system

Abstract

This system provides the ability to quickly generate articles that select optimal keywords based on relevant information and trend data, while maintaining consistency in writing style and format. [Solution] A system comprising: means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the keyword efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated keyword efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for generating article elements based on the received keyword; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 the chatbot's 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] SEO work, such as keyword selection, article writing, and proofreading, which requires a lot of time and labor, not only has difficulty in efficient operation, but also has a problem that the quality of the resulting content varies. Furthermore, it is difficult to maintain consistency in the generation of content optimized for the tone and style unique to a brand through manual work. Therefore, there is an increasing need for a system that can automatically improve the overall efficiency of SEO work and generate high-quality content optimized for a brand.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides the following means: means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the keyword efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated keyword efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for generating article elements based on the received keyword; means for optimizing the generated article elements according to a writing style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. By providing a system that includes these means, it becomes possible to streamline SEO work and automatically generate high-quality content optimized for the brand. This system makes it possible to select the optimal keyword considering competitive information and trend data and generate articles with consistent writing style and formatting in a short amount of time.

[0006] 1. "Brand information" refers to data concerning specific trademarks or company names, their concepts, values, and market positioning.

[0007] 2. "Market information" refers to data concerning the characteristics of the target customer base, the activities of competitors, consumer trends, and market size.

[0008] 3. "Related keywords" are words that are frequently searched on search engines or keywords that are likely to interest the target customers, based on the specified brand information and market information.

[0009] 4. "Keyword efficiency" is a metric that quantifies the search volume, competition level, and relevance of a particular keyword.

[0010] 5. A "keyword list" is a list of multiple related keywords optimized based on keyword efficiency.

[0011] 6. "Article elements" are the constituent elements of an article generated based on keywords (for example, title, headings, body text, etc.).

[0012] 7. A "style guide" is a set of guidelines that provides instructions and rules for writing in accordance with a specific brand or style.

[0013] 8. "Correction instructions" refer to the act of a user providing specific instructions for corrections to an article that has been generated. [Brief explanation of the drawing]

[0014] [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. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the language used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] 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.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception 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 reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] The 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.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[0036] 1. KW selection

[0037] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[0038] 2. Article generation

[0039] When a user selects the most suitable keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server uses relevant databases and pre-trained models to collect information related to the keyword. The server then generates article elements (e.g., title: "Easily Start Shaping Up with the Latest Diet Foods," body text: "A Must-See for Those Who Want to Lose Weight Healthily! Introducing the Latest Diet Foods. These products are rich in vitamins and also effective for beauty.") based on the collected information. The server also optimizes the generated article based on the brand tone (e.g., "casual and approachable") and style guide.

[0040] 3. Proofreading

[0041] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[0042] In this way, the entire system's specific operations automate a series of SEO tasks, from keyword selection to proofreading, significantly reducing the user's burden and enabling the efficient, consistent, and high-quality generation of content.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[0046] Step 2:

[0047] Based on the received brand and market information, the server retrieves relevant keywords (e.g., "dietary foods," "vitamin supplements," "beauty supplements") from the database.

[0048] Step 3:

[0049] The server analyzes competitive information and trend data from search engines for the retrieved related keywords, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[0050] Step 4:

[0051] The server compiles a list of highly efficient keywords and presents it to the user.

[0052] Step 5:

[0053] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device.

[0054] Step 6:

[0055] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[0056] Step 7:

[0057] The server optimizes the generated articles according to the brand's tone and style guide. For example, it adjusts the text to have a "casual and approachable" tone.

[0058] Step 8:

[0059] The server sends the optimized article to the user, who receives it on their device.

[0060] Step 9:

[0061] The user reviews the generated article on their device and, if necessary, enters correction instructions (e.g., "Make the title more impactful") and sends them to the server.

[0062] Step 10:

[0063] The server analyzes user correction requests and automatically modifies the generated articles. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[0064] Step 11:

[0065] The server optimizes the revised article again and sends it to the user. The user receives it again on their device and performs a final check of the article.

[0066] Step 12:

[0067] Once the user is satisfied with the article's content and signals the terminal to complete the review, the terminal sends that information to the server, and the process ends.

[0068] (Example 1)

[0069] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0070] Traditional SEO work is often done manually, making it time-consuming and labor-intensive, and thus inefficient. Furthermore, it is prone to inconsistencies in content quality and consistency, making it difficult to consistently generate high-quality content that is appropriate for the brand. Additionally, proofreading and revising the generated content is time-consuming and requires quick responses. This invention aims to automate these problems and improve efficiency and consistency.

[0071] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0072] In this invention, the server includes means for receiving brand information and market information, means for obtaining relevant keywords, means for calculating keyword efficiency, means for generating a keyword list, means for optimizing the generated article elements according to a style guide, means for revising the article based on revision instructions, and means for receiving revision completion instructions. This enables the automation and efficiency of SEO work, allowing for the rapid generation and revision of high-quality, consistent, and brand-appropriate content.

[0073] "Brand information" refers to identifiable information associated with a specific company, product, or service.

[0074] "Market information" refers to data and insights about a specific market or target audience.

[0075] A "keyword" refers to an important word or phrase related to a specific theme or topic.

[0076] "Keyword efficiency" is an efficiency metric calculated based on factors such as keyword search volume, competition level, and relevance.

[0077] "Article elements" refer to the constituent elements of content, such as the title and body text.

[0078] A "style guide" refers to guidelines regarding the writing style and tone of documents based on a specific brand or style.

[0079] "Tone" refers to the use of language to express the emotions and atmosphere of a text or content.

[0080] "Correction instructions" refer to instructions regarding changes or improvements to user-generated content.

[0081] A "correction completion instruction" refers to an instruction for the user to confirm that the corrected content is appropriate and to ultimately approve it.

[0082] A "generative AI model" refers to an artificial intelligence algorithm used for tasks such as text generation and data analysis.

[0083] To implement this invention, a system is required in which users, terminals, and servers work together. This system automates the streamlining of SEO work and the generation of high-quality content based on brand information and market information.

[0084] The overall system hardware configuration will consist of the user's PC or smartphone (device) and AWS® EC2 instances (servers). The software will utilize MySQL® as the database, OpenAI® GPT as the generative AI model, and Django as the server-side framework.

[0085] Explanation in natural language

[0086] KW selection

[0087] 1. User input

[0088] Users input information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and send it to the server. Input is done through a dedicated form, and processing begins on the server after submission.

[0089] 2. Server processing - Retrieval of related keywords

[0090] The server retrieves relevant keywords from the MySQL database using queries based on the received brand and market information. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[0091] 3. Server Processing - Calculation and Listing of KW Efficiency

[0092] The server analyzes competitive information and search engine trend data for these keywords and calculates keyword efficiency based on each keyword's search volume, competitiveness, and relevance. For example, it uses the Google® Trends API to retrieve data and assigns a weighted score to each keyword to calculate keyword efficiency. Keywords with high scores are then presented to the user as a list.

[0093] Article generation

[0094] 1. User Selection

[0095] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device. The user selects a keyword from the list and clicks the "Confirm" button to submit it.

[0096] 2. Server Processing - Information Gathering and Article Generation

[0097] The server uses a generative AI model such as OpenAI GPT-3 (registered trademark) to collect relevant information based on selected keywords, and then generates article elements based on that information. For example, it sends a prompt sentence such as "Please tell me the latest information on diet foods" to the generative AI model, and then creates a title and body text based on the information obtained.

[0098] 3. Server Processing - Optimization Based on Tone and Style Guides

[0099] The server modifies the generated content to match the brand's tone and style guide (e.g., "casual and approachable"). It changes the style and expression of the generated text to ensure consistency and completes an optimized article for the user.

[0100] Proofreading

[0101] 1. User Verification

[0102] The generated article is sent from the server to the user, who then reviews the content on their device. If there are any problems with the content, the user uses the editing form on their device to enter correction instructions (e.g., "Please change the title to something more attention-grabbing") and sends them to the server.

[0103] 2. Server processing - Article revision

[0104] The server analyzes user correction instructions and automatically corrects the article using a generative AI model. For example, if there is a instruction regarding the title, it will regenerate the article using a prompt such as "Make the title more attention-grabbing."

[0105] 3. User's final confirmation and completion instructions

[0106] The user reviews the revised article again, and if they are finally satisfied, they indicate on their device that the review is complete. By pressing the "Complete" button, the user sends that information to the server, and the process officially ends.

[0107] Specific examples and prompt statements

[0108] Specific example

[0109] KW selection

[0110] Information entered by the user: Brand information "Health Foods", Target market information "Women in their 20s and 30s"

[0111] The server provides a list of keywords: diet foods, vitamin supplements, beauty supplements.

[0112] Article generation

[0113] Keywords selected by users: Diet foods

[0114] Articles generated by the server:

[0115] Title: "Easily Start Shaping Up with the Latest Diet Foods"

[0116] Text: "A must-see for those who want to lose weight healthily! Introducing the latest diet foods. These products are rich in vitamins and also effective for beauty."

[0117] Example of a prompt

[0118] "Please select highly efficient keywords based on health food brands and target market information for women in their 20s and 30s."

[0119] "Please write an article about diet foods. The title should be approachable and casual."

[0120] Thus, the system of the present invention automates a series of SEO tasks, from keyword selection to article generation and proofreading, significantly reducing the burden on the user and enabling efficient, consistent, and high-quality content generation.

[0121] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0122] Processing steps

[0123] KW selection

[0124] Step 1:

[0125] Users enter brand information and market information.

[0126] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and clicks the submit button. This information is then sent to the server.

[0127] Input: Brand information, market information

[0128] Output: Brand information and market information sent to the server

[0129] Step 2:

[0130] The server retrieves related keywords.

[0131] Based on the received brand and market information, the server retrieves relevant keywords from the MySQL database using queries. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[0132] Input: Brand information, market information

[0133] Data processing / calculation: Retrieve relevant keywords from a MySQL database using queries.

[0134] Output: List of related keywords

[0135] Step 3:

[0136] The server calculates keyword efficiency and generates a keyword list.

[0137] The server analyzes the retrieved related keywords using the Google Trends API and other tools to determine the search volume, competition level, relevance, etc., and calculates keyword efficiency. Based on the calculation results, it selects high-scoring keywords and generates a keyword list.

[0138] Input: List of related keywords

[0139] Data processing / calculation: Analyze each keyword using the Google Trends API, etc., and calculate keyword efficiency.

[0140] Output: List of keywords with high KW efficiency

[0141] Article generation

[0142] Step 4:

[0143] The user selects and submits the most suitable keywords.

[0144] The user selects the most suitable keyword (e.g., "diet food") from the presented keyword list and sends it to the server via their device. The user selects a keyword and clicks the "Confirm" button.

[0145] Input: List of highly efficient keywords (KW)

[0146] Output: Optimal keywords sent to the server

[0147] Step 5:

[0148] The server collects information and generates article elements.

[0149] The server uses a generative AI model such as OpenAI GPT-3 to create a prompt based on the most suitable keywords it receives, and then collects relevant information based on that prompt. Specifically, it sends a prompt such as "Please tell me the latest information on diet foods" to the model, and then creates an article title and body based on the generated information.

[0150] Input: Best keyword

[0151] Data Processing / Calculation: Use a generative AI model to create prompt statements, collect information, and generate article elements.

[0152] Output: Generated article elements (title, body)

[0153] Step 6:

[0154] The server optimizes article elements.

[0155] The server adjusts the generated article elements based on the brand's tone and style guide, optimizing them to ensure consistency in writing style and content. For example, it might adjust the writing style to a "casual and approachable" tone.

[0156] Input: Generated article elements (title, body)

[0157] Data processing / calculation: Optimize article elements based on the brand's tone and style guide.

[0158] Output: Optimized article

[0159] Proofreading

[0160] Step 7:

[0161] Users review articles and submit correction requests.

[0162] The server sends an optimized article to the user. The user reviews the article on their device and, if necessary, enters correction instructions (e.g., "Make the title more eye-catching") and sends them to the server.

[0163] Input: Optimized article

[0164] Output: Correction instructions sent to the server

[0165] Step 8:

[0166] The server will modify the article.

[0167] The server analyzes the user's correction instructions and uses a generative AI model to revise the article. For example, in response to the instruction "Make the title more attention-grabbing," it regenerates the prompt as "Generate a more attention-grabbing title."

[0168] Input: Correction Instructions

[0169] Data processing / calculation: Regenerate and correct articles using a generative AI model.

[0170] Output: Corrected article

[0171] Step 9:

[0172] The user submits a correction completion instruction.

[0173] The user reviews the revised article again, and if they are finally satisfied, they send a correction completion notification from their device. By pressing the "Complete" button, the user sends that information to the server.

[0174] Input: Modified article

[0175] Output: Correction completion instruction sent to the server

[0176] (Application Example 1)

[0177] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0178] Traditional SEO and ad copy generation processes required significant time and effort for keyword selection, content creation, and ad copy creation based on brand and market information. Furthermore, verifying and adjusting whether the generated content aligned with brand tone and market trends was cumbersome, making it difficult to provide efficient, consistent, and high-quality content.

[0179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0180] In this invention, the server includes means for receiving brand information and market information, means for acquiring relevant keywords, and means for calculating the keyword efficiency of the acquired keywords. This automates a series of processes, from keyword selection to article and ad copy generation, and style optimization and revision, enabling the efficient, consistent, and high-quality delivery of content and ad copy.

[0181] "Brand information" refers to information about the awareness and image of a particular company or product.

[0182] "Market information" refers to data and statistics related to a specific target market.

[0183] "Related keywords" are terms used by search engines to select keywords based on brand and market information.

[0184] "Keyword efficiency" is an efficiency metric calculated based on factors such as search volume, competition level, and relevance of related keywords.

[0185] A "keyword list" is a list of related keywords generated based on keyword efficiency.

[0186] "Article elements" refer to the constituent elements of an article, such as the title and body text, which are generated based on keywords.

[0187] A "style guide" is a set of guidelines designed to reflect a brand's tone and style.

[0188] "Correction instructions" are instructions from users to change or revise articles or ad copy.

[0189] "Ad copy" refers to marketing and promotional text generated using selected keywords.

[0190] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to achieve the automated generation of efficient, consistent, and high-quality advertising content.

[0191] System Configuration

[0192] Servers, terminals, and users are the main components of the system.

[0193] server

[0194] The server performs the following roles:

[0195] 1. Receiving brand and market information: The system has a means of receiving brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35") entered by the user.

[0196] 2. Acquisition of related keywords: Based on the received brand information and market information, related keywords (e.g., "natural skincare", "additive-free cosmetics") are retrieved from the database.

[0197] 3. Calculation of Keyword Efficiency: Analyze the acquired related keywords, competitive information, and trend data from search engines to calculate keyword efficiency.

[0198] 4. Keyword List Generation: Based on the calculated keyword efficiency, list the most efficient keywords.

[0199] 5. Ad copy generation: Based on the most suitable keywords, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized to match the brand tone.

[0200] terminal

[0201] The terminal will perform the following roles:

[0202] 1. Input of brand and market information: Provide an interface for users to input brand and market information.

[0203] 2. Displaying the Keyword List: The keyword list received from the server is displayed to the user.

[0204] 3. Selection of optimal keywords: The user selects the most suitable keywords from the keyword list and sends them to the server.

[0205] 4. Viewing and modifying the generated ad copy: The user reviews the generated ad copy, enters any necessary modification instructions, and sends them to the server.

[0206] User

[0207] The user will play the following roles:

[0208] 1. Entering brand and market information: Use a terminal to enter brand and market information.

[0209] 2. Keyword Selection: Select the most suitable keyword from the keyword list sent from the server.

[0210] 3. Review and modify the ad copy: Review the generated ad copy and enter any necessary modification instructions.

[0211] Program processing

[0212] The server receives brand and market information via a REST API using the Python requests library. Search engine APIs and a proprietary database are used to retrieve relevant keywords. Pandas and NumPy, Python data analysis libraries, are used to calculate keyword efficiency.

[0213] For generating ad copy, a generative AI model (e.g., GPT-3) is used, utilizing the transformers library. This model is pre-trained, enabling high-quality text generation.

[0214] Specific example

[0215] For example, if you input brand information as "organic cosmetics" and market information as "women aged 25 to 35," the server will select related keywords such as "natural skincare" and "additive-free cosmetics." If you select "additive-free cosmetics" from these, the AI ​​model will generate an ad copy such as "Start gentle skincare with high-quality additive-free cosmetics!"

[0216] Examples of prompts in this system are as follows:

[0217] Please generate high-quality advertising copy using "additive-free cosmetics." The tone should be friendly and convey a trustworthy image.

[0218] As described above, this system enables the automated generation of high-quality advertising content efficiently and consistently.

[0219] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0220] Step 1:

[0221] Enter brand information and market information.

[0222] The user uses a device to input brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35"). The system then receives specific data related to the brand and market.

[0223] Input: Brand information and market information

[0224] Output: Brand information and market information sent to the server

[0225] Step 2:

[0226] Receive brand information and market information.

[0227] The server receives brand and market information transmitted from the terminal. This information serves as base data for obtaining relevant keywords.

[0228] Input: Brand and market information sent from the terminal.

[0229] Output: Brand information and market information stored on the server

[0230] Step 3:

[0231] Retrieving related keywords

[0232] Based on the brand and market information received by the server, it retrieves relevant keywords from search engine APIs and its own database. For example, it retrieves keywords related to "organic cosmetics" and "women aged 25 to 35."

[0233] Input: Brand information and market information

[0234] Output: List of related keywords (e.g., "natural skincare", "additive-free cosmetics")

[0235] Step 4:

[0236] Calculation of KW efficiency

[0237] The server calculates the keyword efficiency of the relevant keywords it retrieves. It collects data such as search volume, competition level, and relevance, and uses this data to calculate keyword efficiency.

[0238] Input: Related Keyword List

[0239] Output: Keyword list for which KW efficiency was calculated

[0240] Step 5:

[0241] Keyword list generation

[0242] The server lists high-efficiency keywords based on keyword efficiency. The listed keywords are sent to the terminal and displayed to the user.

[0243] Input: Keyword used to calculate KW efficiency

[0244] Output: Optimal keyword list

[0245] Step 6:

[0246] Selecting and submitting the most suitable keywords

[0247] The user clicks or selects the most relevant keyword (e.g., "additive-free cosmetics") and sends it from their device to the server.

[0248] Input: Best keyword

[0249] Output: Optimal keywords sent to the server

[0250] Step 7:

[0251] Generating ad copy

[0252] Based on the optimal keywords received by the server, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized based on pre-configured brand tone and style guides.

[0253] Input: Best keyword

[0254] Output: Generated ad copy

[0255] Step 8:

[0256] Display the generated ad copy and enter instructions for modification.

[0257] The user reviews the generated ad copy using their device and enters correction instructions as needed. These correction instructions are then sent from the device to the server.

[0258] Input: Generated ad copy

[0259] Output: Correction instructions

[0260] Step 9:

[0261] Ad copy revision

[0262] The server modifies the ad copy based on the correction instructions received from the user. The modified ad copy is then optimized again and sent to the device.

[0263] Input: Correction Instructions

[0264] Output: Revised ad copy

[0265] Step 10:

[0266] Display of revised ad text

[0267] The revised ad copy is finally displayed on the device for the user to review. At this point, the user can make a final review and request further revisions if necessary.

[0268] Input: Revised ad copy

[0269] Output: Final approved ad copy

[0270] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0271] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[0272] 1. KW selection

[0273] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[0274] 2. Emotion recognition

[0275] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is showing positive emotions, the emotion engine sends that information to the server. Based on this emotion recognition result, the server dynamically changes the content and ranking of the keyword list it presents.

[0276] 3. Article generation

[0277] When a user selects the most relevant keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server gathers information using relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text). It also adjusts the tone and style of the article to match the user's emotions based on feedback from the sentiment engine. For example, if the user expresses positive emotions, the server will adopt a positive and motivational tone.

[0278] 4. Proofreading

[0279] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[0280] In this way, the entire system's specific operation automates a series of SEO tasks, from keyword selection to proofreading, and also enables content personalization based on user sentiment. This significantly reduces the burden on users and enables the efficient, consistent, and high-quality generation of content.

[0281] The processing flow will be described below.

[0282] Step 1:

[0283] The user inputs information about their company brand (e.g., "health food") and target market information (e.g., "women in their 20s to 30s") into the terminal and sends it to the server.

[0284] Step 2:

[0285] Based on the received brand information and market information, the server retrieves relevant keywords (e.g., "diet food", "vitamin supplements", "beauty supplements") from the database.

[0286] Step 3:

[0287] For the retrieved relevant keywords, the server analyzes competitive information and trend data from search engines, and calculates the KW efficiency based on the search volume, competitiveness, and relevance of each keyword.

[0288] Step 4:

[0289] The server summarizes the keywords with high KW efficiency into a list and presents them to the user.

[0290] Step 5:

[0291] The user checks the keyword list via the terminal and selects the optimal keyword (e.g., "diet food").

[0292] Step 6:

[0293] The emotion engine analyzes the user's facial expressions and tone of voice, recognizes the user's emotional state, and sends the result to the server. For example, if the user shows a positive emotion, that information is transmitted to the server.

[0294] Step 7:

[0295] The server dynamically changes the content and order of the keyword list it presents based on feedback from the emotion engine. For example, it prioritizes presenting keywords with a positive tone to users who express positive emotions.

[0296] Step 8:

[0297] The user selects the most suitable keywords and sends them to the server via their device.

[0298] Step 9:

[0299] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[0300] Step 10:

[0301] Based on feedback from the emotion engine, the server adjusts the tone and style of the generated article to match the user's emotions. For example, if the user is expressing positive emotions, the entire article will be adjusted to a positive and motivational tone.

[0302] Step 11:

[0303] The server sends the optimized article to the user, who receives it on their device.

[0304] Step 12:

[0305] The user reviews the generated article on their device and enters correction instructions as needed (e.g., "Make the title more impactful").

[0306] Step 13:

[0307] The terminal sends the user's correction instructions to the server.

[0308] Step 14:

[0309] The server analyzes the user's modification instructions and automatically modifies the generated article. For example, it changes the title to "This is the current popular diet food! Worth a try".

[0310] Step 15:

[0311] The server optimizes the modified article again and sends it to the user. The user receives it again on the terminal and performs a final check of the article.

[0312] Step 16:

[0313] When the user is satisfied with the content of the article and instructs the terminal to complete the proofreading, the terminal sends that information to the server and the process ends.

[0314] (Example 2)

[0315] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0316] In the SEO service, the process from keyword selection to article generation and proofreading requires a great deal of time and effort, and there is a problem that it is difficult to generate content suitable for the user's feelings and brand tone. Also, it is required to appropriately reflect the user's input and the result of sentiment analysis and efficiently generate high-quality content.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following respective means.

[0318] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the KW efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated KW efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for generating article elements based on the received keyword; means for analyzing the user's sentiment based on feedback from the sentiment engine; means for adjusting the tone and style of the article based on the analysis results of the user's sentiment state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables the efficient automation of a series of SEO tasks from keyword selection to article generation and proofreading, and makes it possible to generate content based on the user's sentiment.

[0319] "Brand information" refers to information about a specific brand provided by the user, including the characteristics, value, and positioning of the product or service.

[0320] "Market information" refers to information about a specific market that a user has, including target audience, competitive landscape, and trends.

[0321] "Related keywords" are words and phrases that are extracted based on brand information and market information and are considered effective for SEO.

[0322] "Keyword efficiency" is an index that comprehensively evaluates factors such as search volume, competition level, and relevance for related keywords.

[0323] A "keyword list" refers to a list of related keywords ranked based on calculated keyword efficiency.

[0324] An "emotion engine" is an analytical device or software that recognizes emotions by analyzing the user's facial expressions, voice tone, and other factors.

[0325] "Article elements" refer to the various components that make up an article, such as the title, headings, body text, and images.

[0326] A "style guide" refers to instructions or guidelines regarding the style and tone of an article or piece of writing.

[0327] "User sentiment" refers to the emotional response a user shows to a particular situation or content, and includes positive, negative, and neutral reactions.

[0328] A "correction instruction" is a specific request for changes made by a user to the content of an article they have generated.

[0329] "Optimization" refers to the process of adjusting generated content to make it higher quality and more effective.

[0330] To implement this invention, it is necessary to build a system in which the user, terminal, server, and emotion engine work together in cooperation with each other. The following describes how to implement this system in detail.

[0331] First, users access the system via a terminal. This terminal is essentially a computer or smartphone, providing an interface for users to input information. This terminal displays forms for entering brand and market information.

[0332] When a user enters specific information such as "health foods" or "women in their 20s and 30s," the device sends that information to the server. Upon receiving this brand and market information, the server retrieves relevant keywords from its database based on that information.

[0333] The server calculates the keyword efficiency of acquired keywords by analyzing search engine trend data and competitive information. This analysis utilizes natural language processing and machine learning techniques. Based on the calculated keyword efficiency, the server lists the most efficient keywords and presents this list to the user.

[0334] Next, the system selects the most suitable keywords from the user's provided keyword list. During this process, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. The emotion engine then collects necessary data using input devices such as cameras and microphones.

[0335] The emotion engine analyzes the emotion data, which is then sent to the server. Based on this data, the server dynamically changes the ranking and content of the keyword list. When the user selects the most suitable keyword (e.g., "diet food"), that keyword is sent back to the server from the device.

[0336] Based on the received keywords, the server utilizes relevant databases and pre-trained models (e.g., generative AI models) to generate article elements (e.g., title, headings, body text). During this process, the tone and style of the article are adjusted based on feedback from the sentiment engine. For example, if a user expresses positive emotions, the server generates an article with a positive and motivational tone.

[0337] The generated article is sent from the server to the user's terminal, where the user reviews the content. If improvements are needed, the user enters correction instructions on their terminal and sends them to the server. The server analyzes these instructions and automatically corrects the article. The corrected article is sent back to the user for final review. Once the user approves it, the process is complete.

[0338] For example, if you input information about "health foods," the server will suggest keywords such as "diet foods" and "beauty supplements," and as a result generate articles such as "Latest Trends in Diet Foods."

[0339] Example of a prompt:

[0340] "Please generate an article about the latest trends in health foods targeting women in their 20s and 30s."

[0341] In this way, the entire system flexibly responds based on user input and sentiment analysis, enabling the automatic generation of high-quality content. This efficiently automates SEO tasks and significantly reduces the burden on users.

[0342] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0343] Step 1:

[0344] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[0345] Input: Brand information and market information

[0346] Output: Data to send to the server

[0347] Step 2:

[0348] The server retrieves relevant keywords from the database based on the received brand and market information. For example, from the brand information "health foods" and the market information "women in their 20s and 30s," keywords such as "diet foods," "vitamin supplements," and "beauty supplements" are retrieved.

[0349] Input: Received brand information and market information

[0350] Output: List of related keywords

[0351] Step 3:

[0352] The server analyzes the retrieved relevant keywords, along with competitive information and trend data from search engines, to calculate keyword efficiency. This calculation uses data such as search volume, competition level, and relevance.

[0353] Input: Related keyword list, competitor information, search engine trend data

[0354] Output: Keyword list for calculating kW efficiency

[0355] Step 4:

[0356] The server generates a keyword list based on calculated keyword efficiency and presents it to the user. The most efficient keywords are displayed at the top.

[0357] Input: Keyword list used to calculate KW efficiency

[0358] Output: List of keywords presented to the user

[0359] Step 5:

[0360] The user selects the most suitable keyword from the presented keyword list and sends it to the server via their device. For example, if the user selects the keyword "diet food," that selection data will be sent.

[0361] Input: List of keywords presented to the user

[0362] Output: Selection data for optimal keywords

[0363] Step 6:

[0364] The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state. The emotion engine uses the camera and microphone to generate emotional data such as positive, negative, and neutral, and sends this data to the server.

[0365] Input: User's facial expressions and voice tone acquired from camera and microphone.

[0366] Output: User sentiment data

[0367] Step 7:

[0368] The server dynamically changes the ranking and content of the keyword list it presents based on sentiment data. For example, if a user selects "diet foods" and expresses a positive sentiment, positive keywords will be displayed preferentially.

[0369] Input: User sentiment data

[0370] Output: Dynamically changed keyword list

[0371] Step 8:

[0372] The user sends the keyword they ultimately selected to the server. Here, the keyword "diet food" is confirmed.

[0373] Input: Dynamically changed keyword list

[0374] Output: The keywords that were ultimately selected

[0375] Step 9:

[0376] Based on the received keywords, the server utilizes relevant databases and a pre-trained generative AI model to generate article elements (e.g., title, headings, body text). For example, an article titled "Latest Trends in Diet Foods" might be generated.

[0377] Input: Final selected keywords

[0378] Output: Generated article elements

[0379] Step 10:

[0380] Based on feedback from the emotion engine, the server adjusts the tone and style of the article to match the user's emotions. For positive emotions, a motivational tone is generated.

[0381] Input: Generated article elements, user sentiment data

[0382] Output: Articles adjusted to match emotions

[0383] Step 11:

[0384] The generated article is sent from the server to the user's terminal, where the user reviews the content.

[0385] Input: Articles adjusted to match emotions

[0386] Output: Articles displayed on the user's device

[0387] Step 12:

[0388] If a user finds the content problematic, they input correction instructions into their terminal and send them to the server. For example, a correction instruction might be, "Change the title to something more impactful."

[0389] Input: User's correction instructions

[0390] Output: Correction instruction data to the server

[0391] Step 13:

[0392] The server analyzes the correction instructions and automatically modifies the article. For example, it might change the title to "Diet Revolution! This is the food that's all the rage right now!"

[0393] Input: Correction instruction data

[0394] Output: Corrected article

[0395] Step 14:

[0396] The revised article is sent back to the user for final review. If approved, the process ends.

[0397] Input: Modified article

[0398] Output: Last article displayed to the user

[0399] (Application Example 2)

[0400] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0401] Current content generation systems often produce content uniformly without considering the user's emotional state, making personalization to match the tone and style the user desires difficult. While some degree of keyword selection efficiency and automated article generation has been achieved, dynamic selection and adjustment of ad copy based on user emotions remains lacking. Therefore, there is a need for a system that dynamically adjusts the tone and style of content based on user input and emotional state, automatically generating and revising optimal keywords and high-quality articles.

[0402] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0403] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the keyword efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated keyword efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for recognizing the user's emotional state; means for dynamically changing the content and ranking of the displayed keyword list based on the recognized emotional state; means for generating article elements based on the received keywords; means for adjusting the tone and style of the article based on the user's emotional state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables dynamic keyword selection and personalized content generation based on the user's input information and emotional state.

[0404] "Brand information" refers to basic information about a company or product, and is an element that expresses its characteristics and value.

[0405] "Market information" refers to data about a specific target group or market environment, and is information used to understand customer interests and demand trends.

[0406] "Related keywords" are keywords selected based on brand information and market information, taking into account search frequency and level of competition on search engines.

[0407] "Keyword efficiency" is an indicator that evaluates the effectiveness of keywords by calculating their search volume, competition level, and relevance.

[0408] A "keyword list" is a list of relevant keywords that should be used, generated based on keyword efficiency.

[0409] "Emotional state" refers to the psychological state perceived from the user's facial expressions, tone of voice, and other factors.

[0410] "Article elements" are the elements that make up each part of the generated content (title, headings, body text, etc.).

[0411] A "style guide" is a set of guidelines for maintaining a consistent tone and style in an article.

[0412] A "correction instruction" is a user's instruction to change or improve an article they have generated.

[0413] "Personalization" refers to adjusting the content and presentation of content according to the individual needs and preferences of the user.

[0414] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[0415] First, the user enters brand and market information into their device and sends it to the server. The server retrieves relevant keywords based on the received information and calculates keyword efficiency. This is done using SEO analysis tools such as the Ahrefs API. Based on the calculated keyword efficiency, the server generates a keyword list and displays it on the device.

[0416] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state. This emotion engine utilizes Google Cloud's Emotion API. Based on the recognized emotional state, the server dynamically changes the content and ranking of the displayed keyword list. For example, if a user is showing positive emotions, positive and motivational keywords will be displayed higher.

[0417] Based on selected keywords, the server generates article elements. This uses generative AI models such as GPT-3 and ChatGPT®. Furthermore, the tone and style of the article are adjusted based on the user's sentiment information. For example, if the user expresses positive sentiment, the article will be generated in a motivational tone. The generated article elements are optimized according to the company's style guide and displayed on the device.

[0418] The user reviews the generated article and enters correction instructions if necessary. The server re-edits the article based on these instructions and displays it to the user again. Natural language processing technology is used for the re-editing to accurately reflect the user's intentions for correction. The writing style of the revised article is automatically adjusted to match the brand tone.

[0419] The following are specific examples and examples of prompts for the generative AI model:

[0420] Specific example:

[0421] For example, suppose a marketing manager for a sports brand uses this system. The user inputs information such as "sportswear" and "male in his teens and twenties," and the server provides related keywords such as "running shoes" and "training gear." If the emotion engine recognizes the user's excitement, it generates a positive and motivational article, creating text with a tone like, "Get your best performance out of these running shoes!"

[0422] Examples of prompts for a generative AI model:

[0423] Keywords: Diet foods

[0424] User sentiment: Positive

[0425] Output style: Motivational

[0426] Prompt: Write a positive and motivational article about diet foods.

[0427] Title: This is the trending diet food right now! It's worth trying.

[0428] Introduction: If you want to succeed in your diet, you should definitely try incorporating this food into your diet. The secret to healthy weight loss lies here.

[0429] In this way, it becomes possible to personalize dynamic keyword selection and content generation based on user input information and emotional state.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The user enters brand and market information into their device and sends it to the server.

[0433] Input: Brand information (e.g., sportswear), market information (e.g., men in their teens and twenties)

[0434] Output: Input information is sent to the server.

[0435] Specific operation: The user enters brand information and market information into the input form on the device and presses the "Submit" button. The device sends the input data to the server as an HTTP request.

[0436] Step 2:

[0437] The server retrieves relevant keywords based on the brand and market information it receives.

[0438] Input: Received brand information and market information

[0439] Output: List of related keywords (e.g., running shoes, training gear)

[0440] Specific operation: The server uses external SEO tools such as the Ahrefs API to search the database for keywords related to brand information and market information, and retrieves the relevant keywords.

[0441] Step 3:

[0442] The server calculates the keyword efficiency of the relevant keywords it has acquired and generates a keyword list based on that.

[0443] Input: List of related keywords

[0444] Output: Keyword list ranked based on KW efficiency

[0445] Specific operation: The server calculates the search volume, competition level, and relevance of each keyword, and then calculates keyword efficiency by combining these metrics. After that, keywords are ranked and listed based on keyword efficiency.

[0446] Step 4:

[0447] The server generates a list of keywords, which is then displayed on the terminal.

[0448] Input: Ranked keyword list

[0449] Output: Keyword list displayed on the terminal screen

[0450] Specific operation: The server sends the completed keyword list to the terminal, which receives this information and displays it on the screen.

[0451] Step 5:

[0452] When a user selects a keyword, the emotion engine recognizes the user's emotional state.

[0453] Input: User's facial expressions and tone of voice

[0454] Output: User's emotional state (e.g., positive)

[0455] Specific operation: The device uses its built-in camera and microphone to capture the user's facial expressions and voice, and then uses Google Cloud's Emotion API to analyze their emotional state.

[0456] Step 6:

[0457] The server dynamically changes the content and ranking of the displayed keyword list based on the recognized emotional state.

[0458] Input: User's emotional state, original keyword list

[0459] Output: Dynamically changed keyword list

[0460] Specific operation: The server receives the user's emotional state and reconstructs the keyword list based on it. For example, if the emotional state is positive, motivational keywords will be placed at the top.

[0461] Step 7:

[0462] The user selects keywords and sends them to the server.

[0463] Input: User-selected keyword

[0464] Output: The selected keywords are sent to the server.

[0465] Specific operation: The user selects their desired keyword from the displayed keyword list and presses the "Select" button. This data is sent to the server.

[0466] Step 8:

[0467] The server generates article elements based on the keywords it receives.

[0468] Input: Selected keywords

[0469] Output: Generated article elements (e.g., title, headings, body text)

[0470] Specific operation: The server uses generative AI models such as GPT-3 and ChatGPT to automatically generate article components based on selected keywords.

[0471] Step 9:

[0472] The server adjusts the tone and style of the article based on the user's emotions.

[0473] Input: Generated article elements, user's sentiment state

[0474] Output: Adjusted article

[0475] Specific operation: The generated article elements are adjusted to reflect the user's emotional state (e.g., positive), and their tone and style are modified accordingly. For example, if the emotional state is positive, the overall tone of the article is made more motivational.

[0476] Step 10:

[0477] The server displays optimized articles on the device.

[0478] Input: Adjusted article

[0479] Output: Article displayed on the terminal screen

[0480] Specific operation: The server sends an optimized article to the terminal, which receives it and displays it to the user.

[0481] Step 11:

[0482] The user enters correction instructions for an article and sends that data to the server.

[0483] Input: Correction instructions (e.g., title change, content addition)

[0484] Output: Correction instructions are sent to the server.

[0485] Specific operation: The user reviews the displayed article, enters the necessary corrections into the terminal's editor, and presses the "Submit" button. The correction instructions are sent to the server as an HTTP request.

[0486] Step 12:

[0487] The server corrects the article based on the correction instructions.

[0488] Input: Correction instructions, article generated just a moment ago

[0489] Output: Corrected article

[0490] Specific operation: The server uses natural language processing technology to analyze user correction instructions and rewrite the article. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[0491] Step 13:

[0492] The server will redisplay the corrected article on your device.

[0493] Input: Modified article

[0494] Output: Correction article displayed on the terminal screen

[0495] Specific operation: The server sends the corrected article to the terminal, which receives it and displays it to the user again.

[0496] 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.

[0497] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0498] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0499] [Second Embodiment]

[0500] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0501] 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.

[0502] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0503] 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.

[0504] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0505] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0506] 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.

[0507] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0508] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0509] The 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.

[0510] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0511] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0512] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[0513] 1. KW selection

[0514] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[0515] 2. Article generation

[0516] When a user selects the most suitable keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server uses relevant databases and pre-trained models to collect information related to the keyword. The server then generates article elements (e.g., title: "Easily Start Shaping Up with the Latest Diet Foods," body text: "A Must-See for Those Who Want to Lose Weight Healthily! Introducing the Latest Diet Foods. These products are rich in vitamins and also effective for beauty.") based on the collected information. The server also optimizes the generated article based on the brand tone (e.g., "casual and approachable") and style guide.

[0517] 3. Proofreading

[0518] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[0519] In this way, the entire system's specific operations automate a series of SEO tasks, from keyword selection to proofreading, significantly reducing the user's burden and enabling the efficient, consistent, and high-quality generation of content.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[0523] Step 2:

[0524] Based on the received brand and market information, the server retrieves relevant keywords (e.g., "dietary foods," "vitamin supplements," "beauty supplements") from the database.

[0525] Step 3:

[0526] The server analyzes competitive information and trend data from search engines for the retrieved related keywords, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[0527] Step 4:

[0528] The server compiles a list of highly efficient keywords and presents it to the user.

[0529] Step 5:

[0530] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device.

[0531] Step 6:

[0532] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[0533] Step 7:

[0534] The server optimizes the generated articles according to the brand's tone and style guide. For example, it adjusts the text to have a "casual and approachable" tone.

[0535] Step 8:

[0536] The server sends the optimized article to the user, who receives it on their device.

[0537] Step 9:

[0538] The user reviews the generated article on their device and, if necessary, enters correction instructions (e.g., "Make the title more impactful") and sends them to the server.

[0539] Step 10:

[0540] The server analyzes user correction requests and automatically modifies the generated articles. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[0541] Step 11:

[0542] The server optimizes the revised article again and sends it to the user. The user receives it again on their device and performs a final check of the article.

[0543] Step 12:

[0544] Once the user is satisfied with the article's content and signals the terminal to complete the review, the terminal sends that information to the server, and the process ends.

[0545] (Example 1)

[0546] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0547] Traditional SEO work is often done manually, making it time-consuming and labor-intensive, and thus inefficient. Furthermore, it is prone to inconsistencies in content quality and consistency, making it difficult to consistently generate high-quality content that is appropriate for the brand. Additionally, proofreading and revising the generated content is time-consuming and requires quick responses. This invention aims to automate these problems and improve efficiency and consistency.

[0548] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0549] In this invention, the server includes means for receiving brand information and market information, means for obtaining relevant keywords, means for calculating keyword efficiency, means for generating a keyword list, means for optimizing the generated article elements according to a style guide, means for revising the article based on revision instructions, and means for receiving revision completion instructions. This enables the automation and efficiency of SEO work, allowing for the rapid generation and revision of high-quality, consistent, and brand-appropriate content.

[0550] "Brand information" refers to identifiable information associated with a specific company, product, or service.

[0551] "Market information" refers to data and insights about a specific market or target audience.

[0552] A "keyword" refers to an important word or phrase related to a specific theme or topic.

[0553] "Keyword efficiency" is an efficiency metric calculated based on factors such as keyword search volume, competition level, and relevance.

[0554] "Article elements" refer to the constituent elements of content, such as the title and body text.

[0555] A "style guide" refers to guidelines regarding the writing style and tone of documents based on a specific brand or style.

[0556] "Tone" refers to the use of language to express the emotions and atmosphere of a text or content.

[0557] "Correction instructions" refer to instructions regarding changes or improvements to user-generated content.

[0558] A "correction completion instruction" refers to an instruction for the user to confirm that the corrected content is appropriate and to ultimately approve it.

[0559] A "generative AI model" refers to an artificial intelligence algorithm used for tasks such as text generation and data analysis.

[0560] To implement this invention, a system is required in which users, terminals, and servers work together. This system automates the streamlining of SEO work and the generation of high-quality content based on brand information and market information.

[0561] The overall system hardware configuration will consist of the user's PC or smartphone (device) and an AWS EC2 instance (server). The software will utilize MySQL as the database, OpenAI GPT as the generative AI model, and Django as the server-side framework.

[0562] Explanation in natural language

[0563] KW selection

[0564] 1. User input

[0565] Users input information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and send it to the server. Input is done through a dedicated form, and processing begins on the server after submission.

[0566] 2. Server processing - Retrieval of related keywords

[0567] The server retrieves relevant keywords from the MySQL database using queries based on the received brand and market information. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[0568] 3. Server Processing - Calculation and Listing of KW Efficiency

[0569] The server analyzes competitive information and search engine trend data for these keywords and calculates keyword efficiency based on each keyword's search volume, competitiveness, and relevance. For example, it uses the Google Trends API to retrieve data and assigns a weighted score to each keyword to calculate keyword efficiency. Keywords with high scores are then presented to the user as a list.

[0570] Article generation

[0571] 1. User Selection

[0572] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device. The user selects a keyword from the list and clicks the "Confirm" button to submit it.

[0573] 2. Server Processing - Information Gathering and Article Generation

[0574] The server uses a generative AI model such as OpenAI GPT-3 to collect relevant information based on selected keywords and then generates article elements based on that information. For example, it sends a prompt sentence like "Please tell me the latest information on diet foods" to the generative AI model and uses the obtained information to create a title and body text.

[0575] 3. Server Processing - Optimization Based on Tone and Style Guides

[0576] The server modifies the generated content to match the brand's tone and style guide (e.g., "casual and approachable"). It changes the style and expression of the generated text to ensure consistency and completes an optimized article for the user.

[0577] Proofreading

[0578] 1. User Verification

[0579] The generated article is sent from the server to the user, who then reviews the content on their device. If there are any problems with the content, the user uses the editing form on their device to enter correction instructions (e.g., "Please change the title to something more attention-grabbing") and sends them to the server.

[0580] 2. Server processing - Article revision

[0581] The server analyzes user correction instructions and automatically corrects the article using a generative AI model. For example, if there is a instruction regarding the title, it will regenerate the article using a prompt such as "Make the title more attention-grabbing."

[0582] 3. User's final confirmation and completion instructions

[0583] The user reviews the revised article again, and if they are finally satisfied, they indicate on their device that the review is complete. By pressing the "Complete" button, the user sends that information to the server, and the process officially ends.

[0584] Specific examples and prompt statements

[0585] Specific example

[0586] KW selection

[0587] Information entered by the user: Brand information "Health Foods", Target market information "Women in their 20s and 30s"

[0588] The server provides a list of keywords: diet foods, vitamin supplements, beauty supplements.

[0589] Article generation

[0590] Keywords selected by users: Diet foods

[0591] Articles generated by the server:

[0592] Title: "Easily Start Shaping Up with the Latest Diet Foods"

[0593] Text: "A must-see for those who want to lose weight healthily! Introducing the latest diet foods. These products are rich in vitamins and also effective for beauty."

[0594] Example of a prompt

[0595] "Please select highly efficient keywords based on health food brands and target market information for women in their 20s and 30s."

[0596] "Please write an article about diet foods. The title should be approachable and casual."

[0597] Thus, the system of the present invention automates a series of SEO tasks, from keyword selection to article generation and proofreading, significantly reducing the burden on the user and enabling efficient, consistent, and high-quality content generation.

[0598] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0599] Processing steps

[0600] KW selection

[0601] Step 1:

[0602] Users enter brand information and market information.

[0603] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and clicks the submit button. This information is then sent to the server.

[0604] Input: Brand information, market information

[0605] Output: Brand information and market information sent to the server

[0606] Step 2:

[0607] The server retrieves related keywords.

[0608] Based on the received brand and market information, the server retrieves relevant keywords from the MySQL database using queries. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[0609] Input: Brand information, market information

[0610] Data processing / calculation: Retrieve relevant keywords from a MySQL database using queries.

[0611] Output: List of related keywords

[0612] Step 3:

[0613] The server calculates keyword efficiency and generates a keyword list.

[0614] The server analyzes the retrieved related keywords using the Google Trends API and other tools to determine the search volume, competition level, relevance, etc., and calculates keyword efficiency. Based on the calculation results, it selects high-scoring keywords and generates a keyword list.

[0615] Input: List of related keywords

[0616] Data processing / calculation: Analyze each keyword using the Google Trends API, etc., and calculate keyword efficiency.

[0617] Output: List of keywords with high KW efficiency

[0618] Article generation

[0619] Step 4:

[0620] The user selects and submits the most suitable keywords.

[0621] The user selects the most suitable keyword (e.g., "diet food") from the presented keyword list and sends it to the server via their device. The user selects a keyword and clicks the "Confirm" button.

[0622] Input: List of highly efficient keywords (KW)

[0623] Output: Optimal keywords sent to the server

[0624] Step 5:

[0625] The server collects information and generates article elements.

[0626] The server uses a generative AI model such as OpenAI GPT-3 to create a prompt based on the most suitable keywords it receives, and then collects relevant information based on that prompt. Specifically, it sends a prompt such as "Please tell me the latest information on diet foods" to the model, and then creates an article title and body based on the generated information.

[0627] Input: Best keyword

[0628] Data Processing / Calculation: Use a generative AI model to create prompt statements, collect information, and generate article elements.

[0629] Output: Generated article elements (title, body)

[0630] Step 6:

[0631] The server optimizes article elements.

[0632] The server adjusts the generated article elements based on the brand's tone and style guide, optimizing them to ensure consistency in writing style and content. For example, it might adjust the writing style to a "casual and approachable" tone.

[0633] Input: Generated article elements (title, body)

[0634] Data processing / calculation: Optimize article elements based on the brand's tone and style guide.

[0635] Output: Optimized article

[0636] Proofreading

[0637] Step 7:

[0638] Users review articles and submit correction requests.

[0639] The server sends an optimized article to the user. The user reviews the article on their device and, if necessary, enters correction instructions (e.g., "Make the title more eye-catching") and sends them to the server.

[0640] Input: Optimized article

[0641] Output: Correction instructions sent to the server

[0642] Step 8:

[0643] The server will modify the article.

[0644] The server analyzes the user's correction instructions and uses a generative AI model to revise the article. For example, in response to the instruction "Make the title more attention-grabbing," it regenerates the prompt as "Generate a more attention-grabbing title."

[0645] Input: Correction Instructions

[0646] Data processing / calculation: Regenerate and correct articles using a generative AI model.

[0647] Output: Corrected article

[0648] Step 9:

[0649] The user submits a correction completion instruction.

[0650] The user reviews the revised article again, and if they are finally satisfied, they send a correction completion notification from their device. By pressing the "Complete" button, the user sends that information to the server.

[0651] Input: Modified article

[0652] Output: Correction completion instruction sent to the server

[0653] (Application Example 1)

[0654] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0655] Traditional SEO and ad copy generation processes required significant time and effort for keyword selection, content creation, and ad copy creation based on brand and market information. Furthermore, verifying and adjusting whether the generated content aligned with brand tone and market trends was cumbersome, making it difficult to provide efficient, consistent, and high-quality content.

[0656] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0657] In this invention, the server includes means for receiving brand information and market information, means for acquiring relevant keywords, and means for calculating the keyword efficiency of the acquired keywords. This automates a series of processes, from keyword selection to article and ad copy generation, and style optimization and revision, enabling the efficient, consistent, and high-quality delivery of content and ad copy.

[0658] "Brand information" refers to information about the awareness and image of a particular company or product.

[0659] "Market information" refers to data and statistics related to a specific target market.

[0660] "Related keywords" are terms used by search engines to select keywords based on brand and market information.

[0661] "Keyword efficiency" is an efficiency metric calculated based on factors such as search volume, competition level, and relevance of related keywords.

[0662] A "keyword list" is a list of related keywords generated based on keyword efficiency.

[0663] "Article elements" refer to the constituent elements of an article, such as the title and body text, which are generated based on keywords.

[0664] A "style guide" is a set of guidelines designed to reflect a brand's tone and style.

[0665] "Correction instructions" are instructions from users to change or revise articles or ad copy.

[0666] "Ad copy" refers to marketing and promotional text generated using selected keywords.

[0667] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to achieve the automated generation of efficient, consistent, and high-quality advertising content.

[0668] System Configuration

[0669] Servers, terminals, and users are the main components of the system.

[0670] server

[0671] The server performs the following roles:

[0672] 1. Receiving brand and market information: The system has a means of receiving brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35") entered by the user.

[0673] 2. Acquisition of related keywords: Based on the received brand information and market information, related keywords (e.g., "natural skincare", "additive-free cosmetics") are retrieved from the database.

[0674] 3. Calculation of Keyword Efficiency: Analyze the acquired related keywords, competitive information, and trend data from search engines to calculate keyword efficiency.

[0675] 4. Keyword List Generation: Based on the calculated keyword efficiency, list the most efficient keywords.

[0676] 5. Ad copy generation: Based on the most suitable keywords, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized to match the brand tone.

[0677] terminal

[0678] The terminal will perform the following roles:

[0679] 1. Input of brand and market information: Provide an interface for users to input brand and market information.

[0680] 2. Displaying the Keyword List: The keyword list received from the server is displayed to the user.

[0681] 3. Selection of optimal keywords: The user selects the most suitable keywords from the keyword list and sends them to the server.

[0682] 4. Viewing and modifying the generated ad copy: The user reviews the generated ad copy, enters any necessary modification instructions, and sends them to the server.

[0683] User

[0684] The user will play the following roles:

[0685] 1. Entering brand and market information: Use a terminal to enter brand and market information.

[0686] 2. Keyword Selection: Select the most suitable keyword from the keyword list sent from the server.

[0687] 3. Review and modify the ad copy: Review the generated ad copy and enter any necessary modification instructions.

[0688] Program processing

[0689] The server receives brand and market information via a REST API using the Python requests library. Search engine APIs and a proprietary database are used to retrieve relevant keywords. Pandas and NumPy, Python data analysis libraries, are used to calculate keyword efficiency.

[0690] For generating ad copy, a generative AI model (e.g., GPT-3) is used, utilizing the transformers library. This model is pre-trained, enabling high-quality text generation.

[0691] Specific example

[0692] For example, if you input brand information as "organic cosmetics" and market information as "women aged 25 to 35," the server will select related keywords such as "natural skincare" and "additive-free cosmetics." If you select "additive-free cosmetics" from these, the AI ​​model will generate an ad copy such as "Start gentle skincare with high-quality additive-free cosmetics!"

[0693] Examples of prompts in this system are as follows:

[0694] Please generate high-quality advertising copy using "additive-free cosmetics." The tone should be friendly and convey a trustworthy image.

[0695] As described above, this system enables the automated generation of high-quality advertising content efficiently and consistently.

[0696] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0697] Step 1:

[0698] Enter brand information and market information.

[0699] The user uses a device to input brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35"). The system then receives specific data related to the brand and market.

[0700] Input: Brand information and market information

[0701] Output: Brand information and market information sent to the server

[0702] Step 2:

[0703] Receive brand information and market information.

[0704] The server receives brand and market information transmitted from the terminal. This information serves as base data for obtaining relevant keywords.

[0705] Input: Brand and market information sent from the terminal.

[0706] Output: Brand information and market information stored on the server

[0707] Step 3:

[0708] Retrieving related keywords

[0709] Based on the brand and market information received by the server, it retrieves relevant keywords from search engine APIs and its own database. For example, it retrieves keywords related to "organic cosmetics" and "women aged 25 to 35."

[0710] Input: Brand information and market information

[0711] Output: List of related keywords (e.g., "natural skincare", "additive-free cosmetics")

[0712] Step 4:

[0713] Calculation of KW efficiency

[0714] The server calculates the keyword efficiency of the relevant keywords it retrieves. It collects data such as search volume, competition level, and relevance, and uses this data to calculate keyword efficiency.

[0715] Input: Related Keyword List

[0716] Output: Keyword list for which KW efficiency was calculated

[0717] Step 5:

[0718] Keyword list generation

[0719] The server lists high-efficiency keywords based on keyword efficiency. The listed keywords are sent to the terminal and displayed to the user.

[0720] Input: Keyword used to calculate KW efficiency

[0721] Output: Optimal keyword list

[0722] Step 6:

[0723] Selecting and submitting the most suitable keywords

[0724] The user clicks or selects the most relevant keyword (e.g., "additive-free cosmetics") and sends it from their device to the server.

[0725] Input: Best keyword

[0726] Output: Optimal keywords sent to the server

[0727] Step 7:

[0728] Generating ad copy

[0729] Based on the optimal keywords received by the server, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized based on pre-configured brand tone and style guides.

[0730] Input: Best keyword

[0731] Output: Generated ad copy

[0732] Step 8:

[0733] Display the generated ad copy and enter instructions for modification.

[0734] The user reviews the generated ad copy using their device and enters correction instructions as needed. These correction instructions are then sent from the device to the server.

[0735] Input: Generated ad copy

[0736] Output: Correction instructions

[0737] Step 9:

[0738] Ad copy revision

[0739] The server modifies the ad copy based on the correction instructions received from the user. The modified ad copy is then optimized again and sent to the device.

[0740] Input: Correction Instructions

[0741] Output: Revised ad copy

[0742] Step 10:

[0743] Display of revised ad text

[0744] The revised ad copy is finally displayed on the device for the user to review. At this point, the user can make a final review and request further revisions if necessary.

[0745] Input: Revised ad copy

[0746] Output: Final approved ad copy

[0747] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0748] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[0749] 1. KW selection

[0750] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[0751] 2. Emotion recognition

[0752] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is showing positive emotions, the emotion engine sends that information to the server. Based on this emotion recognition result, the server dynamically changes the content and ranking of the keyword list it presents.

[0753] 3. Article generation

[0754] When a user selects the most relevant keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server gathers information using relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text). It also adjusts the tone and style of the article to match the user's emotions based on feedback from the sentiment engine. For example, if the user expresses positive emotions, the server will adopt a positive and motivational tone.

[0755] 4. Proofreading

[0756] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[0757] In this way, the entire system's specific operation automates a series of SEO tasks, from keyword selection to proofreading, and also enables content personalization based on user sentiment. This significantly reduces the burden on users and enables the efficient, consistent, and high-quality generation of content.

[0758] The following describes the processing flow.

[0759] Step 1:

[0760] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[0761] Step 2:

[0762] Based on the received brand and market information, the server retrieves relevant keywords (e.g., "dietary foods," "vitamin supplements," "beauty supplements") from the database.

[0763] Step 3:

[0764] The server analyzes competitive information and trend data from search engines for the retrieved related keywords, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[0765] Step 4:

[0766] The server compiles a list of highly efficient keywords and presents it to the user.

[0767] Step 5:

[0768] The user checks a list of keywords via their device and selects the most suitable keyword (e.g., "diet foods").

[0769] Step 6:

[0770] The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state and sends the results to the server. For example, if the user is showing positive emotions, that information is transmitted to the server.

[0771] Step 7:

[0772] The server dynamically changes the content and order of the keyword list it presents based on feedback from the emotion engine. For example, it prioritizes presenting keywords with a positive tone to users who express positive emotions.

[0773] Step 8:

[0774] The user selects the most suitable keywords and sends them to the server via their device.

[0775] Step 9:

[0776] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[0777] Step 10:

[0778] Based on feedback from the emotion engine, the server adjusts the tone and style of the generated article to match the user's emotions. For example, if the user is expressing positive emotions, the entire article will be adjusted to a positive and motivational tone.

[0779] Step 11:

[0780] The server sends the optimized article to the user, who receives it on their device.

[0781] Step 12:

[0782] The user reviews the generated article on their device and enters correction instructions as needed (e.g., "Make the title more impactful").

[0783] Step 13:

[0784] The terminal sends the user's correction instructions to the server.

[0785] Step 14:

[0786] The server analyzes user correction requests and automatically modifies the generated articles. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[0787] Step 15:

[0788] The server optimizes the revised article again and sends it to the user. The user receives it again on their device and performs a final review of the article.

[0789] Step 16:

[0790] Once the user is satisfied with the article's content and signals the terminal to complete the review, the terminal sends that information to the server, and the process ends.

[0791] (Example 2)

[0792] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0793] In SEO work, the process from keyword selection to article generation and proofreading is extremely time-consuming and labor-intensive, and there are challenges in generating content that is appropriate for user sentiment and brand tone. Furthermore, there is a need to efficiently generate high-quality content by appropriately reflecting user input and sentiment analysis results.

[0794] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0795] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the KW efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated KW efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for generating article elements based on the received keyword; means for analyzing the user's sentiment based on feedback from the sentiment engine; means for adjusting the tone and style of the article based on the analysis results of the user's sentiment state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables the efficient automation of a series of SEO tasks from keyword selection to article generation and proofreading, and makes it possible to generate content based on the user's sentiment.

[0796] "Brand information" refers to information about a specific brand provided by the user, including the characteristics, value, and positioning of the product or service.

[0797] "Market information" refers to information about a specific market that a user has, including target audience, competitive landscape, and trends.

[0798] "Related keywords" are words and phrases that are extracted based on brand information and market information and are considered effective for SEO.

[0799] "Keyword efficiency" is an index that comprehensively evaluates factors such as search volume, competition level, and relevance for related keywords.

[0800] A "keyword list" refers to a list of related keywords ranked based on calculated keyword efficiency.

[0801] An "emotion engine" is an analytical device or software that recognizes emotions by analyzing the user's facial expressions, voice tone, and other factors.

[0802] "Article elements" refer to the various components that make up an article, such as the title, headings, body text, and images.

[0803] A "style guide" refers to instructions or guidelines regarding the style and tone of an article or piece of writing.

[0804] "User sentiment" refers to the emotional response a user shows to a particular situation or content, and includes positive, negative, and neutral reactions.

[0805] A "correction instruction" is a specific request for changes made by a user to the content of an article they have generated.

[0806] "Optimization" refers to the process of adjusting generated content to make it higher quality and more effective.

[0807] To implement this invention, it is necessary to build a system in which the user, terminal, server, and emotion engine work together in cooperation with each other. The following describes how to implement this system in detail.

[0808] First, users access the system via a terminal. This terminal is essentially a computer or smartphone, providing an interface for users to input information. This terminal displays forms for entering brand and market information.

[0809] When a user enters specific information such as "health foods" or "women in their 20s and 30s," the device sends that information to the server. Upon receiving this brand and market information, the server retrieves relevant keywords from its database based on that information.

[0810] The server calculates the keyword efficiency of acquired keywords by analyzing search engine trend data and competitive information. This analysis utilizes natural language processing and machine learning techniques. Based on the calculated keyword efficiency, the server lists the most efficient keywords and presents this list to the user.

[0811] Next, the system selects the most suitable keywords from the user's provided keyword list. During this process, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. The emotion engine then collects necessary data using input devices such as cameras and microphones.

[0812] The emotion engine analyzes the emotion data, which is then sent to the server. Based on this data, the server dynamically changes the ranking and content of the keyword list. When the user selects the most suitable keyword (e.g., "diet food"), that keyword is sent back to the server from the device.

[0813] Based on the received keywords, the server utilizes relevant databases and pre-trained models (e.g., generative AI models) to generate article elements (e.g., title, headings, body text). During this process, the tone and style of the article are adjusted based on feedback from the sentiment engine. For example, if a user expresses positive emotions, the server generates an article with a positive and motivational tone.

[0814] The generated article is sent from the server to the user's terminal, where the user reviews the content. If improvements are needed, the user enters correction instructions on their terminal and sends them to the server. The server analyzes these instructions and automatically corrects the article. The corrected article is sent back to the user for final review. Once the user approves it, the process is complete.

[0815] For example, if you input information about "health foods," the server will suggest keywords such as "diet foods" and "beauty supplements," and as a result generate articles such as "Latest Trends in Diet Foods."

[0816] Example of a prompt:

[0817] "Please generate an article about the latest trends in health foods targeting women in their 20s and 30s."

[0818] In this way, the entire system flexibly responds based on user input and sentiment analysis, enabling the automatic generation of high-quality content. This efficiently automates SEO tasks and significantly reduces the burden on users.

[0819] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0820] Step 1:

[0821] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[0822] Input: Brand information and market information

[0823] Output: Data to send to the server

[0824] Step 2:

[0825] The server retrieves relevant keywords from the database based on the received brand and market information. For example, from the brand information "health foods" and the market information "women in their 20s and 30s," keywords such as "diet foods," "vitamin supplements," and "beauty supplements" are retrieved.

[0826] Input: Received brand information and market information

[0827] Output: List of related keywords

[0828] Step 3:

[0829] The server analyzes the retrieved relevant keywords, along with competitive information and trend data from search engines, to calculate keyword efficiency. This calculation uses data such as search volume, competition level, and relevance.

[0830] Input: Related keyword list, competitor information, search engine trend data

[0831] Output: Keyword list for calculating kW efficiency

[0832] Step 4:

[0833] The server generates a keyword list based on calculated keyword efficiency and presents it to the user. The most efficient keywords are displayed at the top.

[0834] Input: Keyword list used to calculate KW efficiency

[0835] Output: List of keywords presented to the user

[0836] Step 5:

[0837] The user selects the most suitable keyword from the presented keyword list and sends it to the server via their device. For example, if the user selects the keyword "diet food," that selection data will be sent.

[0838] Input: List of keywords presented to the user

[0839] Output: Selection data for optimal keywords

[0840] Step 6:

[0841] The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state. The emotion engine uses the camera and microphone to generate emotional data such as positive, negative, and neutral, and sends this data to the server.

[0842] Input: User's facial expressions and voice tone acquired from camera and microphone.

[0843] Output: User sentiment data

[0844] Step 7:

[0845] The server dynamically changes the ranking and content of the keyword list it presents based on sentiment data. For example, if a user selects "diet foods" and expresses a positive sentiment, positive keywords will be displayed preferentially.

[0846] Input: User sentiment data

[0847] Output: Dynamically changed keyword list

[0848] Step 8:

[0849] The user sends the keyword they ultimately selected to the server. Here, the keyword "diet food" is confirmed.

[0850] Input: Dynamically changed keyword list

[0851] Output: The keywords that were ultimately selected

[0852] Step 9:

[0853] Based on the received keywords, the server utilizes relevant databases and a pre-trained generative AI model to generate article elements (e.g., title, headings, body text). For example, an article titled "Latest Trends in Diet Foods" might be generated.

[0854] Input: Final selected keywords

[0855] Output: Generated article elements

[0856] Step 10:

[0857] Based on feedback from the emotion engine, the server adjusts the tone and style of the article to match the user's emotions. For positive emotions, a motivational tone is generated.

[0858] Input: Generated article elements, user sentiment data

[0859] Output: Articles adjusted to match emotions

[0860] Step 11:

[0861] The generated article is sent from the server to the user's terminal, where the user reviews the content.

[0862] Input: Articles adjusted to match emotions

[0863] Output: Articles displayed on the user's device

[0864] Step 12:

[0865] If a user finds the content problematic, they input correction instructions into their terminal and send them to the server. For example, a correction instruction might be, "Change the title to something more impactful."

[0866] Input: User's correction instructions

[0867] Output: Correction instruction data to the server

[0868] Step 13:

[0869] The server analyzes the correction instructions and automatically modifies the article. For example, it might change the title to "Diet Revolution! This is the food that's all the rage right now!"

[0870] Input: Correction instruction data

[0871] Output: Corrected article

[0872] Step 14:

[0873] The revised article is sent back to the user for final review. If approved, the process ends.

[0874] Input: Modified article

[0875] Output: Last article displayed to the user

[0876] (Application Example 2)

[0877] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0878] Current content generation systems often produce content uniformly without considering the user's emotional state, making personalization to match the tone and style the user desires difficult. While some degree of keyword selection efficiency and automated article generation has been achieved, dynamic selection and adjustment of ad copy based on user emotions remains lacking. Therefore, there is a need for a system that dynamically adjusts the tone and style of content based on user input and emotional state, automatically generating and revising optimal keywords and high-quality articles.

[0879] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0880] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the keyword efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated keyword efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for recognizing the user's emotional state; means for dynamically changing the content and ranking of the displayed keyword list based on the recognized emotional state; means for generating article elements based on the received keywords; means for adjusting the tone and style of the article based on the user's emotional state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables dynamic keyword selection and personalized content generation based on the user's input information and emotional state.

[0881] "Brand information" refers to basic information about a company or product, and is an element that expresses its characteristics and value.

[0882] "Market information" refers to data about a specific target group or market environment, and is information used to understand customer interests and demand trends.

[0883] "Related keywords" are keywords selected based on brand information and market information, taking into account search frequency and level of competition on search engines.

[0884] "Keyword efficiency" is an indicator that evaluates the effectiveness of keywords by calculating their search volume, competition level, and relevance.

[0885] A "keyword list" is a list of relevant keywords that should be used, generated based on keyword efficiency.

[0886] "Emotional state" refers to the psychological state perceived from the user's facial expressions, tone of voice, and other factors.

[0887] "Article elements" are the elements that make up each part of the generated content (title, headings, body text, etc.).

[0888] A "style guide" is a set of guidelines for maintaining a consistent tone and style in an article.

[0889] A "correction instruction" is a user's instruction to change or improve an article they have generated.

[0890] "Personalization" refers to adjusting the content and presentation of content according to the individual needs and preferences of the user.

[0891] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[0892] First, the user enters brand and market information into their device and sends it to the server. The server retrieves relevant keywords based on the received information and calculates keyword efficiency. This is done using SEO analysis tools such as the Ahrefs API. Based on the calculated keyword efficiency, the server generates a keyword list and displays it on the device.

[0893] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state. This emotion engine utilizes Google Cloud's Emotion API. Based on the recognized emotional state, the server dynamically changes the content and ranking of the displayed keyword list. For example, if a user is showing positive emotions, positive and motivational keywords will be displayed higher.

[0894] Based on selected keywords, the server generates article elements. This uses generative AI models such as GPT-3 and ChatGPT. Furthermore, the tone and style of the article are adjusted based on the user's sentiment information. For example, if the user expresses positive sentiment, the article will be generated with a motivational tone. The generated article elements are optimized according to the company's style guide and displayed on the device.

[0895] The user reviews the generated article and enters correction instructions if necessary. The server re-edits the article based on these instructions and displays it to the user again. Natural language processing technology is used for the re-editing to accurately reflect the user's intentions for correction. The writing style of the revised article is automatically adjusted to match the brand tone.

[0896] The following are specific examples and examples of prompts for the generative AI model:

[0897] Specific example:

[0898] For example, suppose a marketing manager for a sports brand uses this system. The user inputs information such as "sportswear" and "male in his teens and twenties," and the server provides related keywords such as "running shoes" and "training gear." If the emotion engine recognizes the user's excitement, it generates a positive and motivational article, creating text with a tone like, "Get your best performance out of these running shoes!"

[0899] Examples of prompts for a generative AI model:

[0900] Keywords: Diet foods

[0901] User sentiment: Positive

[0902] Output style: Motivational

[0903] Prompt: Write a positive and motivational article about diet foods.

[0904] Title: This is the trending diet food right now! It's worth trying.

[0905] Introduction: If you want to succeed in your diet, you should definitely try incorporating this food into your diet. The secret to healthy weight loss lies here.

[0906] In this way, it becomes possible to personalize dynamic keyword selection and content generation based on user input information and emotional state.

[0907] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0908] Step 1:

[0909] The user enters brand and market information into their device and sends it to the server.

[0910] Input: Brand information (e.g., sportswear), market information (e.g., men in their teens and twenties)

[0911] Output: Input information is sent to the server.

[0912] Specific operation: The user enters brand information and market information into the input form on the device and presses the "Submit" button. The device sends the input data to the server as an HTTP request.

[0913] Step 2:

[0914] The server retrieves relevant keywords based on the brand and market information it receives.

[0915] Input: Received brand information and market information

[0916] Output: List of related keywords (e.g., running shoes, training gear)

[0917] Specific operation: The server uses external SEO tools such as the Ahrefs API to search the database for keywords related to brand information and market information, and retrieves the relevant keywords.

[0918] Step 3:

[0919] The server calculates the keyword efficiency of the relevant keywords it has acquired and generates a keyword list based on that.

[0920] Input: List of related keywords

[0921] Output: Keyword list ranked based on KW efficiency

[0922] Specific operation: The server calculates the search volume, competition level, and relevance of each keyword, and then calculates keyword efficiency by combining these metrics. After that, keywords are ranked and listed based on keyword efficiency.

[0923] Step 4:

[0924] The server generates a list of keywords, which is then displayed on the terminal.

[0925] Input: Ranked keyword list

[0926] Output: Keyword list displayed on the terminal screen

[0927] Specific operation: The server sends the completed keyword list to the terminal, which receives this information and displays it on the screen.

[0928] Step 5:

[0929] When a user selects a keyword, the emotion engine recognizes the user's emotional state.

[0930] Input: User's facial expressions and tone of voice

[0931] Output: User's emotional state (e.g., positive)

[0932] Specific operation: The device uses its built-in camera and microphone to capture the user's facial expressions and voice, and then uses Google Cloud's Emotion API to analyze their emotional state.

[0933] Step 6:

[0934] The server dynamically changes the content and ranking of the displayed keyword list based on the recognized emotional state.

[0935] Input: User's emotional state, original keyword list

[0936] Output: Dynamically changed keyword list

[0937] Specific operation: The server receives the user's emotional state and reconstructs the keyword list based on it. For example, if the emotional state is positive, motivational keywords will be placed at the top.

[0938] Step 7:

[0939] The user selects keywords and sends them to the server.

[0940] Input: User-selected keyword

[0941] Output: The selected keywords are sent to the server.

[0942] Specific operation: The user selects their desired keyword from the displayed keyword list and presses the "Select" button. This data is sent to the server.

[0943] Step 8:

[0944] The server generates article elements based on the keywords it receives.

[0945] Input: Selected keywords

[0946] Output: Generated article elements (e.g., title, headings, body text)

[0947] Specific operation: The server uses generative AI models such as GPT-3 and ChatGPT to automatically generate article components based on selected keywords.

[0948] Step 9:

[0949] The server adjusts the tone and style of the article based on the user's emotions.

[0950] Input: Generated article elements, user's sentiment state

[0951] Output: Adjusted article

[0952] Specific operation: The generated article elements are adjusted to reflect the user's emotional state (e.g., positive), and their tone and style are modified accordingly. For example, if the emotional state is positive, the overall tone of the article is made more motivational.

[0953] Step 10:

[0954] The server displays optimized articles on the device.

[0955] Input: Adjusted article

[0956] Output: Article displayed on the terminal screen

[0957] Specific operation: The server sends an optimized article to the terminal, which receives it and displays it to the user.

[0958] Step 11:

[0959] The user enters correction instructions for an article and sends that data to the server.

[0960] Input: Correction instructions (e.g., title change, content addition)

[0961] Output: Correction instructions are sent to the server.

[0962] Specific operation: The user reviews the displayed article, enters the necessary corrections into the terminal's editor, and presses the "Submit" button. The correction instructions are sent to the server as an HTTP request.

[0963] Step 12:

[0964] The server corrects the article based on the correction instructions.

[0965] Input: Correction instructions, article generated just a moment ago

[0966] Output: Corrected article

[0967] Specific operation: The server uses natural language processing technology to analyze user correction instructions and rewrite the article. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[0968] Step 13:

[0969] The server will redisplay the corrected article on your device.

[0970] Input: Modified article

[0971] Output: Correction article displayed on the terminal screen

[0972] Specific operation: The server sends the corrected article to the terminal, which receives it and displays it to the user again.

[0973] 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.

[0974] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0975] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0976] [Third Embodiment]

[0977] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0978] 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.

[0979] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0980] 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.

[0981] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0982] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0983] 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.

[0984] 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.

[0985] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0986] The 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.

[0987] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0988] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0989] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[0990] 1. KW selection

[0991] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[0992] 2. Article generation

[0993] When a user selects the most suitable keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server uses relevant databases and pre-trained models to collect information related to the keyword. The server then generates article elements (e.g., title: "Easily Start Shaping Up with the Latest Diet Foods," body text: "A Must-See for Those Who Want to Lose Weight Healthily! Introducing the Latest Diet Foods. These products are rich in vitamins and also effective for beauty.") based on the collected information. The server also optimizes the generated article based on the brand tone (e.g., "casual and approachable") and style guide.

[0994] 3. Proofreading

[0995] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[0996] In this way, the entire system's specific operations automate a series of SEO tasks, from keyword selection to proofreading, significantly reducing the user's burden and enabling the efficient, consistent, and high-quality generation of content.

[0997] The following describes the processing flow.

[0998] Step 1:

[0999] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[1000] Step 2:

[1001] Based on the received brand and market information, the server retrieves relevant keywords (e.g., "dietary foods," "vitamin supplements," "beauty supplements") from the database.

[1002] Step 3:

[1003] The server analyzes competitive information and trend data from search engines for the retrieved related keywords, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[1004] Step 4:

[1005] The server compiles a list of highly efficient keywords and presents it to the user.

[1006] Step 5:

[1007] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device.

[1008] Step 6:

[1009] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[1010] Step 7:

[1011] The server optimizes the generated articles according to the brand's tone and style guide. For example, it adjusts the text to have a "casual and approachable" tone.

[1012] Step 8:

[1013] The server sends the optimized article to the user, who receives it on their device.

[1014] Step 9:

[1015] The user reviews the generated article on their device and, if necessary, enters correction instructions (e.g., "Make the title more impactful") and sends them to the server.

[1016] Step 10:

[1017] The server analyzes user correction requests and automatically modifies the generated articles. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[1018] Step 11:

[1019] The server optimizes the revised article again and sends it to the user. The user receives it again on their device and performs a final check of the article.

[1020] Step 12:

[1021] Once the user is satisfied with the article's content and signals the terminal to complete the review, the terminal sends that information to the server, and the process ends.

[1022] (Example 1)

[1023] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1024] Traditional SEO work is often done manually, making it time-consuming and labor-intensive, and thus inefficient. Furthermore, it is prone to inconsistencies in content quality and consistency, making it difficult to consistently generate high-quality content that is appropriate for the brand. Additionally, proofreading and revising the generated content is time-consuming and requires quick responses. This invention aims to automate these problems and improve efficiency and consistency.

[1025] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1026] In this invention, the server includes means for receiving brand information and market information, means for obtaining relevant keywords, means for calculating keyword efficiency, means for generating a keyword list, means for optimizing the generated article elements according to a style guide, means for revising the article based on revision instructions, and means for receiving revision completion instructions. This enables the automation and efficiency of SEO work, allowing for the rapid generation and revision of high-quality, consistent, and brand-appropriate content.

[1027] "Brand information" refers to identifiable information associated with a specific company, product, or service.

[1028] "Market information" refers to data and insights about a specific market or target audience.

[1029] A "keyword" refers to an important word or phrase related to a specific theme or topic.

[1030] "Keyword efficiency" is an efficiency metric calculated based on factors such as keyword search volume, competition level, and relevance.

[1031] "Article elements" refer to the constituent elements of content, such as the title and body text.

[1032] A "style guide" refers to guidelines regarding the writing style and tone of documents based on a specific brand or style.

[1033] "Tone" refers to the use of language to express the emotions and atmosphere of a text or content.

[1034] "Correction instructions" refer to instructions regarding changes or improvements to user-generated content.

[1035] A "correction completion instruction" refers to an instruction for the user to confirm that the corrected content is appropriate and to ultimately approve it.

[1036] A "generative AI model" refers to an artificial intelligence algorithm used for tasks such as text generation and data analysis.

[1037] To implement this invention, a system is required in which users, terminals, and servers work together. This system automates the streamlining of SEO work and the generation of high-quality content based on brand information and market information.

[1038] The overall system hardware configuration will consist of the user's PC or smartphone (device) and an AWS EC2 instance (server). The software will utilize MySQL as the database, OpenAI GPT as the generative AI model, and Django as the server-side framework.

[1039] Explanation in natural language

[1040] KW selection

[1041] 1. User input

[1042] Users input information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and send it to the server. Input is done through a dedicated form, and processing begins on the server after submission.

[1043] 2. Server processing - Retrieval of related keywords

[1044] The server retrieves relevant keywords from the MySQL database using queries based on the received brand and market information. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[1045] 3. Server Processing - Calculation and Listing of KW Efficiency

[1046] The server analyzes competitive information and search engine trend data for these keywords and calculates keyword efficiency based on each keyword's search volume, competitiveness, and relevance. For example, it uses the Google Trends API to retrieve data and assigns a weighted score to each keyword to calculate keyword efficiency. Keywords with high scores are then presented to the user as a list.

[1047] Article generation

[1048] 1. User Selection

[1049] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device. The user selects a keyword from the list and clicks the "Confirm" button to submit it.

[1050] 2. Server Processing - Information Gathering and Article Generation

[1051] The server uses a generative AI model such as OpenAI GPT-3 to collect relevant information based on selected keywords and then generates article elements based on that information. For example, it sends a prompt sentence like "Please tell me the latest information on diet foods" to the generative AI model and uses the obtained information to create a title and body text.

[1052] 3. Server Processing - Optimization Based on Tone and Style Guides

[1053] The server modifies the generated content to match the brand's tone and style guide (e.g., "casual and approachable"). It changes the style and expression of the generated text to ensure consistency and completes an optimized article for the user.

[1054] Proofreading

[1055] 1. User Verification

[1056] The generated article is sent from the server to the user, who then reviews the content on their device. If there are any problems with the content, the user uses the editing form on their device to enter correction instructions (e.g., "Please change the title to something more attention-grabbing") and sends them to the server.

[1057] 2. Server processing - Article revision

[1058] The server analyzes user correction instructions and automatically corrects the article using a generative AI model. For example, if there is a instruction regarding the title, it will regenerate the article using a prompt such as "Make the title more attention-grabbing."

[1059] 3. User's final confirmation and completion instructions

[1060] The user reviews the revised article again, and if they are finally satisfied, they indicate on their device that the review is complete. By pressing the "Complete" button, the user sends that information to the server, and the process officially ends.

[1061] Specific examples and prompt statements

[1062] Specific example

[1063] KW selection

[1064] Information entered by the user: Brand information "Health Foods", Target market information "Women in their 20s and 30s"

[1065] The server provides a list of keywords: diet foods, vitamin supplements, beauty supplements.

[1066] Article generation

[1067] Keywords selected by users: Diet foods

[1068] Articles generated by the server:

[1069] Title: "Easily Start Shaping Up with the Latest Diet Foods"

[1070] Text: "A must-see for those who want to lose weight healthily! Introducing the latest diet foods. These products are rich in vitamins and also effective for beauty."

[1071] Example of a prompt

[1072] "Please select highly efficient keywords based on health food brands and target market information for women in their 20s and 30s."

[1073] "Please write an article about diet foods. The title should be approachable and casual."

[1074] Thus, the system of the present invention automates a series of SEO tasks, from keyword selection to article generation and proofreading, significantly reducing the burden on the user and enabling efficient, consistent, and high-quality content generation.

[1075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1076] Processing steps

[1077] KW selection

[1078] Step 1:

[1079] Users enter brand information and market information.

[1080] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and clicks the submit button. This information is then sent to the server.

[1081] Input: Brand information, market information

[1082] Output: Brand information and market information sent to the server

[1083] Step 2:

[1084] The server retrieves related keywords.

[1085] Based on the received brand and market information, the server retrieves relevant keywords from the MySQL database using queries. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[1086] Input: Brand information, market information

[1087] Data processing / calculation: Retrieve relevant keywords from a MySQL database using queries.

[1088] Output: List of related keywords

[1089] Step 3:

[1090] The server calculates keyword efficiency and generates a keyword list.

[1091] The server analyzes the retrieved related keywords using the Google Trends API and other tools to determine the search volume, competition level, relevance, etc., and calculates keyword efficiency. Based on the calculation results, it selects high-scoring keywords and generates a keyword list.

[1092] Input: List of related keywords

[1093] Data processing / calculation: Analyze each keyword using the Google Trends API, etc., and calculate keyword efficiency.

[1094] Output: List of keywords with high KW efficiency

[1095] Article generation

[1096] Step 4:

[1097] The user selects and submits the most suitable keywords.

[1098] The user selects the most suitable keyword (e.g., "diet food") from the presented keyword list and sends it to the server via their device. The user selects a keyword and clicks the "Confirm" button.

[1099] Input: List of highly efficient keywords (KW)

[1100] Output: Optimal keywords sent to the server

[1101] Step 5:

[1102] The server collects information and generates article elements.

[1103] The server uses a generative AI model such as OpenAI GPT-3 to create a prompt based on the most suitable keywords it receives, and then collects relevant information based on that prompt. Specifically, it sends a prompt such as "Please tell me the latest information on diet foods" to the model, and then creates an article title and body based on the generated information.

[1104] Input: Best keyword

[1105] Data Processing / Calculation: Use a generative AI model to create prompt statements, collect information, and generate article elements.

[1106] Output: Generated article elements (title, body)

[1107] Step 6:

[1108] The server optimizes article elements.

[1109] The server adjusts the generated article elements based on the brand's tone and style guide, optimizing them to ensure consistency in writing style and content. For example, it might adjust the writing style to a "casual and approachable" tone.

[1110] Input: Generated article elements (title, body)

[1111] Data processing / calculation: Optimize article elements based on the brand's tone and style guide.

[1112] Output: Optimized article

[1113] Proofreading

[1114] Step 7:

[1115] Users review articles and submit correction requests.

[1116] The server sends an optimized article to the user. The user reviews the article on their device and, if necessary, enters correction instructions (e.g., "Make the title more eye-catching") and sends them to the server.

[1117] Input: Optimized article

[1118] Output: Correction instructions sent to the server

[1119] Step 8:

[1120] The server will modify the article.

[1121] The server analyzes the user's correction instructions and uses a generative AI model to revise the article. For example, in response to the instruction "Make the title more attention-grabbing," it regenerates the prompt as "Generate a more attention-grabbing title."

[1122] Input: Correction Instructions

[1123] Data processing / calculation: Regenerate and correct articles using a generative AI model.

[1124] Output: Corrected article

[1125] Step 9:

[1126] The user submits a correction completion instruction.

[1127] The user reviews the revised article again, and if they are finally satisfied, they send a correction completion notification from their device. By pressing the "Complete" button, the user sends that information to the server.

[1128] Input: Modified article

[1129] Output: Correction completion instruction sent to the server

[1130] (Application Example 1)

[1131] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1132] Traditional SEO and ad copy generation processes required significant time and effort for keyword selection, content creation, and ad copy creation based on brand and market information. Furthermore, verifying and adjusting whether the generated content aligned with brand tone and market trends was cumbersome, making it difficult to provide efficient, consistent, and high-quality content.

[1133] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1134] In this invention, the server includes means for receiving brand information and market information, means for acquiring relevant keywords, and means for calculating the keyword efficiency of the acquired keywords. This automates a series of processes, from keyword selection to article and ad copy generation, and style optimization and revision, enabling the efficient, consistent, and high-quality delivery of content and ad copy.

[1135] "Brand information" refers to information about the awareness and image of a particular company or product.

[1136] "Market information" refers to data and statistics related to a specific target market.

[1137] "Related keywords" are terms used by search engines to select keywords based on brand and market information.

[1138] "Keyword efficiency" is an efficiency metric calculated based on factors such as search volume, competition level, and relevance of related keywords.

[1139] A "keyword list" is a list of related keywords generated based on keyword efficiency.

[1140] "Article elements" refer to the constituent elements of an article, such as the title and body text, which are generated based on keywords.

[1141] A "style guide" is a set of guidelines designed to reflect a brand's tone and style.

[1142] "Correction instructions" are instructions from users to change or revise articles or ad copy.

[1143] "Ad copy" refers to marketing and promotional text generated using selected keywords.

[1144] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to achieve the automated generation of efficient, consistent, and high-quality advertising content.

[1145] System Configuration

[1146] Servers, terminals, and users are the main components of the system.

[1147] server

[1148] The server performs the following roles:

[1149] 1. Receiving brand and market information: The system has a means of receiving brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35") entered by the user.

[1150] 2. Acquisition of related keywords: Based on the received brand information and market information, related keywords (e.g., "natural skincare", "additive-free cosmetics") are retrieved from the database.

[1151] 3. Calculation of Keyword Efficiency: Analyze the acquired related keywords, competitive information, and trend data from search engines to calculate keyword efficiency.

[1152] 4. Keyword List Generation: Based on the calculated keyword efficiency, list the most efficient keywords.

[1153] 5. Ad copy generation: Based on the most suitable keywords, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized to match the brand tone.

[1154] terminal

[1155] The terminal will perform the following roles:

[1156] 1. Input of brand and market information: Provide an interface for users to input brand and market information.

[1157] 2. Displaying the Keyword List: The keyword list received from the server is displayed to the user.

[1158] 3. Selection of optimal keywords: The user selects the most suitable keywords from the keyword list and sends them to the server.

[1159] 4. Viewing and modifying the generated ad copy: The user reviews the generated ad copy, enters any necessary modification instructions, and sends them to the server.

[1160] User

[1161] The user will play the following roles:

[1162] 1. Entering brand and market information: Use a terminal to enter brand and market information.

[1163] 2. Keyword Selection: Select the most suitable keyword from the keyword list sent from the server.

[1164] 3. Review and modify the ad copy: Review the generated ad copy and enter any necessary modification instructions.

[1165] Program processing

[1166] The server receives brand and market information via a REST API using the Python requests library. Search engine APIs and a proprietary database are used to retrieve relevant keywords. Pandas and NumPy, Python data analysis libraries, are used to calculate keyword efficiency.

[1167] For generating ad copy, a generative AI model (e.g., GPT-3) is used, utilizing the transformers library. This model is pre-trained, enabling high-quality text generation.

[1168] Specific example

[1169] For example, if you input brand information as "organic cosmetics" and market information as "women aged 25 to 35," the server will select related keywords such as "natural skincare" and "additive-free cosmetics." If you select "additive-free cosmetics" from these, the AI ​​model will generate an ad copy such as "Start gentle skincare with high-quality additive-free cosmetics!"

[1170] Examples of prompts in this system are as follows:

[1171] Please generate high-quality advertising copy using "additive-free cosmetics." The tone should be friendly and convey a trustworthy image.

[1172] As described above, this system enables the automated generation of high-quality advertising content efficiently and consistently.

[1173] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1174] Step 1:

[1175] Enter brand information and market information.

[1176] The user uses a device to input brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35"). The system then receives specific data related to the brand and market.

[1177] Input: Brand information and market information

[1178] Output: Brand information and market information sent to the server

[1179] Step 2:

[1180] Receive brand information and market information.

[1181] The server receives brand and market information transmitted from the terminal. This information serves as base data for obtaining relevant keywords.

[1182] Input: Brand and market information sent from the terminal.

[1183] Output: Brand information and market information stored on the server

[1184] Step 3:

[1185] Retrieving related keywords

[1186] Based on the brand and market information received by the server, it retrieves relevant keywords from search engine APIs and its own database. For example, it retrieves keywords related to "organic cosmetics" and "women aged 25 to 35."

[1187] Input: Brand information and market information

[1188] Output: List of related keywords (e.g., "natural skincare", "additive-free cosmetics")

[1189] Step 4:

[1190] Calculation of KW efficiency

[1191] The server calculates the keyword efficiency of the relevant keywords it retrieves. It collects data such as search volume, competition level, and relevance, and uses this data to calculate keyword efficiency.

[1192] Input: Related Keyword List

[1193] Output: Keyword list for which KW efficiency was calculated

[1194] Step 5:

[1195] Keyword list generation

[1196] The server lists high-efficiency keywords based on keyword efficiency. The listed keywords are sent to the terminal and displayed to the user.

[1197] Input: Keyword used to calculate KW efficiency

[1198] Output: Optimal keyword list

[1199] Step 6:

[1200] Selecting and submitting the most suitable keywords

[1201] The user clicks or selects the most relevant keyword (e.g., "additive-free cosmetics") and sends it from their device to the server.

[1202] Input: Best keyword

[1203] Output: Optimal keywords sent to the server

[1204] Step 7:

[1205] Generating ad copy

[1206] Based on the optimal keywords received by the server, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized based on pre-configured brand tone and style guides.

[1207] Input: Best keyword

[1208] Output: Generated ad copy

[1209] Step 8:

[1210] Display the generated ad copy and enter instructions for modification.

[1211] The user reviews the generated ad copy using their device and enters correction instructions as needed. These correction instructions are then sent from the device to the server.

[1212] Input: Generated ad copy

[1213] Output: Correction instructions

[1214] Step 9:

[1215] Ad copy revision

[1216] The server modifies the ad copy based on the correction instructions received from the user. The modified ad copy is then optimized again and sent to the device.

[1217] Input: Correction Instructions

[1218] Output: Revised ad copy

[1219] Step 10:

[1220] Display of revised ad text

[1221] The revised ad copy is finally displayed on the device for the user to review. At this point, the user can make a final review and request further revisions if necessary.

[1222] Input: Revised ad copy

[1223] Output: Final approved ad copy

[1224] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1225] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[1226] 1. KW selection

[1227] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[1228] 2. Emotion recognition

[1229] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is showing positive emotions, the emotion engine sends that information to the server. Based on this emotion recognition result, the server dynamically changes the content and ranking of the keyword list it presents.

[1230] 3. Article generation

[1231] When a user selects the most relevant keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server gathers information using relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text). It also adjusts the tone and style of the article to match the user's emotions based on feedback from the sentiment engine. For example, if the user expresses positive emotions, the server will adopt a positive and motivational tone.

[1232] 4. Proofreading

[1233] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[1234] In this way, the entire system's specific operation automates a series of SEO tasks, from keyword selection to proofreading, and also enables content personalization based on user sentiment. This significantly reduces the burden on users and enables the efficient, consistent, and high-quality generation of content.

[1235] The following describes the processing flow.

[1236] Step 1:

[1237] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[1238] Step 2:

[1239] Based on the received brand and market information, the server retrieves relevant keywords (e.g., "dietary foods," "vitamin supplements," "beauty supplements") from the database.

[1240] Step 3:

[1241] The server analyzes competitive information and trend data from search engines for the retrieved related keywords, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[1242] Step 4:

[1243] The server compiles a list of highly efficient keywords and presents it to the user.

[1244] Step 5:

[1245] The user checks a list of keywords via their device and selects the most suitable keyword (e.g., "diet foods").

[1246] Step 6:

[1247] The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state and sends the results to the server. For example, if the user is showing positive emotions, that information is transmitted to the server.

[1248] Step 7:

[1249] The server dynamically changes the content and order of the keyword list it presents based on feedback from the emotion engine. For example, it prioritizes presenting keywords with a positive tone to users who express positive emotions.

[1250] Step 8:

[1251] The user selects the most suitable keywords and sends them to the server via their device.

[1252] Step 9:

[1253] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[1254] Step 10:

[1255] Based on feedback from the emotion engine, the server adjusts the tone and style of the generated article to match the user's emotions. For example, if the user is expressing positive emotions, the entire article will be adjusted to a positive and motivational tone.

[1256] Step 11:

[1257] The server sends the optimized article to the user, who receives it on their device.

[1258] Step 12:

[1259] The user reviews the generated article on their device and enters correction instructions as needed (e.g., "Make the title more impactful").

[1260] Step 13:

[1261] The terminal sends the user's correction instructions to the server.

[1262] Step 14:

[1263] The server analyzes user correction requests and automatically modifies the generated articles. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[1264] Step 15:

[1265] The server optimizes the revised article again and sends it to the user. The user receives it again on their device and performs a final review of the article.

[1266] Step 16:

[1267] Once the user is satisfied with the article's content and signals the terminal to complete the review, the terminal sends that information to the server, and the process ends.

[1268] (Example 2)

[1269] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1270] In SEO work, the process from keyword selection to article generation and proofreading is extremely time-consuming and labor-intensive, and there are challenges in generating content that is appropriate for user sentiment and brand tone. Furthermore, there is a need to efficiently generate high-quality content by appropriately reflecting user input and sentiment analysis results.

[1271] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1272] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the KW efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated KW efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for generating article elements based on the received keyword; means for analyzing the user's sentiment based on feedback from the sentiment engine; means for adjusting the tone and style of the article based on the analysis results of the user's sentiment state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables the efficient automation of a series of SEO tasks from keyword selection to article generation and proofreading, and makes it possible to generate content based on the user's sentiment.

[1273] "Brand information" refers to information about a specific brand provided by the user, including the characteristics, value, and positioning of the product or service.

[1274] "Market information" refers to information about a specific market that a user has, including target audience, competitive landscape, and trends.

[1275] "Related keywords" are words and phrases that are extracted based on brand information and market information and are considered effective for SEO.

[1276] "Keyword efficiency" is an index that comprehensively evaluates factors such as search volume, competition level, and relevance for related keywords.

[1277] A "keyword list" refers to a list of related keywords ranked based on calculated keyword efficiency.

[1278] An "emotion engine" is an analytical device or software that recognizes emotions by analyzing the user's facial expressions, voice tone, and other factors.

[1279] "Article elements" refer to the various components that make up an article, such as the title, headings, body text, and images.

[1280] A "style guide" refers to instructions or guidelines regarding the style and tone of an article or piece of writing.

[1281] "User sentiment" refers to the emotional response a user shows to a particular situation or content, and includes positive, negative, and neutral reactions.

[1282] A "correction instruction" is a specific request for changes made by a user to the content of an article they have generated.

[1283] "Optimization" refers to the process of adjusting generated content to make it higher quality and more effective.

[1284] To implement this invention, it is necessary to build a system in which the user, terminal, server, and emotion engine work together in cooperation with each other. The following describes how to implement this system in detail.

[1285] First, users access the system via a terminal. This terminal is essentially a computer or smartphone, providing an interface for users to input information. This terminal displays forms for entering brand and market information.

[1286] When a user enters specific information such as "health foods" or "women in their 20s and 30s," the device sends that information to the server. Upon receiving this brand and market information, the server retrieves relevant keywords from its database based on that information.

[1287] The server calculates the keyword efficiency of acquired keywords by analyzing search engine trend data and competitive information. This analysis utilizes natural language processing and machine learning techniques. Based on the calculated keyword efficiency, the server lists the most efficient keywords and presents this list to the user.

[1288] Next, the system selects the most suitable keywords from the user's provided keyword list. During this process, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. The emotion engine then collects necessary data using input devices such as cameras and microphones.

[1289] The emotion engine analyzes the emotion data, which is then sent to the server. Based on this data, the server dynamically changes the ranking and content of the keyword list. When the user selects the most suitable keyword (e.g., "diet food"), that keyword is sent back to the server from the device.

[1290] Based on the received keywords, the server utilizes relevant databases and pre-trained models (e.g., generative AI models) to generate article elements (e.g., title, headings, body text). During this process, the tone and style of the article are adjusted based on feedback from the sentiment engine. For example, if a user expresses positive emotions, the server generates an article with a positive and motivational tone.

[1291] The generated article is sent from the server to the user's terminal, where the user reviews the content. If improvements are needed, the user enters correction instructions on their terminal and sends them to the server. The server analyzes these instructions and automatically corrects the article. The corrected article is sent back to the user for final review. Once the user approves it, the process is complete.

[1292] For example, if you input information about "health foods," the server will suggest keywords such as "diet foods" and "beauty supplements," and as a result generate articles such as "Latest Trends in Diet Foods."

[1293] Example of a prompt:

[1294] "Please generate an article about the latest trends in health foods targeting women in their 20s and 30s."

[1295] In this way, the entire system flexibly responds based on user input and sentiment analysis, enabling the automatic generation of high-quality content. This efficiently automates SEO tasks and significantly reduces the burden on users.

[1296] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1297] Step 1:

[1298] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[1299] Input: Brand information and market information

[1300] Output: Data to send to the server

[1301] Step 2:

[1302] The server retrieves relevant keywords from the database based on the received brand and market information. For example, from the brand information "health foods" and the market information "women in their 20s and 30s," keywords such as "diet foods," "vitamin supplements," and "beauty supplements" are retrieved.

[1303] Input: Received brand information and market information

[1304] Output: List of related keywords

[1305] Step 3:

[1306] The server analyzes the retrieved relevant keywords, along with competitive information and trend data from search engines, to calculate keyword efficiency. This calculation uses data such as search volume, competition level, and relevance.

[1307] Input: Related keyword list, competitor information, search engine trend data

[1308] Output: Keyword list for calculating kW efficiency

[1309] Step 4:

[1310] The server generates a keyword list based on calculated keyword efficiency and presents it to the user. The most efficient keywords are displayed at the top.

[1311] Input: Keyword list used to calculate KW efficiency

[1312] Output: List of keywords presented to the user

[1313] Step 5:

[1314] The user selects the most suitable keyword from the presented keyword list and sends it to the server via their device. For example, if the user selects the keyword "diet food," that selection data will be sent.

[1315] Input: List of keywords presented to the user

[1316] Output: Selection data for optimal keywords

[1317] Step 6:

[1318] The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state. The emotion engine uses the camera and microphone to generate emotional data such as positive, negative, and neutral, and sends this data to the server.

[1319] Input: User's facial expressions and voice tone acquired from camera and microphone.

[1320] Output: User sentiment data

[1321] Step 7:

[1322] The server dynamically changes the ranking and content of the keyword list it presents based on sentiment data. For example, if a user selects "diet foods" and expresses a positive sentiment, positive keywords will be displayed preferentially.

[1323] Input: User sentiment data

[1324] Output: Dynamically changed keyword list

[1325] Step 8:

[1326] The user sends the keyword they ultimately selected to the server. Here, the keyword "diet food" is confirmed.

[1327] Input: Dynamically changed keyword list

[1328] Output: The keywords that were ultimately selected

[1329] Step 9:

[1330] Based on the received keywords, the server utilizes relevant databases and a pre-trained generative AI model to generate article elements (e.g., title, headings, body text). For example, an article titled "Latest Trends in Diet Foods" might be generated.

[1331] Input: Final selected keywords

[1332] Output: Generated article elements

[1333] Step 10:

[1334] Based on feedback from the emotion engine, the server adjusts the tone and style of the article to match the user's emotions. For positive emotions, a motivational tone is generated.

[1335] Input: Generated article elements, user sentiment data

[1336] Output: Articles adjusted to match emotions

[1337] Step 11:

[1338] The generated article is sent from the server to the user's terminal, where the user reviews the content.

[1339] Input: Articles adjusted to match emotions

[1340] Output: Articles displayed on the user's device

[1341] Step 12:

[1342] If a user finds the content problematic, they input correction instructions into their terminal and send them to the server. For example, a correction instruction might be, "Change the title to something more impactful."

[1343] Input: User's correction instructions

[1344] Output: Correction instruction data to the server

[1345] Step 13:

[1346] The server analyzes the correction instructions and automatically modifies the article. For example, it might change the title to "Diet Revolution! This is the food that's all the rage right now!"

[1347] Input: Correction instruction data

[1348] Output: Corrected article

[1349] Step 14:

[1350] The revised article is sent back to the user for final review. If approved, the process ends.

[1351] Input: Modified article

[1352] Output: Last article displayed to the user

[1353] (Application Example 2)

[1354] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1355] Current content generation systems often produce content uniformly without considering the user's emotional state, making personalization to match the tone and style the user desires difficult. While some degree of keyword selection efficiency and automated article generation has been achieved, dynamic selection and adjustment of ad copy based on user emotions remains lacking. Therefore, there is a need for a system that dynamically adjusts the tone and style of content based on user input and emotional state, automatically generating and revising optimal keywords and high-quality articles.

[1356] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1357] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the keyword efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated keyword efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for recognizing the user's emotional state; means for dynamically changing the content and ranking of the displayed keyword list based on the recognized emotional state; means for generating article elements based on the received keywords; means for adjusting the tone and style of the article based on the user's emotional state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables dynamic keyword selection and personalized content generation based on the user's input information and emotional state.

[1358] "Brand information" refers to basic information about a company or product, and is an element that expresses its characteristics and value.

[1359] "Market information" refers to data about a specific target group or market environment, and is information used to understand customer interests and demand trends.

[1360] "Related keywords" are keywords selected based on brand information and market information, taking into account search frequency and level of competition on search engines.

[1361] "Keyword efficiency" is an indicator that evaluates the effectiveness of keywords by calculating their search volume, competition level, and relevance.

[1362] A "keyword list" is a list of relevant keywords that should be used, generated based on keyword efficiency.

[1363] "Emotional state" refers to the psychological state perceived from the user's facial expressions, tone of voice, and other factors.

[1364] "Article elements" are the elements that make up each part of the generated content (title, headings, body text, etc.).

[1365] A "style guide" is a set of guidelines for maintaining a consistent tone and style in an article.

[1366] A "correction instruction" is a user's instruction to change or improve an article they have generated.

[1367] "Personalization" refers to adjusting the content and presentation of content according to the individual needs and preferences of the user.

[1368] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[1369] First, the user enters brand and market information into their device and sends it to the server. The server retrieves relevant keywords based on the received information and calculates keyword efficiency. This is done using SEO analysis tools such as the Ahrefs API. Based on the calculated keyword efficiency, the server generates a keyword list and displays it on the device.

[1370] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state. This emotion engine utilizes Google Cloud's Emotion API. Based on the recognized emotional state, the server dynamically changes the content and ranking of the displayed keyword list. For example, if a user is showing positive emotions, positive and motivational keywords will be displayed higher.

[1371] Based on selected keywords, the server generates article elements. This uses generative AI models such as GPT-3 and ChatGPT. Furthermore, the tone and style of the article are adjusted based on the user's sentiment information. For example, if the user expresses positive sentiment, the article will be generated with a motivational tone. The generated article elements are optimized according to the company's style guide and displayed on the device.

[1372] The user reviews the generated article and enters correction instructions if necessary. The server re-edits the article based on these instructions and displays it to the user again. Natural language processing technology is used for the re-editing to accurately reflect the user's intentions for correction. The writing style of the revised article is automatically adjusted to match the brand tone.

[1373] The following are specific examples and examples of prompts for the generative AI model:

[1374] Specific example:

[1375] For example, suppose a marketing manager for a sports brand uses this system. The user inputs information such as "sportswear" and "male in his teens and twenties," and the server provides related keywords such as "running shoes" and "training gear." If the emotion engine recognizes the user's excitement, it generates a positive and motivational article, creating text with a tone like, "Get your best performance out of these running shoes!"

[1376] Examples of prompts for a generative AI model:

[1377] Keywords: Diet foods

[1378] User sentiment: Positive

[1379] Output style: Motivational

[1380] Prompt: Write a positive and motivational article about diet foods.

[1381] Title: This is the trending diet food right now! It's worth trying.

[1382] Introduction: If you want to succeed in your diet, you should definitely try incorporating this food into your diet. The secret to healthy weight loss lies here.

[1383] In this way, it becomes possible to personalize dynamic keyword selection and content generation based on user input information and emotional state.

[1384] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1385] Step 1:

[1386] The user enters brand and market information into their device and sends it to the server.

[1387] Input: Brand information (e.g., sportswear), market information (e.g., men in their teens and twenties)

[1388] Output: Input information is sent to the server.

[1389] Specific operation: The user enters brand information and market information into the input form on the device and presses the "Submit" button. The device sends the input data to the server as an HTTP request.

[1390] Step 2:

[1391] The server retrieves relevant keywords based on the brand and market information it receives.

[1392] Input: Received brand information and market information

[1393] Output: List of related keywords (e.g., running shoes, training gear)

[1394] Specific operation: The server uses external SEO tools such as the Ahrefs API to search the database for keywords related to brand information and market information, and retrieves the relevant keywords.

[1395] Step 3:

[1396] The server calculates the keyword efficiency of the relevant keywords it has acquired and generates a keyword list based on that.

[1397] Input: List of related keywords

[1398] Output: Keyword list ranked based on KW efficiency

[1399] Specific operation: The server calculates the search volume, competition level, and relevance of each keyword, and then calculates keyword efficiency by combining these metrics. After that, keywords are ranked and listed based on keyword efficiency.

[1400] Step 4:

[1401] The server generates a list of keywords, which is then displayed on the terminal.

[1402] Input: Ranked keyword list

[1403] Output: Keyword list displayed on the terminal screen

[1404] Specific operation: The server sends the completed keyword list to the terminal, which receives this information and displays it on the screen.

[1405] Step 5:

[1406] When a user selects a keyword, the emotion engine recognizes the user's emotional state.

[1407] Input: User's facial expressions and tone of voice

[1408] Output: User's emotional state (e.g., positive)

[1409] Specific operation: The device uses its built-in camera and microphone to capture the user's facial expressions and voice, and then uses Google Cloud's Emotion API to analyze their emotional state.

[1410] Step 6:

[1411] The server dynamically changes the content and ranking of the displayed keyword list based on the recognized emotional state.

[1412] Input: User's emotional state, original keyword list

[1413] Output: Dynamically changed keyword list

[1414] Specific operation: The server receives the user's emotional state and reconstructs the keyword list based on it. For example, if the emotional state is positive, motivational keywords will be placed at the top.

[1415] Step 7:

[1416] The user selects keywords and sends them to the server.

[1417] Input: User-selected keyword

[1418] Output: The selected keywords are sent to the server.

[1419] Specific operation: The user selects their desired keyword from the displayed keyword list and presses the "Select" button. This data is sent to the server.

[1420] Step 8:

[1421] The server generates article elements based on the keywords it receives.

[1422] Input: Selected keywords

[1423] Output: Generated article elements (e.g., title, headings, body text)

[1424] Specific operation: The server uses generative AI models such as GPT-3 and ChatGPT to automatically generate article components based on selected keywords.

[1425] Step 9:

[1426] The server adjusts the tone and style of the article based on the user's emotions.

[1427] Input: Generated article elements, user's sentiment state

[1428] Output: Adjusted article

[1429] Specific operation: The generated article elements are adjusted to reflect the user's emotional state (e.g., positive), and their tone and style are modified accordingly. For example, if the emotional state is positive, the overall tone of the article is made more motivational.

[1430] Step 10:

[1431] The server displays optimized articles on the device.

[1432] Input: Adjusted article

[1433] Output: Article displayed on the terminal screen

[1434] Specific operation: The server sends an optimized article to the terminal, which receives it and displays it to the user.

[1435] Step 11:

[1436] The user enters correction instructions for an article and sends that data to the server.

[1437] Input: Correction instructions (e.g., title change, content addition)

[1438] Output: Correction instructions are sent to the server.

[1439] Specific operation: The user reviews the displayed article, enters the necessary corrections into the terminal's editor, and presses the "Submit" button. The correction instructions are sent to the server as an HTTP request.

[1440] Step 12:

[1441] The server corrects the article based on the correction instructions.

[1442] Input: Correction instructions, article generated just a moment ago

[1443] Output: Corrected article

[1444] Specific operation: The server uses natural language processing technology to analyze user correction instructions and rewrite the article. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[1445] Step 13:

[1446] The server will redisplay the corrected article on your device.

[1447] Input: Modified article

[1448] Output: Correction article displayed on the terminal screen

[1449] Specific operation: The server sends the corrected article to the terminal, which receives it and displays it to the user again.

[1450] 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.

[1451] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1452] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1453] [Fourth Embodiment]

[1454] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1455] 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.

[1456] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[1457] 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.

[1458] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[1459] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1460] 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.

[1461] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1462] 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.

[1463] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[1464] The 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.

[1465] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1466] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1467] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[1468] 1. KW selection

[1469] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[1470] 2. Article generation

[1471] When a user selects the most suitable keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server uses relevant databases and pre-trained models to collect information related to the keyword. The server then generates article elements (e.g., title: "Easily Start Shaping Up with the Latest Diet Foods," body text: "A Must-See for Those Who Want to Lose Weight Healthily! Introducing the Latest Diet Foods. These products are rich in vitamins and also effective for beauty.") based on the collected information. The server also optimizes the generated article based on the brand tone (e.g., "casual and approachable") and style guide.

[1472] 3. Proofreading

[1473] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[1474] In this way, the entire system's specific operations automate a series of SEO tasks, from keyword selection to proofreading, significantly reducing the user's burden and enabling the efficient, consistent, and high-quality generation of content.

[1475] The following describes the processing flow.

[1476] Step 1:

[1477] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[1478] Step 2:

[1479] Based on the received brand and market information, the server retrieves relevant keywords (e.g., "dietary foods," "vitamin supplements," "beauty supplements") from the database.

[1480] Step 3:

[1481] The server analyzes competitive information and trend data from search engines for the retrieved related keywords, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[1482] Step 4:

[1483] The server compiles a list of highly efficient keywords and presents it to the user.

[1484] Step 5:

[1485] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device.

[1486] Step 6:

[1487] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[1488] Step 7:

[1489] The server optimizes the generated articles according to the brand's tone and style guide. For example, it adjusts the text to have a "casual and approachable" tone.

[1490] Step 8:

[1491] The server sends the optimized article to the user, who receives it on their device.

[1492] Step 9:

[1493] The user reviews the generated article on their device and, if necessary, enters correction instructions (e.g., "Make the title more impactful") and sends them to the server.

[1494] Step 10:

[1495] The server analyzes user correction requests and automatically modifies the generated articles. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[1496] Step 11:

[1497] The server optimizes the revised article again and sends it to the user. The user receives it again on their device and performs a final check of the article.

[1498] Step 12:

[1499] Once the user is satisfied with the article's content and signals the terminal to complete the review, the terminal sends that information to the server, and the process ends.

[1500] (Example 1)

[1501] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1502] Traditional SEO work is often done manually, making it time-consuming and labor-intensive, and thus inefficient. Furthermore, it is prone to inconsistencies in content quality and consistency, making it difficult to consistently generate high-quality content that is appropriate for the brand. Additionally, proofreading and revising the generated content is time-consuming and requires quick responses. This invention aims to automate these problems and improve efficiency and consistency.

[1503] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1504] In this invention, the server includes means for receiving brand information and market information, means for obtaining relevant keywords, means for calculating keyword efficiency, means for generating a keyword list, means for optimizing the generated article elements according to a style guide, means for revising the article based on revision instructions, and means for receiving revision completion instructions. This enables the automation and efficiency of SEO work, allowing for the rapid generation and revision of high-quality, consistent, and brand-appropriate content.

[1505] "Brand information" refers to identifiable information associated with a specific company, product, or service.

[1506] "Market information" refers to data and insights about a specific market or target audience.

[1507] A "keyword" refers to an important word or phrase related to a specific theme or topic.

[1508] "Keyword efficiency" is an efficiency metric calculated based on factors such as keyword search volume, competition level, and relevance.

[1509] "Article elements" refer to the constituent elements of content, such as the title and body text.

[1510] A "style guide" refers to guidelines regarding the writing style and tone of documents based on a specific brand or style.

[1511] "Tone" refers to the use of language to express the emotions and atmosphere of a text or content.

[1512] "Correction instructions" refer to instructions regarding changes or improvements to user-generated content.

[1513] A "correction completion instruction" refers to an instruction for the user to confirm that the corrected content is appropriate and to ultimately approve it.

[1514] A "generative AI model" refers to an artificial intelligence algorithm used for tasks such as text generation and data analysis.

[1515] To implement this invention, a system is required in which users, terminals, and servers work together. This system automates the streamlining of SEO work and the generation of high-quality content based on brand information and market information.

[1516] The overall system hardware configuration will consist of the user's PC or smartphone (device) and an AWS EC2 instance (server). The software will utilize MySQL as the database, OpenAI GPT as the generative AI model, and Django as the server-side framework.

[1517] Explanation in natural language

[1518] KW selection

[1519] 1. User input

[1520] Users input information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and send it to the server. Input is done through a dedicated form, and processing begins on the server after submission.

[1521] 2. Server processing - Retrieval of related keywords

[1522] The server retrieves relevant keywords from the MySQL database using queries based on the received brand and market information. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[1523] 3. Server Processing - Calculation and Listing of KW Efficiency

[1524] The server analyzes competitive information and search engine trend data for these keywords and calculates keyword efficiency based on each keyword's search volume, competitiveness, and relevance. For example, it uses the Google Trends API to retrieve data and assigns a weighted score to each keyword to calculate keyword efficiency. Keywords with high scores are then presented to the user as a list.

[1525] Article generation

[1526] 1. User Selection

[1527] The user selects the most suitable keyword (e.g., "diet food") from the provided keyword list and sends it to the server via their device. The user selects a keyword from the list and clicks the "Confirm" button to submit it.

[1528] 2. Server Processing - Information Gathering and Article Generation

[1529] The server uses a generative AI model such as OpenAI GPT-3 to collect relevant information based on selected keywords and then generates article elements based on that information. For example, it sends a prompt sentence like "Please tell me the latest information on diet foods" to the generative AI model and uses the obtained information to create a title and body text.

[1530] 3. Server Processing - Optimization Based on Tone and Style Guides

[1531] The server modifies the generated content to match the brand's tone and style guide (e.g., "casual and approachable"). It changes the style and expression of the generated text to ensure consistency and completes an optimized article for the user.

[1532] Proofreading

[1533] 1. User Verification

[1534] The generated article is sent from the server to the user, who then reviews the content on their device. If there are any problems with the content, the user uses the editing form on their device to enter correction instructions (e.g., "Please change the title to something more attention-grabbing") and sends them to the server.

[1535] 2. Server processing - Article revision

[1536] The server analyzes user correction instructions and automatically corrects the article using a generative AI model. For example, if there is a instruction regarding the title, it will regenerate the article using a prompt such as "Make the title more attention-grabbing."

[1537] 3. User's final confirmation and completion instructions

[1538] The user reviews the revised article again, and if they are finally satisfied, they indicate on their device that the review is complete. By pressing the "Complete" button, the user sends that information to the server, and the process officially ends.

[1539] Specific examples and prompt statements

[1540] Specific example

[1541] KW selection

[1542] Information entered by the user: Brand information "Health Foods", Target market information "Women in their 20s and 30s"

[1543] The server provides a list of keywords: diet foods, vitamin supplements, beauty supplements.

[1544] Article generation

[1545] Keywords selected by users: Diet foods

[1546] Articles generated by the server:

[1547] Title: "Easily Start Shaping Up with the Latest Diet Foods"

[1548] Text: "A must-see for those who want to lose weight healthily! Introducing the latest diet foods. These products are rich in vitamins and also effective for beauty."

[1549] Example of a prompt

[1550] "Please select highly efficient keywords based on health food brands and target market information for women in their 20s and 30s."

[1551] "Please write an article about diet foods. The title should be approachable and casual."

[1552] Thus, the system of the present invention automates a series of SEO tasks, from keyword selection to article generation and proofreading, significantly reducing the burden on the user and enabling efficient, consistent, and high-quality content generation.

[1553] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1554] Processing steps

[1555] KW selection

[1556] Step 1:

[1557] Users enter brand information and market information.

[1558] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and clicks the submit button. This information is then sent to the server.

[1559] Input: Brand information, market information

[1560] Output: Brand information and market information sent to the server

[1561] Step 2:

[1562] The server retrieves related keywords.

[1563] Based on the received brand and market information, the server retrieves relevant keywords from the MySQL database using queries. For example, for the brand information "health foods," it retrieves keywords such as "diet foods," "vitamin supplements," and "beauty supplements."

[1564] Input: Brand information, market information

[1565] Data processing / calculation: Retrieve relevant keywords from a MySQL database using queries.

[1566] Output: List of related keywords

[1567] Step 3:

[1568] The server calculates keyword efficiency and generates a keyword list.

[1569] The server analyzes the retrieved related keywords using the Google Trends API and other tools to determine the search volume, competition level, relevance, etc., and calculates keyword efficiency. Based on the calculation results, it selects high-scoring keywords and generates a keyword list.

[1570] Input: List of related keywords

[1571] Data processing / calculation: Analyze each keyword using the Google Trends API, etc., and calculate keyword efficiency.

[1572] Output: List of keywords with high KW efficiency

[1573] Article generation

[1574] Step 4:

[1575] The user selects and submits the most suitable keywords.

[1576] The user selects the most suitable keyword (e.g., "diet food") from the presented keyword list and sends it to the server via their device. The user selects a keyword and clicks the "Confirm" button.

[1577] Input: List of highly efficient keywords (KW)

[1578] Output: Optimal keywords sent to the server

[1579] Step 5:

[1580] The server collects information and generates article elements.

[1581] The server uses a generative AI model such as OpenAI GPT-3 to create a prompt based on the most suitable keywords it receives, and then collects relevant information based on that prompt. Specifically, it sends a prompt such as "Please tell me the latest information on diet foods" to the model, and then creates an article title and body based on the generated information.

[1582] Input: Best keyword

[1583] Data Processing / Calculation: Use a generative AI model to create prompt statements, collect information, and generate article elements.

[1584] Output: Generated article elements (title, body)

[1585] Step 6:

[1586] The server optimizes article elements.

[1587] The server adjusts the generated article elements based on the brand's tone and style guide, optimizing them to ensure consistency in writing style and content. For example, it might adjust the writing style to a "casual and approachable" tone.

[1588] Input: Generated article elements (title, body)

[1589] Data processing / calculation: Optimize article elements based on the brand's tone and style guide.

[1590] Output: Optimized article

[1591] Proofreading

[1592] Step 7:

[1593] Users review articles and submit correction requests.

[1594] The server sends an optimized article to the user. The user reviews the article on their device and, if necessary, enters correction instructions (e.g., "Make the title more eye-catching") and sends them to the server.

[1595] Input: Optimized article

[1596] Output: Correction instructions sent to the server

[1597] Step 8:

[1598] The server will modify the article.

[1599] The server analyzes the user's correction instructions and uses a generative AI model to revise the article. For example, in response to the instruction "Make the title more attention-grabbing," it regenerates the prompt as "Generate a more attention-grabbing title."

[1600] Input: Correction Instructions

[1601] Data processing / calculation: Regenerate and correct articles using a generative AI model.

[1602] Output: Corrected article

[1603] Step 9:

[1604] The user submits a correction completion instruction.

[1605] The user reviews the revised article again, and if they are finally satisfied, they send a correction completion notification from their device. By pressing the "Complete" button, the user sends that information to the server.

[1606] Input: Modified article

[1607] Output: Correction completion instruction sent to the server

[1608] (Application Example 1)

[1609] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1610] Traditional SEO and ad copy generation processes required significant time and effort for keyword selection, content creation, and ad copy creation based on brand and market information. Furthermore, verifying and adjusting whether the generated content aligned with brand tone and market trends was cumbersome, making it difficult to provide efficient, consistent, and high-quality content.

[1611] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1612] In this invention, the server includes means for receiving brand information and market information, means for acquiring relevant keywords, and means for calculating the keyword efficiency of the acquired keywords. This automates a series of processes, from keyword selection to article and ad copy generation, and style optimization and revision, enabling the efficient, consistent, and high-quality delivery of content and ad copy.

[1613] "Brand information" refers to information about the awareness and image of a particular company or product.

[1614] "Market information" refers to data and statistics related to a specific target market.

[1615] "Related keywords" are terms used by search engines to select keywords based on brand and market information.

[1616] "Keyword efficiency" is an efficiency metric calculated based on factors such as search volume, competition level, and relevance of related keywords.

[1617] A "keyword list" is a list of related keywords generated based on keyword efficiency.

[1618] "Article elements" refer to the constituent elements of an article, such as the title and body text, which are generated based on keywords.

[1619] A "style guide" is a set of guidelines designed to reflect a brand's tone and style.

[1620] "Correction instructions" are instructions from users to change or revise articles or ad copy.

[1621] "Ad copy" refers to marketing and promotional text generated using selected keywords.

[1622] To implement this invention, the following system is required. This system involves the user, terminal, and server working together to achieve the automated generation of efficient, consistent, and high-quality advertising content.

[1623] System Configuration

[1624] Servers, terminals, and users are the main components of the system.

[1625] server

[1626] The server performs the following roles:

[1627] 1. Receiving brand and market information: The system has a means of receiving brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35") entered by the user.

[1628] 2. Acquisition of related keywords: Based on the received brand information and market information, related keywords (e.g., "natural skincare", "additive-free cosmetics") are retrieved from the database.

[1629] 3. Calculation of Keyword Efficiency: Analyze the acquired related keywords, competitive information, and trend data from search engines to calculate keyword efficiency.

[1630] 4. Keyword List Generation: Based on the calculated keyword efficiency, list the most efficient keywords.

[1631] 5. Ad copy generation: Based on the most suitable keywords, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized to match the brand tone.

[1632] terminal

[1633] The terminal will perform the following roles:

[1634] 1. Input of brand and market information: Provide an interface for users to input brand and market information.

[1635] 2. Displaying the Keyword List: The keyword list received from the server is displayed to the user.

[1636] 3. Selection of optimal keywords: The user selects the most suitable keywords from the keyword list and sends them to the server.

[1637] 4. Viewing and modifying the generated ad copy: The user reviews the generated ad copy, enters any necessary modification instructions, and sends them to the server.

[1638] User

[1639] The user will play the following roles:

[1640] 1. Entering brand and market information: Use a terminal to enter brand and market information.

[1641] 2. Keyword Selection: Select the most suitable keyword from the keyword list sent from the server.

[1642] 3. Review and modify the ad copy: Review the generated ad copy and enter any necessary modification instructions.

[1643] Program processing

[1644] The server receives brand and market information via a REST API using the Python requests library. Search engine APIs and a proprietary database are used to retrieve relevant keywords. Pandas and NumPy, Python data analysis libraries, are used to calculate keyword efficiency.

[1645] For generating ad copy, a generative AI model (e.g., GPT-3) is used, utilizing the transformers library. This model is pre-trained, enabling high-quality text generation.

[1646] Specific example

[1647] For example, if you input brand information as "organic cosmetics" and market information as "women aged 25 to 35," the server will select related keywords such as "natural skincare" and "additive-free cosmetics." If you select "additive-free cosmetics" from these, the AI ​​model will generate an ad copy such as "Start gentle skincare with high-quality additive-free cosmetics!"

[1648] Examples of prompts in this system are as follows:

[1649] Please generate high-quality advertising copy using "additive-free cosmetics." The tone should be friendly and convey a trustworthy image.

[1650] As described above, this system enables the automated generation of high-quality advertising content efficiently and consistently.

[1651] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1652] Step 1:

[1653] Enter brand information and market information.

[1654] The user uses a device to input brand information (e.g., "organic cosmetics") and market information (e.g., "women aged 25 to 35"). The system then receives specific data related to the brand and market.

[1655] Input: Brand information and market information

[1656] Output: Brand information and market information sent to the server

[1657] Step 2:

[1658] Receive brand information and market information.

[1659] The server receives brand and market information transmitted from the terminal. This information serves as base data for obtaining relevant keywords.

[1660] Input: Brand and market information sent from the terminal.

[1661] Output: Brand information and market information stored on the server

[1662] Step 3:

[1663] Retrieving related keywords

[1664] Based on the brand and market information received by the server, it retrieves relevant keywords from search engine APIs and its own database. For example, it retrieves keywords related to "organic cosmetics" and "women aged 25 to 35."

[1665] Input: Brand information and market information

[1666] Output: List of related keywords (e.g., "natural skincare", "additive-free cosmetics")

[1667] Step 4:

[1668] Calculation of KW efficiency

[1669] The server calculates the keyword efficiency of the relevant keywords it retrieves. It collects data such as search volume, competition level, and relevance, and uses this data to calculate keyword efficiency.

[1670] Input: Related Keyword List

[1671] Output: Keyword list for which KW efficiency was calculated

[1672] Step 5:

[1673] Keyword list generation

[1674] The server lists high-efficiency keywords based on keyword efficiency. The listed keywords are sent to the terminal and displayed to the user.

[1675] Input: Keyword used to calculate KW efficiency

[1676] Output: Optimal keyword list

[1677] Step 6:

[1678] Selecting and submitting the most suitable keywords

[1679] The user clicks or selects the most relevant keyword (e.g., "additive-free cosmetics") and sends it from their device to the server.

[1680] Input: Best keyword

[1681] Output: Optimal keywords sent to the server

[1682] Step 7:

[1683] Generating ad copy

[1684] Based on the optimal keywords received by the server, ad copy is generated using a generative AI model (e.g., GPT-3). The generated ad copy is optimized based on pre-configured brand tone and style guides.

[1685] Input: Best keyword

[1686] Output: Generated ad copy

[1687] Step 8:

[1688] Display the generated ad copy and enter instructions for modification.

[1689] The user reviews the generated ad copy using their device and enters correction instructions as needed. These correction instructions are then sent from the device to the server.

[1690] Input: Generated ad copy

[1691] Output: Correction instructions

[1692] Step 9:

[1693] Ad copy revision

[1694] The server modifies the ad copy based on the correction instructions received from the user. The modified ad copy is then optimized again and sent to the device.

[1695] Input: Correction Instructions

[1696] Output: Revised ad copy

[1697] Step 10:

[1698] Display of revised ad text

[1699] The revised ad copy is finally displayed on the device for the user to review. At this point, the user can make a final review and request further revisions if necessary.

[1700] Input: Revised ad copy

[1701] Output: Final approved ad copy

[1702] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1703] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[1704] 1. KW selection

[1705] The user inputs information about their brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into a terminal and sends it to the server. Based on the received brand and market information, the server retrieves relevant keywords (e.g., "diet foods," "vitamin supplements," "beauty supplements") from its database. Next, the server analyzes the retrieved relevant keywords with competitive information and trend data from search engines, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword. Finally, the server lists the keywords with high keyword efficiency and presents them to the user.

[1706] 2. Emotion recognition

[1707] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. For example, if the user is showing positive emotions, the emotion engine sends that information to the server. Based on this emotion recognition result, the server dynamically changes the content and ranking of the keyword list it presents.

[1708] 3. Article generation

[1709] When a user selects the most relevant keyword from a list (e.g., "diet foods"), the device sends that keyword to the server. Based on the received keyword, the server gathers information using relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text). It also adjusts the tone and style of the article to match the user's emotions based on feedback from the sentiment engine. For example, if the user expresses positive emotions, the server will adopt a positive and motivational tone.

[1710] 4. Proofreading

[1711] The generated article is sent from the server to the user, who reviews the content on their device. If there are any problems with the content, the user enters correction instructions (e.g., "Make the title more impactful") on their device and sends them to the server. The server analyzes the user's correction instructions and automatically corrects the generated article. For example, it might change the title to "This is the trending diet food right now! Worth trying." Then, it optimizes the corrected article and sends it back to the user. Once the user reviews the corrected article and finally signals on their device that the review is complete, the device sends that information to the server, and the process ends.

[1712] In this way, the entire system's specific operation automates a series of SEO tasks, from keyword selection to proofreading, and also enables content personalization based on user sentiment. This significantly reduces the burden on users and enables the efficient, consistent, and high-quality generation of content.

[1713] The following describes the processing flow.

[1714] Step 1:

[1715] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[1716] Step 2:

[1717] Based on the received brand and market information, the server retrieves relevant keywords (e.g., "dietary foods," "vitamin supplements," "beauty supplements") from the database.

[1718] Step 3:

[1719] The server analyzes competitive information and trend data from search engines for the retrieved related keywords, and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[1720] Step 4:

[1721] The server compiles a list of highly efficient keywords and presents it to the user.

[1722] Step 5:

[1723] The user checks a list of keywords via their device and selects the most suitable keyword (e.g., "diet foods").

[1724] Step 6:

[1725] The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state and sends the results to the server. For example, if the user is showing positive emotions, that information is transmitted to the server.

[1726] Step 7:

[1727] The server dynamically changes the content and order of the keyword list it presents based on feedback from the emotion engine. For example, it prioritizes presenting keywords with a positive tone to users who express positive emotions.

[1728] Step 8:

[1729] The user selects the most suitable keywords and sends them to the server via their device.

[1730] Step 9:

[1731] The server collects information based on the received keywords, utilizing relevant databases and pre-trained models, and then generates article elements (e.g., title, headings, body text) based on that information.

[1732] Step 10:

[1733] Based on feedback from the emotion engine, the server adjusts the tone and style of the generated article to match the user's emotions. For example, if the user is expressing positive emotions, the entire article will be adjusted to a positive and motivational tone.

[1734] Step 11:

[1735] The server sends the optimized article to the user, who receives it on their device.

[1736] Step 12:

[1737] The user reviews the generated article on their device and enters correction instructions as needed (e.g., "Make the title more impactful").

[1738] Step 13:

[1739] The terminal sends the user's correction instructions to the server.

[1740] Step 14:

[1741] The server analyzes user correction requests and automatically modifies the generated articles. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[1742] Step 15:

[1743] The server optimizes the revised article again and sends it to the user. The user receives it again on their device and performs a final review of the article.

[1744] Step 16:

[1745] Once the user is satisfied with the article's content and signals the terminal to complete the review, the terminal sends that information to the server, and the process ends.

[1746] (Example 2)

[1747] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1748] In SEO work, the process from keyword selection to article generation and proofreading is extremely time-consuming and labor-intensive, and there are challenges in generating content that is appropriate for user sentiment and brand tone. Furthermore, there is a need to efficiently generate high-quality content by appropriately reflecting user input and sentiment analysis results.

[1749] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1750] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the KW efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated KW efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for generating article elements based on the received keyword; means for analyzing the user's sentiment based on feedback from the sentiment engine; means for adjusting the tone and style of the article based on the analysis results of the user's sentiment state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables the efficient automation of a series of SEO tasks from keyword selection to article generation and proofreading, and makes it possible to generate content based on the user's sentiment.

[1751] "Brand information" refers to information about a specific brand provided by the user, including the characteristics, value, and positioning of the product or service.

[1752] "Market information" refers to information about a specific market that a user has, including target audience, competitive landscape, and trends.

[1753] "Related keywords" are words and phrases that are extracted based on brand information and market information and are considered effective for SEO.

[1754] "Keyword efficiency" is an index that comprehensively evaluates factors such as search volume, competition level, and relevance for related keywords.

[1755] A "keyword list" refers to a list of related keywords ranked based on calculated keyword efficiency.

[1756] An "emotion engine" is an analytical device or software that recognizes emotions by analyzing the user's facial expressions, voice tone, and other factors.

[1757] "Article elements" refer to the various components that make up an article, such as the title, headings, body text, and images.

[1758] A "style guide" refers to instructions or guidelines regarding the style and tone of an article or piece of writing.

[1759] "User sentiment" refers to the emotional response a user shows to a particular situation or content, and includes positive, negative, and neutral reactions.

[1760] A "correction instruction" is a specific request for changes made by a user to the content of an article they have generated.

[1761] "Optimization" refers to the process of adjusting generated content to make it higher quality and more effective.

[1762] To implement this invention, it is necessary to build a system in which the user, terminal, server, and emotion engine work together in cooperation with each other. The following describes how to implement this system in detail.

[1763] First, users access the system via a terminal. This terminal is essentially a computer or smartphone, providing an interface for users to input information. This terminal displays forms for entering brand and market information.

[1764] When a user enters specific information such as "health foods" or "women in their 20s and 30s," the device sends that information to the server. Upon receiving this brand and market information, the server retrieves relevant keywords from its database based on that information.

[1765] The server calculates the keyword efficiency of acquired keywords by analyzing search engine trend data and competitive information. This analysis utilizes natural language processing and machine learning techniques. Based on the calculated keyword efficiency, the server lists the most efficient keywords and presents this list to the user.

[1766] Next, the system selects the most suitable keywords from the user's provided keyword list. During this process, the emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotional state. The emotion engine then collects necessary data using input devices such as cameras and microphones.

[1767] The emotion engine analyzes the emotion data, which is then sent to the server. Based on this data, the server dynamically changes the ranking and content of the keyword list. When the user selects the most suitable keyword (e.g., "diet food"), that keyword is sent back to the server from the device.

[1768] Based on the received keywords, the server utilizes relevant databases and pre-trained models (e.g., generative AI models) to generate article elements (e.g., title, headings, body text). During this process, the tone and style of the article are adjusted based on feedback from the sentiment engine. For example, if a user expresses positive emotions, the server generates an article with a positive and motivational tone.

[1769] The generated article is sent from the server to the user's terminal, where the user reviews the content. If improvements are needed, the user enters correction instructions on their terminal and sends them to the server. The server analyzes these instructions and automatically corrects the article. The corrected article is sent back to the user for final review. Once the user approves it, the process is complete.

[1770] For example, if you input information about "health foods," the server will suggest keywords such as "diet foods" and "beauty supplements," and as a result generate articles such as "Latest Trends in Diet Foods."

[1771] Example of a prompt:

[1772] "Please generate an article about the latest trends in health foods targeting women in their 20s and 30s."

[1773] In this way, the entire system flexibly responds based on user input and sentiment analysis, enabling the automatic generation of high-quality content. This efficiently automates SEO tasks and significantly reduces the burden on users.

[1774] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1775] Step 1:

[1776] The user enters information about their company's brand (e.g., "health foods") and target market information (e.g., "women in their 20s and 30s") into the terminal and sends it to the server.

[1777] Input: Brand information and market information

[1778] Output: Data to send to the server

[1779] Step 2:

[1780] The server retrieves relevant keywords from the database based on the received brand and market information. For example, from the brand information "health foods" and the market information "women in their 20s and 30s," keywords such as "diet foods," "vitamin supplements," and "beauty supplements" are retrieved.

[1781] Input: Received brand information and market information

[1782] Output: List of related keywords

[1783] Step 3:

[1784] The server analyzes the retrieved relevant keywords, along with competitive information and trend data from search engines, to calculate keyword efficiency. This calculation uses data such as search volume, competition level, and relevance.

[1785] Input: Related keyword list, competitor information, search engine trend data

[1786] Output: Keyword list for calculating kW efficiency

[1787] Step 4:

[1788] The server generates a keyword list based on calculated keyword efficiency and presents it to the user. The most efficient keywords are displayed at the top.

[1789] Input: Keyword list used to calculate KW efficiency

[1790] Output: List of keywords presented to the user

[1791] Step 5:

[1792] The user selects the most suitable keyword from the presented keyword list and sends it to the server via their device. For example, if the user selects the keyword "diet food," that selection data will be sent.

[1793] Input: List of keywords presented to the user

[1794] Output: Selection data for optimal keywords

[1795] Step 6:

[1796] The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotional state. The emotion engine uses the camera and microphone to generate emotional data such as positive, negative, and neutral, and sends this data to the server.

[1797] Input: User's facial expressions and voice tone acquired from camera and microphone.

[1798] Output: User sentiment data

[1799] Step 7:

[1800] The server dynamically changes the ranking and content of the keyword list it presents based on sentiment data. For example, if a user selects "diet foods" and expresses a positive sentiment, positive keywords will be displayed preferentially.

[1801] Input: User sentiment data

[1802] Output: Dynamically changed keyword list

[1803] Step 8:

[1804] The user sends the keyword they ultimately selected to the server. Here, the keyword "diet food" is confirmed.

[1805] Input: Dynamically changed keyword list

[1806] Output: The keywords that were ultimately selected

[1807] Step 9:

[1808] Based on the received keywords, the server utilizes relevant databases and a pre-trained generative AI model to generate article elements (e.g., title, headings, body text). For example, an article titled "Latest Trends in Diet Foods" might be generated.

[1809] Input: Final selected keywords

[1810] Output: Generated article elements

[1811] Step 10:

[1812] Based on feedback from the emotion engine, the server adjusts the tone and style of the article to match the user's emotions. For positive emotions, a motivational tone is generated.

[1813] Input: Generated article elements, user sentiment data

[1814] Output: Articles adjusted to match emotions

[1815] Step 11:

[1816] The generated article is sent from the server to the user's terminal, where the user reviews the content.

[1817] Input: Articles adjusted to match emotions

[1818] Output: Articles displayed on the user's device

[1819] Step 12:

[1820] If a user finds the content problematic, they input correction instructions into their terminal and send them to the server. For example, a correction instruction might be, "Change the title to something more impactful."

[1821] Input: User's correction instructions

[1822] Output: Correction instruction data to the server

[1823] Step 13:

[1824] The server analyzes the correction instructions and automatically modifies the article. For example, it might change the title to "Diet Revolution! This is the food that's all the rage right now!"

[1825] Input: Correction instruction data

[1826] Output: Corrected article

[1827] Step 14:

[1828] The revised article is sent back to the user for final review. If approved, the process ends.

[1829] Input: Modified article

[1830] Output: Last article displayed to the user

[1831] (Application Example 2)

[1832] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1833] Current content generation systems often produce content uniformly without considering the user's emotional state, making personalization to match the tone and style the user desires difficult. While some degree of keyword selection efficiency and automated article generation has been achieved, dynamic selection and adjustment of ad copy based on user emotions remains lacking. Therefore, there is a need for a system that dynamically adjusts the tone and style of content based on user input and emotional state, automatically generating and revising optimal keywords and high-quality articles.

[1834] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1835] In this invention, the server includes means for receiving brand information and market information; means for obtaining relevant keywords based on the received brand information and market information; means for calculating the keyword efficiency of the obtained relevant keywords; means for generating a keyword list based on the calculated keyword efficiency; means for displaying the generated keyword list; means for receiving the optimal keyword; means for recognizing the user's emotional state; means for dynamically changing the content and ranking of the displayed keyword list based on the recognized emotional state; means for generating article elements based on the received keywords; means for adjusting the tone and style of the article based on the user's emotional state; means for optimizing the generated article elements according to a style guide; means for displaying the optimized article; means for receiving correction instructions for the displayed article; means for correcting the article based on the correction instructions; and means for displaying the corrected article. This enables dynamic keyword selection and personalized content generation based on the user's input information and emotional state.

[1836] "Brand information" refers to basic information about a company or product, and is an element that expresses its characteristics and value.

[1837] "Market information" refers to data about a specific target group or market environment, and is information used to understand customer interests and demand trends.

[1838] "Related keywords" are keywords selected based on brand information and market information, taking into account search frequency and level of competition on search engines.

[1839] "Keyword efficiency" is an indicator that evaluates the effectiveness of keywords by calculating their search volume, competition level, and relevance.

[1840] A "keyword list" is a list of relevant keywords that should be used, generated based on keyword efficiency.

[1841] "Emotional state" refers to the psychological state perceived from the user's facial expressions, tone of voice, and other factors.

[1842] "Article elements" are the elements that make up each part of the generated content (title, headings, body text, etc.).

[1843] A "style guide" is a set of guidelines for maintaining a consistent tone and style in an article.

[1844] A "correction instruction" is a user's instruction to change or improve an article they have generated.

[1845] "Personalization" refers to adjusting the content and presentation of content according to the individual needs and preferences of the user.

[1846] To implement this invention, the following system is required. This system involves the user, terminal, server, and emotion engine working together to streamline SEO operations and automatically generate high-quality, brand-optimized content.

[1847] First, the user enters brand and market information into their device and sends it to the server. The server retrieves relevant keywords based on the received information and calculates keyword efficiency. This is done using SEO analysis tools such as the Ahrefs API. Based on the calculated keyword efficiency, the server generates a keyword list and displays it on the device.

[1848] When a user selects keywords, the emotion engine analyzes the user's facial expressions and tone of voice in real time to recognize their emotional state. This emotion engine utilizes Google Cloud's Emotion API. Based on the recognized emotional state, the server dynamically changes the content and ranking of the displayed keyword list. For example, if a user is showing positive emotions, positive and motivational keywords will be displayed higher.

[1849] Based on selected keywords, the server generates article elements. This uses generative AI models such as GPT-3 and ChatGPT. Furthermore, the tone and style of the article are adjusted based on the user's sentiment information. For example, if the user expresses positive sentiment, the article will be generated with a motivational tone. The generated article elements are optimized according to the company's style guide and displayed on the device.

[1850] The user reviews the generated article and enters correction instructions if necessary. The server re-edits the article based on these instructions and displays it to the user again. Natural language processing technology is used for the re-editing to accurately reflect the user's intentions for correction. The writing style of the revised article is automatically adjusted to match the brand tone.

[1851] The following are specific examples and examples of prompts for the generative AI model:

[1852] Specific example:

[1853] For example, suppose a marketing manager for a sports brand uses this system. The user inputs information such as "sportswear" and "male in his teens and twenties," and the server provides related keywords such as "running shoes" and "training gear." If the emotion engine recognizes the user's excitement, it generates a positive and motivational article, creating text with a tone like, "Get your best performance out of these running shoes!"

[1854] Examples of prompts for a generative AI model:

[1855] Keywords: Diet foods

[1856] User sentiment: Positive

[1857] Output style: Motivational

[1858] Prompt: Write a positive and motivational article about diet foods.

[1859] Title: This is the trending diet food right now! It's worth trying.

[1860] Introduction: If you want to succeed in your diet, you should definitely try incorporating this food into your diet. The secret to healthy weight loss lies here.

[1861] In this way, it becomes possible to personalize dynamic keyword selection and content generation based on user input information and emotional state.

[1862] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1863] Step 1:

[1864] The user enters brand and market information into their device and sends it to the server.

[1865] Input: Brand information (e.g., sportswear), market information (e.g., men in their teens and twenties)

[1866] Output: Input information is sent to the server.

[1867] Specific operation: The user enters brand information and market information into the input form on the device and presses the "Submit" button. The device sends the input data to the server as an HTTP request.

[1868] Step 2:

[1869] The server retrieves relevant keywords based on the brand and market information it receives.

[1870] Input: Received brand information and market information

[1871] Output: List of related keywords (e.g., running shoes, training gear)

[1872] Specific operation: The server uses external SEO tools such as the Ahrefs API to search the database for keywords related to brand information and market information, and retrieves the relevant keywords.

[1873] Step 3:

[1874] The server calculates the keyword efficiency of the relevant keywords it has acquired and generates a keyword list based on that.

[1875] Input: List of related keywords

[1876] Output: Keyword list ranked based on KW efficiency

[1877] Specific operation: The server calculates the search volume, competition level, and relevance of each keyword, and then calculates keyword efficiency by combining these metrics. After that, keywords are ranked and listed based on keyword efficiency.

[1878] Step 4:

[1879] The server generates a list of keywords, which is then displayed on the terminal.

[1880] Input: Ranked keyword list

[1881] Output: Keyword list displayed on the terminal screen

[1882] Specific operation: The server sends the completed keyword list to the terminal, which receives this information and displays it on the screen.

[1883] Step 5:

[1884] When a user selects a keyword, the emotion engine recognizes the user's emotional state.

[1885] Input: User's facial expressions and tone of voice

[1886] Output: User's emotional state (e.g., positive)

[1887] Specific operation: The device uses its built-in camera and microphone to capture the user's facial expressions and voice, and then uses Google Cloud's Emotion API to analyze their emotional state.

[1888] Step 6:

[1889] The server dynamically changes the content and ranking of the displayed keyword list based on the recognized emotional state.

[1890] Input: User's emotional state, original keyword list

[1891] Output: Dynamically changed keyword list

[1892] Specific operation: The server receives the user's emotional state and reconstructs the keyword list based on it. For example, if the emotional state is positive, motivational keywords will be placed at the top.

[1893] Step 7:

[1894] The user selects keywords and sends them to the server.

[1895] Input: User-selected keyword

[1896] Output: The selected keywords are sent to the server.

[1897] Specific operation: The user selects their desired keyword from the displayed keyword list and presses the "Select" button. This data is sent to the server.

[1898] Step 8:

[1899] The server generates article elements based on the keywords it receives.

[1900] Input: Selected keywords

[1901] Output: Generated article elements (e.g., title, headings, body text)

[1902] Specific operation: The server uses generative AI models such as GPT-3 and ChatGPT to automatically generate article components based on selected keywords.

[1903] Step 9:

[1904] The server adjusts the tone and style of the article based on the user's emotions.

[1905] Input: Generated article elements, user's sentiment state

[1906] Output: Adjusted article

[1907] Specific operation: The generated article elements are adjusted to reflect the user's emotional state (e.g., positive), and their tone and style are modified accordingly. For example, if the emotional state is positive, the overall tone of the article is made more motivational.

[1908] Step 10:

[1909] The server displays optimized articles on the device.

[1910] Input: Adjusted article

[1911] Output: Article displayed on the terminal screen

[1912] Specific operation: The server sends an optimized article to the terminal, which receives it and displays it to the user.

[1913] Step 11:

[1914] The user enters correction instructions for an article and sends that data to the server.

[1915] Input: Correction instructions (e.g., title change, content addition)

[1916] Output: Correction instructions are sent to the server.

[1917] Specific operation: The user reviews the displayed article, enters the necessary corrections into the terminal's editor, and presses the "Submit" button. The correction instructions are sent to the server as an HTTP request.

[1918] Step 12:

[1919] The server corrects the article based on the correction instructions.

[1920] Input: Correction instructions, article generated just a moment ago

[1921] Output: Corrected article

[1922] Specific operation: The server uses natural language processing technology to analyze user correction instructions and rewrite the article. For example, it might change the title to "This is the trending diet food right now! Worth trying."

[1923] Step 13:

[1924] The server will redisplay the corrected article on your device.

[1925] Input: Modified article

[1926] Output: Correction article displayed on the terminal screen

[1927] Specific operation: The server sends the corrected article to the terminal, which receives it and displays it to the user again.

[1928] 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.

[1929] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1930] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1931] 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.

[1932] Figure 9 shows an 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.

[1933] 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.

[1934] 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.

[1935] 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, motorcycles, etc., 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, for example, based 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.

[1936] 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."

[1937] 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.

[1938] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1939] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1940] 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.

[1941] 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.

[1942] 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.

[1943] 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.

[1944] 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.

[1945] 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.

[1946] 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.

[1947] 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 the like 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.

[1948] 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.

[1949] The following is further disclosed regarding the embodiments described above.

[1950] (Claim 1)

[1951] Means for receiving brand information and market information,

[1952] A means of obtaining relevant keywords based on received brand information and market information,

[1953] A means for calculating the KW efficiency of the acquired related keywords,

[1954] A means for generating a keyword list based on calculated KW efficiency,

[1955] A means of displaying the generated keyword list,

[1956] A means of receiving the most suitable keywords,

[1957] A means for generating article elements based on received keywords,

[1958] A means of optimizing generated article elements according to a style guide,

[1959] A means of displaying optimized articles,

[1960] A means of receiving instructions to correct the displayed article,

[1961] Means of revising articles based on revision instructions,

[1962] A means of displaying the corrected article,

[1963] A system that includes this.

[1964] (Claim 2)

[1965] The system according to claim 1, which takes into account competitive information and search engine trend analysis in selecting the optimal keywords.

[1966] (Claim 3)

[1967] The system according to claim 1, which automatically adjusts the writing style of a revised article to match the brand tone.

[1968] "Example 1"

[1969] (Claim 1)

[1970] Means for receiving brand information and market information,

[1971] A means of obtaining relevant keywords based on received brand information and market information,

[1972] A means for calculating the KW efficiency of the acquired related keywords,

[1973] A means for generating a keyword list based on calculated KW efficiency,

[1974] A means of displaying the generated keyword list,

[1975] A means of receiving the most suitable keywords,

[1976] A means for generating article elements based on received keywords,

[1977] A means of optimizing generated article elements according to a style guide,

[1978] A means of displaying optimized articles,

[1979] A means of receiving instructions to correct the displayed article,

[1980] Means of revising articles based on revision instructions,

[1981] A means of displaying the corrected article,

[1982] A means for receiving instructions that the correction is complete,

[1983] A system that includes this.

[1984] (Claim 2)

[1985] The system according to claim 1, which analyzes competitive information and search engine trend data and calculates keyword efficiency based on the search volume, level of competition, and relevance of each keyword.

[1986] (Claim 3)

[1987] The system according to claim 1, which automatically performs a process to optimize the generated article elements based on a specific tone and style guide.

[1988] "Application Example 1"

[1989] (Claim 1)

[1990] Means for receiving brand information and market information,

[1991] A means of obtaining relevant keywords based on received brand information and market information,

[1992] A means for calculating the KW efficiency of the acquired related keywords,

[1993] A means for generating a keyword list based on calculated KW efficiency,

[1994] A means of displaying the generated keyword list,

[1995] A means of receiving the most suitable keywords,

[1996] A means for generating article elements based on received keywords,

[1997] A means of optimizing generated article elements according to a style guide,

[1998] A means of displaying optimized articles,

[1999] A means of receiving instructions to correct the displayed article,

[2000] Means of revising articles based on revision instructions,

[2001] A means of displaying the corrected article,

[2002] A means of generating ad copy using keywords selected based on brand information and market information,

[2003] A means of displaying the generated ad copy,

[2004] A system that includes this.

[2005] (Claim 2)

[2006] The system according to claim 1, which takes into account competitive information and search engine trend analysis in selecting the optimal keywords.

[2007] (Claim 3)

[2008] The system according to claim 1, which automatically adjusts the writing style of revised articles and advertisements to match the brand tone.

[2009] "Example 2 of combining an emotion engine"

[2010] (Claim 1)

[2011] Means for receiving brand information and market information,

[2012] A means of obtaining relevant keywords based on received brand information and market information,

[2013] A means for calculating the KW efficiency of the acquired related keywords,

[2014] A means for generating a keyword list based on calculated KW efficiency,

[2015] A means of displaying the generated keyword list,

[2016] A means of receiving the most suitable keywords,

[2017] A means for generating article elements based on received keywords,

[2018] A means of analyzing user emotions based on feedback from the emotion engine,

[2019] A means of adjusting the tone and style of an article based on the analysis of the user's emotional state,

[2020] A means of optimizing generated article elements according to a style guide,

[2021] A means of displaying optimized articles,

[2022] A means of receiving instructions to correct the displayed article,

[2023] Means of revising articles based on revision instructions,

[2024] A means of displaying the corrected article,

[2025] A system that includes this.

[2026] (Claim 2)

[2027] The system according to claim 1, which, in selecting the optimal keywords, takes into account competitive information and search engine trend analysis, and presents them based on the results of user sentiment analysis.

[2028] (Claim 3)

[2029] The system according to claim 1, which automatically adjusts the writing style of a revised article to match the brand tone and user sentiment.

[2030] "Application example 2 when combining with an emotional engine"

[2031] (Claim 1)

[2032] Means for receiving brand information and market information,

[2033] A means of obtaining relevant keywords based on received brand information and market information,

[2034] A means for calculating the KW efficiency of the acquired related keywords,

[2035] A means for generating a keyword list based on calculated KW efficiency,

[2036] A means of displaying the generated keyword list,

[2037] A means of receiving the most suitable keywords,

[2038] A means of recognizing the user's emotional state,

[2039] A means of dynamically changing the content and ranking of the keyword list displayed based on the recognized emotional state,

[2040] A means for generating article elements based on received keywords,

[2041] A means of adjusting the tone and style of an article based on the user's emotions,

[2042] A means of optimizing generated article elements according to a style guide,

[2043] A means of displaying optimized articles,

[2044] A means of receiving instructions to correct the displayed article,

[2045] Means of revising articles based on revision instructions,

[2046] A means of displaying the corrected article,

[2047] A system that includes this.

[2048] (Claim 2)

[2049] The system according to claim 1, which takes into account competitive information and search engine trend analysis in selecting the optimal keywords.

[2050] (Claim 3)

[2051] The system according to claim 1, which automatically adjusts the writing style of a revised article to match the brand tone. [Explanation of Symbols]

[2052] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for receiving brand information and market information, A means of obtaining relevant keywords based on received brand information and market information, A means for calculating the KW efficiency of the acquired related keywords, A means for generating a keyword list based on calculated KW efficiency, A means of displaying the generated keyword list, A means of receiving the most suitable keywords, A means for generating article elements based on received keywords, A means of optimizing generated article elements according to a style guide, A means of displaying optimized articles, A means of receiving instructions to correct the displayed article, Means of revising articles based on revision instructions, A means of displaying the corrected article, A system that includes this.

2. The system according to claim 1, which takes into account competitive information and search engine trend analysis in selecting the optimal keywords.

3. The system according to claim 1, which automatically adjusts the writing style of a revised article to match the brand tone.

Images