system

Abstract

The system according to this embodiment aims to automatically generate the most suitable web page based on information provided by the user. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, and an output unit. The reception unit receives information provided by the user. The generation unit generates a web page that satisfies specific conditions based on the information received by the reception unit. The output unit outputs the web page generated by the generation unit.

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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, automatic generation of web pages based on information provided by users has not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically generate an optimal web page based on information provided by a user.

Means for Solving the Problems

[0006] The system according to the embodiment includes a reception unit, a generation unit, and an output unit. The reception unit receives information provided by a user. The generation unit generates a web page that satisfies specific conditions based on the information received by the reception unit. The output unit outputs the web page generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate an optimal web page based on information provided by the user. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. 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).

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

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The webpage automatic generation support system according to an embodiment of the present invention is an AI assistant that automatically generates webpages based on information provided by the user, optimizing them with consideration for SEO and usability. In this system, the reception unit receives information provided by the user, and the generation unit generates webpages that meet specific conditions based on this information. The generation unit includes an SEO optimization unit and a usability optimization unit, optimizing from both an SEO and usability perspective. The generated webpages are output by the output unit and published by the publication unit. Based on the access status of the published webpages, the update unit updates the webpages and optimizes them by tracking the user's eye movements. As a result, users can easily automatically generate optimized webpages that take SEO and usability into consideration. Thus, the webpage automatic generation support system can automatically generate optimized webpages based on information provided by the user.

[0029] The webpage automatic generation support system according to the embodiment comprises a reception unit, a generation unit, and an output unit. The reception unit receives information provided by the user. For example, the reception unit can receive text information and image information entered by the user. The reception unit can also receive voice input. For example, it can use speech recognition technology to convert the user's voice into text and receive it as information. The generation unit generates a webpage that satisfies specific conditions based on the information received by the reception unit. For example, the generation unit uses a generation AI to generate the webpage layout and content based on the user's information. The generation unit includes an SEO optimization unit and a usability optimization unit, performing optimization from both an SEO and usability perspective. The output unit outputs the webpage generated by the generation unit. For example, the output unit can output the generated webpage in HTML format. The output unit can also output in PDF format or image format. Thus, the webpage automatic generation support system according to the embodiment can automatically generate an optimized webpage based on information provided by the user.

[0030] The reception desk receives information provided by the user. Specifically, it can receive text and image information entered by the user. For example, when a user enters the title, content, and image files of a webpage into an input form, this information is sent to the reception desk. The reception desk can also accept voice input. Using speech recognition technology, it can convert the user's voice into text and receive it as information. For example, when a user speaks into a microphone, their voice is converted into text in real time and sent to the reception desk. Furthermore, the reception desk has a function to verify the format and content of the information provided by the user and display error messages as needed. For example, if the image file format is not supported or the text information is incomplete, it can display an appropriate error message to the user and prompt them to re-enter the information. This allows the reception desk to receive information provided by the user accurately and efficiently.

[0031] The generation unit generates web pages that meet specific conditions based on information received by the reception unit. Specifically, it uses generation AI to generate the layout and content of web pages based on user information. For example, the generation AI uses natural language processing technology to analyze the text information provided by the user and automatically generates appropriate headings and paragraph structures. It also uses image recognition technology to analyze the content of provided images and determine the optimal placement and size. Furthermore, the generation unit is equipped with an SEO optimization unit and a usability optimization unit, performing optimization from both an SEO and usability perspective. The SEO optimization unit, for example, appropriately places keywords and generates meta tags to improve search engine rankings. The usability optimization unit, for example, simplifies navigation and applies responsive design to ensure users can comfortably browse web pages. As a result, the generation unit can automatically generate optimal web pages that consider both SEO and usability based on the information provided by the user.

[0032] The output unit outputs the web pages generated by the generation unit. Specifically, it can output the generated web pages in HTML format. The HTML output is optimized for display in web browsers, allowing users to immediately publish the web pages they have generated. The output unit can also output in PDF format and image format. The PDF output is suitable for printing and offline viewing, while the image output can be used as screenshots or thumbnails of the web pages. Furthermore, the output unit also has a function to save the generated web pages to cloud storage. This allows users to access the generated web pages anytime, anywhere. For example, the output unit can automatically upload the generated web pages to a specified cloud storage service and provide the user with a download link. This allows the output unit to output generated web pages in various formats, enabling flexible responses to the user's needs.

[0033] The generation unit comprises an SEO optimization unit that adjusts web pages from an SEO perspective and a usability optimization unit that adjusts web pages from a usability perspective. The SEO optimization unit, for example, optimizes keywords. Based on information provided by the user, the SEO optimization unit selects appropriate keywords and places them on the web page. The SEO optimization unit can also set meta tags. For example, it sets meta descriptions and meta keywords to optimize for search engines. The usability optimization unit, for example, makes adjustments to improve the ease of navigation. Based on information provided by the user, the usability optimization unit designs an intuitive and easy-to-use navigation menu. The usability optimization unit can also apply responsive design. For example, it generates designs that are compatible with different devices such as smartphones and tablets. This makes it possible to generate web pages that are optimized from both an SEO and usability perspective.

[0034] The generation unit includes a template suggestion unit that proposes an appropriate template to the user from among multiple templates. The template suggestion unit, for example, proposes industry-specific templates. Based on the information provided by the user, the template suggestion unit selects and proposes the most suitable industry-specific template. Furthermore, the template suggestion unit can also propose templates that consider design consistency. For example, it can propose a design template that matches the user's brand image. In addition, the template suggestion unit can analyze the user's past selection history and propose the most suitable template. For example, it can propose the most suitable template based on templates the user has previously selected. This allows the system to propose the most suitable template to the user.

[0035] The SEO optimization unit includes an estimation unit that estimates the algorithm of a specific search engine, and performs adjustments based on the algorithm estimated by the estimation unit. For example, the estimation unit estimates the algorithm of Google®. Based on information provided by the user, the estimation unit estimates Google's algorithm and provides it to the SEO optimization unit. The estimation unit can also estimate the algorithm of Bing®. For example, it analyzes Bing's algorithm and provides it to the SEO optimization unit. Furthermore, the estimation unit can also estimate the algorithm of Yahoo®. For example, it analyzes Yahoo's algorithm and provides it to the SEO optimization unit. This allows for SEO optimization based on the algorithm of a specific search engine.

[0036] The usability optimization unit includes a data collection unit that collects user behavior data and makes adjustments based on the data collected by the data collection unit. For example, the data collection unit collects click data. Based on information provided by the user, the data collection unit collects user click data and provides it to the usability optimization unit. The data collection unit can also collect page dwell time. For example, it collects the time a user spends on a particular page and provides it to the usability optimization unit. Furthermore, the data collection unit can also collect scroll data. For example, it collects data on when a user scrolls a page and provides it to the usability optimization unit. This allows usability to be optimized based on user behavior data.

[0037] The generation unit inputs information received by the reception unit, information including the algorithm of a specific search engine, and information regarding usability into the generation AI, causing the generation AI to generate web pages that meet specific conditions. The generation AI generates web pages using, for example, a specific machine learning model. The generation AI generates web pages that meet specific conditions based on the information provided by the user. The generation AI can also learn using training datasets and generate optimal web pages. For example, the generation AI learns from a large amount of web page data and generates optimal layouts and content. This allows the generation AI to generate web pages that meet specific conditions.

[0038] The generation unit comprises a publishing unit that publishes web pages and an updating unit that updates web pages based on the access status of the web pages published by the publishing unit. The publishing unit, for example, publishes the generated web pages on the internet. The publishing unit publishes web pages based on information provided by users. The publishing unit can also publish web pages on specific platforms. For example, the publishing unit publishes web pages on website or blog platforms. The updating unit, for example, analyzes the access status of published web pages and makes optimal updates. The updating unit updates web pages based on information provided by users. The updating unit can also update web pages based on user feedback. For example, it collects user comments and ratings and reflects improvements to the web pages. This allows generated web pages to be published and updated based on access status.

[0039] The update unit tracks and adjusts the user's eye movements. For example, it uses an eye-tracking device to track the user's eye movements. Based on information provided by the user, the update unit tracks the user's eye movements and optimizes the web page. The update unit can also analyze the user's eye movements using eye-tracking algorithms. For example, it can use eye-tracking algorithms to identify which parts of the web page the user is focusing on and adjust the web page design accordingly. Furthermore, the update unit can track the user's eye movements in real time and optimize immediately. For example, if a user is focusing on a particular area for an extended period, it can highlight the information in that area. This allows the web page to be optimized by tracking the user's eye movements.

[0040] The SEO Optimization Department adjusts the internal link structure. For example, it strengthens the internal link structure by linking related content within a webpage. Based on information provided by users, the SEO Optimization Department sets appropriate internal links and optimizes for search engines. The SEO Optimization Department can also prioritize links to important pages. For example, it optimizes the anchor text of internal links to increase their relevance to search engines. Furthermore, the SEO Optimization Department can optimize the hierarchical structure of internal links. For example, it sets links from the top page to each category page to make it easier for users to access the information they are looking for. In this way, optimizing the internal link structure can enhance SEO effectiveness.

[0041] The reception department analyzes the user's past information provision history and selects an appropriate reception method. For example, the reception department prioritizes suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception department can also select the optimal question format based on the user's past information provision history. For example, it analyzes patterns of information the user has provided in the past and selects the optimal question format. Furthermore, the reception department can suggest the most suitable reception method for a specific time period. For example, it suggests the most suitable reception method for a specific time period based on the user's past information provision history. This enables efficient information reception by selecting the optimal reception method based on the user's past information provision history. Some or all of the above processing in the reception department may be performed using AI or not.

[0042] The reception unit filters information upon receipt based on the user's current projects and areas of interest. For example, the reception unit prioritizes receiving only information related to the user's current projects. The reception unit can also filter and receive highly relevant information based on the user's areas of interest. For example, it may prioritize information based on topics the user has shown interest in in the past. The reception unit can also prioritize information based on the user's current projects and areas of interest. For example, it may prioritize receiving information related to the user's current projects. This allows the reception unit to receive highly relevant information by filtering it based on the user's current projects and areas of interest. Some or all of the above processing in the reception unit may be performed using AI or not.

[0043] The reception desk prioritizes receiving information that is highly relevant, taking into account the user's geographical location. For example, if the user is in a specific region, the reception desk prioritizes receiving information related to that region. The reception desk can also filter and receive highly relevant information based on the user's geographical location. For example, if the user is traveling, the reception desk prioritizes receiving information related to their travel destination. Furthermore, if the user is at home, the reception desk can prioritize receiving information about their home area. For example, if the user is at home, the reception desk prioritizes receiving information based on information about their home area. This allows the reception desk to prioritize receiving highly relevant information based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, or it may be performed without using AI.

[0044] The reception unit analyzes the user's social media activity when receiving information and accepts relevant information. For example, the reception unit prioritizes receiving relevant information based on information shared by the user on social media. The reception unit can also filter and accept highly relevant information based on the user's social media activity. For example, it can accept relevant information based on information from accounts the user follows on social media. Furthermore, the reception unit can determine the priority of information based on topics the user has shown interest in on social media. For example, it can determine the priority of information based on topics the user has shown interest in on social media. This allows the reception unit to accept relevant information based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not.

[0045] The generation unit adjusts the level of detail of the generated content based on the importance of the web page during generation. For example, if a web page contains important information, the generation unit generates detailed content. The generation unit evaluates the importance of the web page based on the information provided by the user and adjusts the level of detail of the generated content accordingly. The generation unit can also generate concise content for web pages containing general information. For example, if a web page contains information of particular interest to the user, it generates content with a detailed explanation. By adjusting the level of detail of the generated content based on the importance of the web page, appropriate content can be generated. Some or all of the above-described processes in the generation unit may be performed using AI or not.

[0046] The generation unit applies different generation algorithms depending on the category of the web page during generation. For example, in the case of a product introduction page, the generation unit applies a generation algorithm that emphasizes the product's features. The generation unit identifies the category of the web page based on the information provided by the user and applies the appropriate generation algorithm. In addition, in the case of a blog post, the generation unit can apply a generation algorithm that prioritizes readability. For example, the generation unit can concisely summarize the content of the blog post and generate a visually appealing layout. Furthermore, in the case of a news article, the generation unit can apply a generation algorithm that quickly conveys the latest information. For example, the generation unit can highlight the key points of the news article and provide the information in an easy-to-read format. By applying the appropriate generation algorithm according to the category of the web page, more effective web pages can be generated. Some or all of the above-described processes in the generation unit may be performed using AI or not.

[0047] The generation unit determines the generation priority based on the submission date of the web page during generation. For example, the generation unit prioritizes the generation of web pages with approaching deadlines. The generation unit evaluates the submission date of web pages based on the information provided by the user and determines the generation priority. The generation unit can also postpone the generation of web pages with distant submission dates. For example, if the user is in a particular hurry, it will generate the web page immediately. This allows for efficient generation by determining the generation priority based on the submission date of the web page. Some or all of the above processes in the generation unit may be performed using AI or not.

[0048] The generation unit adjusts the generation order based on the relevance of the web pages during generation. For example, the generation unit prioritizes generating web pages that contain information of particular interest to the user. The generation unit evaluates the relevance of web pages based on the information provided by the user and adjusts the generation order accordingly. The generation unit can also postpone the generation of web pages containing general information. For example, it may prioritize generating web pages related to the user's current project. This allows for the priority generation of important information by adjusting the generation order based on the relevance of the web pages. Some or all of the above-described processes in the generation unit may be performed using AI or not.

[0049] The output unit adjusts the level of detail in the output based on the importance of the web page. For example, if a web page contains important information, the output unit will provide detailed output. The output unit evaluates the importance of the web page based on the information provided by the user and adjusts the level of detail in the output. The output unit can also provide concise output if the web page contains general information. For example, if a web page contains information of particular interest to the user, it will provide output with a detailed explanation. By adjusting the level of detail in the output based on the importance of the web page, appropriate information can be output. Some or all of the above processing in the output unit may be performed using AI or not.

[0050] The output unit applies different output methods depending on the category of the web page during output. For example, in the case of a product introduction page, the output unit applies an output method that emphasizes the product's features. The output unit identifies the category of the web page based on the information provided by the user and applies the appropriate output method. In addition, in the case of a blog post, the output unit can apply an output method that prioritizes readability. For example, the output unit summarizes the content of the blog post concisely and outputs it in a visually appealing layout. Furthermore, in the case of a news article, the output unit can apply an output method that quickly conveys the latest information. For example, the output unit highlights the key points of the news article and provides the information in an easy-to-read format. By applying the appropriate output method according to the category of the web page, more effective information can be output. Some or all of the above processing in the output unit may be performed using AI or not.

[0051] The output unit adjusts the output order based on the submission date of the web pages during output. For example, the output unit prioritizes outputting web pages with approaching deadlines. The output unit evaluates the submission date of web pages based on the information provided by the user and adjusts the output order accordingly. The output unit can also postpone outputting web pages with distant submission dates. For example, if the user is in a particular hurry, it will output them immediately. This allows for efficient output by adjusting the output order based on the submission date of the web pages. Some or all of the above processing in the output unit may be performed using AI or not.

[0052] The output unit adjusts the output order based on the relevance of the web pages during output. For example, the output unit prioritizes outputting web pages containing information of particular interest to the user. The output unit evaluates the relevance of web pages based on the information provided by the user and adjusts the output order accordingly. The output unit can also delay the output of web pages containing general information. For example, it may prioritize the output of web pages related to the user's current project. This allows for the prioritization of important information by adjusting the output order based on the relevance of the web pages. Some or all of the above processing in the output unit may be performed using AI or not.

[0053] The SEO Optimization Department analyzes the algorithms of specific search engines and performs optimizations accordingly. For example, the SEO Optimization Department analyzes Google's algorithm and performs SEO optimizations based on that analysis. The SEO Optimization Department analyzes the algorithms of specific search engines based on information provided by the user and implements optimal SEO measures. The SEO Optimization Department can also analyze Bing's algorithm and perform SEO optimizations based on that analysis. For example, it analyzes Bing's algorithm and implements optimal SEO measures. Furthermore, the SEO Optimization Department can also analyze Yahoo's algorithm and perform SEO optimizations based on that analysis. For example, it analyzes Yahoo's algorithm and implements optimal SEO measures. By analyzing and optimizing based on the algorithms of specific search engines, more effective SEO optimizations can be achieved. Some or all of the above processes in the SEO Optimization Department may be performed using AI, or they may not be performed using AI.

[0054] The SEO Optimization Unit optimizes the internal link structure of a webpage during SEO optimization. For example, the SEO Optimization Unit strengthens the internal link structure by linking related content within the webpage. Based on information provided by the user, the SEO Optimization Unit sets appropriate internal links and optimizes for search engines. The SEO Optimization Unit can also prioritize links to important pages. For example, it optimizes the anchor text of internal links to increase their relevance to search engines. Furthermore, the SEO Optimization Unit can optimize the hierarchical structure of internal links. For example, it sets links from the top page to each category page to make it easier for users to access the information they are looking for. In this way, optimizing the internal link structure of a webpage can enhance its SEO effectiveness. Some or all of the above processes performed by the SEO Optimization Unit may be performed using AI or not.

[0055] The SEO Optimization Department optimizes SEO while considering changes in the algorithms of specific search engines. For example, the SEO Optimization Department optimizes SEO while considering the latest changes in Google's algorithm. The SEO Optimization Department analyzes changes in the algorithms of specific search engines based on information provided by the user and implements the most appropriate SEO measures. The SEO Optimization Department can also optimize SEO while considering changes in Bing's algorithm. For example, it analyzes changes in Bing's algorithm and implements the most appropriate SEO measures. Furthermore, the SEO Optimization Department can also optimize SEO while considering changes in Yahoo's algorithm. For example, it analyzes changes in Yahoo's algorithm and implements the most appropriate SEO measures. By optimizing while considering changes in the algorithms of specific search engines, more effective SEO optimization can be achieved. Some or all of the above processes in the SEO Optimization Department may be performed using AI or not.

[0056] The SEO Optimization Department optimizes the external link structure of a webpage during SEO optimization. For example, the SEO Optimization Department acquires high-quality external links to improve the credibility of the webpage. Based on the information provided by the user, the SEO Optimization Department sets appropriate external links and optimizes them for search engines. The SEO Optimization Department can also optimize the anchor text of external links to increase their relevance to search engines. For example, it optimizes the anchor text of external links to increase their relevance to search engines. Furthermore, the SEO Optimization Department can balance the number and quality of external links to maximize SEO effectiveness. For example, it balances the number and quality of external links to maximize SEO effectiveness. In this way, SEO effectiveness can be enhanced by optimizing the external link structure of a webpage. Some or all of the above processes performed by the SEO Optimization Department may be performed using AI or not.

[0057] The usability optimization unit analyzes user behavior data to perform optimization during usability optimization. For example, the usability optimization unit analyzes user click data and proposes an optimal navigation structure. Based on information provided by the user, the usability optimization unit analyzes user behavior data and implements optimal usability measures. The usability optimization unit can also analyze user scroll data and optimize content placement. For example, based on scroll data, the usability optimization unit proposes placement that highlights important information. Furthermore, the usability optimization unit can analyze user dwell time data and propose placement that highlights important information. For example, based on dwell time data, the usability optimization unit proposes placement that highlights important information. In this way, more effective usability optimization can be achieved by analyzing and optimizing user behavior data. Some or all of the above processes in the usability optimization unit may be performed using AI or not.

[0058] The usability optimization unit optimizes the navigation structure of a web page during usability optimization. For example, the usability optimization unit designs an intuitive and easy-to-use navigation menu based on user behavior data. The usability optimization unit optimizes the navigation structure of a web page based on information provided by the user. The usability optimization unit can also optimize navigation links to facilitate access to important pages. For example, the usability optimization unit prioritizes the placement of links to important pages to maximize the effectiveness of navigation. Furthermore, the usability optimization unit can analyze user behavior patterns and highlight the most frequently used navigation paths. For example, the usability optimization unit highlights the most frequently used navigation paths based on behavior patterns. By optimizing the navigation structure of a web page in this way, usability can be improved. Some or all of the above processes in the usability optimization unit may be performed using AI or not.

[0059] The usability optimization unit performs usability optimization while considering the user's device information. For example, if the user is using a smartphone, the usability optimization unit performs usability optimization that is adapted to the screen size. Based on the information provided by the user, the usability optimization unit considers the user's device information and implements the most appropriate usability measures. Furthermore, if the user is using a tablet, the usability optimization unit can perform usability optimization optimized for the larger screen. For example, it can generate a layout that matches the screen size of a tablet. In addition, if the user is using a desktop, the usability optimization unit can perform usability optimization optimized for mouse operation. For example, it can generate a layout that matches the screen size of a desktop. By performing optimization while considering the user's device information, more effective usability optimization can be achieved. Some or all of the above processing in the usability optimization unit may be performed using AI or not.

[0060] The usability optimization unit optimizes the content placement of a web page during usability optimization. For example, the usability optimization unit proposes a placement that highlights important information based on user behavior data. The usability optimization unit optimizes the content placement of a web page based on information provided by the user. The usability optimization unit can also analyze scroll data and optimize content placement. For example, the usability optimization unit proposes a placement that highlights important information based on scroll data. Furthermore, the usability optimization unit can propose an optimal content placement based on click data. For example, the usability optimization unit proposes a placement that highlights important information based on click data. By optimizing the content placement of a web page in this way, usability can be improved. Some or all of the above processes in the usability optimization unit may be performed using AI or not.

[0061] The template suggestion unit analyzes the user's past selection history to propose the most suitable template. For example, the template suggestion unit proposes the most suitable template based on templates the user has previously selected. The template suggestion unit selects and proposes the most suitable template based on the user's past selection history. The template suggestion unit can also propose the most suitable template for a specific time period. For example, it proposes the most suitable template for a specific time period based on the user's past selection history. Furthermore, the template suggestion unit can analyze the user's past selection patterns and propose the most suitable template. For example, it proposes the most suitable template based on the user's past selection patterns. This enables efficient template suggestion by proposing the most suitable template based on the user's past selection history. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0062] The template suggestion unit proposes templates based on the user's current projects and areas of interest. For example, the template suggestion unit prioritizes templates related to the user's current ongoing projects. The template suggestion unit selects and proposes the most suitable template based on the user's current projects and areas of interest. The template suggestion unit can also propose highly relevant templates based on the user's areas of interest. For example, it proposes the most suitable template based on the user's areas of interest. Furthermore, the template suggestion unit can determine template priorities based on topics the user has shown interest in in the past. For example, it proposes the most suitable template based on topics the user has shown interest in in the past. This allows the template suggestion unit to propose highly relevant templates by proposing templates based on the user's current projects and areas of interest. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0063] The template suggestion unit proposes highly relevant templates by considering the user's geographical location information when suggesting templates. For example, if the user is in a specific region, the template suggestion unit will prioritize suggesting templates related to that region. The template suggestion unit selects and proposes highly relevant templates based on the user's geographical location information. Furthermore, if the user is traveling, the template suggestion unit can also prioritize suggesting templates related to the travel destination. For example, if the user is traveling, it will propose templates related to the travel destination. In addition, if the user is at home, the template suggestion unit can also prioritize suggesting templates based on information about the user's home area. For example, if the user is at home, it will propose templates based on information about the user's home area. By proposing highly relevant templates based on the user's geographical location information, it is possible to propose more appropriate templates. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0064] The template suggestion unit analyzes the user's social media activity and proposes relevant templates when suggesting templates. For example, the template suggestion unit prioritizes suggesting relevant templates based on information shared by the user on social media. The template suggestion unit selects and proposes highly relevant templates based on the user's social media activity. The template suggestion unit can also suggest relevant templates based on information about accounts the user follows on social media. For example, it suggests relevant templates based on information about accounts the user follows on social media. Furthermore, the template suggestion unit can determine template priorities based on topics the user has shown interest in on social media. For example, it suggests the most suitable template based on topics the user has shown interest in on social media. This allows for the suggestion of more appropriate templates by proposing relevant templates based on the user's social media activity. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0065] The estimation unit performs estimation by analyzing past changes in search engine algorithms. For example, the estimation unit analyzes past changes in Google's algorithm and performs estimation based on that analysis. The estimation unit analyzes past changes in search engine algorithms based on information provided by the user and performs optimal algorithm estimation. The estimation unit can also analyze past changes in Bing's algorithm and perform estimation based on that analysis. For example, it analyzes past changes in Bing's algorithm and performs optimal algorithm estimation. Furthermore, the estimation unit can also analyze past changes in Yahoo's algorithm and perform estimation based on that analysis. For example, it analyzes past changes in Yahoo's algorithm and performs optimal algorithm estimation. By analyzing past changes in search engine algorithms and performing estimation, more accurate algorithm estimation can be achieved. Some or all of the above processing in the estimation unit may be performed using AI or not.

[0066] The estimation unit learns the algorithm patterns of specific search engines and performs estimations during the estimation process. For example, the estimation unit learns Google's algorithm patterns and performs estimations based on them. The estimation unit learns the algorithm patterns of specific search engines based on information provided by the user and performs the optimal algorithm estimation. The estimation unit can also learn Bing's algorithm patterns and perform estimations based on them. For example, it learns Bing's algorithm patterns and performs the optimal algorithm estimation. Furthermore, the estimation unit can also learn Yahoo's algorithm patterns and perform estimations based on them. For example, it learns Yahoo's algorithm patterns and performs the optimal algorithm estimation. By learning the algorithm patterns of specific search engines and performing estimations, more accurate algorithm estimations can be achieved. Some or all of the above-described processes in the estimation unit may be performed using AI or not.

[0067] The estimation unit performs estimations while considering changes in the algorithms of specific search engines. For example, the estimation unit considers the latest changes in Google's algorithm. Based on the information provided by the user, the estimation unit analyzes the changes in the algorithms of specific search engines and performs the optimal algorithm estimation. The estimation unit can also perform estimations while considering changes in Bing's algorithm. For example, it analyzes the changes in Bing's algorithm and performs the optimal algorithm estimation. Furthermore, the estimation unit can also perform estimations while considering changes in Yahoo's algorithm. For example, it analyzes the changes in Yahoo's algorithm and performs the optimal algorithm estimation. By performing estimations while considering changes in the algorithms of specific search engines, more accurate algorithm estimations can be made. Some or all of the above processing in the estimation unit may be performed using AI or not.

[0068] The estimation unit performs estimation by referring to relevant literature on the algorithm of a specific search engine. For example, the estimation unit performs estimation by referring to the latest research literature on Google's algorithm. Based on the information provided by the user, the estimation unit performs the optimal algorithm estimation by referring to relevant literature on the algorithm of a specific search engine. The estimation unit can also perform estimation by referring to the latest research literature on Bing's algorithm. For example, it performs the optimal algorithm estimation by referring to the latest research literature on Bing's algorithm. Furthermore, the estimation unit can also perform estimation by referring to the latest research literature on Yahoo's algorithm. For example, it performs the optimal algorithm estimation by referring to the latest research literature on Yahoo's algorithm. This allows for more accurate algorithm estimation by referring to relevant literature on the algorithm of a specific search engine. Some or all of the above processing in the estimation unit may be performed using AI or not.

[0069] The data collection unit analyzes the user's past behavioral history to select the optimal data collection method when collecting behavioral data. For example, the data collection unit may select the optimal data collection method based on actions the user has frequently performed in the past. The data collection unit analyzes the user's past behavioral history based on the information provided by the user and implements the optimal data collection method. The data collection unit can also select the optimal data collection method for a specific time period. For example, it may select the optimal data collection method for a specific time period based on the user's past behavioral history. Furthermore, the data collection unit may analyze the user's past behavioral patterns to select the most efficient data collection method. For example, it may select the optimal data collection method based on the user's past behavioral patterns. This enables efficient data collection by selecting the optimal data collection method based on the user's past behavioral history. Some or all of the above-described processes in the data collection unit may be performed using AI or not.

[0070] The data collection unit filters behavioral data based on the user's current projects and areas of interest. For example, the data collection unit prioritizes collecting only behavioral data related to the user's current projects. Based on the information provided by the user, the data collection unit identifies the user's current projects and areas of interest and collects the most relevant behavioral data. The data collection unit can also filter and collect highly relevant behavioral data based on the user's areas of interest. For example, it collects the most relevant behavioral data based on the user's areas of interest. Furthermore, the data collection unit can determine the priority of behavioral data based on topics the user has shown interest in in the past. For example, it collects the most relevant behavioral data based on topics the user has shown interest in in the past. This allows for the collection of highly relevant behavioral data by filtering behavioral data based on the user's current projects and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not.

[0071] The data collection unit prioritizes collecting highly relevant data, taking into account the user's geographical location when collecting behavioral data. For example, if the user is in a specific region, the data collection unit prioritizes collecting behavioral data related to that region. Based on the information provided by the user, the data collection unit identifies the user's geographical location and collects the most appropriate behavioral data. The data collection unit can also prioritize collecting behavioral data related to the user's travel destination if the user is traveling. For example, if the user is traveling, it collects behavioral data related to the travel destination. Furthermore, if the user is at home, the data collection unit can prioritize collecting behavioral data around the user's home. For example, if the user is at home, it collects behavioral data around the user's home. This allows for the collection of more appropriate behavioral data by prioritizing the collection of highly relevant data based on the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI or not.

[0072] The data collection unit analyzes the user's social media activity and collects relevant data when collecting behavioral data. For example, the data collection unit prioritizes collecting relevant behavioral data based on information shared by the user on social media. The data collection unit analyzes the user's social media activity based on information provided by the user and collects the most appropriate behavioral data. The data collection unit can also collect relevant behavioral data based on information about accounts the user follows on social media. For example, it collects relevant behavioral data based on information about accounts the user follows on social media. Furthermore, the data collection unit can determine the priority of behavioral data based on topics the user has shown interest in on social media. For example, it collects the most appropriate behavioral data based on topics the user has shown interest in on social media. This allows for the collection of more appropriate behavioral data by collecting relevant behavioral data based on the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not.

[0073] The publishing unit adjusts the level of detail of a webpage based on its importance at the time of publication. For example, if a webpage contains important information, the publishing unit will publish it in detail. The publishing unit evaluates the importance of a webpage based on the information provided by the user and adjusts the level of detail of the publication accordingly. The publishing unit can also publish a concise version of a webpage if it contains general information. For example, if a webpage contains information of particular interest to the user, it will publish it with a detailed explanation. This allows for the publication of appropriate information by adjusting the level of detail of the publication based on the importance of the webpage. Some or all of the above processing in the publishing unit may be performed using AI or not.

[0074] The publishing department applies different publishing methods depending on the category of the web page when publishing. For example, for a product introduction page, the publishing department applies a publishing method that emphasizes the product's features. The publishing department identifies the category of the web page based on the information provided by the user and applies the appropriate publishing method. In the case of blog posts, the publishing department can also apply a publishing method that prioritizes readability. For example, it might summarize the content of the blog post concisely and publish it in a visually appealing layout. Furthermore, in the case of news articles, the publishing department can also apply a publishing method that quickly conveys the latest information. For example, it might highlight the key points of the news article and provide the information in an easy-to-read format. By applying the appropriate publishing method according to the category of the web page, more effective information can be published. Some or all of the above processing in the publishing department may be performed using AI or not.

[0075] The publishing department adjusts the publication order based on the submission date of the web pages. For example, the publishing department prioritizes publishing web pages with approaching deadlines. The publishing department evaluates the submission date of web pages based on the information provided by users and adjusts the publication order accordingly. The publishing department can also postpone publishing web pages with later submission dates. For example, if a user is in a particular hurry, it will publish immediately. This allows for efficient publishing by adjusting the publication order based on the submission date of the web pages. Some or all of the above processes in the publishing department may be performed using AI or not.

[0076] The publishing unit adjusts the publication order based on the relevance of web pages at the time of publication. For example, the publishing unit prioritizes publishing web pages that contain information of particular interest to the user. The publishing unit evaluates the relevance of web pages based on the information provided by the user and adjusts the publication order accordingly. The publishing unit can also postpone publishing web pages that contain general information. For example, it may prioritize publishing web pages related to the user's current project. This allows important information to be published preferentially by adjusting the publication order based on the relevance of web pages. Some or all of the above processing in the publishing unit may be performed using AI or not.

[0077] The update unit analyzes the access status of web pages and selects the optimal update method during updates. For example, the update unit prioritizes updating pages with high access to provide the latest information. Based on information provided by users, the update unit analyzes the access status of web pages and implements the optimal update method. The update unit can also postpone updating pages with low access. For example, it postpones updating pages with low access. Furthermore, the update unit can analyze access status and select the most effective update method. For example, it selects the optimal update method based on access status. By analyzing the access status of web pages and selecting the optimal update method, more effective updates can be performed. Some or all of the above processes in the update unit may be performed using AI, or they may not be performed using AI.

[0078] The update unit applies different update methods depending on the category of the web page during the update process. For example, in the case of a product introduction page, the update unit applies an update method that emphasizes the product's features. The update unit identifies the category of the web page based on the information provided by the user and applies the appropriate update method. In the case of blog posts, the update unit can also apply an update method that prioritizes readability. For example, it might summarize the content of the blog post concisely and update it with a visually appealing layout. Furthermore, in the case of news articles, the update unit can also apply an update method that quickly conveys the latest information. For example, it might highlight the key points of the news article and provide the information in an easy-to-read format. By applying the appropriate update method according to the category of the web page, more effective updates can be achieved. Some or all of the above processes in the update unit may be performed using AI or not.

[0079] The update unit adjusts the order of updates based on the submission date of the web pages. For example, the update unit prioritizes updating web pages with approaching deadlines. The update unit evaluates the submission date of web pages based on information provided by the user and adjusts the order of updates accordingly. The update unit can also postpone updating web pages with distant submission dates. For example, if the user is in a particular hurry, the update will be performed immediately. This allows for efficient updates by adjusting the order of updates based on the submission date of the web pages. Some or all of the above processes in the update unit may be performed using AI or not.

[0080] The update unit adjusts the order of updates based on the relevance of the web pages during the update process. For example, the update unit prioritizes updating web pages that contain information of particular interest to the user. The update unit evaluates the relevance of web pages based on the information provided by the user and adjusts the order of updates accordingly. The update unit can also postpone updating web pages that contain general information. For example, it may prioritize updating web pages related to the user's current project. This allows important information to be updated preferentially by adjusting the order of updates based on the relevance of the web pages. Some or all of the above processes in the update unit may be performed using AI or not.

[0081] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0082] The reception desk can analyze user input in real time and provide appropriate feedback based on that input. For example, if there are typos or grammatical errors in the text entered by the user, it will immediately suggest corrections. Furthermore, if the input is unclear, the reception desk can prompt the user to complete the information by asking specific questions. In addition, the reception desk can automatically search for relevant information based on the user's input and provide it to the user. This allows users to efficiently provide information and receive feedback from the system.

[0083] The generation unit can suggest the optimal layout and content when generating a web page, taking into account the user's past web page generation history. For example, it can prioritize suggesting layouts that the user has previously preferred. The generation unit can also analyze the user's past generation history and suggest the most effective content placement. Furthermore, based on the user's past generation history, the generation unit can suggest templates suitable for specific themes and styles. This allows users to leverage their past experience to create more effective web pages.

[0084] The template suggestion function can propose templates based on the user's current project progress. For example, it can suggest basic templates in the early stages of a project and more detailed templates as the project progresses. The template suggestion function can also provide customization options for templates according to the user's project progress. Furthermore, it can suggest relevant resources and tools based on the project progress. This allows the user to select the most suitable template as their project progresses.

[0085] The SEO Optimization Department can monitor changes in the algorithms of specific search engines in real time and perform SEO optimization based on those changes. For example, if Google's algorithm is updated, the department can immediately reflect the update and perform SEO optimization. The SEO Optimization Department can also monitor the algorithms of multiple search engines simultaneously and implement the most suitable SEO measures for each algorithm. Furthermore, the SEO Optimization Department can propose specific SEO measures to users based on algorithm changes. This ensures that users are always implementing the latest SEO strategies.

[0086] The usability optimization unit can analyze user behavior data in real time and optimize web pages based on the analysis results. For example, if a user frequently clicks a particular button, it can adjust the position and design of that button. The usability optimization unit can also optimize the placement of navigation menus based on user behavior data. Furthermore, the usability optimization unit can adjust the display order of content based on user behavior data. This allows for the provision of more user-friendly web pages based on user behavior data.

[0087] The following briefly describes the processing flow for example form 1.

[0088] Step 1: The reception desk receives information provided by the user. The reception desk can receive text information, image information, and voice input entered by the user. For example, it can use speech recognition technology to convert the user's voice into text and receive it as information. Step 2: The generation unit generates web pages that meet specific conditions based on the information received by the reception unit. The generation unit uses generation AI to generate the web page layout and content based on user information. The generation unit also includes an SEO optimization unit and a usability optimization unit, performing optimization from both an SEO and usability perspective. Step 3: The output unit outputs the web page generated by the generation unit. The output unit can output the generated web page in HTML format. It can also output in PDF format or image format.

[0089] (Example of form 2) The webpage automatic generation support system according to an embodiment of the present invention is an AI assistant that automatically generates webpages based on information provided by the user, optimizing them with consideration for SEO and usability. In this system, the reception unit receives information provided by the user, and the generation unit generates webpages that meet specific conditions based on this information. The generation unit includes an SEO optimization unit and a usability optimization unit, optimizing from both an SEO and usability perspective. The generated webpages are output by the output unit and published by the publication unit. Based on the access status of the published webpages, the update unit updates the webpages and optimizes them by tracking the user's eye movements. As a result, users can easily automatically generate optimized webpages that take SEO and usability into consideration. Thus, the webpage automatic generation support system can automatically generate optimized webpages based on information provided by the user.

[0090] The webpage automatic generation support system according to the embodiment comprises a reception unit, a generation unit, and an output unit. The reception unit receives information provided by the user. For example, the reception unit can receive text information and image information entered by the user. The reception unit can also receive voice input. For example, it can use speech recognition technology to convert the user's voice into text and receive it as information. The generation unit generates a webpage that satisfies specific conditions based on the information received by the reception unit. For example, the generation unit uses a generation AI to generate the webpage layout and content based on the user's information. The generation unit includes an SEO optimization unit and a usability optimization unit, performing optimization from both an SEO and usability perspective. The output unit outputs the webpage generated by the generation unit. For example, the output unit can output the generated webpage in HTML format. The output unit can also output in PDF format or image format. Thus, the webpage automatic generation support system according to the embodiment can automatically generate an optimized webpage based on information provided by the user.

[0091] The reception desk receives information provided by the user. Specifically, it can receive text and image information entered by the user. For example, when a user enters the title, content, and image files of a webpage into an input form, this information is sent to the reception desk. The reception desk can also accept voice input. Using speech recognition technology, it can convert the user's voice into text and receive it as information. For example, when a user speaks into a microphone, their voice is converted into text in real time and sent to the reception desk. Furthermore, the reception desk has a function to verify the format and content of the information provided by the user and display error messages as needed. For example, if the image file format is not supported or the text information is incomplete, it can display an appropriate error message to the user and prompt them to re-enter the information. This allows the reception desk to receive information provided by the user accurately and efficiently.

[0092] The generation unit generates web pages that meet specific conditions based on information received by the reception unit. Specifically, it uses generation AI to generate the layout and content of web pages based on user information. For example, the generation AI uses natural language processing technology to analyze the text information provided by the user and automatically generates appropriate headings and paragraph structures. It also uses image recognition technology to analyze the content of provided images and determine the optimal placement and size. Furthermore, the generation unit is equipped with an SEO optimization unit and a usability optimization unit, performing optimization from both an SEO and usability perspective. The SEO optimization unit, for example, appropriately places keywords and generates meta tags to improve search engine rankings. The usability optimization unit, for example, simplifies navigation and applies responsive design to ensure users can comfortably browse web pages. As a result, the generation unit can automatically generate optimal web pages that consider both SEO and usability based on the information provided by the user.

[0093] The output unit outputs the web pages generated by the generation unit. Specifically, it can output the generated web pages in HTML format. The HTML output is optimized for display in web browsers, allowing users to immediately publish the web pages they have generated. The output unit can also output in PDF format and image format. The PDF output is suitable for printing and offline viewing, while the image output can be used as screenshots or thumbnails of the web pages. Furthermore, the output unit also has a function to save the generated web pages to cloud storage. This allows users to access the generated web pages anytime, anywhere. For example, the output unit can automatically upload the generated web pages to a specified cloud storage service and provide the user with a download link. This allows the output unit to output generated web pages in various formats, enabling flexible responses to the user's needs.

[0094] The generation unit comprises an SEO optimization unit that adjusts web pages from an SEO perspective and a usability optimization unit that adjusts web pages from a usability perspective. The SEO optimization unit, for example, optimizes keywords. Based on information provided by the user, the SEO optimization unit selects appropriate keywords and places them on the web page. The SEO optimization unit can also set meta tags. For example, it sets meta descriptions and meta keywords to optimize for search engines. The usability optimization unit, for example, makes adjustments to improve the ease of navigation. Based on information provided by the user, the usability optimization unit designs an intuitive and easy-to-use navigation menu. The usability optimization unit can also apply responsive design. For example, it generates designs that are compatible with different devices such as smartphones and tablets. This makes it possible to generate web pages that are optimized from both an SEO and usability perspective.

[0095] The generation unit includes a template suggestion unit that proposes an appropriate template to the user from among multiple templates. The template suggestion unit, for example, proposes industry-specific templates. Based on the information provided by the user, the template suggestion unit selects and proposes the most suitable industry-specific template. Furthermore, the template suggestion unit can also propose templates that consider design consistency. For example, it can propose a design template that matches the user's brand image. In addition, the template suggestion unit can analyze the user's past selection history and propose the most suitable template. For example, it can propose the most suitable template based on templates the user has previously selected. This allows the system to propose the most suitable template to the user.

[0096] The SEO optimization unit includes an estimation unit that estimates the algorithm of a specific search engine, and performs adjustments based on the algorithm estimated by the estimation unit. For example, the estimation unit estimates Google's algorithm. Based on information provided by the user, the estimation unit estimates Google's algorithm and provides it to the SEO optimization unit. The estimation unit can also estimate Bing's algorithm. For example, it analyzes Bing's algorithm and provides it to the SEO optimization unit. Furthermore, the estimation unit can also estimate Yahoo's algorithm. For example, it analyzes Yahoo's algorithm and provides it to the SEO optimization unit. This allows for SEO optimization based on the algorithm of a specific search engine.

[0097] The usability optimization unit includes a data collection unit that collects user behavior data and makes adjustments based on the data collected by the data collection unit. For example, the data collection unit collects click data. Based on information provided by the user, the data collection unit collects user click data and provides it to the usability optimization unit. The data collection unit can also collect page dwell time. For example, it collects the time a user spends on a particular page and provides it to the usability optimization unit. Furthermore, the data collection unit can also collect scroll data. For example, it collects data on when a user scrolls a page and provides it to the usability optimization unit. This allows usability to be optimized based on user behavior data.

[0098] The generation unit inputs information received by the reception unit, information including the algorithm of a specific search engine, and information regarding usability into the generation AI, causing the generation AI to generate web pages that meet specific conditions. The generation AI generates web pages using, for example, a specific machine learning model. The generation AI generates web pages that meet specific conditions based on the information provided by the user. The generation AI can also learn using training datasets and generate optimal web pages. For example, the generation AI learns from a large amount of web page data and generates optimal layouts and content. This allows the generation AI to generate web pages that meet specific conditions.

[0099] The generation unit comprises a publishing unit that publishes web pages and an updating unit that updates web pages based on the access status of the web pages published by the publishing unit. The publishing unit, for example, publishes the generated web pages on the internet. The publishing unit publishes web pages based on information provided by users. The publishing unit can also publish web pages on specific platforms. For example, the publishing unit publishes web pages on website or blog platforms. The updating unit, for example, analyzes the access status of published web pages and makes optimal updates. The updating unit updates web pages based on information provided by users. The updating unit can also update web pages based on user feedback. For example, it collects user comments and ratings and reflects improvements to the web pages. This allows generated web pages to be published and updated based on access status.

[0100] The update unit tracks and adjusts the user's eye movements. For example, it uses an eye-tracking device to track the user's eye movements. Based on information provided by the user, the update unit tracks the user's eye movements and optimizes the web page. The update unit can also analyze the user's eye movements using eye-tracking algorithms. For example, it can use eye-tracking algorithms to identify which parts of the web page the user is focusing on and adjust the web page design accordingly. Furthermore, the update unit can track the user's eye movements in real time and optimize immediately. For example, if a user is focusing on a particular area for an extended period, it can highlight the information in that area. This allows the web page to be optimized by tracking the user's eye movements.

[0101] The SEO Optimization Department adjusts the internal link structure. For example, it strengthens the internal link structure by linking related content within a webpage. Based on information provided by users, the SEO Optimization Department sets appropriate internal links and optimizes for search engines. The SEO Optimization Department can also prioritize links to important pages. For example, it optimizes the anchor text of internal links to increase their relevance to search engines. Furthermore, the SEO Optimization Department can optimize the hierarchical structure of internal links. For example, it sets links from the top page to each category page to make it easier for users to access the information they are looking for. In this way, optimizing the internal link structure can enhance SEO effectiveness.

[0102] The reception unit estimates the user's emotions and adjusts the timing of information reception based on the estimated emotions. For example, if the user is stressed, the reception unit temporarily delays information reception and resumes reception when the user is relaxed. The reception unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The reception unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the reception unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the reception of more appropriate information by adjusting the timing of information reception based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0103] The reception department analyzes the user's past information provision history and selects an appropriate reception method. For example, the reception department prioritizes suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception department can also select the optimal question format based on the user's past information provision history. For example, it analyzes patterns of information the user has provided in the past and selects the optimal question format. Furthermore, the reception department can suggest the most suitable reception method for a specific time period. For example, it suggests the most suitable reception method for a specific time period based on the user's past information provision history. This enables efficient information reception by selecting the optimal reception method based on the user's past information provision history. Some or all of the above processing in the reception department may be performed using AI or not.

[0104] The reception unit filters information upon receipt based on the user's current projects and areas of interest. For example, the reception unit prioritizes receiving only information related to the user's current projects. The reception unit can also filter and receive highly relevant information based on the user's areas of interest. For example, it may prioritize information based on topics the user has shown interest in in the past. The reception unit can also prioritize information based on the user's current projects and areas of interest. For example, it may prioritize receiving information related to the user's current projects. This allows the reception unit to receive highly relevant information by filtering it based on the user's current projects and areas of interest. Some or all of the above processing in the reception unit may be performed using AI or not.

[0105] The reception desk estimates the user's emotions and determines the priority of information to receive based on the estimated emotions. For example, if the user is stressed, the reception desk will postpone less important information and prioritize more important information. The reception desk captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The reception desk can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the reception desk can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows the system to prioritize information based on the user's emotions, thereby prioritizing the receipt of important information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0106] The reception desk prioritizes receiving information that is highly relevant, taking into account the user's geographical location. For example, if the user is in a specific region, the reception desk prioritizes receiving information related to that region. The reception desk can also filter and receive highly relevant information based on the user's geographical location. For example, if the user is traveling, the reception desk prioritizes receiving information related to their travel destination. Furthermore, if the user is at home, the reception desk can prioritize receiving information about their home area. For example, if the user is at home, the reception desk prioritizes receiving information based on information about their home area. This allows the reception desk to prioritize receiving highly relevant information based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, or it may be performed without using AI.

[0107] The reception unit analyzes the user's social media activity when receiving information and accepts relevant information. For example, the reception unit prioritizes receiving relevant information based on information shared by the user on social media. The reception unit can also filter and accept highly relevant information based on the user's social media activity. For example, it can accept relevant information based on information from accounts the user follows on social media. Furthermore, the reception unit can determine the priority of information based on topics the user has shown interest in on social media. For example, it can determine the priority of information based on topics the user has shown interest in on social media. This allows the reception unit to accept relevant information based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not.

[0108] The generation unit estimates the user's emotions and adjusts the design of the generated webpage based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate a design with calming colors. The generation unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The generation unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the generation of more appropriate designs by adjusting the webpage design based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0109] The generation unit adjusts the level of detail of the generated content based on the importance of the web page during generation. For example, if a web page contains important information, the generation unit generates detailed content. The generation unit evaluates the importance of the web page based on the information provided by the user and adjusts the level of detail of the generated content accordingly. The generation unit can also generate concise content for web pages containing general information. For example, if a web page contains information of particular interest to the user, it generates content with a detailed explanation. By adjusting the level of detail of the generated content based on the importance of the web page, appropriate content can be generated. Some or all of the above-described processes in the generation unit may be performed using AI or not.

[0110] The generation unit applies different generation algorithms depending on the category of the web page during generation. For example, in the case of a product introduction page, the generation unit applies a generation algorithm that emphasizes the product's features. The generation unit identifies the category of the web page based on the information provided by the user and applies the appropriate generation algorithm. In addition, in the case of a blog post, the generation unit can apply a generation algorithm that prioritizes readability. For example, the generation unit can concisely summarize the content of the blog post and generate a visually appealing layout. Furthermore, in the case of a news article, the generation unit can apply a generation algorithm that quickly conveys the latest information. For example, the generation unit can highlight the key points of the news article and provide the information in an easy-to-read format. By applying the appropriate generation algorithm according to the category of the web page, more effective web pages can be generated. Some or all of the above-described processes in the generation unit may be performed using AI or not.

[0111] The generation unit estimates the user's emotions and adjusts the length of the generated webpage based on the estimated emotions. For example, if the user is in a hurry, the generation unit will generate a short, concise webpage. The generation unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The generation unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice to calculate an emotion score. Furthermore, the generation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the generation of webpages of a more appropriate length by adjusting the length based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0112] The generation unit determines the generation priority based on the submission date of the web page during generation. For example, the generation unit prioritizes the generation of web pages with approaching deadlines. The generation unit evaluates the submission date of web pages based on the information provided by the user and determines the generation priority. The generation unit can also postpone the generation of web pages with distant submission dates. For example, if the user is in a particular hurry, it will generate the web page immediately. This allows for efficient generation by determining the generation priority based on the submission date of the web page. Some or all of the above processes in the generation unit may be performed using AI or not.

[0113] The generation unit adjusts the generation order based on the relevance of the web pages during generation. For example, the generation unit prioritizes generating web pages that contain information of particular interest to the user. The generation unit evaluates the relevance of web pages based on the information provided by the user and adjusts the generation order accordingly. The generation unit can also postpone the generation of web pages containing general information. For example, it may prioritize generating web pages related to the user's current project. This allows for the priority generation of important information by adjusting the generation order based on the relevance of the web pages. Some or all of the above-described processes in the generation unit may be performed using AI or not.

[0114] The output unit estimates the user's emotions and adjusts the timing of the output based on the estimated emotions. For example, if the user is stressed, the output unit will temporarily delay the output and output again when the user is relaxed. The output unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The output unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the output unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. By adjusting the timing of the output based on the user's emotions, information can be output at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0115] The output unit adjusts the level of detail in the output based on the importance of the web page. For example, if a web page contains important information, the output unit will provide detailed output. The output unit evaluates the importance of the web page based on the information provided by the user and adjusts the level of detail in the output. The output unit can also provide concise output if the web page contains general information. For example, if a web page contains information of particular interest to the user, it will provide output with a detailed explanation. By adjusting the level of detail in the output based on the importance of the web page, appropriate information can be output. Some or all of the above processing in the output unit may be performed using AI or not.

[0116] The output unit applies different output methods depending on the category of the web page during output. For example, in the case of a product introduction page, the output unit applies an output method that emphasizes the product's features. The output unit identifies the category of the web page based on the information provided by the user and applies the appropriate output method. In addition, in the case of a blog post, the output unit can apply an output method that prioritizes readability. For example, the output unit summarizes the content of the blog post concisely and outputs it in a visually appealing layout. Furthermore, in the case of a news article, the output unit can apply an output method that quickly conveys the latest information. For example, the output unit highlights the key points of the news article and provides the information in an easy-to-read format. By applying the appropriate output method according to the category of the web page, more effective information can be output. Some or all of the above processing in the output unit may be performed using AI or not.

[0117] The output unit estimates the user's emotions and determines the priority of web pages to output based on the estimated emotions. For example, if the user is stressed, the output unit will postpone less important web pages and prioritize outputting more important ones. The output unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The output unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the output unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows important information to be output preferentially by determining the priority of web pages based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0118] The output unit adjusts the output order based on the submission date of the web pages during output. For example, the output unit prioritizes outputting web pages with approaching deadlines. The output unit evaluates the submission date of web pages based on the information provided by the user and adjusts the output order accordingly. The output unit can also postpone outputting web pages with distant submission dates. For example, if the user is in a particular hurry, it will output them immediately. This allows for efficient output by adjusting the output order based on the submission date of the web pages. Some or all of the above processing in the output unit may be performed using AI or not.

[0119] The output unit adjusts the output order based on the relevance of the web pages during output. For example, the output unit prioritizes outputting web pages containing information of particular interest to the user. The output unit evaluates the relevance of web pages based on the information provided by the user and adjusts the output order accordingly. The output unit can also delay the output of web pages containing general information. For example, it may prioritize the output of web pages related to the user's current project. This allows for the prioritization of important information by adjusting the output order based on the relevance of the web pages. Some or all of the above processing in the output unit may be performed using AI or not.

[0120] The SEO optimization unit estimates the user's emotions and adjusts the SEO optimization method based on the estimated emotions. For example, if the user is relaxed, the SEO optimization unit performs detailed SEO optimization. The SEO optimization unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The SEO optimization unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the SEO optimization unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more effective SEO optimization by adjusting the SEO optimization method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0121] The SEO Optimization Department analyzes the algorithms of specific search engines and performs optimizations accordingly. For example, the SEO Optimization Department analyzes Google's algorithm and performs SEO optimizations based on that analysis. The SEO Optimization Department analyzes the algorithms of specific search engines based on information provided by the user and implements optimal SEO measures. The SEO Optimization Department can also analyze Bing's algorithm and perform SEO optimizations based on that analysis. For example, it analyzes Bing's algorithm and implements optimal SEO measures. Furthermore, the SEO Optimization Department can also analyze Yahoo's algorithm and perform SEO optimizations based on that analysis. For example, it analyzes Yahoo's algorithm and implements optimal SEO measures. By analyzing and optimizing based on the algorithms of specific search engines, more effective SEO optimizations can be achieved. Some or all of the above processes in the SEO Optimization Department may be performed using AI, or they may not be performed using AI.

[0122] The SEO Optimization Unit optimizes the internal link structure of a webpage during SEO optimization. For example, the SEO Optimization Unit strengthens the internal link structure by linking related content within the webpage. Based on information provided by the user, the SEO Optimization Unit sets appropriate internal links and optimizes for search engines. The SEO Optimization Unit can also prioritize links to important pages. For example, it optimizes the anchor text of internal links to increase their relevance to search engines. Furthermore, the SEO Optimization Unit can optimize the hierarchical structure of internal links. For example, it sets links from the top page to each category page to make it easier for users to access the information they are looking for. In this way, optimizing the internal link structure of a webpage can enhance its SEO effectiveness. Some or all of the above processes performed by the SEO Optimization Unit may be performed using AI or not.

[0123] The SEO optimization unit estimates the user's emotions and determines the priority of SEO optimization based on the estimated emotions. For example, if the user is stressed, the SEO optimization unit will postpone less important SEO optimizations and prioritize more important ones. The SEO optimization unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The SEO optimization unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice to calculate an emotion score. Furthermore, the SEO optimization unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows the SEO optimization unit to prioritize important SEO optimizations based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0124] The SEO Optimization Department optimizes SEO while considering changes in the algorithms of specific search engines. For example, the SEO Optimization Department optimizes SEO while considering the latest changes in Google's algorithm. The SEO Optimization Department analyzes changes in the algorithms of specific search engines based on information provided by the user and implements the most appropriate SEO measures. The SEO Optimization Department can also optimize SEO while considering changes in Bing's algorithm. For example, it analyzes changes in Bing's algorithm and implements the most appropriate SEO measures. Furthermore, the SEO Optimization Department can also optimize SEO while considering changes in Yahoo's algorithm. For example, it analyzes changes in Yahoo's algorithm and implements the most appropriate SEO measures. By optimizing while considering changes in the algorithms of specific search engines, more effective SEO optimization can be achieved. Some or all of the above processes in the SEO Optimization Department may be performed using AI or not.

[0125] The SEO Optimization Department optimizes the external link structure of a webpage during SEO optimization. For example, the SEO Optimization Department acquires high-quality external links to improve the credibility of the webpage. Based on the information provided by the user, the SEO Optimization Department sets appropriate external links and optimizes them for search engines. The SEO Optimization Department can also optimize the anchor text of external links to increase their relevance to search engines. For example, it optimizes the anchor text of external links to increase their relevance to search engines. Furthermore, the SEO Optimization Department can balance the number and quality of external links to maximize SEO effectiveness. For example, it balances the number and quality of external links to maximize SEO effectiveness. In this way, SEO effectiveness can be enhanced by optimizing the external link structure of a webpage. Some or all of the above processes performed by the SEO Optimization Department may be performed using AI or not.

[0126] The usability optimization unit estimates the user's emotions and adjusts the usability optimization method based on the estimated emotions. For example, if the user is relaxed, the usability optimization unit performs detailed usability optimization. The usability optimization unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The usability optimization unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the usability optimization unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more effective usability optimization by adjusting the usability optimization method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0127] The usability optimization unit analyzes user behavior data to perform optimization during usability optimization. For example, the usability optimization unit analyzes user click data and proposes an optimal navigation structure. Based on information provided by the user, the usability optimization unit analyzes user behavior data and implements optimal usability measures. The usability optimization unit can also analyze user scroll data and optimize content placement. For example, based on scroll data, the usability optimization unit proposes placement that highlights important information. Furthermore, the usability optimization unit can analyze user dwell time data and propose placement that highlights important information. For example, based on dwell time data, the usability optimization unit proposes placement that highlights important information. In this way, more effective usability optimization can be achieved by analyzing and optimizing user behavior data. Some or all of the above processes in the usability optimization unit may be performed using AI or not.

[0128] The usability optimization unit optimizes the navigation structure of a web page during usability optimization. For example, the usability optimization unit designs an intuitive and easy-to-use navigation menu based on user behavior data. The usability optimization unit optimizes the navigation structure of a web page based on information provided by the user. The usability optimization unit can also optimize navigation links to facilitate access to important pages. For example, the usability optimization unit prioritizes the placement of links to important pages to maximize the effectiveness of navigation. Furthermore, the usability optimization unit can analyze user behavior patterns and highlight the most frequently used navigation paths. For example, the usability optimization unit highlights the most frequently used navigation paths based on behavior patterns. By optimizing the navigation structure of a web page in this way, usability can be improved. Some or all of the above processes in the usability optimization unit may be performed using AI or not.

[0129] The usability optimization unit estimates the user's emotions and determines the priority of usability optimizations based on the estimated emotions. For example, if the user is stressed, the usability optimization unit will postpone less important usability optimizations and prioritize more important ones. The usability optimization unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The usability optimization unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice to calculate an emotion score. Furthermore, the usability optimization unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows the unit to prioritize important usability optimizations by determining the priority of usability optimizations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0130] The usability optimization unit performs usability optimization while considering the user's device information. For example, if the user is using a smartphone, the usability optimization unit performs usability optimization that is adapted to the screen size. Based on the information provided by the user, the usability optimization unit considers the user's device information and implements the most appropriate usability measures. Furthermore, if the user is using a tablet, the usability optimization unit can perform usability optimization optimized for the larger screen. For example, it can generate a layout that matches the screen size of a tablet. In addition, if the user is using a desktop, the usability optimization unit can perform usability optimization optimized for mouse operation. For example, it can generate a layout that matches the screen size of a desktop. By performing optimization while considering the user's device information, more effective usability optimization can be achieved. Some or all of the above processing in the usability optimization unit may be performed using AI or not.

[0131] The usability optimization unit optimizes the content placement of a web page during usability optimization. For example, the usability optimization unit proposes a placement that highlights important information based on user behavior data. The usability optimization unit optimizes the content placement of a web page based on information provided by the user. The usability optimization unit can also analyze scroll data and optimize content placement. For example, the usability optimization unit proposes a placement that highlights important information based on scroll data. Furthermore, the usability optimization unit can propose an optimal content placement based on click data. For example, the usability optimization unit proposes a placement that highlights important information based on click data. By optimizing the content placement of a web page in this way, usability can be improved. Some or all of the above processes in the usability optimization unit may be performed using AI or not.

[0132] The template suggestion unit estimates the user's emotions and adjusts the template suggestion method based on the estimated emotions. For example, if the user is relaxed, the template suggestion unit will provide a more detailed template suggestion. The template suggestion unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The template suggestion unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the template suggestion unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. By adjusting the template suggestion method based on the user's emotions, it is possible to suggest a more appropriate template. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0133] The template suggestion unit analyzes the user's past selection history to propose the most suitable template. For example, the template suggestion unit proposes the most suitable template based on templates the user has previously selected. The template suggestion unit selects and proposes the most suitable template based on the user's past selection history. The template suggestion unit can also propose the most suitable template for a specific time period. For example, it proposes the most suitable template for a specific time period based on the user's past selection history. Furthermore, the template suggestion unit can analyze the user's past selection patterns and propose the most suitable template. For example, it proposes the most suitable template based on the user's past selection patterns. This enables efficient template suggestion by proposing the most suitable template based on the user's past selection history. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0134] The template suggestion unit proposes templates based on the user's current projects and areas of interest. For example, the template suggestion unit prioritizes templates related to the user's current ongoing projects. The template suggestion unit selects and proposes the most suitable template based on the user's current projects and areas of interest. The template suggestion unit can also propose highly relevant templates based on the user's areas of interest. For example, it proposes the most suitable template based on the user's areas of interest. Furthermore, the template suggestion unit can determine template priorities based on topics the user has shown interest in in the past. For example, it proposes the most suitable template based on topics the user has shown interest in in the past. This allows the template suggestion unit to propose highly relevant templates by proposing templates based on the user's current projects and areas of interest. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0135] The template suggestion unit estimates the user's emotions and prioritizes templates based on the estimated emotions. For example, if the user is stressed, the template suggestion unit will postpone less important templates and prioritize more important ones. The template suggestion unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The template suggestion unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the template suggestion unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows the system to prioritize important templates by determining their priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0136] The template suggestion unit proposes highly relevant templates by considering the user's geographical location information when suggesting templates. For example, if the user is in a specific region, the template suggestion unit will prioritize suggesting templates related to that region. The template suggestion unit selects and proposes highly relevant templates based on the user's geographical location information. Furthermore, if the user is traveling, the template suggestion unit can also prioritize suggesting templates related to the travel destination. For example, if the user is traveling, it will propose templates related to the travel destination. In addition, if the user is at home, the template suggestion unit can also prioritize suggesting templates based on information about the user's home area. For example, if the user is at home, it will propose templates based on information about the user's home area. By proposing highly relevant templates based on the user's geographical location information, it is possible to propose more appropriate templates. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0137] The template suggestion unit analyzes the user's social media activity and proposes relevant templates when suggesting templates. For example, the template suggestion unit prioritizes suggesting relevant templates based on information shared by the user on social media. The template suggestion unit selects and proposes highly relevant templates based on the user's social media activity. The template suggestion unit can also suggest relevant templates based on information about accounts the user follows on social media. For example, it suggests relevant templates based on information about accounts the user follows on social media. Furthermore, the template suggestion unit can determine template priorities based on topics the user has shown interest in on social media. For example, it suggests the most suitable template based on topics the user has shown interest in on social media. This allows for the suggestion of more appropriate templates by proposing relevant templates based on the user's social media activity. Some or all of the above processing in the template suggestion unit may be performed using AI or not.

[0138] The estimation unit estimates the user's emotions and adjusts the search engine algorithm's estimation method based on the estimated emotions. For example, if the user is relaxed, the estimation unit performs a detailed algorithm estimation. The estimation unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The estimation unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the estimation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more appropriate algorithm estimation by adjusting the search engine algorithm's estimation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0139] The estimation unit performs estimation by analyzing past changes in search engine algorithms. For example, the estimation unit analyzes past changes in Google's algorithm and performs estimation based on that analysis. The estimation unit analyzes past changes in search engine algorithms based on information provided by the user and performs optimal algorithm estimation. The estimation unit can also analyze past changes in Bing's algorithm and perform estimation based on that analysis. For example, it analyzes past changes in Bing's algorithm and performs optimal algorithm estimation. Furthermore, the estimation unit can also analyze past changes in Yahoo's algorithm and perform estimation based on that analysis. For example, it analyzes past changes in Yahoo's algorithm and performs optimal algorithm estimation. By analyzing past changes in search engine algorithms and performing estimation, more accurate algorithm estimation can be achieved. Some or all of the above processing in the estimation unit may be performed using AI or not.

[0140] The estimation unit learns the algorithm patterns of specific search engines and performs estimations during the estimation process. For example, the estimation unit learns Google's algorithm patterns and performs estimations based on them. The estimation unit learns the algorithm patterns of specific search engines based on information provided by the user and performs the optimal algorithm estimation. The estimation unit can also learn Bing's algorithm patterns and perform estimations based on them. For example, it learns Bing's algorithm patterns and performs the optimal algorithm estimation. Furthermore, the estimation unit can also learn Yahoo's algorithm patterns and perform estimations based on them. For example, it learns Yahoo's algorithm patterns and performs the optimal algorithm estimation. By learning the algorithm patterns of specific search engines and performing estimations, more accurate algorithm estimations can be achieved. Some or all of the above-described processes in the estimation unit may be performed using AI or not.

[0141] The estimation unit estimates the user's emotions and determines the priority of algorithm estimations based on the estimated emotions. For example, if the user is stressed, the estimation unit will postpone less important algorithm estimations and prioritize more important ones. The estimation unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The estimation unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the estimation unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for prioritizing important algorithm estimations by determining the priority of algorithm estimations based on the user's emotions. Emotion estimation is implemented using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0142] The estimation unit performs estimations while considering changes in the algorithms of specific search engines. For example, the estimation unit considers the latest changes in Google's algorithm. Based on the information provided by the user, the estimation unit analyzes the changes in the algorithms of specific search engines and performs the optimal algorithm estimation. The estimation unit can also perform estimations while considering changes in Bing's algorithm. For example, it analyzes the changes in Bing's algorithm and performs the optimal algorithm estimation. Furthermore, the estimation unit can also perform estimations while considering changes in Yahoo's algorithm. For example, it analyzes the changes in Yahoo's algorithm and performs the optimal algorithm estimation. By performing estimations while considering changes in the algorithms of specific search engines, more accurate algorithm estimations can be made. Some or all of the above processing in the estimation unit may be performed using AI or not.

[0143] The estimation unit performs estimation by referring to relevant literature on the algorithm of a specific search engine. For example, the estimation unit performs estimation by referring to the latest research literature on Google's algorithm. Based on the information provided by the user, the estimation unit performs the optimal algorithm estimation by referring to relevant literature on the algorithm of a specific search engine. The estimation unit can also perform estimation by referring to the latest research literature on Bing's algorithm. For example, it performs the optimal algorithm estimation by referring to the latest research literature on Bing's algorithm. Furthermore, the estimation unit can also perform estimation by referring to the latest research literature on Yahoo's algorithm. For example, it performs the optimal algorithm estimation by referring to the latest research literature on Yahoo's algorithm. This allows for more accurate algorithm estimation by referring to relevant literature on the algorithm of a specific search engine. Some or all of the above processing in the estimation unit may be performed using AI or not.

[0144] The data collection unit estimates the user's emotions and adjusts the method of collecting behavioral data based on the estimated emotions. For example, if the user is relaxed, the data collection unit collects detailed behavioral data. The data collection unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The data collection unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the data collection unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the collection of more appropriate behavioral data by adjusting the method of collecting behavioral data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0145] The data collection unit analyzes the user's past behavioral history to select the optimal data collection method when collecting behavioral data. For example, the data collection unit may select the optimal data collection method based on actions the user has frequently performed in the past. The data collection unit analyzes the user's past behavioral history based on the information provided by the user and implements the optimal data collection method. The data collection unit can also select the optimal data collection method for a specific time period. For example, it may select the optimal data collection method for a specific time period based on the user's past behavioral history. Furthermore, the data collection unit may analyze the user's past behavioral patterns to select the most efficient data collection method. For example, it may select the optimal data collection method based on the user's past behavioral patterns. This enables efficient data collection by selecting the optimal data collection method based on the user's past behavioral history. Some or all of the above-described processes in the data collection unit may be performed using AI or not.

[0146] The data collection unit filters behavioral data based on the user's current projects and areas of interest. For example, the data collection unit prioritizes collecting only behavioral data related to the user's current projects. Based on the information provided by the user, the data collection unit identifies the user's current projects and areas of interest and collects the most relevant behavioral data. The data collection unit can also filter and collect highly relevant behavioral data based on the user's areas of interest. For example, it collects the most relevant behavioral data based on the user's areas of interest. Furthermore, the data collection unit can determine the priority of behavioral data based on topics the user has shown interest in in the past. For example, it collects the most relevant behavioral data based on topics the user has shown interest in in the past. This allows for the collection of highly relevant behavioral data by filtering behavioral data based on the user's current projects and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not.

[0147] The data collection unit estimates the user's emotions and determines the priority of behavioral data to collect based on the estimated emotions. For example, if the user is stressed, the data collection unit will postpone collecting less important behavioral data and prioritize collecting more important behavioral data. The data collection unit captures the user's facial expressions with a camera and estimates emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The data collection unit can also record the user's voice and estimate emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the data collection unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the priority of collecting important behavioral data by determining the priority of behavioral data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0148] The data collection unit prioritizes collecting highly relevant data, taking into account the user's geographical location when collecting behavioral data. For example, if the user is in a specific region, the data collection unit prioritizes collecting behavioral data related to that region. Based on the information provided by the user, the data collection unit identifies the user's geographical location and collects the most appropriate behavioral data. The data collection unit can also prioritize collecting behavioral data related to the user's travel destination if the user is traveling. For example, if the user is traveling, it collects behavioral data related to the travel destination. Furthermore, if the user is at home, the data collection unit can prioritize collecting behavioral data around the user's home. For example, if the user is at home, it collects behavioral data around the user's home. This allows for the collection of more appropriate behavioral data by prioritizing the collection of highly relevant data based on the user's geographical location. Some or all of the above processing in the data collection unit may be performed using AI or not.

[0149] The data collection unit analyzes the user's social media activity and collects relevant data when collecting behavioral data. For example, the data collection unit prioritizes collecting relevant behavioral data based on information shared by the user on social media. The data collection unit analyzes the user's social media activity based on information provided by the user and collects the most appropriate behavioral data. The data collection unit can also collect relevant behavioral data based on information about accounts the user follows on social media. For example, it collects relevant behavioral data based on information about accounts the user follows on social media. Furthermore, the data collection unit can determine the priority of behavioral data based on topics the user has shown interest in on social media. For example, it collects the most appropriate behavioral data based on topics the user has shown interest in on social media. This allows for the collection of more appropriate behavioral data by collecting relevant behavioral data based on the user's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not.

[0150] The publishing unit estimates the user's emotions and adjusts the timing of web page publication based on the estimated emotions. For example, if the user is relaxed, the publishing unit will publish a web page containing detailed information. The publishing unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The publishing unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice to calculate an emotion score. Furthermore, the publishing unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for web page publication at a more appropriate time by adjusting the timing of web page publication based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0151] The publishing unit adjusts the level of detail of a webpage based on its importance at the time of publication. For example, if a webpage contains important information, the publishing unit will publish it in detail. The publishing unit evaluates the importance of a webpage based on the information provided by the user and adjusts the level of detail of the publication accordingly. The publishing unit can also publish a concise version of a webpage if it contains general information. For example, if a webpage contains information of particular interest to the user, it will publish it with a detailed explanation. This allows for the publication of appropriate information by adjusting the level of detail of the publication based on the importance of the webpage. Some or all of the above processing in the publishing unit may be performed using AI or not.

[0152] The publishing department applies different publishing methods depending on the category of the web page when publishing. For example, for a product introduction page, the publishing department applies a publishing method that emphasizes the product's features. The publishing department identifies the category of the web page based on the information provided by the user and applies the appropriate publishing method. In the case of blog posts, the publishing department can also apply a publishing method that prioritizes readability. For example, it might summarize the content of the blog post concisely and publish it in a visually appealing layout. Furthermore, in the case of news articles, the publishing department can also apply a publishing method that quickly conveys the latest information. For example, it might highlight the key points of the news article and provide the information in an easy-to-read format. By applying the appropriate publishing method according to the category of the web page, more effective information can be published. Some or all of the above processing in the publishing department may be performed using AI or not.

[0153] The publishing unit estimates the user's emotions and prioritizes the web pages to publish based on the estimated emotions. For example, if a user is stressed, the publishing unit will postpone publishing less important web pages and prioritize publishing more important ones. The publishing unit can also capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on changes in facial expressions. The publishing unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it can analyze the tone and speed of their voice to calculate an emotion score. Furthermore, the publishing unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on fluctuations in heart rate. This allows important information to be published preferentially by prioritizing web pages based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0154] The publishing department adjusts the publication order based on the submission date of the web pages. For example, the publishing department prioritizes publishing web pages with approaching deadlines. The publishing department evaluates the submission date of web pages based on the information provided by users and adjusts the publication order accordingly. The publishing department can also postpone publishing web pages with later submission dates. For example, if a user is in a particular hurry, it will publish immediately. This allows for efficient publishing by adjusting the publication order based on the submission date of the web pages. Some or all of the above processes in the publishing department may be performed using AI or not.

[0155] The publishing unit adjusts the publication order based on the relevance of web pages at the time of publication. For example, the publishing unit prioritizes publishing web pages that contain information of particular interest to the user. The publishing unit evaluates the relevance of web pages based on the information provided by the user and adjusts the publication order accordingly. The publishing unit can also postpone publishing web pages that contain general information. For example, it may prioritize publishing web pages related to the user's current project. This allows important information to be published preferentially by adjusting the publication order based on the relevance of web pages. Some or all of the above processing in the publishing unit may be performed using AI or not.

[0156] The update unit estimates the user's emotions and adjusts how the webpage is updated based on the estimated emotions. For example, if the user is relaxed, the update unit will perform a more detailed update. The update unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. The update unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice to calculate an emotion score. Furthermore, the update unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more appropriate updates by adjusting how the webpage is updated based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0157] The update unit analyzes the access status of web pages and selects the optimal update method during updates. For example, the update unit prioritizes updating pages with high access to provide the latest information. Based on information provided by users, the update unit analyzes the access status of web pages and implements the optimal update method. The update unit can also postpone updating pages with low access. For example, it postpones updating pages with low access. Furthermore, the update unit can analyze access status and select the most effective update method. For example, it selects the optimal update method based on access status. By analyzing the access status of web pages and selecting the optimal update method, more effective updates can be performed. Some or all of the above processes in the update unit may be performed using AI, or they may not be performed using AI.

[0158] The update unit applies different update methods depending on the category of the web page during the update process. For example, in the case of a product introduction page, the update unit applies an update method that emphasizes the product's features. The update unit identifies the category of the web page based on the information provided by the user and applies the appropriate update method. In the case of blog posts, the update unit can also apply an update method that prioritizes readability. For example, it might summarize the content of the blog post concisely and update it with a visually appealing layout. Furthermore, in the case of news articles, the update unit can also apply an update method that quickly conveys the latest information. For example, it might highlight the key points of the news article and provide the information in an easy-to-read format. By applying the appropriate update method according to the category of the web page, more effective updates can be achieved. Some or all of the above processes in the update unit may be performed using AI or not.

[0159] The update unit estimates the user's emotions and determines the priority of web pages to update based on the estimated emotions. For example, if the user is stressed, the update unit will postpone updating less important web pages and prioritize updating more important ones. The update unit can also capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on changes in facial expressions. The update unit can also record the user's voice and estimate their emotions using voice analysis technology. For example, it can analyze the tone and speed of their voice to calculate an emotion score. Furthermore, the update unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it can calculate an emotion score based on fluctuations in heart rate. This allows important information to be updated preferentially by determining the priority of web pages to update based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0160] The update unit adjusts the order of updates based on the submission date of the web pages. For example, the update unit prioritizes updating web pages with approaching deadlines. The update unit evaluates the submission date of web pages based on information provided by the user and adjusts the order of updates accordingly. The update unit can also postpone updating web pages with distant submission dates. For example, if the user is in a particular hurry, the update will be performed immediately. This allows for efficient updates by adjusting the order of updates based on the submission date of the web pages. Some or all of the above processes in the update unit may be performed using AI or not.

[0161] The update unit adjusts the order of updates based on the relevance of the web pages during the update process. For example, the update unit prioritizes updating web pages that contain information of particular interest to the user. The update unit evaluates the relevance of web pages based on the information provided by the user and adjusts the order of updates accordingly. The update unit can also postpone updating web pages that contain general information. For example, it may prioritize updating web pages related to the user's current project. This allows important information to be updated preferentially by adjusting the order of updates based on the relevance of the web pages. Some or all of the above processes in the update unit may be performed using AI or not.

[0162] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0163] The reception desk can analyze user input in real time and provide appropriate feedback based on that input. For example, if there are typos or grammatical errors in the text entered by the user, it will immediately suggest corrections. Furthermore, if the input is unclear, the reception desk can prompt the user to complete the information by asking specific questions. In addition, the reception desk can automatically search for relevant information based on the user's input and provide it to the user. This allows users to efficiently provide information and receive feedback from the system.

[0164] The generation unit can suggest the optimal layout and content when generating a web page, taking into account the user's past web page generation history. For example, it can prioritize suggesting layouts that the user has previously preferred. The generation unit can also analyze the user's past generation history and suggest the most effective content placement. Furthermore, based on the user's past generation history, the generation unit can suggest templates suitable for specific themes and styles. This allows users to leverage their past experience to create more effective web pages.

[0165] The template suggestion function can propose templates based on the user's current project progress. For example, it can suggest basic templates in the early stages of a project and more detailed templates as the project progresses. The template suggestion function can also provide customization options for templates according to the user's project progress. Furthermore, it can suggest relevant resources and tools based on the project progress. This allows the user to select the most suitable template as their project progresses.

[0166] The SEO Optimization Department can monitor changes in the algorithms of specific search engines in real time and perform SEO optimization based on those changes. For example, if Google's algorithm is updated, the department can immediately reflect the update and perform SEO optimization. The SEO Optimization Department can also monitor the algorithms of multiple search engines simultaneously and implement the most suitable SEO measures for each algorithm. Furthermore, the SEO Optimization Department can propose specific SEO measures to users based on algorithm changes. This ensures that users are always implementing the latest SEO strategies.

[0167] The usability optimization unit can analyze user behavior data in real time and optimize web pages based on the analysis results. For example, if a user frequently clicks a particular button, it can adjust the position and design of that button. The usability optimization unit can also optimize the placement of navigation menus based on user behavior data. Furthermore, the usability optimization unit can adjust the display order of content based on user behavior data. This allows for the provision of more user-friendly web pages based on user behavior data.

[0168] The reception unit can estimate the user's emotions and adjust the input interface based on those emotions. For example, if the user is feeling stressed, it can provide a simple and intuitive interface. The reception unit can also adjust the number and arrangement of input fields according to the user's emotions. Furthermore, the reception unit can adjust the frequency and content of feedback on the input based on the user's emotions. This allows for the provision of an input interface that is considerate of the user's emotions.

[0169] The generation unit can estimate the user's emotions and adjust the tone and style of the generated webpage based on those emotions. For example, if the user is relaxed, it will generate a webpage with a casual and friendly tone. The generation unit can also adjust the color scheme and font of the webpage according to the user's emotions. Furthermore, the generation unit can adjust the length and level of detail of the webpage's content based on the user's emotions. This allows for the generation of webpages tailored to the user's emotions.

[0170] The SEO Optimization Department can estimate the user's emotions and adjust the SEO recommendations based on those emotions. For example, if a user is feeling stressed, it will suggest simple and easy-to-implement SEO measures. The SEO Optimization Department can also adjust the level of detail and explanation of the suggestions according to the user's emotions. Furthermore, it can adjust the priority of the suggestions based on the user's emotions. This allows the department to provide SEO recommendations that are considerate of the user's feelings.

[0171] The usability optimization unit can estimate the user's emotions and make usability improvement suggestions based on those emotions. For example, if the user is relaxed, it will make detailed improvement suggestions. The usability optimization unit can also adjust the content and format of the improvement suggestions according to the user's emotions. Furthermore, the usability optimization unit can adjust the priority of improvement suggestions based on the user's emotions. This allows for usability improvement suggestions that take the user's emotions into consideration.

[0172] The update unit can estimate the user's emotions and adjust the web page updates based on those emotions. For example, if the user is feeling stressed, it will provide concise and easy-to-understand updates. The update unit can also adjust the level of detail and explanation in the updates according to the user's emotions. Furthermore, the update unit can adjust the priority of the updates based on the user's emotions. This allows for web page updates that are sensitive to the user's emotions.

[0173] The following briefly describes the processing flow for example form 2.

[0174] Step 1: The reception desk receives information provided by the user. The reception desk can receive text information, image information, and voice input entered by the user. For example, it can use speech recognition technology to convert the user's voice into text and receive it as information. Step 2: The generation unit generates web pages that meet specific conditions based on the information received by the reception unit. The generation unit uses generation AI to generate the web page layout and content based on user information. The generation unit also includes an SEO optimization unit and a usability optimization unit, performing optimization from both an SEO and usability perspective. Step 3: The output unit outputs the web page generated by the generation unit. The output unit can output the generated web page in HTML format. It can also output in PDF format or image format.

[0175] 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.

[0176] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0177] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0178] For example, the reception unit is implemented by the reception device 38 of the smart device 14 and receives information provided by the user. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and includes an SEO optimization unit and a usability optimization unit. For example, the output unit is implemented by the output device 40 of the smart device 14 and outputs the generated web page. For example, the publication unit is implemented by the specific processing unit 290 of the data processing device 12 and publishes the web page. For example, the update unit is implemented by the specific processing unit 290 of the data processing device 12 and updates the published web page based on the access status. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0179] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0180] 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.

[0181] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0182] 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.

[0183] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0184] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0185] 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.

[0186] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0187] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0188] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0189] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0190] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0191] 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.

[0192] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0193] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0194] For example, the reception unit is implemented by the microphone 238 of the smart glasses 214 and receives information provided by the user. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and includes an SEO optimization unit and a usability optimization unit. For example, the output unit is implemented by the speaker 240 of the smart glasses 214 and outputs the generated web page. For example, the publication unit is implemented by the specific processing unit 290 of the data processing device 12 and publishes the web page. For example, the update unit is implemented by the specific processing unit 290 of the data processing device 12 and updates the published web page based on the access status. The correspondence between each unit and the device and control unit is not limited to the examples described above and can be changed in various ways.

[0195] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0196] 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.

[0197] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0198] 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.

[0199] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0200] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0201] 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.

[0202] 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.

[0203] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0204] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0205] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0206] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0207] 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.

[0208] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0209] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0210] For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and receives information provided by the user. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and includes an SEO optimization unit and a usability optimization unit. For example, the output unit is implemented by the display 343 of the headset terminal 314 and outputs the generated web page. For example, the publication unit is implemented by the specific processing unit 290 of the data processing device 12 and publishes the web page. For example, the update unit is implemented by the specific processing unit 290 of the data processing device 12 and updates the published web page based on the access status. The correspondence between each unit and the device and control unit is not limited to the examples described above and can be changed in various ways.

[0211] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0212] 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.

[0213] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0214] 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.

[0215] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0216] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0217] 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.

[0218] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0219] 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.

[0220] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0221] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0222] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0223] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0224] 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.

[0225] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0226] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0227] For example, the reception unit is implemented by the microphone 238 of the robot 414 and receives information provided by the user. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and includes an SEO optimization unit and a usability optimization unit. For example, the output unit is implemented by the speaker 240 of the robot 414 and outputs the generated web page. For example, the publication unit is implemented by the specific processing unit 290 of the data processing device 12 and publishes the web page. For example, the update unit is implemented by the specific processing unit 290 of the data processing device 12 and updates the published web page based on the access status. The correspondence between each unit and the device and control unit is not limited to the examples described above and can be changed in various ways.

[0228] 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.

[0229] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0230] 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.

[0231] 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.

[0232] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0233] 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."

[0234] 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.

[0235] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0244] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0245] 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.

[0246] (Note 1) A reception desk that receives information provided by the user, A generation unit generates a web page that meets specific conditions based on the information received by the reception unit, The system comprises an output unit that outputs the web page generated by the generation unit. A system characterized by the following features. (Note 2) The generating unit is The aforementioned web page is adjusted from an SEO perspective by an SEO optimization unit, The system includes a usability optimization unit that adjusts the aforementioned web page from a usability perspective. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is It includes a template suggestion section that proposes the most appropriate template to the user from among multiple templates. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned SEO optimization unit, It includes an estimation unit that estimates the algorithm of a specific search engine, The adjustment is performed based on the algorithm estimated by the estimation unit. The system described in Appendix 2, characterized by the features described herein. (Note 5) The usability optimization unit described above is: It is equipped with a data collection unit that collects user behavior data, Adjustments are made based on the data collected by the aforementioned collection unit. The system described in Appendix 2, characterized by the features described herein. (Note 6) The generating unit is The information received by the aforementioned reception unit, along with information including the algorithm of a specific search engine and information regarding usability, is input into the generating AI. The generation AI is made to generate web pages that meet the aforementioned specific conditions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The generating unit is The public section that publishes the aforementioned web page, The system includes an update unit that updates the web page based on the access status of the web page published by the public access unit. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned update unit is Track and adjust based on the user's eye movements. The system described in Appendix 7, characterized by the features described herein. (Note 9) The aforementioned SEO optimization unit, Adjust the internal link structure. The system described in Appendix 2, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of information reception based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is Analyze the user's past information provision history and select the appropriate method of acceptance. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving information, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is The system estimates the user's emotions and prioritizes the information to be received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is When receiving information, the system prioritizes receiving information that is highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reception unit is When receiving information, the system analyzes the user's social media activity and collects relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the user's emotions and adjusts the design of the generated web pages based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is During generation, adjust the level of detail based on the importance of the web page. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is During generation, different generation algorithms are applied depending on the category of the web page. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the length of the generated web pages based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is During generation, the generation priority is determined based on when the web page was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is During generation, the generation order is adjusted based on the relevance of the web pages. The system described in Appendix 1, characterized by the features described herein. (Note 22) The output unit is, It estimates the user's emotions and adjusts the timing of the output based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The output unit is, At the time of output, adjust the output detail level based on the importance of the web page The system according to Addendum 1, characterized by this (Addendum 24) The output unit At the time of output, apply different output methods according to the category of the web page The system according to Addendum 1, characterized by this (Addendum 25) The output unit Estimate the user's emotion and determine the priority order of the web pages to be output based on the estimated user's emotion The system according to Addendum 1, characterized by this (Addendum 26) The output unit At the time of output, adjust the output order based on the submission time of the web page The system according to Addendum 1, characterized by this (Addendum 27) The output unit At the time of output, adjust the output order based on the relevance of the web page The system according to Addendum 1, characterized by this (Addendum 28) The SEO optimization unit Estimate the user's emotion and adjust the SEO optimization method based on the estimated user's emotion The system according to Addendum 2, characterized by this (Addendum 29) The SEO optimization unit At the time of SEO optimization, analyze the algorithm of a specific search engine and perform optimization The system according to Addendum 2, characterized by this (Addendum 30) The SEO optimization unit At the time of SEO optimization, optimize the internal link structure of the web page The system according to Addendum 2, characterized by this (Addendum 31) The SEO optimization unit It estimates user sentiment and determines SEO optimization priorities based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned SEO optimization unit, When optimizing for SEO, take into account changes in the algorithms of specific search engines. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned SEO optimization unit, When optimizing for SEO, optimize the external link structure of your web pages. The system described in Appendix 2, characterized by the features described herein. (Note 34) The usability optimization unit described above is: We estimate the user's emotions and adjust the usability optimization method based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The usability optimization unit described above is: When optimizing usability, user behavior data is analyzed and used for optimization. The system described in Appendix 2, characterized by the features described herein. (Note 36) The usability optimization unit described above is: When optimizing usability, optimize the navigation structure of a web page. The system described in Appendix 2, characterized by the features described herein. (Note 37) The usability optimization unit described above is: It estimates the user's emotions and determines the priority of usability optimization based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 38) The usability optimization unit described above is: When optimizing usability, the user's device information is taken into consideration. The system described in Appendix 2, characterized by the features described herein. (Note 39) The usability optimization unit optimizes the content layout of the web page during usability optimization. The system according to Supplementary Note 2, characterized by the above. (Supplementary Note 40) The template proposal unit estimates the user's emotion and adjusts the template proposal method based on the estimated user's emotion. The system according to Supplementary Note 3, characterized by the above. (Supplementary Note 41) The template proposal unit analyzes the user's past selection history and proposes an optimal template when proposing a template. The system according to Supplementary Note 3, characterized by the above. (Supplementary Note 42) The template proposal unit proposes a template based on the user's current project or area of interest when proposing a template. The system according to Supplementary Note 3, characterized by the above. (Supplementary Note 43) The template proposal unit estimates the user's emotion and determines the priority of the template based on the estimated user's emotion The system according to Supplementary Note 3, characterized by the above. (Supplementary Note 44) The template proposal unit considers the user's geographical location information and proposes a highly relevant template when proposing a template. The system according to Supplementary Note 3, characterized by the above. (Supplementary Note 45) The template proposal unit analyzes the user's social media activities and proposes a relevant template when proposing a template. The system according to Supplementary Note 3, characterized by the above. (Supplementary Note 46) The estimation unit We estimate the user's emotions and adjust the search engine algorithm's estimation method based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 47) The estimation unit, During estimation, the algorithm changes of past search engines are analyzed to make the estimation. The system described in Appendix 4, characterized by the features described herein. (Note 48) The estimation unit, During estimation, the algorithm patterns of a specific search engine are learned to perform the estimation. The system described in Appendix 4, characterized by the features described herein. (Note 49) The estimation unit, The system estimates the user's emotions and determines the algorithm's estimation priority based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 50) The estimation unit, During estimation, the algorithm of a specific search engine is taken into consideration. The system described in Appendix 4, characterized by the features described herein. (Note 51) The estimation unit, During estimation, the estimation is performed based on relevant literature related to the algorithm of a specific search engine. The system described in Appendix 4, characterized by the features described herein. (Note 52) The aforementioned collection unit is We estimate the user's emotions and adjust the method of collecting behavioral data based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 53) The aforementioned collection unit is When collecting behavioral data, the system analyzes the user's past behavioral history to select the optimal collection method. The system described in Appendix 5, characterized by the features described herein. (Note 54) The aforementioned collection unit is When collecting behavioral data, filter it based on the user's current projects and areas of interest. The system described in Appendix 5, characterized by the features described herein. (Note 55) The aforementioned collection unit is It estimates the user's emotions and determines the priority of behavioral data to collect based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 56) The aforementioned collection unit is When collecting behavioral data, the system prioritizes collecting highly relevant data by considering the user's geographical location. The system described in Appendix 5, characterized by the features described herein. (Note 57) The aforementioned collection unit is When collecting behavioral data, analyze users' social media activity to collect relevant data. The system described in Appendix 5, characterized by the features described herein. (Note 58) The aforementioned public section is, We estimate the user's emotions and adjust the timing of web page publication based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 59) The aforementioned public section is, When publishing, adjust the level of detail based on the importance of the web page. The system described in Appendix 7, characterized by the features described herein. (Note 60) The aforementioned public section is, When publishing, apply different publishing methods depending on the category of the web page. The system described in Appendix 7, characterized by the features described herein. (Note 61) The aforementioned public section is, It estimates the user's emotions and determines the priority of web pages to publish based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 62) The aforementioned public section is, When publishing, the publication order will be adjusted based on when the web pages were submitted. The system described in Appendix 7, characterized by the features described herein. (Note 63) The aforementioned public section is, When publishing, adjust the publication order based on the relevance of the web pages. The system described in Appendix 7, characterized by the features described herein. (Note 64) The aforementioned update unit is It estimates the user's emotions and adjusts how web pages are updated based on those estimated emotions. The system described in Appendix 7, characterized by the features described herein. (Note 65) The aforementioned update unit is When updating, the system analyzes web page access data to select the most suitable update method. The system described in Appendix 7, characterized by the features described herein. (Note 66) The aforementioned update unit is When updating, apply different update methods depending on the web page category. The system described in Appendix 7, characterized by the features described herein. (Note 67) The aforementioned update unit is It estimates the user's emotions and determines the priority of web pages to update based on the estimated user emotions. The system described in Appendix 7, characterized by the features described herein. (Note 68) The aforementioned update unit is When updating, adjust the order of updates based on when the web pages were submitted. The system described in Appendix 7, characterized by the features described herein. (Note 69) The aforementioned update unit is When updating, adjust the update order based on the relevance of the web pages. The system described in Appendix 7, characterized by the features described herein. [Explanation of Symbols]

[0247] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that receives information provided by the user, A generation unit generates a web page that meets specific conditions based on the information received by the reception unit, The system comprises an output unit that outputs the web page generated by the generation unit. A system characterized by the following features.

2. The generating unit is The aforementioned web page is adjusted from an SEO perspective by an SEO optimization unit, The system includes a usability optimization unit that adjusts the aforementioned web page from a usability perspective. The system according to feature 1.

3. The generating unit is It includes a template suggestion section that proposes the most appropriate template to the user from among multiple templates. The system according to feature 1.

4. The aforementioned SEO optimization unit, It includes an estimation unit that estimates the algorithm of a specific search engine, The adjustment is performed based on the algorithm estimated by the estimation unit. The system according to feature 2.

5. The usability optimization unit described above is: It is equipped with a data collection unit that collects user behavior data, Adjustments are made based on the data collected by the aforementioned collection unit. The system according to feature 2.

6. The generating unit is The information received by the aforementioned reception unit, along with information including the algorithm of a specific search engine and information regarding usability, is input into the generating AI. The generation AI is made to generate web pages that satisfy the aforementioned specific conditions. The system according to feature 1.

7. The generating unit is The public section that publishes the aforementioned web page, The system includes an update unit that updates the web page based on the access status of the web page published by the public access unit. The system according to feature 1.

8. The aforementioned update unit is Track and adjust based on the user's eye movements. The system according to feature 7.

9. The aforementioned SEO optimization unit, Adjust the internal link structure. The system according to feature 2.

Images