system

Abstract

The system according to this embodiment aims to efficiently achieve both improved content quality and monetization. [Solution] The system according to the embodiment comprises a topic selection unit, an article generation unit, an SEO optimization unit, and a monetization proposal unit. The topic selection unit selects a topic. The article generation unit generates an article based on the topic selected by the topic selection unit. The SEO optimization unit performs SEO optimization on the article generated by the article generation unit. The monetization proposal unit proposes a monetization strategy based on the article optimized by the SEO optimization unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to achieve both improvement in the quality of content and monetization, and it is difficult to establish an efficient monetization strategy.

[0005] The system according to the embodiment aims to efficiently achieve both improvement in the quality of content and monetization.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a topic selection unit, an article generation unit, an SEO optimization unit, and a monetization proposal unit. The topic selection unit selects a topic. The article generation unit generates an article based on the topic selected by the topic selection unit. The SEO optimization unit performs SEO optimization on the article generated by the article generation unit. The monetization proposal unit proposes a monetization strategy based on the article optimized by the SEO optimization unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently achieve both improved content quality and monetization. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is a system for bloggers, freelance writers, and content creators that balances improving content quality with monetization. This system provides an environment where creators can concentrate on content creation by consistently handling everything from topic selection to article generation, SEO optimization, and monetization strategy proposals. For example, the AI ​​agent system uses natural language processing to extract popular topics from social media and news sites. Next, it automatically generates high-quality articles using a large-scale language model and also makes adjustments to suit the user's style. Furthermore, an SEO-specialized AI optimizes keywords and generates metadata to improve visibility in search engines. Finally, it uses a machine learning model to propose optimizations for ad placement and subscription models to maximize revenue. This mechanism provides creators with an environment where they can concentrate on content creation. For example, the AI ​​agent system uses natural language processing to perform trend analysis and extract popular topics from social media and news sites. For example, if a particular keyword is rapidly increasing in popularity, it selects topics related to that keyword. This information forms the basis for writing articles in the next step. Next, it automatically generates high-quality articles using a large-scale language model. For example, based on a selected topic, the AI ​​will plan the article's structure and write the specific content. It can also be adjusted to the user's style, generating articles tailored to their preferences, such as a casual or professional writing style. Furthermore, an SEO-focused AI optimizes keywords and generates metadata. For instance, it selects appropriate keywords and places them within the article to improve search engine visibility. It also generates metadata to accurately communicate the article's content to search engines. Finally, a machine learning model is used to propose monetization strategies. For example, it optimizes ad placement and suggests subscription models to maximize revenue. This allows creators to focus on content creation while implementing efficient monetization strategies. This system enables creators to balance improving content quality with monetization, overcoming time and resource constraints.For example, by providing comprehensive support from topic selection and article writing to SEO measures and monetization strategy proposals, creators are given an environment where they can concentrate on content creation. This allows the AI ​​agent system to enable creators to focus on content creation while also implementing efficient monetization strategies.

[0029] The AI ​​agent system according to this embodiment comprises a topic selection unit, an article generation unit, an SEO optimization unit, and a monetization proposal unit. The topic selection unit selects topics. The topic selection unit extracts popular topics from social media and news sites, for example, by utilizing natural language processing. For example, if a particular keyword is trending, the topic selection unit selects topics related to that keyword. The topic selection unit can extract popular topics from social media and news sites, for example, by performing trend analysis. The article generation unit generates articles based on the topics selected by the topic selection unit. The article generation unit automatically generates high-quality articles, for example, by using a large-scale language model. For example, based on the selected topic, the article generation unit uses AI to consider the structure of the article and write the specific content. The article generation unit can also make adjustments to match the user's style. For example, the article generation unit can generate articles according to the user's preferences, such as a casual writing style or a professional writing style. The SEO optimization unit performs SEO optimization of the articles generated by the article generation unit. The SEO optimization unit performs keyword optimization and metadata generation, for example. For example, the SEO optimization unit selects appropriate keywords and places them within the article to improve visibility in search engines. The SEO optimization unit also generates metadata, enabling it to accurately convey the article's content to search engines. The monetization proposal unit proposes monetization strategies based on the articles optimized by the SEO optimization unit. For example, the monetization proposal unit proposes optimizations for ad placement and subscription models using machine learning models. For example, the monetization proposal unit optimizes ad placement and proposes subscription models to maximize revenue. By proposing monetization strategies, the monetization proposal unit enables creators to focus on content creation while achieving efficient monetization strategies. As a result, the AI ​​agent system according to this embodiment enables creators to focus on content creation while achieving efficient monetization strategies.

[0030] The topic selection unit selects topics. For example, it extracts popular topics from social media and news sites using natural language processing. Specifically, the topic selection unit collects data from social media and news sites and analyzes the text data using natural language processing technology. Techniques such as topic modeling, sentiment analysis, and keyword extraction are used in the analysis. For example, by using topic modeling to identify topics that are frequently mentioned within a specific period and performing sentiment analysis, it is possible to evaluate user interest and reactions. Furthermore, keyword extraction is performed to identify rapidly trending keywords and related topics. This allows the topic selection unit to quickly grasp real-time changing trends and select popular topics. The topic selection unit can also predict trends based on past data. For example, by analyzing past trend data, it predicts fluctuations in topics related to specific seasons or events. This allows the topic selection unit to pre-select topics that are likely to become popular in the future. In addition, the topic selection unit can also suggest personalized topics based on user interests. For example, it analyzes the user's past browsing and search history and suggests topics that are most suitable for the user. This allows the topic selection unit to select topics that meet user needs and support more effective content creation.

[0031] The article generation unit generates articles based on topics selected by the topic selection unit. The article generation unit automatically generates high-quality articles, for example, using a large-scale language model. Specifically, the article generation unit collects information related to the selected topic, the AI ​​considers the article's structure, and writes the specific content. The AI ​​uses natural language generation technology to organize information related to the topic and generate a logically structured article. For example, the AI ​​constructs the introduction, body, and conclusion sections, placing appropriate information in each section. Furthermore, the article generation unit can also adjust the style to suit the user. For example, it can generate articles in casual or professional styles, according to the user's preferences. The AI ​​has parameters for adjusting style and tone, and changes the article's style according to user instructions. This allows the article generation unit to generate a variety of articles to meet user needs. The article generation unit can also evaluate the quality of the generated articles and make corrections as needed. For example, the AI ​​checks the grammar and expression of the generated articles and corrects errors. Additionally, the article generation unit can collect user feedback to improve the generation algorithm. This allows the article generation unit to consistently provide high-quality articles and improve user satisfaction.

[0032] The SEO Optimization Department optimizes the articles generated by the Article Generation Department for search engine optimization (SEO). This includes, for example, keyword optimization and metadata generation. Specifically, the SEO Optimization Department selects appropriate keywords and places them within the article to improve search engine visibility. AI analyzes search engine algorithms to select the most effective keywords. For example, AI analyzes the search volume and competitive landscape of keywords related to the topic to identify the most effective keywords. Furthermore, the SEO Optimization Department also generates metadata to accurately communicate the article's content to search engines. For example, AI generates metadata such as the article's title, description, and tags to appropriately convey the article's content to search engines. This allows the SEO Optimization Department to improve search engine rankings and increase article visibility. The SEO Optimization Department also optimizes internal and external links within articles. For example, AI links relevant content within the article to encourage user navigation within the site. Additionally, it proposes strategies for acquiring links from external sites, improving the article's credibility and authority. This allows the SEO optimization team to maximize the article's performance in search engines and increase user traffic to the site.

[0033] The Monetization Proposal Department proposes monetization strategies based on articles optimized by the SEO Optimization Department. For example, the Monetization Proposal Department uses machine learning models to propose optimal ad placement and subscription model optimization. Specifically, the Monetization Proposal Department analyzes article content and user behavior data to suggest optimal ad placement. AI analyzes user browsing history and interests to identify the most effective ad placement locations and timings. For example, AI places ads in specific sections of articles to attract user attention and improve click-through rates. The Monetization Proposal Department also optimizes subscription models. For example, AI analyzes user subscription history and behavior data to suggest the optimal subscription plan. This allows the Monetization Proposal Department to provide flexible monetization strategies tailored to user needs and maximize revenue. Furthermore, the Monetization Proposal Department continuously monitors the effectiveness of monetization strategies and makes adjustments as needed. For example, AI analyzes ad performance data in real time and proposes new strategies if effectiveness declines. This ensures the Monetization Proposal Department always provides optimal monetization strategies, creating an environment where creators can focus on content creation.

[0034] The topic selection unit can extract popular topics from social media and news sites using natural language processing. For example, the topic selection unit can extract popular topics from social media and news sites using natural language processing. For example, if a particular keyword is trending, the topic selection unit can select topics related to that keyword. The topic selection unit can perform trend analysis and extract popular topics from social media and news sites. In this way, popular topics can be efficiently extracted by utilizing natural language processing. Natural language processing includes techniques such as morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above processing in the topic selection unit may be performed using AI, for example, or without AI. For example, the topic selection unit can input data obtained from social media and news sites into a generating AI and have the generating AI perform the extraction of popular topics.

[0035] The article generation unit can automatically generate high-quality articles using a large-scale language model. For example, the article generation unit can use a large-scale language model to automatically generate high-quality articles. For example, based on a selected topic, the AI ​​in the article generation unit considers the structure of the article and writes the specific content. The article generation unit can also make adjustments to suit the user's style. For example, the article generation unit can generate articles according to the user's preferences, such as a casual writing style or a professional writing style. In this way, high-quality articles can be automatically generated by using a large-scale language model. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the article generation unit can input a selected topic into a generation AI and have the generation AI execute the generation of a high-quality article.

[0036] The SEO optimization unit can perform keyword optimization and metadata generation. For example, the SEO optimization unit selects appropriate keywords and places them within articles to improve visibility in search engines. The SEO optimization unit also generates metadata, ensuring that the content of the article is accurately communicated to search engines. This allows for improved visibility in search engines through keyword optimization and metadata generation. Keyword optimization includes, for example, keyword selection criteria and optimization methods. Metadata generation includes, for example, meta tag types and generation methods. Some or all of the above-described processes in the SEO optimization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the SEO optimization unit can have a generation AI perform keyword optimization and metadata generation within articles.

[0037] The monetization proposal unit can use machine learning models to propose optimizations for ad placement and subscription models. For example, the monetization proposal unit can use machine learning models to propose optimizations for ad placement and subscription models. For example, the monetization proposal unit optimizes ad placement and proposes subscription models to maximize revenue. In this way, the use of machine learning models enables the proposal of optimized monetization strategies. Machine learning models include, for example, regression models and classification models. Some or all of the above processing in the monetization proposal unit may be performed using, for example, generative AI, or not using generative AI. For example, the monetization proposal unit can have generative AI perform the optimization of ad placement and subscription models.

[0038] The topic selection unit can predict future trends by referring to past trend data when selecting topics. For example, the topic selection unit can analyze trend data from the past few years to predict popular topics for each season. For example, the topic selection unit can compare past trend data with current trends to predict upcoming trends. For example, the topic selection unit can predict topics related to specific events or occurrences based on past trend data. In this way, future trends can be predicted by referring to past trend data. Past trend data includes, for example, past search data and social media trend data. Some or all of the above processing in the topic selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the topic selection unit can input past trend data into a generative AI and have the generative AI perform predictions of future trends.

[0039] The topic selection unit can extract topics specific to a particular region or culture during the topic selection process. For example, the topic selection unit can analyze news sites and social media in a specific region and extract popular topics in that region. For example, the topic selection unit can select topics related to a specific culture and generate articles specific to that culture. For example, the topic selection unit can select topics related to events and festivals in a specific region or culture. In this way, by extracting topics specific to a particular region or culture, content related to that region or culture can be generated. A specific region or culture includes, for example, a definition of the region and a method for extracting cultural elements. Some or all of the above-described processes in the topic selection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the topic selection unit can input data related to a specific region or culture into a generative AI and have the generative AI perform topic extraction.

[0040] The topic selection unit can select highly relevant topics by analyzing the user's past posting history. For example, the topic selection unit can analyze the content of articles previously posted by the user and select highly relevant topics. For example, the topic selection unit can select topics related to a specific theme from the user's past posting history. For example, the topic selection unit can select topics that match the user's interests and concerns based on the user's past posting history. In this way, highly relevant topics can be selected by analyzing the user's past posting history. The user's past posting history includes, for example, the type of content posted and the analysis method. Some or all of the above processing in the topic selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the topic selection unit can input the user's past posting history into a generative AI and have the generative AI perform the selection of highly relevant topics.

[0041] The topic selection unit can analyze a user's social media activity and extract relevant topics during topic selection. For example, the topic selection unit can analyze the content of a user's social media posts and extract relevant topics. For example, the topic selection unit can analyze the activity of a user's followers and followed accounts on social media and extract relevant topics. For example, the topic selection unit can analyze a user's social media engagement data and extract popular topics. In this way, relevant topics can be extracted by analyzing a user's social media activity. Social media activity includes, for example, posts and engagement data. Some or all of the above processing in the topic selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the topic selection unit can input the user's social media activity data into a generative AI and have the generative AI perform the extraction of relevant topics.

[0042] The article generation unit can adjust the level of detail in an article based on the importance of the topic during article generation. For example, the article generation unit can generate articles containing detailed information for topics with high importance. For example, the article generation unit can generate articles containing concise information for topics with low importance. For example, the article generation unit can adjust the length and depth of content of an article according to the importance of the topic. This allows for the generation of articles with an appropriate amount of information by adjusting the level of detail based on the importance of the topic. Topic importance includes, for example, evaluation criteria and evaluation methods. Some or all of the above processing in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input topic importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the article.

[0043] The article generation unit can generate customized articles for specific reader segments during article generation. For example, the article generation unit can generate articles for a specific age group. For example, the article generation unit can generate articles for a reader segment with specific interests or concerns. For example, the article generation unit can generate articles for a reader segment related to a specific region or culture. By generating customized articles for specific reader segments, it is possible to attract the interest of readers. Specific reader segments include, for example, reader attributes and customization methods. Some or all of the above-described processes in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input data for a specific reader segment into a generation AI and have the generation AI execute the generation of customized articles.

[0044] The article generation unit can analyze the user's past writing style and generate articles in a matching style when generating articles. For example, the article generation unit can analyze the writing style of articles the user has written in the past and generate articles in a matching style. For example, the article generation unit can generate articles tailored to a specific theme based on the user's past writing style. For example, the article generation unit can generate articles that are easy for readers to understand by referring to the user's past writing style. In this way, by analyzing the user's past writing style, it is possible to generate articles in a matching style. Writing style includes, for example, stylistic characteristics and style matching methods. Some or all of the above processing in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input the user's past writing style data into a generation AI and have the generation AI perform article generation in a matching style.

[0045] The article generation unit can add relevant information based on the user's areas of interest when generating an article. For example, the article generation unit can add the latest news and trend information related to the user's areas of interest. For example, the article generation unit can add specialized information and data related to the user's areas of interest. For example, the article generation unit can add links to other content and resources related to the user's areas of interest. This makes it possible to generate more interesting articles by adding relevant information based on the user's areas of interest. Areas of interest include, for example, methods for identifying areas of interest and methods for adding relevant information. Some or all of the above processing in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input user area of ​​interest data into a generation AI and have the generation AI perform the addition of relevant information.

[0046] The SEO Optimization Department can analyze the SEO strategies of competitor sites and select the optimal keywords during SEO optimization. For example, the SEO Optimization Department can analyze the keyword usage of competitor sites and select the optimal keywords. For example, the SEO Optimization Department can select effective keywords by referring to the SEO strategies of competitor sites. For example, the SEO Optimization Department can analyze the traffic data of competitor sites and select the optimal keywords. In this way, the optimal keywords can be selected by analyzing the SEO strategies of competitor sites. The SEO strategies of competitor sites include, for example, competitive analysis methods and strategy evaluation criteria. Some or all of the above processes in the SEO Optimization Department may be performed using, for example, a generative AI, or without using a generative AI. For example, the SEO Optimization Department can input SEO data from competitor sites into a generative AI and have the generative AI perform the selection of optimal keywords.

[0047] The SEO optimization unit can perform optimizations specifically tailored to particular search engines during the SEO optimization process. This allows for improved visibility in search engines. Some or all of the above-described processes in the SEO optimization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the SEO optimization unit can have a generative AI perform optimizations tailored to a specific search engine.

[0048] The SEO Optimization Department can analyze a user's past SEO performance during SEO optimization and propose the optimal strategy. For example, the SEO Optimization Department can analyze a user's past SEO performance data and propose the optimal strategy. For example, the SEO Optimization Department can suggest effective keywords based on a user's past SEO performance. For example, the SEO Optimization Department can suggest areas for improvement based on a user's past SEO performance. In this way, by analyzing a user's past SEO performance, the optimal SEO strategy can be proposed. Past SEO performance includes, for example, search ranking data and traffic data. Some or all of the above processing in the SEO Optimization Department may be performed using, for example, a generative AI, or without a generative AI. For example, the SEO Optimization Department can input a user's past SEO performance data into a generative AI and have the generative AI propose the optimal strategy.

[0049] The SEO Optimization Department can select keywords based on the user's target market during SEO optimization. For example, the SEO Optimization Department can select keywords related to the user's target market. For example, the SEO Optimization Department can analyze trends in the user's target market and select the most suitable keywords. For example, the SEO Optimization Department can analyze competitor sites in the user's target market and select effective keywords. This allows for more effective SEO measures by selecting keywords based on the user's target market. The target market includes, for example, market attributes and keyword selection criteria. Some or all of the above processes in the SEO Optimization Department may be performed using, for example, a generative AI, or without a generative AI. For example, the SEO Optimization Department can input the user's target market data into a generative AI and have the generative AI perform keyword selection.

[0050] The monetization proposal unit can analyze past revenue data to propose optimal ad placement when making monetization proposals. For example, the monetization proposal unit can analyze a user's past revenue data and propose optimal ad placement. For example, the monetization proposal unit can place ads on specific pages or sections based on a user's past revenue data. For example, the monetization proposal unit can optimize the frequency and timing of ad display by referring to a user's past revenue data. This allows the unit to propose optimal ad placement by analyzing past revenue data. Past revenue data includes, for example, revenue type and analysis method. Some or all of the above processing in the monetization proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the monetization proposal unit can input a user's past revenue data into a generative AI and have the generative AI propose optimal ad placement.

[0051] The monetization proposal unit can propose monetization strategies tailored to specific advertisers when making monetization proposals. For example, the monetization proposal unit can propose monetization strategies that are tailored to the needs of a specific advertiser. For example, the monetization proposal unit can propose ad placements that are tailored to the target market of a specific advertiser. For example, the monetization proposal unit can create content related to a specific advertiser's products or services and monetize it. This maximizes revenue by proposing monetization strategies tailored to specific advertisers. A specific advertiser includes, for example, the advertiser's attributes and proposal methods. Some or all of the above processes in the monetization proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monetization proposal unit can input data of a specific advertiser into a generative AI and have the generative AI execute the monetization strategy proposal.

[0052] The monetization proposal unit can analyze a user's past monetization history and propose the optimal strategy when making a monetization proposal. For example, the monetization proposal unit can analyze a user's past monetization history and propose the optimal strategy. For example, the monetization proposal unit can propose specific ad placements or subscription models based on a user's past monetization history. For example, the monetization proposal unit can suggest areas for improvement in monetization by referring to a user's past monetization history. In this way, by analyzing a user's past monetization history, the optimal monetization strategy can be proposed. Past monetization history includes, for example, the type of monetization and the analysis method. Some or all of the above processing in the monetization proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monetization proposal unit can input the user's past monetization history data into a generative AI and have the generative AI execute a proposal for the optimal strategy.

[0053] The monetization proposal unit can customize monetization strategies based on the user's target market when proposing monetization strategies. For example, the monetization proposal unit can propose monetization strategies related to the user's target market. For example, the monetization proposal unit can analyze trends in the user's target market and propose the optimal monetization strategy. For example, the monetization proposal unit can analyze competitor sites in the user's target market and propose effective monetization strategies. By customizing the monetization strategy based on the user's target market, a more effective monetization strategy can be proposed. The target market includes, for example, market attributes and methods for customizing the monetization strategy. Some or all of the above processing in the monetization proposal unit may be performed using, for example, generative AI, or without generative AI. For example, the monetization proposal unit can input the user's target market data into generative AI and have the generative AI perform the customization of the monetization strategy.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The topic selection unit can analyze a user's past search history and select highly relevant topics. For example, it can extract relevant topics based on keywords the user has searched for in the past. The topic selection unit can select topics related to a specific theme from the user's search history. Furthermore, it can select topics that match the user's interests and concerns based on their search history. In this way, by analyzing the user's past search history, it is possible to select highly relevant topics.

[0056] The topic selection unit can analyze a user's social media activity and extract relevant topics. For example, it can analyze the content of a user's social media posts and extract relevant topics. It can also analyze the activity of a user's followers and followed accounts on social media and extract relevant topics. It can analyze a user's social media engagement data and extract popular topics. In this way, relevant topics can be extracted by analyzing a user's social media activity.

[0057] The SEO Optimization Department can select the most suitable keywords by analyzing the SEO strategies of competitor websites during the SEO optimization process. For example, it can analyze the keyword usage of competitor websites and select the most suitable keywords. It can select effective keywords by referring to the SEO strategies of competitor websites. It can select the most suitable keywords by analyzing the traffic data of competitor websites. In this way, by analyzing the SEO strategies of competitor websites, the most suitable keywords can be selected.

[0058] The monetization proposal team can analyze past revenue data to suggest optimal ad placement when proposing monetization strategies. For example, it can analyze a user's past revenue data and suggest the optimal ad placement. Based on a user's past revenue data, it can place ads on specific pages or sections. By referring to a user's past revenue data, it can optimize the frequency and timing of ad displays. In this way, by analyzing past revenue data, it can suggest the optimal ad placement.

[0059] The topic selection unit can extract topics specific to a particular region or culture during the topic selection process. For example, it can analyze news sites and social media in a specific region to extract popular topics in that region. It can select topics related to a specific culture and generate articles specific to that culture. It can also select topics related to events and festivals in a specific region or culture. In this way, by extracting topics specific to a particular region or culture, it can generate content related to that region or culture.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The topic selection unit selects topics. For example, the topic selection unit uses natural language processing to extract popular topics from social media and news sites. If a particular keyword is trending, it selects topics related to that keyword. Trend analysis can be performed to extract popular topics from social media and news sites. Step 2: The article generation unit generates articles based on the topics selected by the topic selection unit. The article generation unit automatically generates high-quality articles, for example, using a large-scale language model. Based on the selected topic, the AI ​​considers the structure of the article and writes the specific content. It can also make adjustments to suit the user's style, generating articles that match the user's preferences, such as a casual or professional writing style. Step 3: The SEO Optimization Department optimizes the articles generated by the Article Generation Department for SEO purposes. For example, the SEO Optimization Department optimizes keywords and generates metadata. To improve visibility in search engines, it selects appropriate keywords and places them within the article. It also generates metadata to accurately convey the content of the article to search engines. Step 4: The Monetization Proposal Department proposes a monetization strategy based on the articles optimized by the SEO Optimization Department. For example, the Monetization Proposal Department proposes optimizations for ad placement and subscription models using machine learning models. By proposing optimizations for ad placement and subscription models, they maximize revenue. By proposing monetization strategies, creators can focus on content creation while achieving an efficient monetization strategy.

[0062] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system for bloggers, freelance writers, and content creators that balances improving content quality with monetization. This system provides an environment where creators can concentrate on content creation by consistently handling everything from topic selection to article generation, SEO optimization, and monetization strategy proposals. For example, the AI ​​agent system uses natural language processing to extract popular topics from social media and news sites. Next, it automatically generates high-quality articles using a large-scale language model and also makes adjustments to suit the user's style. Furthermore, an SEO-specialized AI optimizes keywords and generates metadata to improve visibility in search engines. Finally, it uses a machine learning model to propose optimizations for ad placement and subscription models to maximize revenue. This mechanism provides creators with an environment where they can concentrate on content creation. For example, the AI ​​agent system uses natural language processing to perform trend analysis and extract popular topics from social media and news sites. For example, if a particular keyword is rapidly increasing in popularity, it selects topics related to that keyword. This information forms the basis for writing articles in the next step. Next, it automatically generates high-quality articles using a large-scale language model. For example, based on a selected topic, the AI ​​will plan the article's structure and write the specific content. It can also be adjusted to the user's style, generating articles tailored to their preferences, such as a casual or professional writing style. Furthermore, an SEO-focused AI optimizes keywords and generates metadata. For instance, it selects appropriate keywords and places them within the article to improve search engine visibility. It also generates metadata to accurately communicate the article's content to search engines. Finally, a machine learning model is used to propose monetization strategies. For example, it optimizes ad placement and suggests subscription models to maximize revenue. This allows creators to focus on content creation while implementing efficient monetization strategies. This system enables creators to balance improving content quality with monetization, overcoming time and resource constraints.For example, by providing comprehensive support from topic selection and article writing to SEO measures and monetization strategy proposals, creators are given an environment where they can concentrate on content creation. This allows the AI ​​agent system to enable creators to focus on content creation while also implementing efficient monetization strategies.

[0063] The AI ​​agent system according to this embodiment comprises a topic selection unit, an article generation unit, an SEO optimization unit, and a monetization proposal unit. The topic selection unit selects topics. The topic selection unit extracts popular topics from social media and news sites, for example, by utilizing natural language processing. For example, if a particular keyword is trending, the topic selection unit selects topics related to that keyword. The topic selection unit can extract popular topics from social media and news sites, for example, by performing trend analysis. The article generation unit generates articles based on the topics selected by the topic selection unit. The article generation unit automatically generates high-quality articles, for example, by using a large-scale language model. For example, based on the selected topic, the article generation unit uses AI to consider the structure of the article and write the specific content. The article generation unit can also make adjustments to match the user's style. For example, the article generation unit can generate articles according to the user's preferences, such as a casual writing style or a professional writing style. The SEO optimization unit performs SEO optimization of the articles generated by the article generation unit. The SEO optimization unit performs keyword optimization and metadata generation, for example. For example, the SEO optimization unit selects appropriate keywords and places them within the article to improve visibility in search engines. The SEO optimization unit also generates metadata, enabling it to accurately convey the article's content to search engines. The monetization proposal unit proposes monetization strategies based on the articles optimized by the SEO optimization unit. For example, the monetization proposal unit proposes optimizations for ad placement and subscription models using machine learning models. For example, the monetization proposal unit optimizes ad placement and proposes subscription models to maximize revenue. By proposing monetization strategies, the monetization proposal unit enables creators to focus on content creation while achieving efficient monetization strategies. As a result, the AI ​​agent system according to this embodiment enables creators to focus on content creation while achieving efficient monetization strategies.

[0064] The topic selection unit selects topics. For example, it extracts popular topics from social media and news sites using natural language processing. Specifically, the topic selection unit collects data from social media and news sites and analyzes the text data using natural language processing technology. Techniques such as topic modeling, sentiment analysis, and keyword extraction are used in the analysis. For example, by using topic modeling to identify topics that are frequently mentioned within a specific period and performing sentiment analysis, it is possible to evaluate user interest and reactions. Furthermore, keyword extraction is performed to identify rapidly trending keywords and related topics. This allows the topic selection unit to quickly grasp real-time changing trends and select popular topics. The topic selection unit can also predict trends based on past data. For example, by analyzing past trend data, it predicts fluctuations in topics related to specific seasons or events. This allows the topic selection unit to pre-select topics that are likely to become popular in the future. In addition, the topic selection unit can also suggest personalized topics based on user interests. For example, it analyzes the user's past browsing and search history and suggests topics that are most suitable for the user. This allows the topic selection unit to select topics that meet user needs and support more effective content creation.

[0065] The article generation unit generates articles based on topics selected by the topic selection unit. The article generation unit automatically generates high-quality articles, for example, using a large-scale language model. Specifically, the article generation unit collects information related to the selected topic, the AI ​​considers the article's structure, and writes the specific content. The AI ​​uses natural language generation technology to organize information related to the topic and generate a logically structured article. For example, the AI ​​constructs the introduction, body, and conclusion sections, placing appropriate information in each section. Furthermore, the article generation unit can also adjust the style to suit the user. For example, it can generate articles in casual or professional styles, according to the user's preferences. The AI ​​has parameters for adjusting style and tone, and changes the article's style according to user instructions. This allows the article generation unit to generate a variety of articles to meet user needs. The article generation unit can also evaluate the quality of the generated articles and make corrections as needed. For example, the AI ​​checks the grammar and expression of the generated articles and corrects errors. Additionally, the article generation unit can collect user feedback to improve the generation algorithm. This allows the article generation unit to consistently provide high-quality articles and improve user satisfaction.

[0066] The SEO Optimization Department optimizes the articles generated by the Article Generation Department for search engine optimization (SEO). This includes, for example, keyword optimization and metadata generation. Specifically, the SEO Optimization Department selects appropriate keywords and places them within the article to improve search engine visibility. AI analyzes search engine algorithms to select the most effective keywords. For example, AI analyzes the search volume and competitive landscape of keywords related to the topic to identify the most effective keywords. Furthermore, the SEO Optimization Department also generates metadata to accurately communicate the article's content to search engines. For example, AI generates metadata such as the article's title, description, and tags to appropriately convey the article's content to search engines. This allows the SEO Optimization Department to improve search engine rankings and increase article visibility. The SEO Optimization Department also optimizes internal and external links within articles. For example, AI links relevant content within the article to encourage user navigation within the site. Additionally, it proposes strategies for acquiring links from external sites, improving the article's credibility and authority. This allows the SEO optimization team to maximize the article's performance in search engines and increase user traffic to the site.

[0067] The Monetization Proposal Department proposes monetization strategies based on articles optimized by the SEO Optimization Department. For example, the Monetization Proposal Department uses machine learning models to propose optimal ad placement and subscription model optimization. Specifically, the Monetization Proposal Department analyzes article content and user behavior data to suggest optimal ad placement. AI analyzes user browsing history and interests to identify the most effective ad placement locations and timings. For example, AI places ads in specific sections of articles to attract user attention and improve click-through rates. The Monetization Proposal Department also optimizes subscription models. For example, AI analyzes user subscription history and behavior data to suggest the optimal subscription plan. This allows the Monetization Proposal Department to provide flexible monetization strategies tailored to user needs and maximize revenue. Furthermore, the Monetization Proposal Department continuously monitors the effectiveness of monetization strategies and makes adjustments as needed. For example, AI analyzes ad performance data in real time and proposes new strategies if effectiveness declines. This ensures the Monetization Proposal Department always provides optimal monetization strategies, creating an environment where creators can focus on content creation.

[0068] The topic selection unit can extract popular topics from social media and news sites using natural language processing. For example, the topic selection unit can extract popular topics from social media and news sites using natural language processing. For example, if a particular keyword is trending, the topic selection unit can select topics related to that keyword. The topic selection unit can perform trend analysis and extract popular topics from social media and news sites. In this way, popular topics can be efficiently extracted by utilizing natural language processing. Natural language processing includes techniques such as morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above processing in the topic selection unit may be performed using AI, for example, or without AI. For example, the topic selection unit can input data obtained from social media and news sites into a generating AI and have the generating AI perform the extraction of popular topics.

[0069] The article generation unit can automatically generate high-quality articles using a large-scale language model. For example, the article generation unit can use a large-scale language model to automatically generate high-quality articles. For example, based on a selected topic, the AI ​​in the article generation unit considers the structure of the article and writes the specific content. The article generation unit can also make adjustments to suit the user's style. For example, the article generation unit can generate articles according to the user's preferences, such as a casual writing style or a professional writing style. In this way, high-quality articles can be automatically generated by using a large-scale language model. Some or all of the above-described processes in the article generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the article generation unit can input a selected topic into a generation AI and have the generation AI execute the generation of a high-quality article.

[0070] The SEO optimization unit can perform keyword optimization and metadata generation. For example, the SEO optimization unit selects appropriate keywords and places them within articles to improve visibility in search engines. The SEO optimization unit also generates metadata, ensuring that the content of the article is accurately communicated to search engines. This allows for improved visibility in search engines through keyword optimization and metadata generation. Keyword optimization includes, for example, keyword selection criteria and optimization methods. Metadata generation includes, for example, meta tag types and generation methods. Some or all of the above-described processes in the SEO optimization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the SEO optimization unit can have a generation AI perform keyword optimization and metadata generation within articles.

[0071] The monetization proposal unit can use machine learning models to propose optimizations for ad placement and subscription models. For example, the monetization proposal unit can use machine learning models to propose optimizations for ad placement and subscription models. For example, the monetization proposal unit optimizes ad placement and proposes subscription models to maximize revenue. In this way, the use of machine learning models enables the proposal of optimized monetization strategies. Machine learning models include, for example, regression models and classification models. Some or all of the above processing in the monetization proposal unit may be performed using, for example, generative AI, or not using generative AI. For example, the monetization proposal unit can have generative AI perform the optimization of ad placement and subscription models.

[0072] The topic selection unit can estimate the user's emotions and adjust the topic selection criteria based on the estimated emotions. For example, if the user is excited, the topic selection unit may prioritize highly entertaining topics. For example, if the user is depressed, the topic selection unit may select topics that offer encouragement or comfort. For example, if the user is stressed, the topic selection unit may select topics related to relaxation or stress relief. This allows for the selection of more appropriate topics by adjusting the topic selection criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the topic selection unit may be performed using AI or not. For example, the topic selection unit can input user emotion data into a generative AI and have the generative AI adjust the topic selection criteria.

[0073] The topic selection unit can predict future trends by referring to past trend data when selecting topics. For example, the topic selection unit can analyze trend data from the past few years to predict popular topics for each season. For example, the topic selection unit can compare past trend data with current trends to predict upcoming trends. For example, the topic selection unit can predict topics related to specific events or occurrences based on past trend data. In this way, future trends can be predicted by referring to past trend data. Past trend data includes, for example, past search data and social media trend data. Some or all of the above processing in the topic selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the topic selection unit can input past trend data into a generative AI and have the generative AI perform predictions of future trends.

[0074] The topic selection unit can extract topics specific to a particular region or culture during the topic selection process. For example, the topic selection unit can analyze news sites and social media in a specific region and extract popular topics in that region. For example, the topic selection unit can select topics related to a specific culture and generate articles specific to that culture. For example, the topic selection unit can select topics related to events and festivals in a specific region or culture. In this way, by extracting topics specific to a particular region or culture, content related to that region or culture can be generated. A specific region or culture includes, for example, a definition of the region and a method for extracting cultural elements. Some or all of the above-described processes in the topic selection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the topic selection unit can input data related to a specific region or culture into a generative AI and have the generative AI perform topic extraction.

[0075] The topic selection unit can estimate the user's emotions and determine topic priorities based on the estimated emotions. For example, if the user is excited, the topic selection unit may prioritize displaying highly entertaining topics. For example, if the user is depressed, the topic selection unit may prioritize displaying topics that offer encouragement or comfort. For example, if the user is stressed, the topic selection unit may prioritize displaying topics related to relaxation or stress relief. In this way, more appropriate topics can be displayed by determining topic priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the topic selection unit may be performed using AI, for example, or not using AI. For example, the topic selection unit can input user emotion data into a generative AI and have the generative AI perform the determination of topic priorities.

[0076] The topic selection unit can select highly relevant topics by analyzing the user's past posting history. For example, the topic selection unit can analyze the content of articles previously posted by the user and select highly relevant topics. For example, the topic selection unit can select topics related to a specific theme from the user's past posting history. For example, the topic selection unit can select topics that match the user's interests and concerns based on the user's past posting history. In this way, highly relevant topics can be selected by analyzing the user's past posting history. The user's past posting history includes, for example, the type of content posted and the analysis method. Some or all of the above processing in the topic selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the topic selection unit can input the user's past posting history into a generative AI and have the generative AI perform the selection of highly relevant topics.

[0077] The topic selection unit can analyze a user's social media activity and extract relevant topics during topic selection. For example, the topic selection unit can analyze the content of a user's social media posts and extract relevant topics. For example, the topic selection unit can analyze the activity of a user's followers and followed accounts on social media and extract relevant topics. For example, the topic selection unit can analyze a user's social media engagement data and extract popular topics. In this way, relevant topics can be extracted by analyzing a user's social media activity. Social media activity includes, for example, posts and engagement data. Some or all of the above processing in the topic selection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the topic selection unit can input the user's social media activity data into a generative AI and have the generative AI perform the extraction of relevant topics.

[0078] The article generation unit can estimate the user's emotions and adjust the way the article is written based on those emotions. For example, if the user is relaxed, the article generation unit can generate an article in a casual style. If the user is excited, the article generation unit can generate an article in an energetic style. If the user is depressed, the article generation unit can generate an article in a style that offers encouragement and comfort. By adjusting the way the article is written based on the user's emotions, a more appropriate article can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the article generation unit may be performed using AI, for example, or not using AI. For example, the article generation unit can input user emotion data into the generation AI and have the generation AI adjust the way the article is written.

[0079] The article generation unit can adjust the level of detail in an article based on the importance of the topic during article generation. For example, the article generation unit can generate articles containing detailed information for topics with high importance. For example, the article generation unit can generate articles containing concise information for topics with low importance. For example, the article generation unit can adjust the length and depth of content of an article according to the importance of the topic. This allows for the generation of articles with an appropriate amount of information by adjusting the level of detail based on the importance of the topic. Topic importance includes, for example, evaluation criteria and evaluation methods. Some or all of the above processing in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input topic importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the article.

[0080] The article generation unit can generate customized articles for specific reader segments during article generation. For example, the article generation unit can generate articles for a specific age group. For example, the article generation unit can generate articles for a reader segment with specific interests or concerns. For example, the article generation unit can generate articles for a reader segment related to a specific region or culture. By generating customized articles for specific reader segments, it is possible to attract the interest of readers. Specific reader segments include, for example, reader attributes and customization methods. Some or all of the above-described processes in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input data for a specific reader segment into a generation AI and have the generation AI execute the generation of customized articles.

[0081] The article generation unit can estimate the user's emotions and adjust the length of the article based on the estimated emotions. For example, if the user is in a hurry, the article generation unit can generate a short, concise article. For example, if the user is relaxed, the article generation unit can generate a longer article with detailed explanations. For example, if the user is excited, the article generation unit can generate an article with visually stimulating effects. By adjusting the length of the article based on the user's emotions, it is possible to generate an article of a more appropriate length. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the article generation unit may be performed using AI, or not using AI. For example, the article generation unit can input user emotion data into the generation AI and have the generation AI adjust the length of the article.

[0082] The article generation unit can analyze the user's past writing style and generate articles in a matching style when generating articles. For example, the article generation unit can analyze the writing style of articles the user has written in the past and generate articles in a matching style. For example, the article generation unit can generate articles tailored to a specific theme based on the user's past writing style. For example, the article generation unit can generate articles that are easy for readers to understand by referring to the user's past writing style. In this way, by analyzing the user's past writing style, it is possible to generate articles in a matching style. Writing style includes, for example, stylistic characteristics and style matching methods. Some or all of the above processing in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input the user's past writing style data into a generation AI and have the generation AI perform article generation in a matching style.

[0083] The article generation unit can add relevant information based on the user's areas of interest when generating an article. For example, the article generation unit can add the latest news and trend information related to the user's areas of interest. For example, the article generation unit can add specialized information and data related to the user's areas of interest. For example, the article generation unit can add links to other content and resources related to the user's areas of interest. This makes it possible to generate more interesting articles by adding relevant information based on the user's areas of interest. Areas of interest include, for example, methods for identifying areas of interest and methods for adding relevant information. Some or all of the above processing in the article generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the article generation unit can input user area of ​​interest data into a generation AI and have the generation AI perform the addition of relevant information.

[0084] The SEO optimization unit can estimate a user's emotions and adjust the priority of SEO measures based on those emotions. For example, if a user is excited, the SEO optimization unit can prioritize keywords that are highly entertaining. If a user is depressed, the SEO optimization unit can prioritize keywords that offer encouragement or comfort. If a user is stressed, the SEO optimization unit can prioritize keywords related to relaxation or stress relief. By adjusting the priority of SEO measures based on the user's emotions, more effective SEO measures can be implemented. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the SEO optimization unit may be performed using AI, for example, or not using AI. For example, the SEO optimization unit can input user emotion data into a generative AI and have the generative AI adjust the priority of SEO measures.

[0085] The SEO Optimization Department can analyze the SEO strategies of competitor sites and select the optimal keywords during SEO optimization. For example, the SEO Optimization Department can analyze the keyword usage of competitor sites and select the optimal keywords. For example, the SEO Optimization Department can select effective keywords by referring to the SEO strategies of competitor sites. For example, the SEO Optimization Department can analyze the traffic data of competitor sites and select the optimal keywords. In this way, the optimal keywords can be selected by analyzing the SEO strategies of competitor sites. The SEO strategies of competitor sites include, for example, competitive analysis methods and strategy evaluation criteria. Some or all of the above processes in the SEO Optimization Department may be performed using, for example, a generative AI, or without using a generative AI. For example, the SEO Optimization Department can input SEO data from competitor sites into a generative AI and have the generative AI perform the selection of optimal keywords.

[0086] The SEO optimization unit can perform optimizations specifically tailored to particular search engines during the SEO optimization process. This allows for improved visibility in search engines. Some or all of the above-described processes in the SEO optimization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the SEO optimization unit can have a generative AI perform optimizations tailored to a specific search engine.

[0087] The SEO optimization unit can estimate the user's emotions and adjust the metadata generation method based on the estimated user emotions. For example, if the user is excited, the SEO optimization unit can generate highly entertaining metadata. For example, if the user is depressed, the SEO optimization unit can generate encouraging or comforting metadata. For example, if the user is stressed, the SEO optimization unit can generate metadata related to relaxation and stress relief. By adjusting the metadata generation method based on the user's emotions, more effective metadata can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the SEO optimization unit may be performed using AI, for example, or not using AI. For example, the SEO optimization unit can input user emotion data into a generative AI and have the generative AI adjust the metadata generation method.

[0088] The SEO Optimization Department can analyze a user's past SEO performance during SEO optimization and propose the optimal strategy. For example, the SEO Optimization Department can analyze a user's past SEO performance data and propose the optimal strategy. For example, the SEO Optimization Department can suggest effective keywords based on a user's past SEO performance. For example, the SEO Optimization Department can suggest areas for improvement based on a user's past SEO performance. In this way, by analyzing a user's past SEO performance, the optimal SEO strategy can be proposed. Past SEO performance includes, for example, search ranking data and traffic data. Some or all of the above processing in the SEO Optimization Department may be performed using, for example, a generative AI, or without a generative AI. For example, the SEO Optimization Department can input a user's past SEO performance data into a generative AI and have the generative AI propose the optimal strategy.

[0089] The SEO Optimization Department can select keywords based on the user's target market during SEO optimization. For example, the SEO Optimization Department can select keywords related to the user's target market. For example, the SEO Optimization Department can analyze trends in the user's target market and select the most suitable keywords. For example, the SEO Optimization Department can analyze competitor sites in the user's target market and select effective keywords. This allows for more effective SEO measures by selecting keywords based on the user's target market. The target market includes, for example, market attributes and keyword selection criteria. Some or all of the above processes in the SEO Optimization Department may be performed using, for example, a generative AI, or without a generative AI. For example, the SEO Optimization Department can input the user's target market data into a generative AI and have the generative AI perform keyword selection.

[0090] The monetization suggestion unit can estimate the user's emotions and adjust the method of suggesting monetization strategies based on the estimated user emotions. For example, if the user is excited, the monetization suggestion unit can suggest an aggressive monetization strategy. For example, if the user is depressed, the monetization suggestion unit can suggest a low-risk monetization strategy. For example, if the user is stressed, the monetization suggestion unit can suggest a simple and easy monetization strategy. By adjusting the method of suggesting monetization strategies based on the user's emotions, a more appropriate monetization strategy can be suggested. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monetization suggestion unit may be performed using AI or not using AI. For example, the monetization suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the method of suggesting monetization strategies.

[0091] The monetization proposal unit can analyze past revenue data to propose optimal ad placement when making monetization proposals. For example, the monetization proposal unit can analyze a user's past revenue data and propose optimal ad placement. For example, the monetization proposal unit can place ads on specific pages or sections based on a user's past revenue data. For example, the monetization proposal unit can optimize the frequency and timing of ad display by referring to a user's past revenue data. This allows the unit to propose optimal ad placement by analyzing past revenue data. Past revenue data includes, for example, revenue type and analysis method. Some or all of the above processing in the monetization proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the monetization proposal unit can input a user's past revenue data into a generative AI and have the generative AI propose optimal ad placement.

[0092] The monetization proposal unit can propose monetization strategies tailored to specific advertisers when making monetization proposals. For example, the monetization proposal unit can propose monetization strategies that are tailored to the needs of a specific advertiser. For example, the monetization proposal unit can propose ad placements that are tailored to the target market of a specific advertiser. For example, the monetization proposal unit can create content related to a specific advertiser's products or services and monetize it. This maximizes revenue by proposing monetization strategies tailored to specific advertisers. A specific advertiser includes, for example, the advertiser's attributes and proposal methods. Some or all of the above processes in the monetization proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monetization proposal unit can input data of a specific advertiser into a generative AI and have the generative AI execute the monetization strategy proposal.

[0093] The monetization suggestion unit can estimate the user's emotions and prioritize monetization strategies based on those emotions. For example, if the user is excited, the monetization suggestion unit may prioritize aggressive monetization strategies. If the user is depressed, for example, the monetization suggestion unit may prioritize low-risk monetization strategies. If the user is stressed, for example, the monetization suggestion unit may prioritize simple and easy monetization strategies. By prioritizing monetization strategies based on the user's emotions, more appropriate monetization strategies can be suggested. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monetization suggestion unit may be performed using AI or not. For example, the monetization suggestion unit can input user emotion data into a generative AI and have the generative AI determine the priority of monetization strategies.

[0094] The monetization proposal unit can analyze a user's past monetization history and propose the optimal strategy when making a monetization proposal. For example, the monetization proposal unit can analyze a user's past monetization history and propose the optimal strategy. For example, the monetization proposal unit can propose specific ad placements or subscription models based on a user's past monetization history. For example, the monetization proposal unit can suggest areas for improvement in monetization by referring to a user's past monetization history. In this way, by analyzing a user's past monetization history, the optimal monetization strategy can be proposed. Past monetization history includes, for example, the type of monetization and the analysis method. Some or all of the above processing in the monetization proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the monetization proposal unit can input the user's past monetization history data into a generative AI and have the generative AI execute a proposal for the optimal strategy.

[0095] The monetization proposal unit can customize monetization strategies based on the user's target market when proposing monetization strategies. For example, the monetization proposal unit can propose monetization strategies related to the user's target market. For example, the monetization proposal unit can analyze trends in the user's target market and propose the optimal monetization strategy. For example, the monetization proposal unit can analyze competitor sites in the user's target market and propose effective monetization strategies. By customizing the monetization strategy based on the user's target market, a more effective monetization strategy can be proposed. The target market includes, for example, market attributes and methods for customizing the monetization strategy. Some or all of the above processing in the monetization proposal unit may be performed using, for example, generative AI, or without generative AI. For example, the monetization proposal unit can input the user's target market data into generative AI and have the generative AI perform the customization of the monetization strategy.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] The topic selection unit can analyze a user's past search history and select highly relevant topics. For example, it can extract relevant topics based on keywords the user has searched for in the past. The topic selection unit can select topics related to a specific theme from the user's search history. Furthermore, it can select topics that match the user's interests and concerns based on their search history. In this way, by analyzing the user's past search history, it is possible to select highly relevant topics.

[0098] The article generation unit can estimate the user's emotions and adjust the article content based on those emotions. For example, if the user is excited, it can generate an energetic article. If the user is depressed, it can generate an article that offers encouragement and comfort. If the user is stressed, it can generate an article related to relaxation and stress relief. By adjusting the article content based on the user's emotions, it can generate more appropriate articles.

[0099] The SEO optimization team can estimate user emotions and adjust the priority of SEO measures based on those emotions. For example, if a user is excited, it can prioritize keywords with high entertainment value. If a user is depressed, it can prioritize keywords that offer encouragement or comfort. If a user is stressed, it can prioritize keywords related to relaxation and stress relief. By adjusting the priority of SEO measures based on user emotions, more effective SEO can be achieved.

[0100] The monetization suggestion department can estimate user emotions and adjust how monetization strategies are suggested based on those emotions. For example, if a user is excited, it can suggest an aggressive monetization strategy. If a user is depressed, it can suggest a low-risk monetization strategy. If a user is stressed, it can suggest a simple and easy monetization strategy. By adjusting how monetization strategies are suggested based on user emotions, it can propose more appropriate monetization strategies.

[0101] The topic selection unit can analyze a user's social media activity and extract relevant topics. For example, it can analyze the content of a user's social media posts and extract relevant topics. It can also analyze the activity of a user's followers and followed accounts on social media and extract relevant topics. It can analyze a user's social media engagement data and extract popular topics. In this way, relevant topics can be extracted by analyzing a user's social media activity.

[0102] The article generation unit can estimate the user's emotions and adjust the article's style of expression based on those emotions. For example, if the user is relaxed, it can generate an article in a casual style. If the user is excited, it can generate an article in an energetic style. If the user is depressed, it can generate an article in a style that offers encouragement and comfort. By adjusting the article's style of expression based on the user's emotions, it can generate more appropriate articles.

[0103] The SEO Optimization Department can select the most suitable keywords by analyzing the SEO strategies of competitor websites during the SEO optimization process. For example, it can analyze the keyword usage of competitor websites and select the most suitable keywords. It can select effective keywords by referring to the SEO strategies of competitor websites. It can select the most suitable keywords by analyzing the traffic data of competitor websites. In this way, by analyzing the SEO strategies of competitor websites, the most suitable keywords can be selected.

[0104] The monetization proposal team can analyze past revenue data to suggest optimal ad placement when proposing monetization strategies. For example, it can analyze a user's past revenue data and suggest the optimal ad placement. Based on a user's past revenue data, it can place ads on specific pages or sections. By referring to a user's past revenue data, it can optimize the frequency and timing of ad displays. In this way, by analyzing past revenue data, it can suggest the optimal ad placement.

[0105] The topic selection unit can extract topics specific to a particular region or culture during the topic selection process. For example, it can analyze news sites and social media in a specific region to extract popular topics in that region. It can select topics related to a specific culture and generate articles specific to that culture. It can also select topics related to events and festivals in a specific region or culture. In this way, by extracting topics specific to a particular region or culture, it can generate content related to that region or culture.

[0106] The monetization suggestion unit can estimate user emotions and prioritize monetization strategies based on those emotions. For example, if a user is excited, it can prioritize suggesting aggressive monetization strategies. If a user is depressed, it can prioritize suggesting low-risk monetization strategies. If a user is stressed, it can prioritize suggesting simple and easy monetization strategies. By prioritizing monetization strategies based on user emotions, it can suggest more appropriate strategies.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The topic selection unit selects topics. For example, the topic selection unit uses natural language processing to extract popular topics from social media and news sites. If a particular keyword is trending, it selects topics related to that keyword. Trend analysis can be performed to extract popular topics from social media and news sites. Step 2: The article generation unit generates articles based on the topics selected by the topic selection unit. The article generation unit automatically generates high-quality articles, for example, using a large-scale language model. Based on the selected topic, the AI ​​considers the structure of the article and writes the specific content. It can also make adjustments to suit the user's style, generating articles that match the user's preferences, such as a casual or professional writing style. Step 3: The SEO Optimization Department optimizes the articles generated by the Article Generation Department for SEO purposes. For example, the SEO Optimization Department optimizes keywords and generates metadata. To improve visibility in search engines, it selects appropriate keywords and places them within the article. It also generates metadata to accurately convey the content of the article to search engines. Step 4: The Monetization Proposal Department proposes a monetization strategy based on the articles optimized by the SEO Optimization Department. For example, the Monetization Proposal Department proposes optimizations for ad placement and subscription models using machine learning models. By proposing optimizations for ad placement and subscription models, they maximize revenue. By proposing monetization strategies, creators can focus on content creation while achieving an efficient monetization strategy.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0111] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0112] Each of the multiple elements described above, including the topic selection unit, article generation unit, SEO optimization unit, and monetization proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the topic selection unit is implemented by the control unit 46A of the smart device 14 and extracts popular topics from social media and news sites. The article generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates high-quality articles using a large-scale language model. The SEO optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs keyword optimization and metadata generation. The monetization proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes optimizations for ad placement and subscription models. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0116] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0117] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0119] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0120] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0121] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0122] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0123] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0124] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0127] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the topic selection unit, article generation unit, SEO optimization unit, and monetization proposal unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the topic selection unit is implemented by the control unit 46A of the smart glasses 214 and extracts popular topics from social media and news sites. The article generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates high-quality articles using a large-scale language model. The SEO optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs keyword optimization and metadata generation. The monetization proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes optimizations for ad placement and subscription models. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the topic selection unit, article generation unit, SEO optimization unit, and monetization proposal unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the topic selection unit is implemented by the control unit 46A of the headset terminal 314 and extracts popular topics from social networking services and news sites. The article generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates high-quality articles using a large-scale language model. The SEO optimization unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs keyword optimization and metadata generation. The monetization proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes optimizations for ad placement and subscription models. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0153] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0158] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0159] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0160] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0161] Each of the multiple elements described above, including the topic selection unit, article generation unit, SEO optimization unit, and monetization proposal unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the topic selection unit is implemented by the control unit 46A of the robot 414 and extracts popular topics from social media and news sites. The article generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically generates high-quality articles using a large-scale language model. The SEO optimization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and performs keyword optimization and metadata generation. The monetization proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes optimizations for ad placement and subscription models. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0162] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0164] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0165] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0166] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0170] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0171] 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.

[0172] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0173] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0174] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0175] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0177] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0178] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0179] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0180] (Note 1) The topic selection unit selects topics, An article generation unit that generates an article based on a topic selected by the aforementioned topic selection unit, An SEO optimization unit that performs SEO optimization on articles generated by the aforementioned article generation unit, The system comprises a monetization proposal unit that proposes a monetization strategy based on articles optimized by the aforementioned SEO optimization unit. A system characterized by the following features. (Note 2) The aforementioned topic selection unit, Extract popular topics from social media and news sites using natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned article generation unit, Automatically generate high-quality articles using large-scale language models. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned SEO optimization unit, Keyword optimization and metadata generation The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned monetization proposal department, We propose optimizing ad placement and subscription models using machine learning models. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned topic selection unit, We estimate user sentiment and adjust topic selection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned topic selection unit, When selecting a topic, we refer to past trend data to predict future trends. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned topic selection unit, When selecting topics, extract topics that are specific to a particular region or culture. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned topic selection unit, It estimates user sentiment and prioritizes topics based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned topic selection unit, When selecting a topic, the system analyzes the user's past posting history to select the most relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned topic selection unit, When selecting topics, we analyze users' social media activity to extract relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned article generation unit, We estimate the user's emotions and adjust the way the article is written based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned article generation unit, When generating an article, adjust the level of detail based on the importance of the topic. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned article generation unit, When generating articles, create customized articles tailored to a specific readership. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned article generation unit, It estimates the user's sentiment and adjusts the article length based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned article generation unit, When generating an article, the system analyzes the user's past writing style and generates articles using a matching style. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned article generation unit, When generating an article, add relevant information based on the user's areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned SEO optimization unit, It estimates user sentiment and adjusts SEO priorities based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned SEO optimization unit, When optimizing for SEO, analyze the SEO strategies of competitor websites to select the most suitable keywords. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned SEO optimization unit, When optimizing for SEO, perform optimization specifically tailored to a particular search engine. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned SEO optimization unit, It estimates the user's emotions and adjusts how metadata is generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned SEO optimization unit, When optimizing SEO, we analyze the user's past SEO performance and propose the optimal strategy. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned SEO optimization unit, When optimizing for SEO, select keywords based on the user's target market. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned monetization proposal department, We estimate user sentiment and adjust how we propose monetization strategies based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned monetization proposal department, When proposing monetization, we analyze past revenue data to suggest the optimal ad placement. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned monetization proposal department, When proposing monetization strategies, we propose monetization strategies tailored to specific advertisers. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned monetization proposal department, We estimate user sentiment and prioritize monetization strategies based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned monetization proposal department, When proposing monetization strategies, we analyze the user's past monetization history to suggest the optimal strategy. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned monetization proposal department, When proposing monetization strategies, customize them based on the user's target market. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The topic selection unit selects topics, An article generation unit that generates an article based on a topic selected by the aforementioned topic selection unit, An SEO optimization unit that performs SEO optimization on articles generated by the aforementioned article generation unit, The system comprises a monetization proposal unit that proposes a monetization strategy based on articles optimized by the aforementioned SEO optimization unit. A system characterized by the following features.

2. The aforementioned topic selection unit, Extract popular topics from social media and news sites using natural language processing. The system according to feature 1.

3. The aforementioned article generation unit, Automatically generate high-quality articles using large-scale language models. The system according to feature 1.

4. The aforementioned SEO optimization unit, Keyword optimization and metadata generation The system according to feature 1.

5. The aforementioned monetization proposal department, We propose optimizing ad placement and subscription models using machine learning models. The system according to feature 1.

6. The aforementioned topic selection unit, We estimate user sentiment and adjust topic selection criteria based on the estimated user sentiment. The system according to feature 1.

7. The aforementioned topic selection unit, When selecting a topic, we refer to past trend data to predict future trends. The system according to feature 1.

8. The aforementioned topic selection unit, When selecting topics, extract topics that are specific to a particular region or culture. The system according to feature 1.

9. The aforementioned topic selection unit, It estimates user sentiment and prioritizes topics based on the estimated user sentiment. The system according to feature 1.

10. The aforementioned topic selection unit, When selecting a topic, the system analyzes the user's past posting history to select the most relevant topics. The system according to feature 1.

Images