13:

[0319] The server periodically checks published articles to determine whether updates are necessary to keep up with new trends or service changes. If necessary, it sends update notifications to personnel via terminals. The input is performance data and trend information, and the output is update notifications.

[0320] Step 14:

[0321] The user (person in charge) receives the notification and updates the article content. The updated article is again checked by the server and finally republished. The input is the update notification and the output is the updated article.

[0322] Through the above processing steps, the system can efficiently generate personalized articles that reflect the user's feelings and provide the latest information.

[0323] (Application example 2)

[0324] 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."

[0325] Conventional content generation systems generate and distribute articles without considering user emotions, which results in a lack of quality improvement in the user experience. Additionally, the lack of appropriate keyword adjustment and personalization based on emotions makes it difficult to provide content tailored to user interests.

[0326] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing search keywords entered by a user, means for extracting related keywords based on the analysis results and collecting information from various databases, means for automatically generating articles using natural language generation technology based on the collected information, means for recognizing the user's emotions and adjusting the related keywords based on the emotions, means for notifying the person in charge of the generated article, means for rechecking the article revised by the person in charge using natural language processing technology, means for publishing the article on the site after the check is complete, and means for monitoring the performance of the article after publication and providing feedback. This enables personalized article generation based on the user's emotions, improving the quality of the user experience.

[0327] A "user" is an individual or entity that searches for specific information through a search engine or website.

[0328] "Search keywords" are words or phrases that users enter to find specific information.

[0329] "Means of analysis" refers to methods or technologies that use natural language processing technology to understand the content and context of search keywords.

[0330] "Means for extracting related keywords" refers to methods or techniques for finding other keywords that are highly related to the analyzed search keywords.

[0331] "Various databases" are digital repositories for collecting and storing information, including news sites, academic paper databases, and industry blogs.

[0332] "Natural language generation technology" is technology for automatically generating meaningful text in human language.

[0333] "Means for automatically generating articles" refers to methods or technologies for automatically creating articles based on collected information.

[0334] "Means for recognizing emotions" refers to technology for determining emotions from user input and behavior.

[0335] "Means for adjusting related keywords based on emotions" refers to methods or techniques for reselecting appropriate keywords according to the recognized emotions of the user.

[0336] The "means for notifying the person in charge" refers to a method or technique for ensuring that the generated article is confirmed by the person in charge.

[0337] "Natural language processing technology" is a technology for analyzing human language and understanding or generating meaning.

[0338] The "means of publishing the article on the site" refers to the method or technology used to display the final reviewed article on the website.

[0339] "Article performance monitoring measures" means methods or techniques for collecting performance data, such as number of views, time spent, and click-through rates, for published articles.

[0340] "Feedback methods" are methods and techniques that use collected performance data to improve articles or generate future articles.

[0341] "Post-publication article performance monitoring measures" are methods or techniques used to evaluate how well an article is performing after it has been published.

[0342] "Means for suggesting updates" are methods or techniques for suggesting modifications to existing articles in accordance with outdated articles or new trends.

[0343] This invention is a system that analyzes search keywords entered by users, extracts related keywords based on the analysis results, and collects information from various databases. Furthermore, it recognizes the user's emotions and adjusts and generates related keywords based on those emotions, automatically generating and publishing more personalized articles. Specific embodiments for implementing this invention are described below.

[0344] Hardware and software used

[0345] Hardware: Servers, smartphones, smart glasses

[0346] Software: Natural Language Processing (NLP) module, Natural Language Generation (NLG) module, Emotion engine, API request module (e.g., requests)

[0347] Data processing and calculation

[0348] 1. Enter and analyze user search keywords

[0349] A user uses a smartphone or smart glasses to enter a specific keyword into the search box. For example, the keyword "latest SEO trends" is entered. This search keyword is sent to the natural language processing (NLP) module on the server, where analysis begins.

[0350] 2. Extracting related keywords and collecting information

[0351] The NLP module analyzes the meaning and context of the input keywords and extracts related keywords. The extracted related keywords are then used to gather information from various databases and the web. In this process, information is collected from news sites, academic paper databases, industry blogs, etc.

[0352] 3. Recognizing user emotions with an emotion engine

[0353] The server uses an emotion engine to determine the user's emotions based on the user's search keywords and past browsing history. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[0354] 4. Personalized article generation

[0355] The server adjusts relevant keywords based on the recognized emotional information. For example, positive keywords such as "SEO success stories" and "SEO improvement points" are added to a user who is feeling anxious. The NLG module then automatically generates articles based on the adjusted keywords. The content of the generated articles reflects the user's emotions and provides a sense of security.

[0356] 5. Check and publish the generated article

[0357] The generated article is notified to the person in charge and can be viewed via a smartphone or other device. The person in charge checks the content of the article and makes corrections or additions as necessary. The corrected article is then sent back to the server where it is checked for grammar and consistency by the NLP module.

[0358] 6. Publishing articles and monitoring performance

[0359] Once the article has passed the check, it is published on the site by the server. After publication, the server monitors the article's performance, including the number of views, time spent, click-through rate, etc. Performance data is collected as feedback and used when generating the next article.

[0360] Examples and prompts

[0361] For example, suppose a user enters the following keywords:

[0362] Input keywords: Latest SEO trends

[0363] Past Search History: SEO Failures and How to Succeed

[0364] In this case, the server uses an emotion engine to recognize the user's anxiety, generate positive articles such as "SEO success stories," and provide them to the user.

[0365] Example prompt sentence:

[0366] Latest SEO Trends

[0367] SEO failure case

[0368] How to succeed with SEO

[0369] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0370] Step 1:

[0371] The user enters a search keyword.

[0372] Input: A user uses a smartphone or smart glasses to type a specific keyword into a search box.

[0373] Example: A user types in the keywords "latest SEO trends."

[0374] Output: The entered search keywords are sent to the server.

[0375] Step 2:

[0376] The server analyzes the search keywords.

[0377] Input: Search keyword (e.g. latest SEO trends)

[0378] Data processing / computation: Using natural language processing (NLP) modules, we analyze the meaning and context of keywords.

[0379] Output: List of related keywords as analysis results (e.g., SEO strategies, SEO success stories)

[0380] Step 3:

[0381] The server extracts related keywords and collects information.

[0382] Input: Analyzed related keywords (e.g., SEO strategies, SEO success stories)

[0383] Data processing / calculation: Collect information from various databases (news sites, academic paper databases, industry blogs, etc.) based on related keywords.

[0384] Output: Collected information (e.g., articles and papers on the latest SEO strategies)

[0385] Step 4:

[0386] The server recognizes the user's emotions.

[0387] Input: Search keywords, past search history, browsing history (e.g., SEO failure cases, how to succeed with SEO)

[0388] Data processing / calculation: Using an emotion engine to analyze emotions (e.g., anxiety) from users' search behavior and history.

[0389] Output: Recognized emotion information (e.g., anxiety)

[0390] Step 5:

[0391] The server adjusts and generates related keywords based on the emotion information.

[0392] Input: Recognized emotion information and related keywords (e.g., anxiety, SEO strategies, SEO success stories)

[0393] Data processing / calculation: Add positive keywords based on sentiment (e.g., SEO success stories)

[0394] Output: Tailored keyword list (e.g., SEO strategies, SEO success stories, SEO improvement points)

[0395] Step 6:

[0396] The server automatically generates the articles.

[0397] Input: Tailored keyword list and collected information (e.g., SEO strategies, SEO success stories, SEO improvement points)

[0398] Data processing / computation: Uses a natural language generation (NLG) module to automatically generate personalized articles.

[0399] Output: Generated article draft (e.g., article about the latest SEO best practices)

[0400] Step 7:

[0401] The server notifies the person in charge of the generated article.

[0402] Input: Generated article draft

[0403] Specific operation: The server uses the notification API to send notifications to the person in charge's smartphone or other device.

[0404] Output: The assignee is notified and the article draft is displayed.

[0405] Step 8:

[0406] The person in charge will check and correct the content of the article.

[0407] Input: Generated article draft

[0408] Specific operations: The person in charge checks the article on a smartphone or device and makes corrections or additions as necessary.

[0409] Output: revised article draft

[0410] Step 9:

[0411] The server rechecks the modified article.

[0412] Input: Revised article draft

[0413] Data processing / calculation: Using NLP modules, grammar and consistency checks are performed.

[0414] Output: Checked article draft

[0415] Step 10:

[0416] The server publishes the article to the site.

[0417] Input: Checked article draft

[0418] Specific behavior: Publish the article on the website using the site's public API.

[0419] Output: Published articles

[0420] Step 11:

[0421] The server monitors the performance of the article after it is published.

[0422] Input: Performance data for published articles (e.g., views, time spent, click-through rate)

[0423] Data processing / calculation: Collecting and analyzing performance data.

[0424] Output: Performance report

[0425] Step 12:

[0426] The server provides feedback based on performance data.

[0427] Input: Performance Report

[0428] What it does: Based on the performance data collected, it will summarize improvements that can be used in the next article generation.

[0429] Output: Feedback for improvements

[0430] 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.

[0431] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0432] 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.

[0433] [Second embodiment]

[0434] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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).

[0440] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0445] 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."

[0446] This invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. The program processing of an embodiment of this system will be specifically explained in natural language.

[0447] First, a user enters a specific keyword into a search box on a website. This can be a specific theme, such as "latest SEO trends," or a topic of interest. The server receives the keyword and begins analyzing it. This analysis evaluates the relevance and trendiness of the entered keyword and extracts related keywords.

[0448] Next, the server collects reliable information from various databases and the web based on the extracted related keywords. For example, based on related keywords such as "SEO 2023" and "search engine algorithm changes," it retrieves the latest information from reliable news sites, academic papers, industry blogs, etc.

[0449] Because the collected data is not always consistent, the server filters it and organizes important information, using NLP (natural language processing) technology to evaluate the usefulness of the data and extract only high-quality information.

[0450] The server then uses NLG (Natural Language Generation) technology to generate natural-sounding sentences based on the filtered data, such as a draft article on "The Latest SEO Trends for 2023." This process is fast and automatic.

[0451] The generated draft is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once that is complete, the draft is returned to the server.

[0452] The server then uses NLP technology to check the revised draft again for grammar and consistency. Once this step is complete, the article is finally published by the server. Furthermore, even after publication, the server continues to monitor the article's performance, collecting data such as the number of views and click-through rates.

[0453] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked and published again.

[0454] Through the above process, the present invention provides an efficient system for improving SEO and can quickly provide users with the latest, high-quality information they desire. The system also continuously monitors the performance of published articles and quickly updates them as needed, ensuring that the latest information is always available. In this way, the present invention maximizes SEO effectiveness and enhances the competitiveness of websites.

[0455] The processing flow will be explained below.

[0456] Step 1:

[0457] A user types specific keywords into a search box on a website, which relate to the information they want to know or the topic that interests them.

[0458] Step 2:

[0459] The server analyzes the keywords entered and evaluates their relevance, using natural language processing technology to interpret the meaning and context of the keywords.

[0460] Step 3:

[0461] The server extracts related keywords based on the analysis results. For example, if the keyword "latest SEO trends" is entered, related keywords such as "SEO 2023" and "search engine algorithm changes" will be extracted.

[0462] Step 4:

[0463] The server gathers reliable information from various databases and the web based on relevant keywords, including news sites, academic papers, industry blogs, and other reliable sources.

[0464] Step 5:

[0465] The server organizes and filters the collected data, using NLP techniques to evaluate the usefulness of the data and extract only the important information.

[0466] Step 6:

[0467] The server uses NLG (Natural Language Generation) technology to generate a draft article based on the filtered data, such as an article about "Latest SEO Trends for 2023."

[0468] Step 7:

[0469] The terminal notifies the person in charge of the generated article draft, including a request to review and revise the draft.

[0470] Step 8:

[0471] The user (person in charge) checks the article draft and makes corrections or additions as necessary. Here, they add missing information and check the accuracy of the content.

[0472] Step 9:

[0473] The device then sends the revised article back to the server, which receives it and again checks its grammar and consistency using NLP technology.

[0474] Step 10:

[0475] Once the server has completed the check, the article is published. This process also includes SEO-friendly settings such as setting metadata and adding internal links.

[0476] Step 11:

[0477] After publishing, the server monitors the performance of the article, including metrics such as views, time spent, and click-through rates.

[0478] Step 12:

[0479] The server periodically checks the articles and determines if they need to be updated based on new trends or changes in the service.

[0480] Step 13:

[0481] If a device is needed, a notification is sent to the person in charge to request that they update the article. Once the user (person in charge) has completed the update, they will republish the article.

[0482] This creates an efficient process for improving SEO and ensures the timeliness and quality of information.

[0483] Example 1

[0484] 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."

[0485] The traditional article generation process for SEO improvement required a lot of manual work, which made it inefficient and time-consuming. Furthermore, updates to keep up with rapidly changing trends were delayed, resulting in outdated information being left behind. Furthermore, insufficient filtering and evaluation of the collected information could result in a decline in the quality of the articles.

[0486] 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.

[0487] In this invention, the server includes means for analyzing search keywords entered by users, means for extracting related keywords based on the analysis results and collecting information from various information sources, means for automatically generating articles based on the collected information using natural language generation technology, means for notifying users of the generated articles, means for rechecking articles revised by users using natural language processing technology, means for publishing the articles on the website after the check is complete, means for monitoring the performance of the articles after publication and providing feedback, means for filtering the collected data to evaluate their usefulness, and means for periodically reviewing published articles and determining whether they need to be updated. This streamlines the article generation process for improving SEO and enables the provision of fast, high-quality information.

[0488] "Analysis" is the process of analyzing the search keywords entered by the user and evaluating their meaning and relevance.

[0489] "Related keywords" are keywords that are related to the keywords entered by the user and are extracted based on search results and trends on search engines.

[0490] "Sources" refers to various databases and websites that provide reliable data.

[0491] "Automatic generation" is the process by which a computer program automatically creates articles based on collected information.

[0492] "Notification" is a communication method for informing users of generated draft articles.

[0493] "Natural language processing technology" is a set of technologies that enable computers to understand, generate, and process human language.

[0494] A "Website" is a collection of information that is publicly available on the Internet and accessible to users.

[0495] "Monitoring" is the process of monitoring the performance of published articles in real time.

[0496] "Feedback" is information used to evaluate the performance of an article based on monitoring results and reflect it in the next steps.

[0497] "Filtering" is the process of selecting useful data from collected information and eliminating unnecessary data.

[0498] "Review" is the process of reevaluating a published article to determine whether the content needs to be updated.

[0499] "Updating" is the process of improving or changing an existing article based on new information or trends.

[0500] The present invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. An embodiment of this system will be described in detail below.

[0501] First, a user enters a specific keyword into a search box on a website, such as a topic like "latest SEO trends." The server receives the keyword and begins analyzing it. Here, it uses tools like Google Trends API and SEMrush to evaluate the relevance and trendiness of the entered keyword and extract related keywords.

[0502] Next, the server collects reliable information from various sources based on the extracted related keywords, such as Google Scholarly, News API, and RSS feeds, to obtain the latest information based on related keywords such as "SEO 2023" and "search engine algorithm changes."

[0503] Because the collected data is not always consistent, the server filters it and organizes important information using natural language processing (NLP) models such as BERT and GPT-3 to evaluate the usefulness of the data and extract only high-quality information.

[0504] The server then uses natural language generation (NLG) technology to generate natural-sounding sentences based on the filtered data. Specifically, it uses the GPT-3 API to generate a draft article on "The Latest SEO Trends for 2023." This process is fast and automated.

[0505] The generated draft is notified to the person in charge via their terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once this is complete, the draft is returned to the server.

[0506] The server then checks the revised draft again using NLP techniques to ensure grammar and consistency. Once this step is complete, the article is finally published by the server, for example by publishing the article using the WordPress API.

[0507] After publication, the server monitors the performance of the article and collects data such as the number of views and click-through rates, using the Google Analytics API.

[0508] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked again and published.

[0509] Below are some examples of prompt sentences.

[0510] Generate in-depth articles on the latest SEO trends for 2023.

[0511] When this prompt is input into the generative AI model (GPT-3), the server generates a draft of the "Latest SEO Trends in 2023," and the process proceeds. This system makes it possible to quickly provide users with the latest, high-quality information they desire, maximizing SEO effectiveness.

[0512] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0513] Step 1:

[0514] A user enters a specific keyword into a search box, for example, "latest SEO trends," and this input is sent to the server.

[0515] Input: The keyword entered by the user (e.g., "latest SEO trends")

[0516] Output: Keyword data for analysis

[0517] Specific operation: The user inputs a keyword through the web interface and submits it. The server receives this input.

[0518] Step 2:

[0519] The server receives the keywords entered by the user and begins analysis, using the Google Trends API and SEMrush to evaluate and extract related keywords and their trending nature.

[0520] Input: Keyword data entered by the user

[0521] Output: List of related keywords

[0522] What it does: The server sends a request to the Google Trends API or SEMrush to retrieve related keywords and their trend data.

[0523] Step 3:

[0524] Based on the extracted related keywords, the server collects reliable information from various sources, such as Google Scholarly, News API, and RSS feeds.

[0525] Input: List of related keywords

[0526] Output: Collected information data

[0527] Specific operation: The server sends requests to multiple information sources based on related keywords and collects the returned information.

[0528] Step 4:

[0529] The server filters the collected data and organizes important information, using NLP models such as BERT and GPT-3 to evaluate the usefulness of the data and extract only high-quality information.

[0530] Input: Collected information data

[0531] Output: Filtered useful information data

[0532] How it works: The server uses NLP models to assess the quality of the information and select important data.

[0533] Step 5:

[0534] The server uses natural language generation (NLG) technology to generate draft articles based on the filtered data. Specifically, it uses the GPT-3 API to create an article on "The Latest SEO Trends in 2023."

[0535] Input: Filtered useful information data

[0536] Output: Generated article draft

[0537] What happens: The server sends a prompt to the NLG model and receives the generated text.

[0538] Step 6:

[0539] The generated draft article is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and modifies the draft.

[0540] Input: Generated article draft

[0541] Output: revised draft article

[0542] Specific operation: The server sends the draft to the terminal, and the user edits the article through a web interface.

[0543] Step 7:

[0544] The server then runs the revised draft through NLP techniques again to check grammar and consistency, and once this step is complete, the article is finally published.

[0545] Input: revised draft article

[0546] Output: Finalized article draft

[0547] What it does: The server uses NLP models to double-check the grammar and consistency of the sentence.

[0548] Step 8:

[0549] The server publishes the finalized article to the website, for example by using the WordPress API to upload the article to the website.

[0550] Input: Finalized article draft

[0551] Output: Published articles

[0552] Specific operation: The server generates and executes an API request for publishing.

[0553] Step 9:

[0554] The server monitors the performance of published articles, for example by collecting data such as views and click-through rates through the Google Analytics API.

[0555] Input: Published article

[0556] Output: Performance data

[0557] Specific operation: The server periodically sends API requests to collect and analyze performance data.

[0558] Step 10:

[0559] The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services, and if necessary, the suggested updates are sent to the user via the terminal.

[0560] Input: Performance data, new trend information

[0561] Output: Notification of whether an update is required

[0562] What it does: The server reviews articles according to a schedule, determines updates based on the latest information, and sends notifications.

[0563] Through these steps, the system provides an efficient way to improve SEO and quickly provide users with the latest, high-quality information they desire.

[0564] (Application example 1)

[0565] 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."

[0566] Providing users with the high-quality information they desire efficiently and quickly is a key challenge for modern content distribution services. In particular, improving SEO and providing content that reflects the latest trends requires automating the creation and updating of articles and content to improve accuracy. However, traditional methods often involve manual processes, from information collection to creation, publication, and feedback, which limits efficiency and accuracy. Furthermore, the lack of a function for intuitively searching and playing content using voice commands poses a challenge for improving the user experience.

[0567] 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.

[0568] In this invention, the server includes means for analyzing search keywords entered by the user, means for presenting related content based on the analyzed voice command, and means for selecting and playing the presented content, thereby efficiently providing high-quality content desired by the user and enabling access to the content through intuitive operations.

[0569] "Search keywords" are words or phrases that users enter to identify the information they are looking for.

[0570] "Natural language generation technology" is a technology that automatically generates natural-sounding sentences that sound like they were written by a human based on collected information.

[0571] "Natural language processing technology" is an artificial intelligence technology for understanding, analyzing, and processing human language.

[0572] "Voice command" is an input method that allows a user to give instructions to a system through voice.

[0573] "Content" means a collection of materials or information made available online or in digital form, including videos, articles, images, etc.

[0574] A "website" is a collection of web pages that provide information on the Internet.

[0575] "Related keywords" are words or phrases that provide additional useful information related to the search keywords entered by the user.

[0576] "Performance data" refers to data that indicates user reactions and behavior, such as the number of views and click rates of published content.

[0577] "Feedback" is the process of providing information for improving and updating content based on data collected by the system and user ratings.

[0578] "Data Source" means an external or internal database or repository used to collect or retrieve information.

[0579] "Contact Person" refers to the person or user responsible for reviewing and correcting the generated articles and content.

[0580] This invention is a content distribution system for efficiently providing users with high-quality content that they desire. This system uses a display device such as a head-mounted display (HMD) to allow users to search for content through voice commands, and automates the process of presenting and playing related content.

[0581] Hardware and software used

[0582] Hardware: Head-mounted display (HMD), server, microphone

[0583] Software: Google Cloud Speech-to-Text API, natural language processing libraries (such as spaCy and Hugging Face's BERT model), database management systems, filtering algorithms, content playback software

[0584] Processing Description

[0585] First, the user puts on the HMD and inputs voice commands into the microphone, which are then sent to a server via the Internet.

[0586] The server converts the audio data to text using the Google Cloud Speech-to-Text API, which is then analyzed using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent.

[0587] Based on the extracted keywords, the server searches the database and filters relevant content (e.g., videos, articles). The filtered content is presented on the HMD display for the user to select.

[0588] Once the user selects the desired content, the server will instruct the HMD to play that content, and feedback and additional instructions during playback can be given via voice commands.

[0589] Examples of concrete examples and prompts

[0590] For example, if a user is looking for a video about the latest SEO trends, the prompt might look something like this:

[0591] Example prompt sentence:

[0592] User: "Show me a video on the latest SEO trends"

[0593] Server: "Searching for videos on the latest SEO trends..."

[0594] / / The search process continues below.

[0595] Server: "The following videos were found:

[0596] 1. "The Latest SEO Trends for 2023"

[0597] 2. "Latest SEO Algorithm Updates"

[0598] 3. "SEO Experts Explain the Latest Trends"

[0599] Begins playing the video selected by the user.

[0600] This allows users to efficiently search for content using voice commands and use it intuitively. This system not only greatly improves user convenience but also provides relevant content quickly and accurately.

[0601] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0602] Step 1:

[0603] The user wears the HMD and inputs voice commands into the microphone. This voice data is collected by the HMD microphone and sent to a server via the Internet. The input is a user's voice command such as "Show me a video about the latest SEO trends."

[0604] Step 2:

[0605] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data. The specific process of analyzing voice data (input) and converting it into text data (output) is to break down the voice signal into phonemes and assemble them into a string of characters.

[0606] Step 3:

[0607] The server analyzes the text data using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent. The specific operations for obtaining keywords and user intent (output) from text data (input) involve a process of performing morphological analysis and dependency analysis of the text to identify important words and phrases.

[0608] Step 4:

[0609] The server searches the database based on the extracted keywords and filters relevant content. The specific operations of searching for content in a database using keywords (input) and generating a list of highly relevant content (output) are creating a search query and executing a database query using that query.

[0610] Step 5:

[0611] The server presents the filtered content on the HMD display for user selection. It converts the list of filtered content (input) into a display format for the HMD and displays it on the display (output). Specific operations include setting the display layout and rendering the content.

[0612] Step 6:

[0613] When a user selects a desired content, the selection is sent to the server. The specific operation of sending the content identification information (output) to the server in response to the user's selection operation (input) is to detect the selection operation and send the data.

[0614] Step 7:

[0615] The server issues an instruction to play the selected content on the HMD. Based on the identification information of the content selected by the user (input), the content is loaded and playback begins on the HMD (output). Specific operations include streaming and playback control of the content.

[0616] 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.

[0617] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information, and by combining it with an emotion engine that recognizes user emotions, it realizes more personalized article generation. Detailed embodiments of this system are described below.

[0618] First, a user types a specific keyword into a search box on a website, such as "latest SEO trends," and this typing behavior may reflect the user's emotions and intentions.

[0619] The server then receives the keywords and begins analyzing them. The technology used here is natural language processing (NLP), which analyzes the meaning and context of the keywords. Furthermore, an emotion engine recognizes emotions based on the user's input behavior and browsing history. For example, if a user frequently searches for negative keywords such as "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[0620] The server extracts related keywords based on the recognized emotional information. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. Based on the extracted related keywords, the server collects reliable information from various databases and the web. This collection process includes news sites, academic papers, industry blogs, etc.

[0621] The collected data may be inconsistent, so the server organizes and filters it. NLP technology is used to evaluate the usefulness of the data and extract only the important information. Next, NLG (Natural Language Generation) technology is used to generate an article draft based on the filtered data. The content of this draft reflects the recognized sentiment, and if the user is feeling anxious, for example, the content is adjusted to provide reassurance.

[0622] The generated article draft is notified to the person in charge via the terminal. The user (person in charge) checks the content of the article and makes corrections or additions as necessary. The corrected draft is then returned to the server and checked for grammar and consistency using NLP technology.

[0623] After the check is complete, the server publishes the article on the site. At this point, it also performs SEO-friendly settings such as setting metadata and adding internal links. After publishing, the server monitors the article's performance and collects data such as the number of views, time spent, and click-through rate. This allows it to evaluate how effective the published article is.

[0624] Furthermore, the server periodically checks the articles and determines whether they need to be updated in response to new trends or changes in the service. If an update is necessary, a notification is sent to the person in charge via their device. The user (person in charge) updates the article, and the content is checked again by the server and finally republished.

[0625] In this way, the introduction of an emotion engine in this system enables personalized article generation based on user emotions, achieving further SEO benefits. This allows users to quickly and accurately provide the information they are looking for, improving the competitiveness of websites.

[0626] The processing flow will be explained below.

[0627] Step 1:

[0628] A user types a specific keyword into a search box on a website, for example, a user types "latest SEO trends."

[0629] Step 2:

[0630] The server receives the input keywords and analyzes them using natural language processing (NLP) techniques to understand the meaning and context of the keywords.

[0631] Step 3:

[0632] The server uses an emotion engine to recognize the user's emotions based on their input behavior and browsing history. For example, if a user frequently searches for negative keywords, it can determine that the user is feeling anxious or concerned.

[0633] Step 4:

[0634] The server extracts related keywords based on the results of keyword analysis and emotion recognition. For example, if a user enters "latest SEO trends" and feels anxious, the server extracts positive related keywords such as "SEO success stories" and "effective SEO strategies."

[0635] Step 5:

[0636] The server then uses the extracted related keywords to gather reliable information from various databases and the web, such as news sites, industry blogs, and academic papers, to obtain the latest SEO information.

[0637] Step 6:

[0638] The server organizes and filters the collected information, using NLP technology to evaluate the usefulness of the data and extract only the important information. For example, it prioritizes highly reliable data and the latest information.

[0639] Step 7:

[0640] The server uses NLG (Natural Language Generation) technology to generate article drafts based on the filtered data, which include reassuring content that reflects the perceived user sentiment.

[0641] Step 8:

[0642] The terminal notifies the person in charge of the generated article draft. The user (person in charge) receives the notification and checks the content of the article. For example, he / she checks the corrections and missing information in the draft.

[0643] Step 9:

[0644] The user modifies the draft article and adds additional information, for example adding the latest data or industry insights.

[0645] Step 10:

[0646] The device then sends the revised article back to the server, which receives it and again uses NLP techniques to check for grammar and consistency.

[0647] Step 11:

[0648] After the check is complete, the server publishes the article to the site, and also performs SEO-friendly settings such as setting metadata and adding internal links.

[0649] Step 12:

[0650] The server monitors the performance of the article after it is published, collecting data such as the number of views, time spent on the page, and click-through rate to evaluate its performance.

[0651] Step 13:

[0652] The server periodically checks published articles to determine if they need to be updated to keep up with new trends or changes in the service.

[0653] Step 14:

[0654] If an article needs to be updated, the device will send a notification to the person in charge. The user (person in charge) will receive the notification and update the article.

[0655] Step 15:

[0656] The terminal sends the updated article back to the server, which checks the updated content and republishes it if necessary.

[0657] Through the above process, this system can take user sentiment into consideration and efficiently collect, generate, and publish information, maximizing SEO effectiveness.

[0658] Example 2

[0659] 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."

[0660] The Internet is overflowing with information, making it difficult to efficiently gather and provide the appropriate and useful information users desire. Furthermore, personalized article generation that takes user sentiment into consideration is uncommon, and there is no consistent method for improving user experience. In particular, it is difficult to dynamically update content while maintaining article quality and responding to the latest trends and service changes.

[0661] 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.

[0662] In this invention, the server includes a means for analyzing search keywords entered by users, a means for extracting related keywords based on the analysis results and the user's emotion recognition results, and collecting information from various databases, and a means for automatically generating articles using natural language generation technology based on the collected information. This enables personalized article generation that takes user emotions into consideration. The system also includes a means for notifying a person in charge of the generated article, and after the person in charge has revised the article and checked it again using natural language processing technology, the article is published on the site, and metadata is set and internal links are added. Furthermore, by including a means for monitoring the performance of the article after publication and providing feedback, and a means for periodically checking published articles and notifying the person in charge when updates are necessary, the system can always provide the latest information.

[0663] "Search keywords" are specific words or phrases that users type into a website's search box.

[0664] "Analysis" is the process of using a computer program to understand the meaning and context of the search keywords entered.

[0665] "Emotion recognition" is a technology that determines what emotions a user is feeling based on their input behavior and past browsing history.

[0666] "Related keywords" are other words or phrases that are relevant to the user's interests based on the analysis and emotion recognition results.

[0667] "Information gathering" is the process of obtaining useful data from various databases on the Internet based on the extracted related keywords.

[0668] "Natural language generation technology" is a technology that automatically creates text that humans can understand using collected data.

[0669] An "article draft" is an initial version of an article that is automatically generated using natural language generation technology.

[0670] "Notification" is an action of notifying the person in charge of the generated article draft.

[0671] "Revising" is the process by which the person in charge reviews the contents of the article draft and makes any necessary changes.

[0672] "Natural language processing technology" is a computer program that checks the grammar and consistency of revised articles.

[0673] "Publishing" means making an article that has passed the check available for viewing on the website.

[0674] "Metadata setting" is the process of setting keywords and descriptions to improve SEO effectiveness when publishing an article.

[0675] "Internal linking" is the process of embedding links to related pages within your articles to improve the overall SEO effectiveness of your website.

[0676] "Performance monitoring" involves collecting data such as the number of views, time spent, and click-through rate of published articles to evaluate their effectiveness.

[0677] "Feedback" is the process of identifying areas for improvement based on the results of performance monitoring and communicating them to the person in charge.

[0678] "Regular checks" refer to the process of periodically reviewing published articles to determine whether they need to be updated to keep up with the latest trends or service changes.

[0679] "Update notification" is an action that notifies the person in charge when an article needs to be updated.

[0680] The "person in charge" is a person who is responsible for checking the generated article draft and making any necessary corrections or updates.

[0681] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information. Furthermore, by combining it with an emotion engine that recognizes user emotions, more personalized article generation is realized. Detailed embodiments of the present invention are described below.

[0682] First, a user types a specific keyword into a search box on a website, for example, "latest SEO trends." At this time, the user's typing behavior may reflect emotions and intentions.

[0683] The server then receives the keywords entered by the user and analyzes them. Natural language processing (NLP) technology is used for this analysis, for example, by using the Google Cloud Natural Language API to analyze the meaning and context of the keywords. At the same time, an emotion engine (e.g., IBM Watson Tone Analyzer) is used to recognize emotions from the user's past search history and input behavior. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will determine that the user is feeling anxious.

[0684] Next, the server extracts related keywords based on the emotion recognition results. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. In this step, the server uses natural language processing and machine learning algorithms.

[0685] The server then uses the extracted related keywords to gather reliable information from various databases, such as news sites, academic papers, industry blogs, etc. For example, it retrieves the latest information on "SEO best practices" from the Google News and Google Scholar databases.

[0686] The server then organizes and filters the collected data, using NLP techniques such as the SpaCy library to remove unnecessary information and extract only the important information.

[0687] The server then uses natural language generation (NLG) technology, such as OpenAI's GPT-3, to generate a draft article based on the filtered data, adjusting the tone and content to reflect the user's emotions and ease their anxiety.

[0688] The generated article draft is notified to the person in charge via the terminal, and this notification is done via email or the system's message board.

[0689] Next, the user (person in charge) receives a notification and checks the contents of the article draft, making corrections and additions as necessary to further enhance the content.

[0690] The revised draft is then sent back to the server where it is checked for grammar and consistency using NLP techniques, for example, using the Google Cloud Natural Language API.

[0691] Once the check is complete, the server publishes the article to the website, including setting metadata and adding internal links using tools like Yoast SEO, to maximize SEO effectiveness and help the article rank higher in search engines.

[0692] After publication, the server monitors the article's performance, using tools such as Google Analytics to collect data such as the number of views, time spent, and click-through rate, and displays it on a dashboard to evaluate the article's effectiveness.

[0693] Additionally, the server periodically checks published articles to determine if they need to be updated to reflect new trends or service changes. If an update is required, a notification is sent to the user via the device.

[0694] Finally, the user (person in charge) receives the update notification and updates the article content. The updated article is again checked by the server and finally republished.

[0695] Example prompt sentence:

[0696] "Write an article about the latest SEO trends. Include the following points: 1) Recent developments, 2) Success stories, and 3) Specific ways to improve. Also, be sure to provide reassurance to users, as they may be feeling anxious."

[0697] In this way, the system can generate personalized articles that reflect the user's feelings and always provide the latest information.

[0698] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0699] Step 1:

[0700] A user enters a specific keyword into a search box on a website. For example, they enter the keyword "latest SEO trends" and press the enter key. This input action triggers the system. The input data is "latest SEO trends."

[0701] Step 2:

[0702] The server receives the keywords entered by the user and analyzes them using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to analyze the meaning and context of "latest SEO trends." The input is "latest SEO trends," and the output is the analysis results.

[0703] Step 3:

[0704] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's past search history and input behavior. The input is the user's past search history and input behavior, and the output is the user's emotional state (e.g., anxiety).

[0705] Step 4:

[0706] The server extracts related keywords based on the analysis results and emotion recognition results. For example, if a user is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. The input is the analysis results and the user's emotional state, and the output is the related keywords.

[0707] Step 5:

[0708] The server uses related keywords to collect reliable information from various databases. Specifically, it obtains the latest information on "SEO success stories" from Google News, Google Scholar, etc. The input is related keywords, and the output is the collected information.

[0709] Step 6:

[0710] The server organizes and filters the collected information. It uses NLP techniques (e.g., the SpaCy library) to extract only the important information. The input is the collected information, and the output is the filtered data.

[0711] Step 7:

[0712] The server generates an article draft based on the filtered data using natural language generation (NLG) technology. Specifically, it uses OpenAI's GPT-3 to generate the article draft. The input is the filtered data, and the output is the article draft.

[0713] Step 8:

[0714] The terminal notifies the person in charge of the generated article draft. Notification is done via email or the system's message board. The input is the article draft, and the output is a notification message.

[0715] Step 9:

[0716] The user (person in charge) checks the contents of the article draft and makes corrections or additions as necessary. The input is the article draft, and the output is the corrected draft.

[0717] Step 10:

[0718] The server receives the revised draft again and checks it for grammar and consistency using NLP techniques, specifically the Google Cloud Natural Language API, with the input being the revised draft and the output being the grammar-checked draft.

[0719] Step 11:

[0720] The server publishes the checked article to the website, setting metadata and adding internal links using tools like Yoast SEO. The input is a grammar-checked draft, and the output is the published article.

[0721] Step 12:

[0722] The server monitors the performance of published articles, using tools such as Google Analytics to collect data such as number of views, time spent, click-through rates, etc. The input is the published article, and the output is performance data.

[0723] Step 13:

[0724] The server periodically checks published articles to determine whether updates are necessary to keep up with new trends or service changes. If necessary, it sends update notifications to personnel via terminals. The input is performance data and trend information, and the output is update notifications.

[0725] Step 14:

[0726] The user (person in charge) receives the notification and updates the article content. The updated article is again checked by the server and finally republished. The input is the update notification and the output is the updated article.

[0727] Through the above processing steps, the system can efficiently generate personalized articles that reflect the user's feelings and provide the latest information.

[0728] (Application example 2)

[0729] 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."

[0730] Conventional content generation systems generate and distribute articles without considering user emotions, which results in a lack of quality improvement in the user experience. Additionally, the lack of appropriate keyword adjustment and personalization based on emotions makes it difficult to provide content tailored to user interests.

[0731] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing search keywords entered by a user, means for extracting related keywords based on the analysis results and collecting information from various databases, means for automatically generating articles using natural language generation technology based on the collected information, means for recognizing the user's emotions and adjusting the related keywords based on the emotions, means for notifying the person in charge of the generated article, means for rechecking the article revised by the person in charge using natural language processing technology, means for publishing the article on the site after the check is complete, and means for monitoring the performance of the article after publication and providing feedback. This enables personalized article generation based on the user's emotions, improving the quality of the user experience.

[0732] A "user" is an individual or entity that searches for specific information through a search engine or website.

[0733] "Search keywords" are words or phrases that users enter to find specific information.

[0734] "Means of analysis" refers to methods or technologies that use natural language processing technology to understand the content and context of search keywords.

[0735] "Means for extracting related keywords" refers to methods or techniques for finding other keywords that are highly related to the analyzed search keywords.

[0736] "Various databases" are digital repositories for collecting and storing information, including news sites, academic paper databases, and industry blogs.

[0737] "Natural language generation technology" is technology for automatically generating meaningful text in human language.

[0738] "Means for automatically generating articles" refers to methods or technologies for automatically creating articles based on collected information.

[0739] "Means for recognizing emotions" refers to technology for determining emotions from user input and behavior.

[0740] "Means for adjusting related keywords based on emotions" refers to methods or techniques for reselecting appropriate keywords according to the recognized emotions of the user.

[0741] The "means for notifying the person in charge" refers to a method or technique for ensuring that the generated article is confirmed by the person in charge.

[0742] "Natural language processing technology" is a technology for analyzing human language and understanding or generating meaning.

[0743] The "means of publishing the article on the site" refers to the method or technology used to display the final reviewed article on the website.

[0744] "Article performance monitoring measures" means methods or techniques for collecting performance data, such as number of views, time spent, and click-through rates, for published articles.

[0745] "Feedback methods" are methods and techniques that use collected performance data to improve articles or generate future articles.

[0746] "Post-publication article performance monitoring measures" are methods or techniques used to evaluate how well an article is performing after it has been published.

[0747] "Means for suggesting updates" are methods or techniques for suggesting modifications to existing articles in accordance with outdated articles or new trends.

[0748] This invention is a system that analyzes search keywords entered by users, extracts related keywords based on the analysis results, and collects information from various databases. Furthermore, it recognizes the user's emotions and adjusts and generates related keywords based on those emotions, automatically generating and publishing more personalized articles. Specific embodiments for implementing this invention are described below.

[0749] Hardware and software used

[0750] Hardware: Servers, smartphones, smart glasses

[0751] Software: Natural Language Processing (NLP) module, Natural Language Generation (NLG) module, Emotion engine, API request module (e.g., requests)

[0752] Data processing and calculation

[0753] 1. Enter and analyze user search keywords

[0754] A user uses a smartphone or smart glasses to enter a specific keyword into the search box. For example, the keyword "latest SEO trends" is entered. This search keyword is sent to the natural language processing (NLP) module on the server, where analysis begins.

[0755] 2. Extracting related keywords and collecting information

[0756] The NLP module analyzes the meaning and context of the input keywords and extracts related keywords. The extracted related keywords are then used to gather information from various databases and the web. In this process, information is collected from news sites, academic paper databases, industry blogs, etc.

[0757] 3. Recognizing user emotions with an emotion engine

[0758] The server uses an emotion engine to determine the user's emotions based on the user's search keywords and past browsing history. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[0759] 4. Personalized article generation

[0760] The server adjusts relevant keywords based on the recognized emotional information. For example, positive keywords such as "SEO success stories" and "SEO improvement points" are added to a user who is feeling anxious. The NLG module then automatically generates articles based on the adjusted keywords. The content of the generated articles reflects the user's emotions and provides a sense of security.

[0761] 5. Check and publish the generated article

[0762] The generated article is notified to the person in charge and can be viewed via a smartphone or other device. The person in charge checks the content of the article and makes corrections or additions as necessary. The corrected article is then sent back to the server where it is checked for grammar and consistency by the NLP module.

[0763] 6. Publishing articles and monitoring performance

[0764] Once the article has passed the check, it is published on the site by the server. After publication, the server monitors the article's performance, including the number of views, time spent, click-through rate, etc. Performance data is collected as feedback and used when generating the next article.

[0765] Examples and prompts

[0766] For example, suppose a user enters the following keywords:

[0767] Input keywords: Latest SEO trends

[0768] Past Search History: SEO Failures and How to Succeed

[0769] In this case, the server uses an emotion engine to recognize the user's anxiety, generate positive articles such as "SEO success stories," and provide them to the user.

[0770] Example prompt sentence:

[0771] Latest SEO Trends

[0772] SEO failure case

[0773] How to succeed with SEO

[0774] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0775] Step 1:

[0776] The user enters a search keyword.

[0777] Input: A user uses a smartphone or smart glasses to type a specific keyword into a search box.

[0778] Example: A user types in the keywords "latest SEO trends."

[0779] Output: The entered search keywords are sent to the server.

[0780] Step 2:

[0781] The server analyzes the search keywords.

[0782] Input: Search keyword (e.g. latest SEO trends)

[0783] Data processing / computation: Using natural language processing (NLP) modules, we analyze the meaning and context of keywords.

[0784] Output: List of related keywords as analysis results (e.g., SEO strategies, SEO success stories)

[0785] Step 3:

[0786] The server extracts related keywords and collects information.

[0787] Input: Analyzed related keywords (e.g., SEO strategies, SEO success stories)

[0788] Data processing / calculation: Collect information from various databases (news sites, academic paper databases, industry blogs, etc.) based on related keywords.

[0789] Output: Collected information (e.g., articles and papers on the latest SEO strategies)

[0790] Step 4:

[0791] The server recognizes the user's emotions.

[0792] Input: Search keywords, past search history, browsing history (e.g., SEO failure cases, how to succeed with SEO)

[0793] Data processing / calculation: Using an emotion engine to analyze emotions (e.g., anxiety) from users' search behavior and history.

[0794] Output: Recognized emotion information (e.g., anxiety)

[0795] Step 5:

[0796] The server adjusts and generates related keywords based on the emotion information.

[0797] Input: Recognized emotion information and related keywords (e.g., anxiety, SEO strategies, SEO success stories)

[0798] Data processing / calculation: Add positive keywords based on sentiment (e.g., SEO success stories)

[0799] Output: Tailored keyword list (e.g., SEO strategies, SEO success stories, SEO improvement points)

[0800] Step 6:

[0801] The server automatically generates the articles.

[0802] Input: Tailored keyword list and collected information (e.g., SEO strategies, SEO success stories, SEO improvement points)

[0803] Data processing / computation: Uses a natural language generation (NLG) module to automatically generate personalized articles.

[0804] Output: Generated article draft (e.g., article about the latest SEO best practices)

[0805] Step 7:

[0806] The server notifies the person in charge of the generated article.

[0807] Input: Generated article draft

[0808] Specific operation: The server uses the notification API to send notifications to the person in charge's smartphone or other device.

[0809] Output: The assignee is notified and the article draft is displayed.

[0810] Step 8:

[0811] The person in charge will check and correct the content of the article.

[0812] Input: Generated article draft

[0813] Specific operations: The person in charge checks the article on a smartphone or device and makes corrections or additions as necessary.

[0814] Output: revised article draft

[0815] Step 9:

[0816] The server rechecks the modified article.

[0817] Input: Revised article draft

[0818] Data processing / calculation: Using NLP modules, grammar and consistency checks are performed.

[0819] Output: Checked article draft

[0820] Step 10:

[0821] The server publishes the article to the site.

[0822] Input: Checked article draft

[0823] Specific behavior: Publish the article on the website using the site's public API.

[0824] Output: Published articles

[0825] Step 11:

[0826] The server monitors the performance of the article after it is published.

[0827] Input: Performance data for published articles (e.g., views, time spent, click-through rate)

[0828] Data processing / calculation: Collecting and analyzing performance data.

[0829] Output: Performance report

[0830] Step 12:

[0831] The server provides feedback based on performance data.

[0832] Input: Performance Report

[0833] What it does: Based on the performance data collected, it will summarize improvements that can be used in the next article generation.

[0834] Output: Feedback for improvements

[0835] 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.

[0836] 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.

[0837] 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.

[0838] [Third embodiment]

[0839] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0840] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0841] 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).

[0842] 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.

[0843] 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.

[0844] 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).

[0845] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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."

[0851] This invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. The program processing of an embodiment of this system will be specifically explained in natural language.

[0852] First, a user enters a specific keyword into a search box on a website. This can be a specific theme, such as "latest SEO trends," or a topic of interest. The server receives the keyword and begins analyzing it. This analysis evaluates the relevance and trendiness of the entered keyword and extracts related keywords.

[0853] Next, the server collects reliable information from various databases and the web based on the extracted related keywords. For example, based on related keywords such as "SEO 2023" and "search engine algorithm changes," it retrieves the latest information from reliable news sites, academic papers, industry blogs, etc.

[0854] Because the collected data is not always consistent, the server filters it and organizes important information, using NLP (natural language processing) technology to evaluate the usefulness of the data and extract only high-quality information.

[0855] The server then uses NLG (Natural Language Generation) technology to generate natural-sounding sentences based on the filtered data, such as a draft article on "The Latest SEO Trends for 2023." This process is fast and automatic.

[0856] The generated draft is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once that is complete, the draft is returned to the server.

[0857] The server then uses NLP technology to check the revised draft again for grammar and consistency. Once this step is complete, the article is finally published by the server. Furthermore, even after publication, the server continues to monitor the article's performance, collecting data such as the number of views and click-through rates.

[0858] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked and published again.

[0859] Through the above process, the present invention provides an efficient system for improving SEO and can quickly provide users with the latest, high-quality information they desire. The system also continuously monitors the performance of published articles and quickly updates them as needed, ensuring that the latest information is always available. In this way, the present invention maximizes SEO effectiveness and enhances the competitiveness of websites.

[0860] The processing flow will be explained below.

[0861] Step 1:

[0862] A user types specific keywords into a search box on a website, which relate to the information they want to know or the topic that interests them.

[0863] Step 2:

[0864] The server analyzes the keywords entered and evaluates their relevance, using natural language processing technology to interpret the meaning and context of the keywords.

[0865] Step 3:

[0866] The server extracts related keywords based on the analysis results. For example, if the keyword "latest SEO trends" is entered, related keywords such as "SEO 2023" and "search engine algorithm changes" will be extracted.

[0867] Step 4:

[0868] The server gathers reliable information from various databases and the web based on relevant keywords, including news sites, academic papers, industry blogs, and other reliable sources.

[0869] Step 5:

[0870] The server organizes and filters the collected data, using NLP techniques to evaluate the usefulness of the data and extract only the important information.

[0871] Step 6:

[0872] The server uses NLG (Natural Language Generation) technology to generate a draft article based on the filtered data, such as an article about "Latest SEO Trends for 2023."

[0873] Step 7:

[0874] The terminal notifies the person in charge of the generated article draft, including a request to review and revise the draft.

[0875] Step 8:

[0876] The user (person in charge) checks the article draft and makes corrections or additions as necessary. Here, they add missing information and check the accuracy of the content.

[0877] Step 9:

[0878] The device then sends the revised article back to the server, which receives it and again checks its grammar and consistency using NLP technology.

[0879] Step 10:

[0880] Once the server has completed the check, the article is published. This process also includes SEO-friendly settings such as setting metadata and adding internal links.

[0881] Step 11:

[0882] After publishing, the server monitors the performance of the article, including metrics such as views, time spent, and click-through rates.

[0883] Step 12:

[0884] The server periodically checks the articles and determines if they need to be updated based on new trends or changes in the service.

[0885] Step 13:

[0886] If a device is needed, a notification is sent to the person in charge to request that they update the article. Once the user (person in charge) has completed the update, they will republish the article.

[0887] This creates an efficient process for improving SEO and ensures the timeliness and quality of information.

[0888] Example 1

[0889] 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."

[0890] The traditional article generation process for SEO improvement required a lot of manual work, which made it inefficient and time-consuming. Furthermore, updates to keep up with rapidly changing trends were delayed, resulting in outdated information being left behind. Furthermore, insufficient filtering and evaluation of the collected information could result in a decline in the quality of the articles.

[0891] 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.

[0892] In this invention, the server includes means for analyzing search keywords entered by users, means for extracting related keywords based on the analysis results and collecting information from various information sources, means for automatically generating articles based on the collected information using natural language generation technology, means for notifying users of the generated articles, means for rechecking articles revised by users using natural language processing technology, means for publishing the articles on the website after the check is complete, means for monitoring the performance of the articles after publication and providing feedback, means for filtering the collected data to evaluate their usefulness, and means for periodically reviewing published articles and determining whether they need to be updated. This streamlines the article generation process for improving SEO and enables the provision of fast, high-quality information.

[0893] "Analysis" is the process of analyzing the search keywords entered by the user and evaluating their meaning and relevance.

[0894] "Related keywords" are keywords that are related to the keywords entered by the user and are extracted based on search results and trends on search engines.

[0895] "Sources" refers to various databases and websites that provide reliable data.

[0896] "Automatic generation" is the process by which a computer program automatically creates articles based on collected information.

[0897] "Notification" is a communication method for informing users of generated draft articles.

[0898] "Natural language processing technology" is a set of technologies that enable computers to understand, generate, and process human language.

[0899] A "Website" is a collection of information that is publicly available on the Internet and accessible to users.

[0900] "Monitoring" is the process of monitoring the performance of published articles in real time.

[0901] "Feedback" is information used to evaluate the performance of an article based on monitoring results and reflect it in the next steps.

[0902] "Filtering" is the process of selecting useful data from collected information and eliminating unnecessary data.

[0903] "Review" is the process of reevaluating a published article to determine whether the content needs to be updated.

[0904] "Updating" is the process of improving or changing an existing article based on new information or trends.

[0905] The present invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. An embodiment of this system will be described in detail below.

[0906] First, a user enters a specific keyword into a search box on a website, such as a topic like "latest SEO trends." The server receives the keyword and begins analyzing it. Here, it uses tools like Google Trends API and SEMrush to evaluate the relevance and trendiness of the entered keyword and extract related keywords.

[0907] Next, the server collects reliable information from various sources based on the extracted related keywords, such as Google Scholarly, News API, and RSS feeds, to obtain the latest information based on related keywords such as "SEO 2023" and "search engine algorithm changes."

[0908] Because the collected data is not always consistent, the server filters it and organizes important information using natural language processing (NLP) models such as BERT and GPT-3 to evaluate the usefulness of the data and extract only high-quality information.

[0909] The server then uses natural language generation (NLG) technology to generate natural-sounding sentences based on the filtered data. Specifically, it uses the GPT-3 API to generate a draft article on "The Latest SEO Trends for 2023." This process is fast and automated.

[0910] The generated draft is notified to the person in charge via their terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once this is complete, the draft is returned to the server.

[0911] The server then checks the revised draft again using NLP techniques to ensure grammar and consistency. Once this step is complete, the article is finally published by the server, for example by publishing the article using the WordPress API.

[0912] After publication, the server monitors the performance of the article and collects data such as the number of views and click-through rates, using the Google Analytics API.

[0913] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked again and published.

[0914] Below are some examples of prompt sentences.

[0915] Generate in-depth articles on the latest SEO trends for 2023.

[0916] When this prompt is input into the generative AI model (GPT-3), the server generates a draft of the "Latest SEO Trends in 2023," and the process proceeds. This system makes it possible to quickly provide users with the latest, high-quality information they desire, maximizing SEO effectiveness.

[0917] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0918] Step 1:

[0919] A user enters a specific keyword into a search box, for example, "latest SEO trends," and this input is sent to the server.

[0920] Input: The keyword entered by the user (e.g., "latest SEO trends")

[0921] Output: Keyword data for analysis

[0922] Specific operation: The user inputs a keyword through the web interface and submits it. The server receives this input.

[0923] Step 2:

[0924] The server receives the keywords entered by the user and begins analysis, using the Google Trends API and SEMrush to evaluate and extract related keywords and their trending nature.

[0925] Input: Keyword data entered by the user

[0926] Output: List of related keywords

[0927] What it does: The server sends a request to the Google Trends API or SEMrush to retrieve related keywords and their trend data.

[0928] Step 3:

[0929] Based on the extracted related keywords, the server collects reliable information from various sources, such as Google Scholarly, News API, and RSS feeds.

[0930] Input: List of related keywords

[0931] Output: Collected information data

[0932] Specific operation: The server sends requests to multiple information sources based on related keywords and collects the returned information.

[0933] Step 4:

[0934] The server filters the collected data and organizes important information, using NLP models such as BERT and GPT-3 to evaluate the usefulness of the data and extract only high-quality information.

[0935] Input: Collected information data

[0936] Output: Filtered useful information data

[0937] How it works: The server uses NLP models to assess the quality of the information and select important data.

[0938] Step 5:

[0939] The server uses natural language generation (NLG) technology to generate draft articles based on the filtered data. Specifically, it uses the GPT-3 API to create an article on "The Latest SEO Trends in 2023."

[0940] Input: Filtered useful information data

[0941] Output: Generated article draft

[0942] What happens: The server sends a prompt to the NLG model and receives the generated text.

[0943] Step 6:

[0944] The generated draft article is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and modifies the draft.

[0945] Input: Generated article draft

[0946] Output: revised draft article

[0947] Specific operation: The server sends the draft to the terminal, and the user edits the article through a web interface.

[0948] Step 7:

[0949] The server then runs the revised draft through NLP techniques again to check grammar and consistency, and once this step is complete, the article is finally published.

[0950] Input: revised draft article

[0951] Output: Finalized article draft

[0952] What it does: The server uses NLP models to double-check the grammar and consistency of the sentence.

[0953] Step 8:

[0954] The server publishes the finalized article to the website, for example by using the WordPress API to upload the article to the website.

[0955] Input: Finalized article draft

[0956] Output: Published articles

[0957] Specific operation: The server generates and executes an API request for publishing.

[0958] Step 9:

[0959] The server monitors the performance of published articles, for example by collecting data such as views and click-through rates through the Google Analytics API.

[0960] Input: Published article

[0961] Output: Performance data

[0962] Specific operation: The server periodically sends API requests to collect and analyze performance data.

[0963] Step 10:

[0964] The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services, and if necessary, the suggested updates are sent to the user via the terminal.

[0965] Input: Performance data, new trend information

[0966] Output: Notification of whether an update is required

[0967] What it does: The server reviews articles according to a schedule, determines updates based on the latest information, and sends notifications.

[0968] Through these steps, the system provides an efficient way to improve SEO and quickly provide users with the latest, high-quality information they desire.

[0969] (Application example 1)

[0970] 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."

[0971] Providing users with the high-quality information they desire efficiently and quickly is a key challenge for modern content distribution services. In particular, improving SEO and providing content that reflects the latest trends requires automating the creation and updating of articles and content to improve accuracy. However, traditional methods often involve manual processes, from information collection to creation, publication, and feedback, which limits efficiency and accuracy. Furthermore, the lack of a function for intuitively searching and playing content using voice commands poses a challenge for improving the user experience.

[0972] 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.

[0973] In this invention, the server includes means for analyzing search keywords entered by the user, means for presenting related content based on the analyzed voice command, and means for selecting and playing the presented content, thereby efficiently providing high-quality content desired by the user and enabling access to the content through intuitive operations.

[0974] "Search keywords" are words or phrases that users enter to identify the information they are looking for.

[0975] "Natural language generation technology" is a technology that automatically generates natural-sounding sentences that sound like they were written by a human based on collected information.

[0976] "Natural language processing technology" is an artificial intelligence technology for understanding, analyzing, and processing human language.

[0977] "Voice command" is an input method that allows a user to give instructions to a system through voice.

[0978] "Content" means a collection of materials or information made available online or in digital form, including videos, articles, images, etc.

[0979] A "website" is a collection of web pages that provide information on the Internet.

[0980] "Related keywords" are words or phrases that provide additional useful information related to the search keywords entered by the user.

[0981] "Performance data" refers to data that indicates user reactions and behavior, such as the number of views and click rates of published content.

[0982] "Feedback" is the process of providing information for improving and updating content based on data collected by the system and user ratings.

[0983] "Data Source" means an external or internal database or repository used to collect or retrieve information.

[0984] "Contact Person" refers to the person or user responsible for reviewing and correcting the generated articles and content.

[0985] This invention is a content distribution system for efficiently providing users with high-quality content that they desire. This system uses a display device such as a head-mounted display (HMD) to allow users to search for content through voice commands, and automates the process of presenting and playing related content.

[0986] Hardware and software used

[0987] Hardware: Head-mounted display (HMD), server, microphone

[0988] Software: Google Cloud Speech-to-Text API, natural language processing libraries (such as spaCy and Hugging Face's BERT model), database management systems, filtering algorithms, content playback software

[0989] Processing Description

[0990] First, the user puts on the HMD and inputs voice commands into the microphone, which are then sent to a server via the Internet.

[0991] The server converts the audio data to text using the Google Cloud Speech-to-Text API, which is then analyzed using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent.

[0992] Based on the extracted keywords, the server searches the database and filters relevant content (e.g., videos, articles). The filtered content is presented on the HMD display for the user to select.

[0993] Once the user selects the desired content, the server will instruct the HMD to play that content, and feedback and additional instructions during playback can be given via voice commands.

[0994] Examples of concrete examples and prompts

[0995] For example, if a user is looking for a video about the latest SEO trends, the prompt might look something like this:

[0996] Example prompt sentence:

[0997] User: "Show me a video on the latest SEO trends"

[0998] Server: "Searching for videos on the latest SEO trends..."

[0999] / / The search process continues below.

[1000] Server: "The following videos were found:

[1001] 1. "The Latest SEO Trends for 2023"

[1002] 2. "Latest SEO Algorithm Updates"

[1003] 3. "SEO Experts Explain the Latest Trends"

[1004] Begins playing the video selected by the user.

[1005] This allows users to efficiently search for content using voice commands and use it intuitively. This system not only greatly improves user convenience but also provides relevant content quickly and accurately.

[1006] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1007] Step 1:

[1008] The user wears the HMD and inputs voice commands into the microphone. This voice data is collected by the HMD microphone and sent to a server via the Internet. The input is a user's voice command such as "Show me a video about the latest SEO trends."

[1009] Step 2:

[1010] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data. The specific process of analyzing voice data (input) and converting it into text data (output) is to break down the voice signal into phonemes and assemble them into a string of characters.

[1011] Step 3:

[1012] The server analyzes the text data using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent. The specific operations for obtaining keywords and user intent (output) from text data (input) involve a process of performing morphological analysis and dependency analysis of the text to identify important words and phrases.

[1013] Step 4:

[1014] The server searches the database based on the extracted keywords and filters relevant content. The specific operations of searching for content in a database using keywords (input) and generating a list of highly relevant content (output) are creating a search query and executing a database query using that query.

[1015] Step 5:

[1016] The server presents the filtered content on the HMD display for user selection. It converts the list of filtered content (input) into a display format for the HMD and displays it on the display (output). Specific operations include setting the display layout and rendering the content.

[1017] Step 6:

[1018] When a user selects a desired content, the selection is sent to the server. The specific operation of sending the content identification information (output) to the server in response to the user's selection operation (input) is to detect the selection operation and send the data.

[1019] Step 7:

[1020] The server issues an instruction to play the selected content on the HMD. Based on the identification information of the content selected by the user (input), the content is loaded and playback begins on the HMD (output). Specific operations include streaming and playback control of the content.

[1021] 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.

[1022] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information, and by combining it with an emotion engine that recognizes user emotions, it realizes more personalized article generation. Detailed embodiments of this system are described below.

[1023] First, a user types a specific keyword into a search box on a website, such as "latest SEO trends," and this typing behavior may reflect the user's emotions and intentions.

[1024] The server then receives the keywords and begins analyzing them. The technology used here is natural language processing (NLP), which analyzes the meaning and context of the keywords. Furthermore, an emotion engine recognizes emotions based on the user's input behavior and browsing history. For example, if a user frequently searches for negative keywords such as "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[1025] The server extracts related keywords based on the recognized emotional information. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. Based on the extracted related keywords, the server collects reliable information from various databases and the web. This collection process includes news sites, academic papers, industry blogs, etc.

[1026] The collected data may be inconsistent, so the server organizes and filters it. NLP technology is used to evaluate the usefulness of the data and extract only the important information. Next, NLG (Natural Language Generation) technology is used to generate an article draft based on the filtered data. The content of this draft reflects the recognized sentiment, and if the user is feeling anxious, for example, the content is adjusted to provide reassurance.

[1027] The generated article draft is notified to the person in charge via the terminal. The user (person in charge) checks the content of the article and makes corrections or additions as necessary. The corrected draft is then returned to the server and checked for grammar and consistency using NLP technology.

[1028] After the check is complete, the server publishes the article on the site. At this point, it also performs SEO-friendly settings such as setting metadata and adding internal links. After publishing, the server monitors the article's performance and collects data such as the number of views, time spent, and click-through rate. This allows it to evaluate how effective the published article is.

[1029] Furthermore, the server periodically checks the articles and determines whether they need to be updated in response to new trends or changes in the service. If an update is necessary, a notification is sent to the person in charge via their device. The user (person in charge) updates the article, and the content is checked again by the server and finally republished.

[1030] In this way, the introduction of an emotion engine in this system enables personalized article generation based on user emotions, achieving further SEO benefits. This allows users to quickly and accurately provide the information they are looking for, improving the competitiveness of websites.

[1031] The processing flow will be explained below.

[1032] Step 1:

[1033] A user types a specific keyword into a search box on a website, for example, a user types "latest SEO trends."

[1034] Step 2:

[1035] The server receives the input keywords and analyzes them using natural language processing (NLP) techniques to understand the meaning and context of the keywords.

[1036] Step 3:

[1037] The server uses an emotion engine to recognize the user's emotions based on their input behavior and browsing history. For example, if a user frequently searches for negative keywords, it can determine that the user is feeling anxious or concerned.

[1038] Step 4:

[1039] The server extracts related keywords based on the results of keyword analysis and emotion recognition. For example, if a user enters "latest SEO trends" and feels anxious, the server extracts positive related keywords such as "SEO success stories" and "effective SEO strategies."

[1040] Step 5:

[1041] The server then uses the extracted related keywords to gather reliable information from various databases and the web, such as news sites, industry blogs, and academic papers, to obtain the latest SEO information.

[1042] Step 6:

[1043] The server organizes and filters the collected information, using NLP technology to evaluate the usefulness of the data and extract only the important information. For example, it prioritizes highly reliable data and the latest information.

[1044] Step 7:

[1045] The server uses NLG (Natural Language Generation) technology to generate article drafts based on the filtered data, which include reassuring content that reflects the perceived user sentiment.

[1046] Step 8:

[1047] The terminal notifies the person in charge of the generated article draft. The user (person in charge) receives the notification and checks the content of the article. For example, he / she checks the corrections and missing information in the draft.

[1048] Step 9:

[1049] The user modifies the draft article and adds additional information, for example adding the latest data or industry insights.

[1050] Step 10:

[1051] The device then sends the revised article back to the server, which receives it and again uses NLP techniques to check for grammar and consistency.

[1052] Step 11:

[1053] After the check is complete, the server publishes the article to the site, and also performs SEO-friendly settings such as setting metadata and adding internal links.

[1054] Step 12:

[1055] The server monitors the performance of the article after it is published, collecting data such as the number of views, time spent on the page, and click-through rate to evaluate its performance.

[1056] Step 13:

[1057] The server periodically checks published articles to determine if they need to be updated to keep up with new trends or changes in the service.

[1058] Step 14:

[1059] If an article needs to be updated, the device will send a notification to the person in charge. The user (person in charge) will receive the notification and update the article.

[1060] Step 15:

[1061] The terminal sends the updated article back to the server, which checks the updated content and republishes it if necessary.

[1062] Through the above process, this system can take user sentiment into consideration and efficiently collect, generate, and publish information, maximizing SEO effectiveness.

[1063] Example 2

[1064] 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."

[1065] The Internet is overflowing with information, making it difficult to efficiently gather and provide the appropriate and useful information users desire. Furthermore, personalized article generation that takes user sentiment into consideration is uncommon, and there is no consistent method for improving user experience. In particular, it is difficult to dynamically update content while maintaining article quality and responding to the latest trends and service changes.

[1066] 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.

[1067] In this invention, the server includes a means for analyzing search keywords entered by users, a means for extracting related keywords based on the analysis results and the user's emotion recognition results, and collecting information from various databases, and a means for automatically generating articles using natural language generation technology based on the collected information. This enables personalized article generation that takes user emotions into consideration. The system also includes a means for notifying a person in charge of the generated article, and after the person in charge has revised the article and checked it again using natural language processing technology, the article is published on the site, and metadata is set and internal links are added. Furthermore, by including a means for monitoring the performance of the article after publication and providing feedback, and a means for periodically checking published articles and notifying the person in charge when updates are necessary, the system can always provide the latest information.

[1068] "Search keywords" are specific words or phrases that users type into a website's search box.

[1069] "Analysis" is the process of using a computer program to understand the meaning and context of the search keywords entered.

[1070] "Emotion recognition" is a technology that determines what emotions a user is feeling based on their input behavior and past browsing history.

[1071] "Related keywords" are other words or phrases that are relevant to the user's interests based on the analysis and emotion recognition results.

[1072] "Information gathering" is the process of obtaining useful data from various databases on the Internet based on the extracted related keywords.

[1073] "Natural language generation technology" is a technology that automatically creates text that humans can understand using collected data.

[1074] An "article draft" is an initial version of an article that is automatically generated using natural language generation technology.

[1075] "Notification" is an action of notifying the person in charge of the generated article draft.

[1076] "Revising" is the process by which the person in charge reviews the contents of the article draft and makes any necessary changes.

[1077] "Natural language processing technology" is a computer program that checks the grammar and consistency of revised articles.

[1078] "Publishing" means making an article that has passed the check available for viewing on the website.

[1079] "Metadata setting" is the process of setting keywords and descriptions to improve SEO effectiveness when publishing an article.

[1080] "Internal linking" is the process of embedding links to related pages within your articles to improve the overall SEO effectiveness of your website.

[1081] "Performance monitoring" involves collecting data such as the number of views, time spent, and click-through rate of published articles to evaluate their effectiveness.

[1082] "Feedback" is the process of identifying areas for improvement based on the results of performance monitoring and communicating them to the person in charge.

[1083] "Regular checks" refer to the process of periodically reviewing published articles to determine whether they need to be updated to keep up with the latest trends or service changes.

[1084] "Update notification" is an action that notifies the person in charge when an article needs to be updated.

[1085] The "person in charge" is a person who is responsible for checking the generated article draft and making any necessary corrections or updates.

[1086] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information. Furthermore, by combining it with an emotion engine that recognizes user emotions, more personalized article generation is realized. Detailed embodiments of the present invention are described below.

[1087] First, a user types a specific keyword into a search box on a website, for example, "latest SEO trends." At this time, the user's typing behavior may reflect emotions and intentions.

[1088] The server then receives the keywords entered by the user and analyzes them. Natural language processing (NLP) technology is used for this analysis, for example, by using the Google Cloud Natural Language API to analyze the meaning and context of the keywords. At the same time, an emotion engine (e.g., IBM Watson Tone Analyzer) is used to recognize emotions from the user's past search history and input behavior. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will determine that the user is feeling anxious.

[1089] Next, the server extracts related keywords based on the emotion recognition results. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. In this step, the server uses natural language processing and machine learning algorithms.

[1090] The server then uses the extracted related keywords to gather reliable information from various databases, such as news sites, academic papers, industry blogs, etc. For example, it retrieves the latest information on "SEO best practices" from the Google News and Google Scholar databases.

[1091] The server then organizes and filters the collected data, using NLP techniques such as the SpaCy library to remove unnecessary information and extract only the important information.

[1092] The server then uses natural language generation (NLG) technology, such as OpenAI's GPT-3, to generate a draft article based on the filtered data, adjusting the tone and content to reflect the user's emotions and ease their anxiety.

[1093] The generated article draft is notified to the person in charge via the terminal, and this notification is done via email or the system's message board.

[1094] Next, the user (person in charge) receives a notification and checks the contents of the article draft, making corrections and additions as necessary to further enhance the content.

[1095] The revised draft is then sent back to the server where it is checked for grammar and consistency using NLP techniques, for example, using the Google Cloud Natural Language API.

[1096] Once the check is complete, the server publishes the article to the website, including setting metadata and adding internal links using tools like Yoast SEO, to maximize SEO effectiveness and help the article rank higher in search engines.

[1097] After publication, the server monitors the article's performance, using tools such as Google Analytics to collect data such as the number of views, time spent, and click-through rate, and displays it on a dashboard to evaluate the article's effectiveness.

[1098] Additionally, the server periodically checks published articles to determine if they need to be updated to reflect new trends or service changes. If an update is required, a notification is sent to the user via the device.

[1099] Finally, the user (person in charge) receives the update notification and updates the article content. The updated article is again checked by the server and finally republished.

[1100] Example prompt sentence:

[1101] "Write an article about the latest SEO trends. Include the following points: 1) Recent developments, 2) Success stories, and 3) Specific ways to improve. Also, be sure to provide reassurance to users, as they may be feeling anxious."

[1102] In this way, the system can generate personalized articles that reflect the user's feelings and always provide the latest information.

[1103] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1104] Step 1:

[1105] A user enters a specific keyword into a search box on a website. For example, they enter the keyword "latest SEO trends" and press the enter key. This input action triggers the system. The input data is "latest SEO trends."

[1106] Step 2:

[1107] The server receives the keywords entered by the user and analyzes them using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to analyze the meaning and context of "latest SEO trends." The input is "latest SEO trends," and the output is the analysis results.

[1108] Step 3:

[1109] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's past search history and input behavior. The input is the user's past search history and input behavior, and the output is the user's emotional state (e.g., anxiety).

[1110] Step 4:

[1111] The server extracts related keywords based on the analysis results and emotion recognition results. For example, if a user is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. The input is the analysis results and the user's emotional state, and the output is the related keywords.

[1112] Step 5:

[1113] The server uses related keywords to collect reliable information from various databases. Specifically, it obtains the latest information on "SEO success stories" from Google News, Google Scholar, etc. The input is related keywords, and the output is the collected information.

[1114] Step 6:

[1115] The server organizes and filters the collected information. It uses NLP techniques (e.g., the SpaCy library) to extract only the important information. The input is the collected information, and the output is the filtered data.

[1116] Step 7:

[1117] The server generates an article draft based on the filtered data using natural language generation (NLG) technology. Specifically, it uses OpenAI's GPT-3 to generate the article draft. The input is the filtered data, and the output is the article draft.

[1118] Step 8:

[1119] The terminal notifies the person in charge of the generated article draft. Notification is done via email or the system's message board. The input is the article draft, and the output is a notification message.

[1120] Step 9:

[1121] The user (person in charge) checks the contents of the article draft and makes corrections or additions as necessary. The input is the article draft, and the output is the corrected draft.

[1122] Step 10:

[1123] The server receives the revised draft again and checks it for grammar and consistency using NLP techniques, specifically the Google Cloud Natural Language API, with the input being the revised draft and the output being the grammar-checked draft.

[1124] Step 11:

[1125] The server publishes the checked article to the website, setting metadata and adding internal links using tools like Yoast SEO. The input is a grammar-checked draft, and the output is the published article.

[1126] Step 12:

[1127] The server monitors the performance of published articles, using tools such as Google Analytics to collect data such as number of views, time spent, click-through rates, etc. The input is the published article, and the output is performance data.

[1128] Step 13:

[1129] The server periodically checks published articles to determine whether updates are necessary to keep up with new trends or service changes. If necessary, it sends update notifications to personnel via terminals. The input is performance data and trend information, and the output is update notifications.

[1130] Step 14:

[1131] The user (person in charge) receives the notification and updates the article content. The updated article is again checked by the server and finally republished. The input is the update notification and the output is the updated article.

[1132] Through the above processing steps, the system can efficiently generate personalized articles that reflect the user's feelings and provide the latest information.

[1133] (Application example 2)

[1134] 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."

[1135] Conventional content generation systems generate and distribute articles without considering user emotions, which results in a lack of quality improvement in the user experience. Additionally, the lack of appropriate keyword adjustment and personalization based on emotions makes it difficult to provide content tailored to user interests.

[1136] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing search keywords entered by a user, means for extracting related keywords based on the analysis results and collecting information from various databases, means for automatically generating articles using natural language generation technology based on the collected information, means for recognizing the user's emotions and adjusting the related keywords based on the emotions, means for notifying the person in charge of the generated article, means for rechecking the article revised by the person in charge using natural language processing technology, means for publishing the article on the site after the check is complete, and means for monitoring the performance of the article after publication and providing feedback. This enables personalized article generation based on the user's emotions, improving the quality of the user experience.

[1137] A "user" is an individual or entity that searches for specific information through a search engine or website.

[1138] "Search keywords" are words or phrases that users enter to find specific information.

[1139] "Means of analysis" refers to methods or technologies that use natural language processing technology to understand the content and context of search keywords.

[1140] "Means for extracting related keywords" refers to methods or techniques for finding other keywords that are highly related to the analyzed search keywords.

[1141] "Various databases" are digital repositories for collecting and storing information, including news sites, academic paper databases, and industry blogs.

[1142] "Natural language generation technology" is technology for automatically generating meaningful text in human language.

[1143] "Means for automatically generating articles" refers to methods or technologies for automatically creating articles based on collected information.

[1144] "Means for recognizing emotions" refers to technology for determining emotions from user input and behavior.

[1145] "Means for adjusting related keywords based on emotions" refers to methods or techniques for reselecting appropriate keywords according to the recognized emotions of the user.

[1146] The "means for notifying the person in charge" refers to a method or technique for ensuring that the generated article is confirmed by the person in charge.

[1147] "Natural language processing technology" is a technology for analyzing human language and understanding or generating meaning.

[1148] The "means of publishing the article on the site" refers to the method or technology used to display the final reviewed article on the website.

[1149] "Article performance monitoring measures" means methods or techniques for collecting performance data, such as number of views, time spent, and click-through rates, for published articles.

[1150] "Feedback methods" are methods and techniques that use collected performance data to improve articles or generate future articles.

[1151] "Post-publication article performance monitoring measures" are methods or techniques used to evaluate how well an article is performing after it has been published.

[1152] "Means for suggesting updates" are methods or techniques for suggesting modifications to existing articles in accordance with outdated articles or new trends.

[1153] This invention is a system that analyzes search keywords entered by users, extracts related keywords based on the analysis results, and collects information from various databases. Furthermore, it recognizes the user's emotions and adjusts and generates related keywords based on those emotions, automatically generating and publishing more personalized articles. Specific embodiments for implementing this invention are described below.

[1154] Hardware and software used

[1155] Hardware: Servers, smartphones, smart glasses

[1156] Software: Natural Language Processing (NLP) module, Natural Language Generation (NLG) module, Emotion engine, API request module (e.g., requests)

[1157] Data processing and calculation

[1158] 1. Enter and analyze user search keywords

[1159] A user uses a smartphone or smart glasses to enter a specific keyword into the search box. For example, the keyword "latest SEO trends" is entered. This search keyword is sent to the natural language processing (NLP) module on the server, where analysis begins.

[1160] 2. Extracting related keywords and collecting information

[1161] The NLP module analyzes the meaning and context of the input keywords and extracts related keywords. The extracted related keywords are then used to gather information from various databases and the web. In this process, information is collected from news sites, academic paper databases, industry blogs, etc.

[1162] 3. Recognizing user emotions with an emotion engine

[1163] The server uses an emotion engine to determine the user's emotions based on the user's search keywords and past browsing history. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[1164] 4. Personalized article generation

[1165] The server adjusts relevant keywords based on the recognized emotional information. For example, positive keywords such as "SEO success stories" and "SEO improvement points" are added to a user who is feeling anxious. The NLG module then automatically generates articles based on the adjusted keywords. The content of the generated articles reflects the user's emotions and provides a sense of security.

[1166] 5. Check and publish the generated article

[1167] The generated article is notified to the person in charge and can be viewed via a smartphone or other device. The person in charge checks the content of the article and makes corrections or additions as necessary. The corrected article is then sent back to the server where it is checked for grammar and consistency by the NLP module.

[1168] 6. Publishing articles and monitoring performance

[1169] Once the article has passed the check, it is published on the site by the server. After publication, the server monitors the article's performance, including the number of views, time spent, click-through rate, etc. Performance data is collected as feedback and used when generating the next article.

[1170] Examples and prompts

[1171] For example, suppose a user enters the following keywords:

[1172] Input keywords: Latest SEO trends

[1173] Past Search History: SEO Failures and How to Succeed

[1174] In this case, the server uses an emotion engine to recognize the user's anxiety, generate positive articles such as "SEO success stories," and provide them to the user.

[1175] Example prompt sentence:

[1176] Latest SEO Trends

[1177] SEO failure case

[1178] How to succeed with SEO

[1179] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1180] Step 1:

[1181] The user enters a search keyword.

[1182] Input: A user uses a smartphone or smart glasses to type a specific keyword into a search box.

[1183] Example: A user types in the keywords "latest SEO trends."

[1184] Output: The entered search keywords are sent to the server.

[1185] Step 2:

[1186] The server analyzes the search keywords.

[1187] Input: Search keyword (e.g. latest SEO trends)

[1188] Data processing / computation: Using natural language processing (NLP) modules, we analyze the meaning and context of keywords.

[1189] Output: List of related keywords as analysis results (e.g., SEO strategies, SEO success stories)

[1190] Step 3:

[1191] The server extracts related keywords and collects information.

[1192] Input: Analyzed related keywords (e.g., SEO strategies, SEO success stories)

[1193] Data processing / calculation: Collect information from various databases (news sites, academic paper databases, industry blogs, etc.) based on related keywords.

[1194] Output: Collected information (e.g., articles and papers on the latest SEO strategies)

[1195] Step 4:

[1196] The server recognizes the user's emotions.

[1197] Input: Search keywords, past search history, browsing history (e.g., SEO failure cases, how to succeed with SEO)

[1198] Data processing / calculation: Using an emotion engine to analyze emotions (e.g., anxiety) from users' search behavior and history.

[1199] Output: Recognized emotion information (e.g., anxiety)

[1200] Step 5:

[1201] The server adjusts and generates related keywords based on the emotion information.

[1202] Input: Recognized emotion information and related keywords (e.g., anxiety, SEO strategies, SEO success stories)

[1203] Data processing / calculation: Add positive keywords based on sentiment (e.g., SEO success stories)

[1204] Output: Tailored keyword list (e.g., SEO strategies, SEO success stories, SEO improvement points)

[1205] Step 6:

[1206] The server automatically generates the articles.

[1207] Input: Tailored keyword list and collected information (e.g., SEO strategies, SEO success stories, SEO improvement points)

[1208] Data processing / computation: Uses a natural language generation (NLG) module to automatically generate personalized articles.

[1209] Output: Generated article draft (e.g., article about the latest SEO best practices)

[1210] Step 7:

[1211] The server notifies the person in charge of the generated article.

[1212] Input: Generated article draft

[1213] Specific operation: The server uses the notification API to send notifications to the person in charge's smartphone or other device.

[1214] Output: The assignee is notified and the article draft is displayed.

[1215] Step 8:

[1216] The person in charge will check and correct the content of the article.

[1217] Input: Generated article draft

[1218] Specific operations: The person in charge checks the article on a smartphone or device and makes corrections or additions as necessary.

[1219] Output: revised article draft

[1220] Step 9:

[1221] The server rechecks the modified article.

[1222] Input: Revised article draft

[1223] Data processing / calculation: Using NLP modules, grammar and consistency checks are performed.

[1224] Output: Checked article draft

[1225] Step 10:

[1226] The server publishes the article to the site.

[1227] Input: Checked article draft

[1228] Specific behavior: Publish the article on the website using the site's public API.

[1229] Output: Published articles

[1230] Step 11:

[1231] The server monitors the performance of the article after it is published.

[1232] Input: Performance data for published articles (e.g., views, time spent, click-through rate)

[1233] Data processing / calculation: Collecting and analyzing performance data.

[1234] Output: Performance report

[1235] Step 12:

[1236] The server provides feedback based on performance data.

[1237] Input: Performance Report

[1238] What it does: Based on the performance data collected, it will summarize improvements that can be used in the next article generation.

[1239] Output: Feedback for improvements

[1240] 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.

[1241] 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.

[1242] 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.

[1243] [Fourth embodiment]

[1244] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1245] 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.

[1246] 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).

[1247] 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.

[1248] 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.

[1249] 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).

[1250] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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.

[1256] 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."

[1257] This invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. The program processing of an embodiment of this system will be specifically explained in natural language.

[1258] First, a user enters a specific keyword into a search box on a website. This can be a specific theme, such as "latest SEO trends," or a topic of interest. The server receives the keyword and begins analyzing it. This analysis evaluates the relevance and trendiness of the entered keyword and extracts related keywords.

[1259] Next, the server collects reliable information from various databases and the web based on the extracted related keywords. For example, based on related keywords such as "SEO 2023" and "search engine algorithm changes," it retrieves the latest information from reliable news sites, academic papers, industry blogs, etc.

[1260] Because the collected data is not always consistent, the server filters it and organizes important information, using NLP (natural language processing) technology to evaluate the usefulness of the data and extract only high-quality information.

[1261] The server then uses NLG (Natural Language Generation) technology to generate natural-sounding sentences based on the filtered data, such as a draft article on "The Latest SEO Trends for 2023." This process is fast and automatic.

[1262] The generated draft is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once that is complete, the draft is returned to the server.

[1263] The server then uses NLP technology to check the revised draft again for grammar and consistency. Once this step is complete, the article is finally published by the server. Furthermore, even after publication, the server continues to monitor the article's performance, collecting data such as the number of views and click-through rates.

[1264] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked and published again.

[1265] Through the above process, the present invention provides an efficient system for improving SEO and can quickly provide users with the latest, high-quality information they desire. The system also continuously monitors the performance of published articles and quickly updates them as needed, ensuring that the latest information is always available. In this way, the present invention maximizes SEO effectiveness and enhances the competitiveness of websites.

[1266] The processing flow will be explained below.

[1267] Step 1:

[1268] A user types specific keywords into a search box on a website, which relate to the information they want to know or the topic that interests them.

[1269] Step 2:

[1270] The server analyzes the keywords entered and evaluates their relevance, using natural language processing technology to interpret the meaning and context of the keywords.

[1271] Step 3:

[1272] The server extracts related keywords based on the analysis results. For example, if the keyword "latest SEO trends" is entered, related keywords such as "SEO 2023" and "search engine algorithm changes" will be extracted.

[1273] Step 4:

[1274] The server gathers reliable information from various databases and the web based on relevant keywords, including news sites, academic papers, industry blogs, and other reliable sources.

[1275] Step 5:

[1276] The server organizes and filters the collected data, using NLP techniques to evaluate the usefulness of the data and extract only the important information.

[1277] Step 6:

[1278] The server uses NLG (Natural Language Generation) technology to generate a draft article based on the filtered data, such as an article about "Latest SEO Trends for 2023."

[1279] Step 7:

[1280] The terminal notifies the person in charge of the generated article draft, including a request to review and revise the draft.

[1281] Step 8:

[1282] The user (person in charge) checks the article draft and makes corrections or additions as necessary. Here, they add missing information and check the accuracy of the content.

[1283] Step 9:

[1284] The device then sends the revised article back to the server, which receives it and again checks its grammar and consistency using NLP technology.

[1285] Step 10:

[1286] Once the server has completed the check, the article is published. This process also includes SEO-friendly settings such as setting metadata and adding internal links.

[1287] Step 11:

[1288] After publishing, the server monitors the performance of the article, including metrics such as views, time spent, and click-through rates.

[1289] Step 12:

[1290] The server periodically checks the articles and determines if they need to be updated based on new trends or changes in the service.

[1291] Step 13:

[1292] If a device is needed, a notification is sent to the person in charge to request that they update the article. Once the user (person in charge) has completed the update, they will republish the article.

[1293] This creates an efficient process for improving SEO and ensures the timeliness and quality of information.

[1294] Example 1

[1295] 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."

[1296] The traditional article generation process for SEO improvement required a lot of manual work, which made it inefficient and time-consuming. Furthermore, updates to keep up with rapidly changing trends were delayed, resulting in outdated information being left behind. Furthermore, insufficient filtering and evaluation of the collected information could result in a decline in the quality of the articles.

[1297] 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.

[1298] In this invention, the server includes means for analyzing search keywords entered by users, means for extracting related keywords based on the analysis results and collecting information from various information sources, means for automatically generating articles based on the collected information using natural language generation technology, means for notifying users of the generated articles, means for rechecking articles revised by users using natural language processing technology, means for publishing the articles on the website after the check is complete, means for monitoring the performance of the articles after publication and providing feedback, means for filtering the collected data to evaluate their usefulness, and means for periodically reviewing published articles and determining whether they need to be updated. This streamlines the article generation process for improving SEO and enables the provision of fast, high-quality information.

[1299] "Analysis" is the process of analyzing the search keywords entered by the user and evaluating their meaning and relevance.

[1300] "Related keywords" are keywords that are related to the keywords entered by the user and are extracted based on search results and trends on search engines.

[1301] "Sources" refers to various databases and websites that provide reliable data.

[1302] "Automatic generation" is the process by which a computer program automatically creates articles based on collected information.

[1303] "Notification" is a communication method for informing users of generated draft articles.

[1304] "Natural language processing technology" is a set of technologies that enable computers to understand, generate, and process human language.

[1305] A "Website" is a collection of information that is publicly available on the Internet and accessible to users.

[1306] "Monitoring" is the process of monitoring the performance of published articles in real time.

[1307] "Feedback" is information used to evaluate the performance of an article based on monitoring results and reflect it in the next steps.

[1308] "Filtering" is the process of selecting useful data from collected information and eliminating unnecessary data.

[1309] "Review" is the process of reevaluating a published article to determine whether the content needs to be updated.

[1310] "Updating" is the process of improving or changing an existing article based on new information or trends.

[1311] The present invention is a system for efficiently improving SEO, which quickly and accurately collects information desired by users and automates the process of generating and publishing articles based on that information. An embodiment of this system will be described in detail below.

[1312] First, a user enters a specific keyword into a search box on a website, such as a topic like "latest SEO trends." The server receives the keyword and begins analyzing it. Here, it uses tools like Google Trends API and SEMrush to evaluate the relevance and trendiness of the entered keyword and extract related keywords.

[1313] Next, the server collects reliable information from various sources based on the extracted related keywords, such as Google Scholarly, News API, and RSS feeds, to obtain the latest information based on related keywords such as "SEO 2023" and "search engine algorithm changes."

[1314] Because the collected data is not always consistent, the server filters it and organizes important information using natural language processing (NLP) models such as BERT and GPT-3 to evaluate the usefulness of the data and extract only high-quality information.

[1315] The server then uses natural language generation (NLG) technology to generate natural-sounding sentences based on the filtered data. Specifically, it uses the GPT-3 API to generate a draft article on "The Latest SEO Trends for 2023." This process is fast and automated.

[1316] The generated draft is notified to the person in charge via their terminal. The user (person in charge) receives the notification and checks and corrects the draft. For example, they can add missing information or check the accuracy of the content. Once this is complete, the draft is returned to the server.

[1317] The server then checks the revised draft again using NLP techniques to ensure grammar and consistency. Once this step is complete, the article is finally published by the server, for example by publishing the article using the WordPress API.

[1318] After publication, the server monitors the performance of the article and collects data such as the number of views and click-through rates, using the Google Analytics API.

[1319] Maintenance after publication is also important. The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services. If necessary, suggested updates are notified to the person in charge via the terminal. If an update is made, the content is also checked again and published.

[1320] Below are some examples of prompt sentences.

[1321] Generate in-depth articles on the latest SEO trends for 2023.

[1322] When this prompt is input into the generative AI model (GPT-3), the server generates a draft of the "Latest SEO Trends in 2023," and the process proceeds. This system makes it possible to quickly provide users with the latest, high-quality information they desire, maximizing SEO effectiveness.

[1323] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1324] Step 1:

[1325] A user enters a specific keyword into a search box, for example, "latest SEO trends," and this input is sent to the server.

[1326] Input: The keyword entered by the user (e.g., "latest SEO trends")

[1327] Output: Keyword data for analysis

[1328] Specific operation: The user inputs a keyword through the web interface and submits it. The server receives this input.

[1329] Step 2:

[1330] The server receives the keywords entered by the user and begins analysis, using the Google Trends API and SEMrush to evaluate and extract related keywords and their trending nature.

[1331] Input: Keyword data entered by the user

[1332] Output: List of related keywords

[1333] What it does: The server sends a request to the Google Trends API or SEMrush to retrieve related keywords and their trend data.

[1334] Step 3:

[1335] Based on the extracted related keywords, the server collects reliable information from various sources, such as Google Scholarly, News API, and RSS feeds.

[1336] Input: List of related keywords

[1337] Output: Collected information data

[1338] Specific operation: The server sends requests to multiple information sources based on related keywords and collects the returned information.

[1339] Step 4:

[1340] The server filters the collected data and organizes important information, using NLP models such as BERT and GPT-3 to evaluate the usefulness of the data and extract only high-quality information.

[1341] Input: Collected information data

[1342] Output: Filtered useful information data

[1343] How it works: The server uses NLP models to assess the quality of the information and select important data.

[1344] Step 5:

[1345] The server uses natural language generation (NLG) technology to generate draft articles based on the filtered data. Specifically, it uses the GPT-3 API to create an article on "The Latest SEO Trends in 2023."

[1346] Input: Filtered useful information data

[1347] Output: Generated article draft

[1348] What happens: The server sends a prompt to the NLG model and receives the generated text.

[1349] Step 6:

[1350] The generated draft article is notified to the person in charge via the terminal. The user (person in charge) receives the notification and checks and modifies the draft.

[1351] Input: Generated article draft

[1352] Output: revised draft article

[1353] Specific operation: The server sends the draft to the terminal, and the user edits the article through a web interface.

[1354] Step 7:

[1355] The server then runs the revised draft through NLP techniques again to check grammar and consistency, and once this step is complete, the article is finally published.

[1356] Input: revised draft article

[1357] Output: Finalized article draft

[1358] What it does: The server uses NLP models to double-check the grammar and consistency of the sentence.

[1359] Step 8:

[1360] The server publishes the finalized article to the website, for example by using the WordPress API to upload the article to the website.

[1361] Input: Finalized article draft

[1362] Output: Published articles

[1363] Specific operation: The server generates and executes an API request for publishing.

[1364] Step 9:

[1365] The server monitors the performance of published articles, for example by collecting data such as views and click-through rates through the Google Analytics API.

[1366] Input: Published article

[1367] Output: Performance data

[1368] Specific operation: The server periodically sends API requests to collect and analyze performance data.

[1369] Step 10:

[1370] The server periodically reviews published articles to determine whether they need to be updated to reflect new trends or changes in services, and if necessary, the suggested updates are sent to the user via the terminal.

[1371] Input: Performance data, new trend information

[1372] Output: Notification of whether an update is required

[1373] What it does: The server reviews articles according to a schedule, determines updates based on the latest information, and sends notifications.

[1374] Through these steps, the system provides an efficient way to improve SEO and quickly provide users with the latest, high-quality information they desire.

[1375] (Application example 1)

[1376] 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."

[1377] Providing users with the high-quality information they desire efficiently and quickly is a key challenge for modern content distribution services. In particular, improving SEO and providing content that reflects the latest trends requires automating the creation and updating of articles and content to improve accuracy. However, traditional methods often involve manual processes, from information collection to creation, publication, and feedback, which limits efficiency and accuracy. Furthermore, the lack of a function for intuitively searching and playing content using voice commands poses a challenge for improving the user experience.

[1378] 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.

[1379] In this invention, the server includes means for analyzing search keywords entered by the user, means for presenting related content based on the analyzed voice command, and means for selecting and playing the presented content, thereby efficiently providing high-quality content desired by the user and enabling access to the content through intuitive operations.

[1380] "Search keywords" are words or phrases that users enter to identify the information they are looking for.

[1381] "Natural language generation technology" is a technology that automatically generates natural-sounding sentences that sound like they were written by a human based on collected information.

[1382] "Natural language processing technology" is an artificial intelligence technology for understanding, analyzing, and processing human language.

[1383] "Voice command" is an input method that allows a user to give instructions to a system through voice.

[1384] "Content" means a collection of materials or information made available online or in digital form, including videos, articles, images, etc.

[1385] A "website" is a collection of web pages that provide information on the Internet.

[1386] "Related keywords" are words or phrases that provide additional useful information related to the search keywords entered by the user.

[1387] "Performance data" refers to data that indicates user reactions and behavior, such as the number of views and click rates of published content.

[1388] "Feedback" is the process of providing information for improving and updating content based on data collected by the system and user ratings.

[1389] "Data Source" means an external or internal database or repository used to collect or retrieve information.

[1390] "Contact Person" refers to the person or user responsible for reviewing and correcting the generated articles and content.

[1391] This invention is a content distribution system for efficiently providing users with high-quality content that they desire. This system uses a display device such as a head-mounted display (HMD) to allow users to search for content through voice commands, and automates the process of presenting and playing related content.

[1392] Hardware and software used

[1393] Hardware: Head-mounted display (HMD), server, microphone

[1394] Software: Google Cloud Speech-to-Text API, natural language processing libraries (such as spaCy and Hugging Face's BERT model), database management systems, filtering algorithms, content playback software

[1395] Processing Description

[1396] First, the user puts on the HMD and inputs voice commands into the microphone, which are then sent to a server via the Internet.

[1397] The server converts the audio data to text using the Google Cloud Speech-to-Text API, which is then analyzed using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent.

[1398] Based on the extracted keywords, the server searches the database and filters relevant content (e.g., videos, articles). The filtered content is presented on the HMD display for the user to select.

[1399] Once the user selects the desired content, the server will instruct the HMD to play that content, and feedback and additional instructions during playback can be given via voice commands.

[1400] Examples of concrete examples and prompts

[1401] For example, if a user is looking for a video about the latest SEO trends, the prompt might look something like this:

[1402] Example prompt sentence:

[1403] User: "Show me a video on the latest SEO trends"

[1404] Server: "Searching for videos on the latest SEO trends..."

[1405] / / The search process continues below.

[1406] Server: "The following videos were found:

[1407] 1. "The Latest SEO Trends for 2023"

[1408] 2. "Latest SEO Algorithm Updates"

[1409] 3. "SEO Experts Explain the Latest Trends"

[1410] Begins playing the video selected by the user.

[1411] This allows users to efficiently search for content using voice commands and use it intuitively. This system not only greatly improves user convenience but also provides relevant content quickly and accurately.

[1412] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1413] Step 1:

[1414] The user wears the HMD and inputs voice commands into the microphone. This voice data is collected by the HMD microphone and sent to a server via the Internet. The input is a user's voice command such as "Show me a video about the latest SEO trends."

[1415] Step 2:

[1416] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data. The specific process of analyzing voice data (input) and converting it into text data (output) is to break down the voice signal into phonemes and assemble them into a string of characters.

[1417] Step 3:

[1418] The server analyzes the text data using a natural language processing library (e.g., spaCy or Hugging Face's BERT model) to extract key keywords and user intent. The specific operations for obtaining keywords and user intent (output) from text data (input) involve a process of performing morphological analysis and dependency analysis of the text to identify important words and phrases.

[1419] Step 4:

[1420] The server searches the database based on the extracted keywords and filters relevant content. The specific operations of searching for content in a database using keywords (input) and generating a list of highly relevant content (output) are creating a search query and executing a database query using that query.

[1421] Step 5:

[1422] The server presents the filtered content on the HMD display for user selection. It converts the list of filtered content (input) into a display format for the HMD and displays it on the display (output). Specific operations include setting the display layout and rendering the content.

[1423] Step 6:

[1424] When a user selects a desired content, the selection is sent to the server. The specific operation of sending the content identification information (output) to the server in response to the user's selection operation (input) is to detect the selection operation and send the data.

[1425] Step 7:

[1426] The server issues an instruction to play the selected content on the HMD. Based on the identification information of the content selected by the user (input), the content is loaded and playback begins on the HMD (output). Specific operations include streaming and playback control of the content.

[1427] 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.

[1428] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information, and by combining it with an emotion engine that recognizes user emotions, it realizes more personalized article generation. Detailed embodiments of this system are described below.

[1429] First, a user types a specific keyword into a search box on a website, such as "latest SEO trends," and this typing behavior may reflect the user's emotions and intentions.

[1430] The server then receives the keywords and begins analyzing them. The technology used here is natural language processing (NLP), which analyzes the meaning and context of the keywords. Furthermore, an emotion engine recognizes emotions based on the user's input behavior and browsing history. For example, if a user frequently searches for negative keywords such as "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[1431] The server extracts related keywords based on the recognized emotional information. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. Based on the extracted related keywords, the server collects reliable information from various databases and the web. This collection process includes news sites, academic papers, industry blogs, etc.

[1432] The collected data may be inconsistent, so the server organizes and filters it. NLP technology is used to evaluate the usefulness of the data and extract only the important information. Next, NLG (Natural Language Generation) technology is used to generate an article draft based on the filtered data. The content of this draft reflects the recognized sentiment, and if the user is feeling anxious, for example, the content is adjusted to provide reassurance.

[1433] The generated article draft is notified to the person in charge via the terminal. The user (person in charge) checks the content of the article and makes corrections or additions as necessary. The corrected draft is then returned to the server and checked for grammar and consistency using NLP technology.

[1434] After the check is complete, the server publishes the article on the site. At this point, it also performs SEO-friendly settings such as setting metadata and adding internal links. After publishing, the server monitors the article's performance and collects data such as the number of views, time spent, and click-through rate. This allows it to evaluate how effective the published article is.

[1435] Furthermore, the server periodically checks the articles and determines whether they need to be updated in response to new trends or changes in the service. If an update is necessary, a notification is sent to the person in charge via their device. The user (person in charge) updates the article, and the content is checked again by the server and finally republished.

[1436] In this way, the introduction of an emotion engine in this system enables personalized article generation based on user emotions, achieving further SEO benefits. This allows users to quickly and accurately provide the information they are looking for, improving the competitiveness of websites.

[1437] The processing flow will be explained below.

[1438] Step 1:

[1439] A user types a specific keyword into a search box on a website, for example, a user types "latest SEO trends."

[1440] Step 2:

[1441] The server receives the input keywords and analyzes them using natural language processing (NLP) techniques to understand the meaning and context of the keywords.

[1442] Step 3:

[1443] The server uses an emotion engine to recognize the user's emotions based on their input behavior and browsing history. For example, if a user frequently searches for negative keywords, it can determine that the user is feeling anxious or concerned.

[1444] Step 4:

[1445] The server extracts related keywords based on the results of keyword analysis and emotion recognition. For example, if a user enters "latest SEO trends" and feels anxious, the server extracts positive related keywords such as "SEO success stories" and "effective SEO strategies."

[1446] Step 5:

[1447] The server then uses the extracted related keywords to gather reliable information from various databases and the web, such as news sites, industry blogs, and academic papers, to obtain the latest SEO information.

[1448] Step 6:

[1449] The server organizes and filters the collected information, using NLP technology to evaluate the usefulness of the data and extract only the important information. For example, it prioritizes highly reliable data and the latest information.

[1450] Step 7:

[1451] The server uses NLG (Natural Language Generation) technology to generate article drafts based on the filtered data, which include reassuring content that reflects the perceived user sentiment.

[1452] Step 8:

[1453] The terminal notifies the person in charge of the generated article draft. The user (person in charge) receives the notification and checks the content of the article. For example, he / she checks the corrections and missing information in the draft.

[1454] Step 9:

[1455] The user modifies the draft article and adds additional information, for example adding the latest data or industry insights.

[1456] Step 10:

[1457] The device then sends the revised article back to the server, which receives it and again uses NLP techniques to check for grammar and consistency.

[1458] Step 11:

[1459] After the check is complete, the server publishes the article to the site, and also performs SEO-friendly settings such as setting metadata and adding internal links.

[1460] Step 12:

[1461] The server monitors the performance of the article after it is published, collecting data such as the number of views, time spent on the page, and click-through rate to evaluate its performance.

[1462] Step 13:

[1463] The server periodically checks published articles to determine if they need to be updated to keep up with new trends or changes in the service.

[1464] Step 14:

[1465] If an article needs to be updated, the device will send a notification to the person in charge. The user (person in charge) will receive the notification and update the article.

[1466] Step 15:

[1467] The terminal sends the updated article back to the server, which checks the updated content and republishes it if necessary.

[1468] Through the above process, this system can take user sentiment into consideration and efficiently collect, generate, and publish information, maximizing SEO effectiveness.

[1469] Example 2

[1470] 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."

[1471] The Internet is overflowing with information, making it difficult to efficiently gather and provide the appropriate and useful information users desire. Furthermore, personalized article generation that takes user sentiment into consideration is uncommon, and there is no consistent method for improving user experience. In particular, it is difficult to dynamically update content while maintaining article quality and responding to the latest trends and service changes.

[1472] 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.

[1473] In this invention, the server includes a means for analyzing search keywords entered by users, a means for extracting related keywords based on the analysis results and the user's emotion recognition results, and collecting information from various databases, and a means for automatically generating articles using natural language generation technology based on the collected information. This enables personalized article generation that takes user emotions into consideration. The system also includes a means for notifying a person in charge of the generated article, and after the person in charge has revised the article and checked it again using natural language processing technology, the article is published on the site, and metadata is set and internal links are added. Furthermore, by including a means for monitoring the performance of the article after publication and providing feedback, and a means for periodically checking published articles and notifying the person in charge when updates are necessary, the system can always provide the latest information.

[1474] "Search keywords" are specific words or phrases that users type into a website's search box.

[1475] "Analysis" is the process of using a computer program to understand the meaning and context of the search keywords entered.

[1476] "Emotion recognition" is a technology that determines what emotions a user is feeling based on their input behavior and past browsing history.

[1477] "Related keywords" are other words or phrases that are relevant to the user's interests based on the analysis and emotion recognition results.

[1478] "Information gathering" is the process of obtaining useful data from various databases on the Internet based on the extracted related keywords.

[1479] "Natural language generation technology" is a technology that automatically creates text that humans can understand using collected data.

[1480] An "article draft" is an initial version of an article that is automatically generated using natural language generation technology.

[1481] "Notification" is an action of notifying the person in charge of the generated article draft.

[1482] "Revising" is the process by which the person in charge reviews the contents of the article draft and makes any necessary changes.

[1483] "Natural language processing technology" is a computer program that checks the grammar and consistency of revised articles.

[1484] "Publishing" means making an article that has passed the check available for viewing on the website.

[1485] "Metadata setting" is the process of setting keywords and descriptions to improve SEO effectiveness when publishing an article.

[1486] "Internal linking" is the process of embedding links to related pages within your articles to improve the overall SEO effectiveness of your website.

[1487] "Performance monitoring" involves collecting data such as the number of views, time spent, and click-through rate of published articles to evaluate their effectiveness.

[1488] "Feedback" is the process of identifying areas for improvement based on the results of performance monitoring and communicating them to the person in charge.

[1489] "Regular checks" refer to the process of periodically reviewing published articles to determine whether they need to be updated to keep up with the latest trends or service changes.

[1490] "Update notification" is an action that notifies the person in charge when an article needs to be updated.

[1491] The "person in charge" is a person who is responsible for checking the generated article draft and making any necessary corrections or updates.

[1492] The present invention is a system that efficiently collects information desired by users and publishes articles automatically generated based on that information. Furthermore, by combining it with an emotion engine that recognizes user emotions, more personalized article generation is realized. Detailed embodiments of the present invention are described below.

[1493] First, a user types a specific keyword into a search box on a website, for example, "latest SEO trends." At this time, the user's typing behavior may reflect emotions and intentions.

[1494] The server then receives the keywords entered by the user and analyzes them. Natural language processing (NLP) technology is used for this analysis, for example, by using the Google Cloud Natural Language API to analyze the meaning and context of the keywords. At the same time, an emotion engine (e.g., IBM Watson Tone Analyzer) is used to recognize emotions from the user's past search history and input behavior. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will determine that the user is feeling anxious.

[1495] Next, the server extracts related keywords based on the emotion recognition results. For example, for a user who is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. In this step, the server uses natural language processing and machine learning algorithms.

[1496] The server then uses the extracted related keywords to gather reliable information from various databases, such as news sites, academic papers, industry blogs, etc. For example, it retrieves the latest information on "SEO best practices" from the Google News and Google Scholar databases.

[1497] The server then organizes and filters the collected data, using NLP techniques such as the SpaCy library to remove unnecessary information and extract only the important information.

[1498] The server then uses natural language generation (NLG) technology, such as OpenAI's GPT-3, to generate a draft article based on the filtered data, adjusting the tone and content to reflect the user's emotions and ease their anxiety.

[1499] The generated article draft is notified to the person in charge via the terminal, and this notification is done via email or the system's message board.

[1500] Next, the user (person in charge) receives a notification and checks the contents of the article draft, making corrections and additions as necessary to further enhance the content.

[1501] The revised draft is then sent back to the server where it is checked for grammar and consistency using NLP techniques, for example, using the Google Cloud Natural Language API.

[1502] Once the check is complete, the server publishes the article to the website, including setting metadata and adding internal links using tools like Yoast SEO, to maximize SEO effectiveness and help the article rank higher in search engines.

[1503] After publication, the server monitors the article's performance, using tools such as Google Analytics to collect data such as the number of views, time spent, and click-through rate, and displays it on a dashboard to evaluate the article's effectiveness.

[1504] Additionally, the server periodically checks published articles to determine if they need to be updated to reflect new trends or service changes. If an update is required, a notification is sent to the user via the device.

[1505] Finally, the user (person in charge) receives the update notification and updates the article content. The updated article is again checked by the server and finally republished.

[1506] Example prompt sentence:

[1507] "Write an article about the latest SEO trends. Include the following points: 1) Recent developments, 2) Success stories, and 3) Specific ways to improve. Also, be sure to provide reassurance to users, as they may be feeling anxious."

[1508] In this way, the system can generate personalized articles that reflect the user's feelings and always provide the latest information.

[1509] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1510] Step 1:

[1511] A user enters a specific keyword into a search box on a website. For example, they enter the keyword "latest SEO trends" and press the enter key. This input action triggers the system. The input data is "latest SEO trends."

[1512] Step 2:

[1513] The server receives the keywords entered by the user and analyzes them using natural language processing (NLP) technology. Specifically, it uses the Google Cloud Natural Language API to analyze the meaning and context of "latest SEO trends." The input is "latest SEO trends," and the output is the analysis results.

[1514] Step 3:

[1515] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's past search history and input behavior. The input is the user's past search history and input behavior, and the output is the user's emotional state (e.g., anxiety).

[1516] Step 4:

[1517] The server extracts related keywords based on the analysis results and emotion recognition results. For example, if a user is feeling anxious, positive related keywords such as "SEO success stories" and "SEO improvement points" are extracted. The input is the analysis results and the user's emotional state, and the output is the related keywords.

[1518] Step 5:

[1519] The server uses related keywords to collect reliable information from various databases. Specifically, it obtains the latest information on "SEO success stories" from Google News, Google Scholar, etc. The input is related keywords, and the output is the collected information.

[1520] Step 6:

[1521] The server organizes and filters the collected information. It uses NLP techniques (e.g., the SpaCy library) to extract only the important information. The input is the collected information, and the output is the filtered data.

[1522] Step 7:

[1523] The server generates an article draft based on the filtered data using natural language generation (NLG) technology. Specifically, it uses OpenAI's GPT-3 to generate the article draft. The input is the filtered data, and the output is the article draft.

[1524] Step 8:

[1525] The terminal notifies the person in charge of the generated article draft. Notification is done via email or the system's message board. The input is the article draft, and the output is a notification message.

[1526] Step 9:

[1527] The user (person in charge) checks the contents of the article draft and makes corrections or additions as necessary. The input is the article draft, and the output is the corrected draft.

[1528] Step 10:

[1529] The server receives the revised draft again and checks it for grammar and consistency using NLP techniques, specifically the Google Cloud Natural Language API, with the input being the revised draft and the output being the grammar-checked draft.

[1530] Step 11:

[1531] The server publishes the checked article to the website, setting metadata and adding internal links using tools like Yoast SEO. The input is a grammar-checked draft, and the output is the published article.

[1532] Step 12:

[1533] The server monitors the performance of published articles, using tools such as Google Analytics to collect data such as number of views, time spent, click-through rates, etc. The input is the published article, and the output is performance data.

[1534] Step 13:

[1535] The server periodically checks published articles to determine whether updates are necessary to keep up with new trends or service changes. If necessary, it sends update notifications to personnel via terminals. The input is performance data and trend information, and the output is update notifications.

[1536] Step 14:

[1537] The user (person in charge) receives the notification and updates the article content. The updated article is again checked by the server and finally republished. The input is the update notification and the output is the updated article.

[1538] Through the above processing steps, the system can efficiently generate personalized articles that reflect the user's feelings and provide the latest information.

[1539] (Application example 2)

[1540] 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."

[1541] Conventional content generation systems generate and distribute articles without considering user emotions, which results in a lack of quality improvement in the user experience. Additionally, the lack of appropriate keyword adjustment and personalization based on emotions makes it difficult to provide content tailored to user interests.

[1542] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing search keywords entered by a user, means for extracting related keywords based on the analysis results and collecting information from various databases, means for automatically generating articles using natural language generation technology based on the collected information, means for recognizing the user's emotions and adjusting the related keywords based on the emotions, means for notifying the person in charge of the generated article, means for rechecking the article revised by the person in charge using natural language processing technology, means for publishing the article on the site after the check is complete, and means for monitoring the performance of the article after publication and providing feedback. This enables personalized article generation based on the user's emotions, improving the quality of the user experience.

[1543] A "user" is an individual or entity that searches for specific information through a search engine or website.

[1544] "Search keywords" are words or phrases that users enter to find specific information.

[1545] "Means of analysis" refers to methods or technologies that use natural language processing technology to understand the content and context of search keywords.

[1546] "Means for extracting related keywords" refers to methods or techniques for finding other keywords that are highly related to the analyzed search keywords.

[1547] "Various databases" are digital repositories for collecting and storing information, including news sites, academic paper databases, and industry blogs.

[1548] "Natural language generation technology" is technology for automatically generating meaningful text in human language.

[1549] "Means for automatically generating articles" refers to methods or technologies for automatically creating articles based on collected information.

[1550] "Means for recognizing emotions" refers to technology for determining emotions from user input and behavior.

[1551] "Means for adjusting related keywords based on emotions" refers to methods or techniques for reselecting appropriate keywords according to the recognized emotions of the user.

[1552] The "means for notifying the person in charge" refers to a method or technique for ensuring that the generated article is confirmed by the person in charge.

[1553] "Natural language processing technology" is a technology for analyzing human language and understanding or generating meaning.

[1554] The "means of publishing the article on the site" refers to the method or technology used to display the final reviewed article on the website.

[1555] "Article performance monitoring measures" means methods or techniques for collecting performance data, such as number of views, time spent, and click-through rates, for published articles.

[1556] "Feedback methods" are methods and techniques that use collected performance data to improve articles or generate future articles.

[1557] "Post-publication article performance monitoring measures" are methods or techniques used to evaluate how well an article is performing after it has been published.

[1558] "Means for suggesting updates" are methods or techniques for suggesting modifications to existing articles in accordance with outdated articles or new trends.

[1559] This invention is a system that analyzes search keywords entered by users, extracts related keywords based on the analysis results, and collects information from various databases. Furthermore, it recognizes the user's emotions and adjusts and generates related keywords based on those emotions, automatically generating and publishing more personalized articles. Specific embodiments for implementing this invention are described below.

[1560] Hardware and software used

[1561] Hardware: Servers, smartphones, smart glasses

[1562] Software: Natural Language Processing (NLP) module, Natural Language Generation (NLG) module, Emotion engine, API request module (e.g., requests)

[1563] Data processing and calculation

[1564] 1. Enter and analyze user search keywords

[1565] A user uses a smartphone or smart glasses to enter a specific keyword into the search box. For example, the keyword "latest SEO trends" is entered. This search keyword is sent to the natural language processing (NLP) module on the server, where analysis begins.

[1566] 2. Extracting related keywords and collecting information

[1567] The NLP module analyzes the meaning and context of the input keywords and extracts related keywords. The extracted related keywords are then used to gather information from various databases and the web. In this process, information is collected from news sites, academic paper databases, industry blogs, etc.

[1568] 3. Recognizing user emotions with an emotion engine

[1569] The server uses an emotion engine to determine the user's emotions based on the user's search keywords and past browsing history. For example, if a user frequently searches for the negative keyword "SEO failure cases," the emotion engine will recognize that the user is feeling anxious.

[1570] 4. Personalized article generation

[1571] The server adjusts relevant keywords based on the recognized emotional information. For example, positive keywords such as "SEO success stories" and "SEO improvement points" are added to a user who is feeling anxious. The NLG module then automatically generates articles based on the adjusted keywords. The content of the generated articles reflects the user's emotions and provides a sense of security.

[1572] 5. Check and publish the generated article

[1573] The generated article is notified to the person in charge and can be viewed via a smartphone or other device. The person in charge checks the content of the article and makes corrections or additions as necessary. The corrected article is then sent back to the server where it is checked for grammar and consistency by the NLP module.

[1574] 6. Publishing articles and monitoring performance

[1575] Once the article has passed the check, it is published on the site by the server. After publication, the server monitors the article's performance, including the number of views, time spent, click-through rate, etc. Performance data is collected as feedback and used when generating the next article.

[1576] Examples and prompts

[1577] For example, suppose a user enters the following keywords:

[1578] Input keywords: Latest SEO trends

[1579] Past Search History: SEO Failures and How to Succeed

[1580] In this case, the server uses an emotion engine to recognize the user's anxiety, generate positive articles such as "SEO success stories," and provide them to the user.

[1581] Example prompt sentence:

[1582] Latest SEO Trends

[1583] SEO failure case

[1584] How to succeed with SEO

[1585] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1586] Step 1:

[1587] The user enters a search keyword.

[1588] Input: A user uses a smartphone or smart glasses to type a specific keyword into a search box.

[1589] Example: A user types in the keywords "latest SEO trends."

[1590] Output: The entered search keywords are sent to the server.

[1591] Step 2:

[1592] The server analyzes the search keywords.

[1593] Input: Search keyword (e.g. latest SEO trends)

[1594] Data processing / computation: Using natural language processing (NLP) modules, we analyze the meaning and context of keywords.

[1595] Output: List of related keywords as analysis results (e.g., SEO strategies, SEO success stories)

[1596] Step 3:

[1597] The server extracts related keywords and collects information.

[1598] Input: Analyzed related keywords (e.g., SEO strategies, SEO success stories)

[1599] Data processing / calculation: Collect information from various databases (news sites, academic paper databases, industry blogs, etc.) based on related keywords.

[1600] Output: Collected information (e.g., articles and papers on the latest SEO strategies)

[1601] Step 4:

[1602] The server recognizes the user's emotions.

[1603] Input: Search keywords, past search history, browsing history (e.g., SEO failure cases, how to succeed with SEO)

[1604] Data processing / calculation: Using an emotion engine to analyze emotions (e.g., anxiety) from users' search behavior and history.

[1605] Output: Recognized emotion information (e.g., anxiety)

[1606] Step 5:

[1607] The server adjusts and generates related keywords based on the emotion information.

[1608] Input: Recognized emotion information and related keywords (e.g., anxiety, SEO strategies, SEO success stories)

[1609] Data processing / calculation: Add positive keywords based on sentiment (e.g., SEO success stories)

[1610] Output: Tailored keyword list (e.g., SEO strategies, SEO success stories, SEO improvement points)

[1611] Step 6:

[1612] The server automatically generates the articles.

[1613] Input: Tailored keyword list and collected information (e.g., SEO strategies, SEO success stories, SEO improvement points)

[1614] Data processing / computation: Uses a natural language generation (NLG) module to automatically generate personalized articles.

[1615] Output: Generated article draft (e.g., article about the latest SEO best practices)

[1616] Step 7:

[1617] The server notifies the person in charge of the generated article.

[1618] Input: Generated article draft

[1619] Specific operation: The server uses the notification API to send notifications to the person in charge's smartphone or other device.

[1620] Output: The assignee is notified and the article draft is displayed.

[1621] Step 8:

[1622] The person in charge will check and correct the content of the article.

[1623] Input: Generated article draft

[1624] Specific operations: The person in charge checks the article on a smartphone or device and makes corrections or additions as necessary.

[1625] Output: revised article draft

[1626] Step 9:

[1627] The server rechecks the modified article.

[1628] Input: Revised article draft

[1629] Data processing / calculation: Using NLP modules, grammar and consistency checks are performed.

[1630] Output: Checked article draft

[1631] Step 10:

[1632] The server publishes the article to the site.

[1633] Input: Checked article draft

[1634] Specific behavior: Publish the article on the website using the site's public API.

[1635] Output: Published articles

[1636] Step 11:

[1637] The server monitors the performance of the article after it is published.

[1638] Input: Performance data for published articles (e.g., views, time spent, click-through rate)

[1639] Data processing / calculation: Collecting and analyzing performance data.

[1640] Output: Performance report

[1641] Step 12:

[1642] The server provides feedback based on performance data.

[1643] Input: Performance Report

[1644] What it does: Based on the performance data collected, it will summarize improvements that can be used in the next article generation.

[1645] Output: Feedback for improvements

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] FIG. 9 illustrates 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 behaviors 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.

[1651] 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.

[1652] 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).

[1653] 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.

[1654] 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."

[1655] 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.

[1656] 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).

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] The following is further disclosed regarding the above embodiment.

[1668] (Claim 1)

[1669] A means of analyzing search keywords entered by users;

[1670] A means of extracting related keywords based on the analysis results and collecting information from various databases;

[1671] A means for automatically generating articles using natural language generation technology based on the collected information;

[1672] a means for notifying the person in charge of the generated article;

[1673] A method to check the articles revised by the person in charge again using natural language processing technology,

[1674] A way to publish the article on the site after the check is complete,

[1675] A means to monitor and provide feedback on article performance after publication;

[1676] A system including:

[1677] (Claim 2)

[1678] 10. The system of claim 1, further comprising means for periodically checking articles and providing suggested updates based on emerging trends or service changes after the articles are published.

[1679] (Claim 3)

[1680] 10. The system of claim 1, further comprising means for accumulating performance data of published articles and using the data to generate subsequent articles.

[1681] "Example 1"

[1682] (Claim 1)

[1683] A means of analyzing search keywords entered by users;

[1684] A means for extracting related keywords based on the analysis results and collecting information from various sources;

[1685] A means for automatically generating articles using natural language generation technology based on the collected information;

[1686] a means for notifying the user of the generated article;

[1687] A means to check articles revised by users again using natural language processing technology,

[1688] A way to publish the article on the website after the check is complete, and

[1689] A means to monitor and provide feedback on article performance after publication;

[1690] a means of filtering the collected data and assessing its usefulness;

[1691] A means of periodically reviewing published articles to determine whether they require updating; and

[1692] A system including:

[1693] (Claim 2)

[1694] 10. The system of claim 1, further comprising means for periodically checking articles based on emerging trends or service changes after the articles are published and notifying the user of suggested updates.

[1695] (Claim 3)

[1696] 10. The system of claim 1, further comprising means for accumulating performance data of published articles and using the data to generate subsequent articles.

[1697] "Application Example 1"

[1698] (Claim 1)

[1699] A means of analyzing search keywords entered by users;

[1700] A means of extracting related keywords based on the analysis results and collecting information from various data sources;

[1701] A means for automatically generating sentences using natural language generation technology based on the collected information;

[1702] A means for notifying the person in charge of the generated text;

[1703] A method to check the text corrected by the person in charge again using natural language processing technology,

[1704] A means to publish the text on the website after the check is complete,

[1705] A means of monitoring and providing feedback on the performance of the text after publication;

[1706] means for recognizing and analyzing a user's voice commands;

[1707] means for presenting relevant content based on the analyzed voice command;

[1708] means for selecting and playing the presented content;

[1709] A system including:

[1710] (Claim 2)

[1711] 10. The system of claim 1, further comprising means for periodically checking articles and providing suggested updates based on emerging trends or service changes after the articles are published.

[1712] (Claim 3)

[1713] 10. The system of claim 1, further comprising means for accumulating performance data of published texts and using the data to generate subsequent texts.

[1714] "Example 2: Combining Emotion Engines"

[1715] (Claim 1)

[1716] A means of analyzing search keywords entered by users;

[1717] A means for extracting related keywords based on the analysis results and the user's emotion recognition results, and collecting information from various databases;

[1718] A means for automatically generating articles using natural language generation technology based on the collected information;

[1719] a means for notifying the person in charge of the generated article;

[1720] A method to check the articles revised by the person in charge again using natural language processing technology,

[1721] After the check is complete, you can publish the article to the site, set metadata, and add internal links.

[1722] A means to monitor and provide feedback on article performance after publication;

[1723] A means to regularly check published articles and notify personnel when updates are needed;

[1724] A system including:

[1725] (Claim 2)

[1726] 10. The system of claim 1, further comprising means for periodically checking articles and providing suggested updates based on emerging trends or service changes after the articles are published.

[1727] (Claim 3)

[1728] 10. The system of claim 1, further comprising means for accumulating performance data of published articles and using the data to generate subsequent articles.

[1729] "Application example 2 when combining emotion engines"

[1730] (Claim 1)

[1731] A means of analyzing search keywords entered by users;

[1732] A means of extracting related keywords based on the analysis results and collecting information from various databases;

[1733] A means for automatically generating articles using natural language generation technology based on the collected information;

[1734] A means of recognizing user sentiment and adjusting related keywords based on that sentiment;

[1735] a means for notifying the person in charge of the generated article;

[1736] A method to check the articles revised by the person in charge again using natural language processing technology,

[1737] A way to publish the article on the site after the check is complete,

[1738] A means to monitor and provide feedback on article performance after publication;

[1739] A system including:

[1740] (Claim 2)

[1741] 10. The system of claim 1, further comprising means for periodically checking articles and providing suggested updates based on emerging trends or service changes after the articles are published.

[1742] (Claim 3)

[1743] 10. The system of claim 1, further comprising means for using an emotion engine based on a user's search history and emotions to reflect the emotions when generating the next article. [Explanation of symbols]

[1744] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing search keywords entered by users; A means of extracting related keywords based on the analysis results and collecting information from various databases; A means for automatically generating articles using natural language generation technology based on the collected information; a means for notifying the person in charge of the generated article; A method to check the articles revised by the person in charge again using natural language processing technology, A way to publish the article on the site after the check is complete, A means to monitor and provide feedback on article performance after publication; A system including:

2. 10. The system of claim 1, further comprising means for periodically checking articles and providing suggested updates based on emerging trends and service changes after the articles are published.

3. 2. The system of claim 1, further comprising means for accumulating performance data of published articles and using the data when generating subsequent articles.

Images