system

Abstract

We provide a system that allows visually impaired users to easily navigate web pages and access information. [Solution] The system consists of an editorial department that dynamically edits the HTML of a web page, a support department that adapts the edited HTML to the web standard WAI-ARIA, a navigation department that provides keyboard navigation based on the adapted HTML, an alternative text generation department that generates alternative text for images based on the navigation, a labeling department that adds labels to form fields based on the alternative text, a filter department that provides a filter function to accommodate color blindness based on the labels, and a summarization department that summarizes the content based on the filter function.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the accessibility support for websites varies from site to site, and there is a problem that users with visual impairments feel difficulty when using the Internet.

[0005] The system according to the embodiment aims to enable a user with a visual impairment to easily navigate a web page and access information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an editing unit, a correspondence unit, a navigation unit, an alternative text generation unit, a labeling unit, a filter unit, and a summarization unit. The editing unit dynamically edits the HTML of a web page. The correspondence unit makes the HTML edited by the editing unit compatible with the web standard WAI-ARIA. The navigation unit provides keyboard navigation based on the HTML made compatible by the correspondence unit. The alternative text generation unit generates alternative text for images based on the navigation provided by the navigation unit. The labeling unit adds labels to form fields based on the alternative text generated by the alternative text generation unit. The filter unit provides a filter function for color blindness based on the labels added by the labeling unit. The summarization unit summarizes the content based on the filter function provided by the filter unit. [Effects of the Invention]

[0007] The system according to this embodiment can enable visually impaired users to easily navigate web pages and access information. [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 tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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 tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 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 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by the contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 (see FIG. 2) acquires 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) An accessibility-supporting browser or browser extension according to an embodiment of the present invention is a system for eliminating difficulties faced by visually impaired and elderly people when using the internet. When a user opens a web page, the system uses AI to dynamically edit the page's HTML and make it compliant with the web standard WAI-ARIA. This allows visually impaired and elderly people to easily navigate web pages and access information without having to learn additional tools. For example, when a user opens a web page, the AI ​​analyzes the page's HTML. The analyzed HTML is converted into a format accessible to visually impaired and elderly people. For example, appropriate tags are added to links and buttons on the page to enable keyboard navigation. The system also analyzes image content and automatically generates appropriate alternative text (alt text), making it easier to understand image content. Next, appropriate labels are added to form fields, making it easier to interact with interactive elements and allowing visually impaired and elderly people to easily use forms. The system also provides a filter function to adjust the page's colors for users with color blindness, enabling them to accurately understand the page content. Furthermore, it includes a function to summarize the content of long articles and pages, extracting and providing only the important points. This will enable visually impaired and elderly individuals to efficiently acquire information. This mechanism eliminates difficulties for visually impaired and elderly individuals when using the internet, making information access easier. For example, when a visually impaired person opens a webpage, AI can automatically analyze the page and provide features such as keyboard navigation, alternative text generation, form field labeling, color blindness support, and content summarization, allowing visually impaired individuals to easily navigate pages and acquire information. For the elderly, this also eliminates problems with declining eyesight and complex interfaces, making webpage browsing easier. Therefore, accessibility-supported browsers or browser extensions can eliminate difficulties for visually impaired and elderly individuals when using the internet, making information access easier.

[0029] The accessibility support browser or browser extension according to the embodiment comprises an editing unit, a response unit, a navigation unit, an alternative text generation unit, a labeling unit, a filter unit, and a summarization unit. The editing unit dynamically edits the HTML of a web page. The editing unit can perform real-time editing using, for example, JavaScript®. The editing unit can also perform server-side editing. For example, the editing unit parses the HTML of a web page and converts it into a format accessible to visually impaired and elderly people. The response unit makes the HTML edited by the editing unit compatible with the web standard WAI-ARIA. For example, the response unit adds appropriate attributes to the HTML according to specific methods and criteria for WAI-ARIA compatibility. The navigation unit provides keyboard navigation based on the HTML made compatible by the response unit. For example, the navigation unit adds appropriate tags to links and buttons on the page to enable keyboard navigation. The alternative text generation unit generates alternative text for images based on the navigation provided by the navigation unit. For example, the alternative text generation unit parses the content of an image and automatically generates appropriate alternative text. The labeling unit adds labels to form fields based on alternative text generated by the alternative text generation unit. The labeling unit, for example, adds appropriate labels to form fields to facilitate interaction with interactive elements. The filter unit provides colorblind-friendly filtering based on the labels added by the labeling unit. The filter unit, for example, provides filtering to adjust the page colors for users with color blindness. The summarization unit summarizes the content based on the filtering function provided by the filter unit. The summarization unit, for example, summarizes the content of long articles or pages, extracting and providing only the important points. As a result, the accessibility-supported browser or browser extension according to the embodiment can eliminate difficulties for visually impaired and elderly people when using the internet and make it easier for them to access information.

[0030] The editorial team dynamically edits the HTML of web pages. For example, they can perform real-time editing using JavaScript. Specifically, they can dynamically add, delete, and modify elements of web pages using JavaScript's DOM manipulation. This allows the content of the page to be changed as needed, even after the user has loaded the page. The editorial team can also perform server-side editing. For example, they can use server-side scripts (PHP, Python, Node.js, etc.) to generate HTML in response to requests and send it to the client. This ensures that the latest information is provided every time the user accesses the page. Furthermore, the editorial team parses the HTML of web pages and converts it into an accessible format for the visually impaired and the elderly. Specifically, they analyze the HTML structure, appropriately place heading tags (h1, h2, etc.) and list tags (ul, ol, etc.) so that screen readers can accurately read the content. They can also remove unnecessary decorations and animations and change to a simple and easy-to-read layout. This allows the editorial team to perform flexible editing according to user needs and improve accessibility.

[0031] The support team will make the HTML edited by the editorial team compliant with the web standard WAI-ARIA. For example, the support team will add appropriate attributes to the HTML according to the specific methods and standards of WAI-ARIA compliance. Specifically, they will use the role attribute to clarify the role of each element and the aria-label and aria-labelledby attributes to add descriptions to the elements. This will allow screen readers to accurately convey the role and content of each element. It is also possible to notify dynamically updated content in real time using the aria-live attribute. Furthermore, the support team will improve the usability of interactive elements (buttons, links, form fields, etc.) according to WAI-ARIA best practices. For example, they will appropriately set the tabindex attribute so that all interactive elements can be accessed using only keyboard operations. This will allow visually impaired and elderly people to operate web pages using only a keyboard. Through these measures, the support team can significantly improve the accessibility of web pages.

[0032] The navigation section provides keyboard navigation based on the HTML handled by the corresponding section. For example, the navigation section adds appropriate tags to links and buttons on the page to enable keyboard navigation. Specifically, it sets the tabindex attribute for each link and button, allowing focus to be moved sequentially using the keyboard's Tab key. It also manages the state of interactive elements such as dropdown menus and modal windows using the aria-controls and aria-expanded attributes. This allows users to access and interact with all elements on the page using only keyboard operations. Furthermore, the navigation section can also provide keyboard shortcuts. For example, pressing a specific key combination can jump to a specific section on the page or perform a specific operation. This allows users to efficiently navigate the page and quickly access the information they need. Through these functions, the navigation section helps visually impaired and elderly people to comfortably use web pages.

[0033] The alternative text generation unit generates alternative text for images based on the navigation provided by the navigation unit. For example, the alternative text generation unit analyzes the content of an image and automatically generates appropriate alternative text. Specifically, it analyzes the content of an image using image recognition technology to identify key objects and scenes. For example, if a person is in the image, it analyzes the person's actions and facial expressions and generates specific alternative text such as "A smiling woman is jogging in a park." It is also possible to express the content of an image in natural language using the generation AI. For example, a prompt such as "Please describe the content of this image" can be entered into the generation AI, and the generated text can be used as alternative text. This allows visually impaired people to understand the content of images through screen readers. Furthermore, the alternative text generation unit can collect feedback from users and continuously improve the accuracy of the generated alternative text. This allows the alternative text generation unit to provide more accurate and useful information to visually impaired people.

[0034] The labeling unit adds labels to form fields based on alternative text generated by the alternative text generation unit. For example, the labeling unit adds appropriate labels to form fields, facilitating interaction with interactive elements. Specifically, it adds a label tag to each form field and associates it with the corresponding form field using the for attribute. This allows screen readers to read the form field labels, making it easier for users to understand the purpose of each field. It is also possible to provide additional explanations for form fields using the aria-label and aria-labelledby attributes. This allows users to accurately understand and input form content. Furthermore, the labeling unit also provides functionality to appropriately display error messages and hints for form fields. For example, it can be configured to display a visual error message along with the screen reader reading the error message if a required field is left blank or the input is inaccurate. This allows users to quickly correct input errors and provide accurate information. Through these functions, the labeling unit can significantly improve the usability and accessibility of forms.

[0035] The filter unit provides colorblind-friendly filtering based on labels added by the labeling unit. For example, the filter unit provides a filter function that adjusts page colors for users with color blindness. Specifically, it uses an algorithm that dynamically converts page colors according to the type of color blindness (red-green color blindness, blue-yellow color blindness, total color blindness, etc.). For example, for users with red-green color blindness, it converts red and green colors to colors that are easier to distinguish, and for users with blue-yellow color blindness, it converts blue and yellow colors to colors that are easier to distinguish. Furthermore, for users with total color blindness, it converts all colors to grayscale and emphasizes the contrast between light and dark. This makes it easier for users with color blindness to accurately recognize the content of the page. In addition, the filter unit also provides a function that allows users to customize filter settings according to their type of color blindness. For example, a user can select their type of color blindness on the settings screen and apply the corresponding filter. This allows the filter unit to provide flexible and individualized support for users with color blindness.

[0036] The summarization unit summarizes content based on the filtering functions provided by the filtering unit. For example, the summarization unit summarizes the content of long articles or pages, extracting and providing only the important points. Specifically, it uses natural language processing technology to analyze the structure of the text and extract the main topics and keywords. For example, a prompt such as "Summarize the main points of this text" can be input to the generation AI, and the generated summary can be provided. This saves users time reading long texts and allows them to quickly access important information. Furthermore, the summarization unit can also customize the content of the summary based on the user's interests. For example, if a user is interested in a particular topic, information related to that topic can be prioritized and included in the summary. In this way, the summarization unit can provide the user with the most important and useful information. Through these functions, the summarization unit can help visually impaired and elderly people efficiently understand the content of web pages and easily access information.

[0037] The editorial team can parse the HTML of a webpage and convert it into a format accessible to the visually impaired and the elderly. For example, the editorial team can parse the HTML of a webpage and convert it into a format accessible to the visually impaired and the elderly. For example, the editorial team can adjust font sizes, contrast, and enable text-to-speech. This allows the visually impaired and the elderly to easily navigate webpages and access information without having to learn additional tools. Some or all of the above processing by the editorial team may be performed using AI, for example, or not. For example, the editorial team can use an AI model to parse the HTML of a webpage and convert it into a format accessible to the visually impaired and the elderly.

[0038] The navigation unit can add appropriate tags to links and buttons on a page, enabling keyboard navigation. For example, the navigation unit can add appropriate tags to links and buttons on a page, enabling keyboard navigation. The navigation unit can also clarify, for example, which tags to add to which elements, and the attributes of those tags. This allows visually impaired and elderly people to navigate web pages using a keyboard. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not. For example, the navigation unit can use an AI model to add appropriate tags to links and buttons on a page and enable keyboard navigation.

[0039] The alternative text generation unit can analyze the content of an image and automatically generate appropriate alternative text. For example, the alternative text generation unit can analyze the content of an image and automatically generate appropriate alternative text. The alternative text generation unit can clarify, for example, how to analyze the content of an image and what information to include. This makes it easier for visually impaired people to understand image content. Some or all of the above-described processes in the alternative text generation unit may be performed using AI, for example, or without AI. For example, the alternative text generation unit can use an AI model to analyze the content of an image and automatically generate appropriate alternative text.

[0040] The labeling unit can add appropriate labels to form fields and facilitate the operation of interactive elements. For example, the labeling unit can add appropriate labels to form fields and facilitate the operation of interactive elements. The labeling unit can clarify, for example, which form fields to add what labels to. This makes forms easy for visually impaired and elderly people to use. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit can use an AI model to add appropriate labels to form fields and facilitate the operation of interactive elements.

[0041] The filter unit can provide a filter function that adjusts the page colors for users with color blindness. For example, the filter unit can clarify which colors to adjust, how to adjust them, and the algorithms used. This allows users with color blindness to accurately understand the page content. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to provide a filter function that adjusts the page colors for users with color blindness.

[0042] The summarization function can summarize the content of long articles or pages, extracting and providing only the important points. For example, the summarization function can summarize the content of long articles or pages, extracting and providing only the important points. The summarization function can clarify, for example, which information to extract, the length and format of the summary, etc. This allows visually impaired people and the elderly to efficiently acquire information. Some or all of the processing described above in the summarization function may be performed using AI, for example, or not using AI. For example, the summarization function can use an AI model to summarize the content of long articles or pages and extract and provide only the important points.

[0043] The editorial department can analyze the past access history of a web page and select the optimal editing method. For example, the editorial department can analyze the past access history of a web page and select the optimal editing method. For example, the editorial department can select the optimal editing method based on the history of pages that users frequently access. The editorial department can also suggest the optimal editing method by referring to the editing methods that users have used in the past. Furthermore, the editorial department can select the optimal editing method for a specific time period based on the user's past access history. In this way, the optimal editing method is selected based on past access history. Some or all of the above processes performed by the editorial department may be performed using AI, for example, or not using AI. For example, the editorial department can use an AI model to analyze the past access history of a web page and select the optimal editing method.

[0044] The editorial team can perform filtering when editing HTML based on the user's current browsing status and areas of interest. For example, the editorial team can filter HTML based on the user's current browsing status and areas of interest. For example, the editorial team can prioritize editing information relevant to the page the user is currently viewing. The editorial team can also edit HTML to highlight important information based on the user's areas of interest. Furthermore, the editorial team can select the optimal filtering method by referring to the user's browsing history. This ensures that optimal filtering is performed based on the user's current situation and areas of interest. Some or all of the above processing by the editorial team may be performed using AI, for example, or not. For example, the editorial team can use an AI model to perform filtering based on the user's current browsing status and areas of interest when editing HTML.

[0045] The editorial team can prioritize editing relevant content by considering the user's geographical location when editing HTML. For example, the editorial team can prioritize editing relevant content by considering the user's geographical location when editing HTML. For example, the editorial team can prioritize editing information for the area the user is currently in. The editorial team can also prioritize editing relevant local news and event information based on the user's geographical location. Furthermore, the editorial team can prioritize editing optimal route guidance and map information based on the user's location. This ensures that the most relevant content is prioritized based on the user's geographical location. Some or all of the above processing by the editorial team may be performed using AI, for example, or not. For example, the editorial team can use an AI model to prioritize editing relevant content by considering the user's geographical location when editing HTML.

[0046] The editorial team can analyze a user's social media activity and edit relevant content when editing HTML. For example, the editorial team can analyze a user's social media activity and edit relevant content when editing HTML. For example, the editorial team can prioritize editing relevant content based on information shared by the user on social media. The editorial team can also edit relevant content based on information of interest to the user's social media followers and friends. Furthermore, the editorial team can analyze a user's social media activity history and select the optimal editing method. This ensures that the most relevant content is edited based on the user's social media activity. Some or all of the above processes performed by the editorial team may be done using AI, for example, or not. For example, the editorial team can use an AI model to analyze a user's social media activity and edit relevant content when editing HTML.

[0047] The response unit can adjust the level of detail of the response based on the importance of the web page when implementing WAI-ARIA. For example, the response unit adjusts the level of detail of the response based on the importance of the web page when implementing WAI-ARIA. For example, the response unit performs detailed WAI-ARIA response on pages that contain important information. The response unit can also perform basic WAI-ARIA response on pages that contain general information. Furthermore, the response unit can perform particularly detailed WAI-ARIA response on pages that users frequently access. This ensures that optimal WAI-ARIA response is performed based on the importance of the web page. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can use an AI model to adjust the level of detail of the response based on the importance of the web page when implementing WAI-ARIA.

[0048] The response unit can apply different response algorithms depending on the category of the web page when performing WAI-ARIA analysis. For example, the response unit can apply different response algorithms depending on the category of the web page when performing WAI-ARIA analysis. For example, on a news site, the response unit can perform appropriate WAI-ARIA analysis on article headlines and body text. The response unit can also perform appropriate WAI-ARIA analysis on shopping sites for product information and cart functions. Furthermore, the response unit can perform appropriate WAI-ARIA analysis on social media sites for posting and commenting functions. This ensures that optimal WAI-ARIA analysis is performed according to the category of the web page. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can use an AI model to apply different response algorithms depending on the category of the web page when performing WAI-ARIA analysis.

[0049] The support unit can determine the priority of WAI-ARIA implementation based on the update frequency of web pages. For example, the support unit can prioritize WAI-ARIA implementation on pages that are frequently updated. It can also perform basic WAI-ARIA implementation on pages that are not frequently updated. Furthermore, it can perform particularly detailed WAI-ARIA implementation on pages that are frequently accessed by users. This ensures that optimal WAI-ARIA implementation is performed based on the update frequency of web pages. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can use an AI model to determine the priority of implementation based on the update frequency of web pages when implementing WAI-ARIA.

[0050] The response unit can adjust the order of responses based on the relevance of web pages when implementing WAI-ARIA. For example, the response unit adjusts the order of responses based on the relevance of web pages when implementing WAI-ARIA. For example, the response unit prioritizes relevant information based on the content of the page the user is currently viewing. The response unit can also highlight important information based on the user's areas of interest. Furthermore, the response unit can select the optimal response method by referring to the user's browsing history. This ensures that optimal WAI-ARIA support is provided based on the relevance of web pages. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can use an AI model to adjust the order of responses based on the relevance of web pages when implementing WAI-ARIA.

[0051] The navigation unit can improve the accuracy of navigation by considering the relationships between web pages during navigation. For example, the navigation unit can improve the accuracy of navigation by considering the relationships between web pages during navigation. For example, the navigation unit can improve the accuracy of navigation by highlighting links between related pages. The navigation unit can also provide optimal navigation by considering the relationships between pages that the user frequently accesses. Furthermore, the navigation unit can analyze the structure of web pages and propose the optimal navigation route. This improves the accuracy of navigation by considering the relationships between web pages. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to improve the accuracy of navigation by considering the relationships between web pages during navigation.

[0052] The navigation unit can perform navigation while considering the attribute information of the web page provider. For example, the navigation unit can perform navigation while considering the attribute information of the web page provider. For example, if the web page provider provides reliable information, the navigation unit will prioritize that information in the navigation. Furthermore, if the web page provider has specialized knowledge, the navigation unit can also emphasize that information in the navigation. In addition, the navigation unit can propose the optimal navigation route based on the attribute information of the web page provider. This allows for navigation prioritizing reliable information by considering the attribute information of the web page provider. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to perform navigation while considering the attribute information of the web page provider.

[0053] The navigation unit can perform navigation while considering the geographical distribution of web pages. For example, the navigation unit can perform navigation while considering the geographical distribution of web pages. For example, the navigation unit can prioritize navigation to information in the user's current location. The navigation unit can also prioritize navigation to relevant local news and event information based on the user's geographical location. Furthermore, the navigation unit can prioritize navigation to the optimal route guidance and map information based on the user's location. This ensures optimal navigation based on the user's geographical location. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to perform navigation while considering the geographical distribution of web pages.

[0054] The navigation unit can improve the accuracy of navigation by referring to relevant literature on the web page during navigation. For example, the navigation unit can improve the accuracy of navigation by referring to relevant literature on the web page during navigation. The navigation unit can improve the accuracy of navigation by referring to relevant literature. The navigation unit can also provide optimal navigation based on literature that the user frequently accesses. Furthermore, the navigation unit can analyze the content of the web page and suggest a navigation route by referring to relevant literature. This improves the accuracy of navigation by referring to relevant literature. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to improve the accuracy of navigation by referring to relevant literature on the web page during navigation.

[0055] The alt text generation unit can adjust the level of detail of the alt text based on the importance of the image when generating alt text. For example, the alt text generation unit can adjust the level of detail of the alt text based on the importance of the image when generating alt text. For example, the alt text generation unit can generate detailed alt text for images that contain important information. The alt text generation unit can also generate basic alt text for images that contain general information. Furthermore, the alt text generation unit can generate particularly detailed alt text for images that users frequently access. This ensures that optimal alt text is generated based on the importance of the image. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to adjust the level of detail of the alt text based on the importance of the image when generating alt text.

[0056] The alt text generation unit can apply different generation algorithms depending on the image category when generating alt text. For example, the alt text generation unit can apply different generation algorithms depending on the image category when generating alt text. For example, for news images, the alt text generation unit can generate alt text related to the article's headline and body text. The alt text generation unit can also generate alt text related to product information for images on shopping sites. Furthermore, the alt text generation unit can generate alt text related to the content of social media posts for images on social media. This ensures that the most suitable alt text is generated depending on the image category. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to apply different generation algorithms depending on the image category when generating alt text.

[0057] The alt text generation unit can determine the priority of alt text based on the image submission date when generating alt text. For example, the alt text generation unit can prioritize generating alt text for recently submitted images. The alt text generation unit can also limit the alt text for older images to basic content. Furthermore, the alt text generation unit can prioritize generating alt text for images that users frequently access. This ensures that alt text is generated with the optimal priority based on the image submission date. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to determine the priority of alt text based on the image submission date when generating alt text.

[0058] The alt text generation unit can adjust the order of alt text based on the relevance of images when generating alt text. For example, the alt text generation unit can adjust the order of alt text based on the relevance of images when generating alt text. For example, the alt text generation unit can prioritize generating alt text for relevant images based on the content of the page the user is currently viewing. The alt text generation unit can also highlight alt text for important images based on the user's areas of interest. Furthermore, the alt text generation unit can generate optimal alt text by referring to the user's browsing history. This ensures that alt text is generated in the optimal order based on image relevance. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to adjust the order of alt text based on image relevance when generating alt text.

[0059] The labeling unit can adjust the level of detail of labels based on the importance of the form fields during labeling. For example, the labeling unit can adjust the level of detail of labels based on the importance of the form fields during labeling. For example, the labeling unit can perform detailed labeling on form fields that contain important information. It can also perform basic labeling on form fields that contain general information. Furthermore, the labeling unit can perform particularly detailed labeling on form fields that users frequently access. This ensures that optimal labeling is performed based on the importance of the form fields. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not using AI. For example, the labeling unit can use an AI model to adjust the level of detail of labels based on the importance of the form fields during labeling.

[0060] The labeling unit can apply different labeling algorithms depending on the category of the form field during labeling. For example, the labeling unit can apply different labeling algorithms depending on the category of the form field during labeling. For example, in a registration form, the labeling unit can apply labels related to user information. In addition, in a shopping cart, the labeling unit can apply labels related to product information. Furthermore, in an inquiry form, the labeling unit can apply labels related to the content of the inquiry. This ensures that the labeling unit applies the most appropriate labels depending on the category of the form field. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit can use an AI model to apply different labeling algorithms depending on the category of the form field during labeling.

[0061] The labeling unit can determine the labeling priority based on the submission date of the form fields during the labeling process. For example, the labeling unit may prioritize labeling of recently submitted form fields. It may also limit the labeling of older form fields to basic labeling. Furthermore, the labeling unit may prioritize labeling of form fields that users frequently access. This ensures that labeling is performed with optimal priority based on the submission date of the form fields. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit may use an AI model to determine the labeling priority based on the submission date of the form fields during the labeling process.

[0062] The labeling unit can adjust the order of labels based on the relevance of form fields during labeling. For example, the labeling unit can adjust the order of labels based on the relevance of form fields during labeling. For example, the labeling unit can prioritize relevant labels based on the content of the form field the user is currently entering. The labeling unit can also highlight important form field labels based on the user's areas of interest. Furthermore, the labeling unit can perform optimal labeling by referring to the user's browsing history. This ensures that labels are applied in the optimal order based on the relevance of form fields. Some or all of the above processes in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit can use an AI model to adjust the order of labels based on the relevance of form fields during labeling.

[0063] The filter unit can adjust the level of detail of the filter based on the importance of the web page when applying the filter. For example, the filter unit can adjust the level of detail of the filter based on the importance of the web page when applying the filter. For example, the filter unit can apply a detailed filter to pages that contain important information. The filter unit can also apply a basic filter to pages that contain general information. Furthermore, the filter unit can apply a particularly detailed filter to pages that users frequently access. This ensures that the optimal filter is applied based on the importance of the web page. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to adjust the level of detail of the filter based on the importance of the web page when applying the filter.

[0064] The filter unit can apply different filter algorithms depending on the category of the web page when applying a filter. For example, the filter unit can apply filters related to article headlines and body text on news sites. It can also apply filters related to product information on shopping sites. Furthermore, it can apply filters related to posting and commenting functions on social media sites. This ensures that the most suitable filter is applied depending on the category of the web page. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to apply different filter algorithms depending on the category of the web page when applying a filter.

[0065] The filter unit can determine the priority of filters based on the update frequency of web pages when applying filters. For example, the filter unit can determine the priority of filters based on the update frequency of web pages when applying filters. For example, the filter unit can apply filters preferentially to pages that are frequently updated. The filter unit can also apply basic filters to pages that are not frequently updated. Furthermore, the filter unit can apply particularly detailed filters to pages that users frequently access. This ensures that filters are applied with the optimal priority based on the update frequency of web pages. Some or all of the above processing in the filter unit may be performed using AI, for example, or not. For example, the filter unit can use an AI model to determine the priority of filters based on the update frequency of web pages when applying filters.

[0066] The filter unit can adjust the order of filters based on the relevance of the web pages when applying filters. For example, the filter unit adjusts the order of filters based on the relevance of the web pages when applying filters. For example, the filter unit prioritizes filtering based on the content of the page the user is currently viewing. The filter unit can also filter to highlight important information based on the user's areas of interest. Furthermore, the filter unit can select the optimal filtering method by referring to the user's browsing history. This ensures that filters are applied in the optimal order based on the relevance of the web pages. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to adjust the order of filters based on the relevance of the web pages when applying filters.

[0067] The summarization unit can adjust the level of detail of the summary based on the importance of the content when generating the summary. For example, the summarization unit can adjust the level of detail of the summary based on the importance of the content when generating the summary. For example, the summarization unit can provide a detailed summary for content that contains important information. The summarization unit can also provide a basic summary for content that contains general information. Furthermore, the summarization unit can provide a particularly detailed summary for content that users frequently access. This ensures that the optimal summary is provided based on the importance of the content. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can use an AI model to adjust the level of detail of the summary based on the importance of the content when generating the summary.

[0068] The summarization unit can apply different summarization algorithms depending on the content category when generating summaries. For example, the summarization unit can apply different summarization algorithms depending on the content category when generating summaries. For example, in news articles, the summarization unit can provide summaries related to headlines and body text. In addition, in shopping site content, the summarization unit can provide summaries related to product information. Furthermore, in social media posts, the summarization unit can provide summaries related to the content of the posts. This ensures that the most appropriate summary is provided depending on the content category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can use an AI model to apply different summarization algorithms depending on the content category when generating summaries.

[0069] The summarization unit can determine the priority of summaries based on the submission date of the content when generating summaries. For example, the summarization unit can prioritize summaries of recently submitted content. The summarization unit can also limit summaries of older content to basic information. Furthermore, the summarization unit can prioritize summaries of content that users frequently access. This ensures that summaries are provided with optimal priority based on the submission date of the content. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can use an AI model to determine the priority of summaries based on the submission date of the content when generating summaries.

[0070] The summarization unit can adjust the order of summaries based on the relevance of the content when generating summaries. For example, the summarization unit can adjust the order of summaries based on the relevance of the content when generating summaries. For example, the summarization unit can prioritize summaries of relevant content based on the content of the page the user is currently viewing. The summarization unit can also highlight summaries of important content based on the user's areas of interest. Furthermore, the summarization unit can provide the most suitable summaries by referring to the user's browsing history. This ensures that summaries are provided in the most appropriate order based on the relevance of the content. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can use an AI model to adjust the order of summaries based on the relevance of the content when generating summaries.

[0071] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0072] Accessibility-supported browsers or browser extensions can analyze a user's past browsing history and suggest the optimal navigation route. For example, they can prioritize pages the user frequently accesses, streamlining navigation. They can also identify the user's areas of interest from past browsing history and prioritize the provision of relevant information. Furthermore, they can analyze the trends of pages accessed at specific times and suggest the optimal navigation route for those times. This provides optimal navigation based on past browsing history. Navigation route suggestions may or may not be performed using AI.

[0073] Accessibility-supported browsers or browser extensions can prioritize the display of relevant local news and events information, taking into account the user's geographical location. For example, they can prioritize news and events in the user's current location, providing timely information relevant to the area. They can also provide optimal route guidance and map information based on the user's location. Furthermore, they can prioritize information for areas the user frequently visits. This ensures that the user receives the most relevant information based on their geographical location. The consideration of geographical location may be performed using AI or not.

[0074] Accessibility-supported browsers or browser extensions can analyze a user's social media activity and prioritize the display of relevant information. For example, they can prioritize displaying relevant news and articles based on information the user has shared on social media. They can also display relevant content based on the interests of the user's followers and friends. Furthermore, they can analyze a user's social media activity history and provide the most relevant information. This ensures that the information provided is optimal based on the user's social media activity. The analysis of social media activity may be performed using AI or not.

[0075] Accessibility-supporting browsers or browser extensions can prioritize the display of reliable information by considering the attribute information of the web page provider. For example, if the web page provider provides reliable information, that information will be displayed preferentially. Furthermore, if the provider possesses specialized knowledge, that information may be highlighted. In addition, the browser can provide the most relevant information based on the provider's attribute information. This ensures that reliable information is provided based on the web page provider's attribute information. The consideration of the provider's attribute information may be performed using AI or not.

[0076] Accessibility-supported browsers or browser extensions can prioritize the display of important information based on how often a webpage is updated. For example, frequently updated pages can prioritize the display of the most recent information. Pages that are not frequently updated can display basic information. Furthermore, pages that users frequently access can prioritize the display of particularly detailed information. This ensures that the most relevant information is provided based on the webpage's update frequency. The consideration of update frequency may be performed using AI or not.

[0077] The following briefly describes the processing flow for example form 1.

[0078] Step 1: The editorial team dynamically edits the HTML of the web page. The editorial team can, for example, perform real-time editing using JavaScript or server-side editing. The editorial team parses the HTML of the web page and converts it into an accessible format for visually impaired and elderly people. Step 2: The support team will make the HTML edited by the editorial team compliant with the web standard WAI-ARIA. The support team will add appropriate attributes to the HTML according to the specific methods and standards for WAI-ARIA compliance. Step 3: The navigation section provides keyboard navigation based on the HTML handled by the corresponding section. The navigation section adds appropriate tags to links and buttons on the page, enabling keyboard navigation. Step 4: The alternative text generation unit generates alternative text for the image based on the navigation provided by the navigation unit. The alternative text generation unit analyzes the image content and automatically generates appropriate alternative text. Step 5: The labeling unit adds labels to the form fields based on the alternative text generated by the alternative text generation unit. The labeling unit adds appropriate labels to the form fields, making it easier to interact with the interactive elements. Step 6: The filter unit provides a colorblind-friendly filter function based on the labels added by the labeling unit. The filter unit provides a filter function that adjusts the page colors for users with color blindness. Step 7: The summary section summarizes the content based on the filtering functions provided by the filter section. The summary section summarizes the content of long articles or pages, extracting and providing only the important points.

[0079] (Example of form 2) An accessibility-supporting browser or browser extension according to an embodiment of the present invention is a system for eliminating difficulties faced by visually impaired and elderly people when using the internet. When a user opens a web page, the system uses AI to dynamically edit the page's HTML and make it compliant with the web standard WAI-ARIA. This allows visually impaired and elderly people to easily navigate web pages and access information without having to learn additional tools. For example, when a user opens a web page, the AI ​​analyzes the page's HTML. The analyzed HTML is converted into a format accessible to visually impaired and elderly people. For example, appropriate tags are added to links and buttons on the page to enable keyboard navigation. The system also analyzes image content and automatically generates appropriate alternative text (alt text), making it easier to understand image content. Next, appropriate labels are added to form fields, making it easier to interact with interactive elements and allowing visually impaired and elderly people to easily use forms. The system also provides a filter function to adjust the page's colors for users with color blindness, enabling them to accurately understand the page content. Furthermore, it includes a function to summarize the content of long articles and pages, extracting and providing only the important points. This will enable visually impaired and elderly individuals to efficiently acquire information. This mechanism eliminates difficulties for visually impaired and elderly individuals when using the internet, making information access easier. For example, when a visually impaired person opens a webpage, AI can automatically analyze the page and provide features such as keyboard navigation, alternative text generation, form field labeling, color blindness support, and content summarization, allowing visually impaired individuals to easily navigate pages and acquire information. For the elderly, this also eliminates problems with declining eyesight and complex interfaces, making webpage browsing easier. Therefore, accessibility-supported browsers or browser extensions can eliminate difficulties for visually impaired and elderly individuals when using the internet, making information access easier.

[0080] The accessibility support browser or browser extension according to the embodiment comprises an editing unit, a response unit, a navigation unit, an alternative text generation unit, a labeling unit, a filter unit, and a summarization unit. The editing unit dynamically edits the HTML of a web page. The editing unit can perform real-time editing using JavaScript, for example. The editing unit can also perform server-side editing. For example, the editing unit parses the HTML of a web page and converts it into a format accessible to visually impaired and elderly people. The response unit makes the HTML edited by the editing unit compatible with the web standard WAI-ARIA. For example, the response unit adds appropriate attributes to the HTML according to specific methods and criteria for WAI-ARIA compatibility. The navigation unit provides keyboard navigation based on the HTML made compatible by the response unit. For example, the navigation unit adds appropriate tags to links and buttons on the page to enable keyboard navigation. The alternative text generation unit generates alternative text for images based on the navigation provided by the navigation unit. For example, the alternative text generation unit parses the content of an image and automatically generates appropriate alternative text. The labeling unit adds labels to form fields based on alternative text generated by the alternative text generation unit. The labeling unit, for example, adds appropriate labels to form fields to facilitate interaction with interactive elements. The filter unit provides colorblind-friendly filtering based on the labels added by the labeling unit. The filter unit, for example, provides filtering to adjust the page colors for users with color blindness. The summarization unit summarizes the content based on the filtering function provided by the filter unit. The summarization unit, for example, summarizes the content of long articles or pages, extracting and providing only the important points. As a result, the accessibility-supported browser or browser extension according to the embodiment can eliminate difficulties for visually impaired and elderly people when using the internet and make it easier for them to access information.

[0081] The editorial team dynamically edits the HTML of web pages. For example, they can perform real-time editing using JavaScript. Specifically, they can dynamically add, delete, and modify elements of web pages using JavaScript's DOM manipulation. This allows the content of the page to be changed as needed, even after the user has loaded the page. The editorial team can also perform server-side editing. For example, they can use server-side scripts (PHP, Python, Node.js, etc.) to generate HTML in response to requests and send it to the client. This ensures that the latest information is provided every time the user accesses the page. Furthermore, the editorial team parses the HTML of web pages and converts it into an accessible format for the visually impaired and the elderly. Specifically, they analyze the HTML structure, appropriately place heading tags (h1, h2, etc.) and list tags (ul, ol, etc.) so that screen readers can accurately read the content. They can also remove unnecessary decorations and animations and change to a simple and easy-to-read layout. This allows the editorial team to perform flexible editing according to user needs and improve accessibility.

[0082] The support team will make the HTML edited by the editorial team compliant with the web standard WAI-ARIA. For example, the support team will add appropriate attributes to the HTML according to the specific methods and standards of WAI-ARIA compliance. Specifically, they will use the role attribute to clarify the role of each element and the aria-label and aria-labelledby attributes to add descriptions to the elements. This will allow screen readers to accurately convey the role and content of each element. It is also possible to notify dynamically updated content in real time using the aria-live attribute. Furthermore, the support team will improve the usability of interactive elements (buttons, links, form fields, etc.) according to WAI-ARIA best practices. For example, they will appropriately set the tabindex attribute so that all interactive elements can be accessed using only keyboard operations. This will allow visually impaired and elderly people to operate web pages using only a keyboard. Through these measures, the support team can significantly improve the accessibility of web pages.

[0083] The navigation section provides keyboard navigation based on the HTML handled by the corresponding section. For example, the navigation section adds appropriate tags to links and buttons on the page to enable keyboard navigation. Specifically, it sets the tabindex attribute for each link and button, allowing focus to be moved sequentially using the keyboard's Tab key. It also manages the state of interactive elements such as dropdown menus and modal windows using the aria-controls and aria-expanded attributes. This allows users to access and interact with all elements on the page using only keyboard operations. Furthermore, the navigation section can also provide keyboard shortcuts. For example, pressing a specific key combination can jump to a specific section on the page or perform a specific operation. This allows users to efficiently navigate the page and quickly access the information they need. Through these functions, the navigation section helps visually impaired and elderly people to comfortably use web pages.

[0084] The alternative text generation unit generates alternative text for images based on the navigation provided by the navigation unit. For example, the alternative text generation unit analyzes the content of an image and automatically generates appropriate alternative text. Specifically, it analyzes the content of an image using image recognition technology to identify key objects and scenes. For example, if a person is in the image, it analyzes the person's actions and facial expressions and generates specific alternative text such as "A smiling woman is jogging in a park." It is also possible to express the content of an image in natural language using the generation AI. For example, a prompt such as "Please describe the content of this image" can be entered into the generation AI, and the generated text can be used as alternative text. This allows visually impaired people to understand the content of images through screen readers. Furthermore, the alternative text generation unit can collect feedback from users and continuously improve the accuracy of the generated alternative text. This allows the alternative text generation unit to provide more accurate and useful information to visually impaired people.

[0085] The labeling unit adds labels to form fields based on alternative text generated by the alternative text generation unit. For example, the labeling unit adds appropriate labels to form fields, facilitating interaction with interactive elements. Specifically, it adds a label tag to each form field and associates it with the corresponding form field using the for attribute. This allows screen readers to read the form field labels, making it easier for users to understand the purpose of each field. It is also possible to provide additional explanations for form fields using the aria-label and aria-labelledby attributes. This allows users to accurately understand and input form content. Furthermore, the labeling unit also provides functionality to appropriately display error messages and hints for form fields. For example, it can be configured to display a visual error message along with the screen reader reading the error message if a required field is left blank or the input is inaccurate. This allows users to quickly correct input errors and provide accurate information. Through these functions, the labeling unit can significantly improve the usability and accessibility of forms.

[0086] The filter unit provides colorblind-friendly filtering based on labels added by the labeling unit. For example, the filter unit provides a filter function that adjusts page colors for users with color blindness. Specifically, it uses an algorithm that dynamically converts page colors according to the type of color blindness (red-green color blindness, blue-yellow color blindness, total color blindness, etc.). For example, for users with red-green color blindness, it converts red and green colors to colors that are easier to distinguish, and for users with blue-yellow color blindness, it converts blue and yellow colors to colors that are easier to distinguish. Furthermore, for users with total color blindness, it converts all colors to grayscale and emphasizes the contrast between light and dark. This makes it easier for users with color blindness to accurately recognize the content of the page. In addition, the filter unit also provides a function that allows users to customize filter settings according to their type of color blindness. For example, a user can select their type of color blindness on the settings screen and apply the corresponding filter. This allows the filter unit to provide flexible and individualized support for users with color blindness.

[0087] The summarization unit summarizes content based on the filtering functions provided by the filtering unit. For example, the summarization unit summarizes the content of long articles or pages, extracting and providing only the important points. Specifically, it uses natural language processing technology to analyze the structure of the text and extract the main topics and keywords. For example, a prompt such as "Summarize the main points of this text" can be input to the generation AI, and the generated summary can be provided. This saves users time reading long texts and allows them to quickly access important information. Furthermore, the summarization unit can also customize the content of the summary based on the user's interests. For example, if a user is interested in a particular topic, information related to that topic can be prioritized and included in the summary. In this way, the summarization unit can provide the user with the most important and useful information. Through these functions, the summarization unit can help visually impaired and elderly people efficiently understand the content of web pages and easily access information.

[0088] The editorial team can parse the HTML of a webpage and convert it into a format accessible to the visually impaired and the elderly. For example, the editorial team can parse the HTML of a webpage and convert it into a format accessible to the visually impaired and the elderly. For example, the editorial team can adjust font sizes, contrast, and enable text-to-speech. This allows the visually impaired and the elderly to easily navigate webpages and access information without having to learn additional tools. Some or all of the above processing by the editorial team may be performed using AI, for example, or not. For example, the editorial team can use an AI model to parse the HTML of a webpage and convert it into a format accessible to the visually impaired and the elderly.

[0089] The navigation unit can add appropriate tags to links and buttons on a page, enabling keyboard navigation. For example, the navigation unit can add appropriate tags to links and buttons on a page, enabling keyboard navigation. The navigation unit can also clarify, for example, which tags to add to which elements, and the attributes of those tags. This allows visually impaired and elderly people to navigate web pages using a keyboard. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not. For example, the navigation unit can use an AI model to add appropriate tags to links and buttons on a page and enable keyboard navigation.

[0090] The alternative text generation unit can analyze the content of an image and automatically generate appropriate alternative text. For example, the alternative text generation unit can analyze the content of an image and automatically generate appropriate alternative text. The alternative text generation unit can clarify, for example, how to analyze the content of an image and what information to include. This makes it easier for visually impaired people to understand image content. Some or all of the above-described processes in the alternative text generation unit may be performed using AI, for example, or without AI. For example, the alternative text generation unit can use an AI model to analyze the content of an image and automatically generate appropriate alternative text.

[0091] The labeling unit can add appropriate labels to form fields and facilitate the operation of interactive elements. For example, the labeling unit can add appropriate labels to form fields and facilitate the operation of interactive elements. The labeling unit can clarify, for example, which form fields to add what labels to. This makes forms easy for visually impaired and elderly people to use. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit can use an AI model to add appropriate labels to form fields and facilitate the operation of interactive elements.

[0092] The filter unit can provide a filter function that adjusts the page colors for users with color blindness. For example, the filter unit can clarify which colors to adjust, how to adjust them, and the algorithms used. This allows users with color blindness to accurately understand the page content. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to provide a filter function that adjusts the page colors for users with color blindness.

[0093] The summarization function can summarize the content of long articles or pages, extracting and providing only the important points. For example, the summarization function can summarize the content of long articles or pages, extracting and providing only the important points. The summarization function can clarify, for example, which information to extract, the length and format of the summary, etc. This allows visually impaired people and the elderly to efficiently acquire information. Some or all of the processing described above in the summarization function may be performed using AI, for example, or not using AI. For example, the summarization function can use an AI model to summarize the content of long articles or pages and extract and provide only the important points.

[0094] The editorial team can estimate the user's emotions and adjust the timing of HTML edits based on those emotions. For example, if the user is stressed, the editorial team can quickly edit the HTML to make the page accessible immediately. If the user is relaxed, the editorial team can edit the HTML gradually to allow the user to adapt to the changes on the page. Furthermore, if the user is in a hurry, the editorial team can prioritize editing the HTML from the most important parts to quickly provide accessible information. This ensures that HTML is edited at the optimal time according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editorial team may be performed using AI or not. For example, the editorial team could use an AI model to estimate user sentiment and adjust the timing of HTML edits based on that estimated sentiment.

[0095] The editorial department can analyze the past access history of a web page and select the optimal editing method. For example, the editorial department can analyze the past access history of a web page and select the optimal editing method. For example, the editorial department can select the optimal editing method based on the history of pages that users frequently access. The editorial department can also suggest the optimal editing method by referring to the editing methods that users have used in the past. Furthermore, the editorial department can select the optimal editing method for a specific time period based on the user's past access history. In this way, the optimal editing method is selected based on past access history. Some or all of the above processes performed by the editorial department may be performed using AI, for example, or not using AI. For example, the editorial department can use an AI model to analyze the past access history of a web page and select the optimal editing method.

[0096] The editorial team can perform filtering when editing HTML based on the user's current browsing status and areas of interest. For example, the editorial team can filter HTML based on the user's current browsing status and areas of interest. For example, the editorial team can prioritize editing information relevant to the page the user is currently viewing. The editorial team can also edit HTML to highlight important information based on the user's areas of interest. Furthermore, the editorial team can select the optimal filtering method by referring to the user's browsing history. This ensures that optimal filtering is performed based on the user's current situation and areas of interest. Some or all of the above processing by the editorial team may be performed using AI, for example, or not. For example, the editorial team can use an AI model to perform filtering based on the user's current browsing status and areas of interest when editing HTML.

[0097] The editorial team can estimate the user's emotions and determine the priority of the HTML to edit based on those emotions. For example, if the user is stressed, the editorial team can prioritize and quickly deliver important information. If the user is relaxed, the editorial team can also edit the HTML considering the overall balance. Furthermore, if the user is in a hurry, the editorial team can prioritize editing the HTML starting with the most important parts. This ensures that the HTML is edited with the optimal priority according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editorial team may be performed using AI or not. For example, the editorial team can use an AI model to estimate the user's emotions and determine the priority of the HTML to edit based on those emotions.

[0098] The editorial team can prioritize editing relevant content by considering the user's geographical location when editing HTML. For example, the editorial team can prioritize editing relevant content by considering the user's geographical location when editing HTML. For example, the editorial team can prioritize editing information for the area the user is currently in. The editorial team can also prioritize editing relevant local news and event information based on the user's geographical location. Furthermore, the editorial team can prioritize editing optimal route guidance and map information based on the user's location. This ensures that the most relevant content is prioritized based on the user's geographical location. Some or all of the above processing by the editorial team may be performed using AI, for example, or not. For example, the editorial team can use an AI model to prioritize editing relevant content by considering the user's geographical location when editing HTML.

[0099] The editorial team can analyze a user's social media activity and edit relevant content when editing HTML. For example, the editorial team can analyze a user's social media activity and edit relevant content when editing HTML. For example, the editorial team can prioritize editing relevant content based on information shared by the user on social media. The editorial team can also edit relevant content based on information of interest to the user's social media followers and friends. Furthermore, the editorial team can analyze a user's social media activity history and select the optimal editing method. This ensures that the most relevant content is edited based on the user's social media activity. Some or all of the above processes performed by the editorial team may be done using AI, for example, or not. For example, the editorial team can use an AI model to analyze a user's social media activity and edit relevant content when editing HTML.

[0100] The response unit can estimate the user's emotions and adjust the WAI-ARIA response method based on the estimated user emotions. For example, if the user is stressed, the response unit can provide a concise and intuitive WAI-ARIA response. If the user is relaxed, the response unit can also provide a detailed WAI-ARIA response. Furthermore, if the user is in a hurry, the response unit can prioritize the most important parts of the WAI-ARIA response. This ensures that the optimal WAI-ARIA response is provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can use an AI model to estimate the user's emotions and adjust the WAI-ARIA response method based on the estimated user emotions.

[0101] The response unit can adjust the level of detail of the response based on the importance of the web page when implementing WAI-ARIA. For example, the response unit adjusts the level of detail of the response based on the importance of the web page when implementing WAI-ARIA. For example, the response unit performs detailed WAI-ARIA response on pages that contain important information. The response unit can also perform basic WAI-ARIA response on pages that contain general information. Furthermore, the response unit can perform particularly detailed WAI-ARIA response on pages that users frequently access. This ensures that optimal WAI-ARIA response is performed based on the importance of the web page. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can use an AI model to adjust the level of detail of the response based on the importance of the web page when implementing WAI-ARIA.

[0102] The response unit can apply different response algorithms depending on the category of the web page when performing WAI-ARIA analysis. For example, the response unit can apply different response algorithms depending on the category of the web page when performing WAI-ARIA analysis. For example, on a news site, the response unit can perform appropriate WAI-ARIA analysis on article headlines and body text. The response unit can also perform appropriate WAI-ARIA analysis on shopping sites for product information and cart functions. Furthermore, the response unit can perform appropriate WAI-ARIA analysis on social media sites for posting and commenting functions. This ensures that optimal WAI-ARIA analysis is performed according to the category of the web page. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can use an AI model to apply different response algorithms depending on the category of the web page when performing WAI-ARIA analysis.

[0103] The response unit can estimate the user's emotions and determine the priority of responses based on the estimated emotions. For example, if the user is stressed, the response unit will prioritize important information. If the user is relaxed, the response unit can also consider the overall balance when responding. Furthermore, if the user is in a hurry, the response unit can prioritize responding to the most important parts first. This ensures that WAI-ARIA responses are performed with optimal priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can use an AI model to estimate the user's emotions and determine the priority of responses based on the estimated emotions.

[0104] The support unit can determine the priority of WAI-ARIA implementation based on the update frequency of web pages. For example, the support unit can prioritize WAI-ARIA implementation on pages that are frequently updated. It can also perform basic WAI-ARIA implementation on pages that are not frequently updated. Furthermore, it can perform particularly detailed WAI-ARIA implementation on pages that are frequently accessed by users. This ensures that optimal WAI-ARIA implementation is performed based on the update frequency of web pages. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can use an AI model to determine the priority of implementation based on the update frequency of web pages when implementing WAI-ARIA.

[0105] The response unit can adjust the order of responses based on the relevance of web pages when implementing WAI-ARIA. For example, the response unit adjusts the order of responses based on the relevance of web pages when implementing WAI-ARIA. For example, the response unit prioritizes relevant information based on the content of the page the user is currently viewing. The response unit can also highlight important information based on the user's areas of interest. Furthermore, the response unit can select the optimal response method by referring to the user's browsing history. This ensures that optimal WAI-ARIA support is provided based on the relevance of web pages. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can use an AI model to adjust the order of responses based on the relevance of web pages when implementing WAI-ARIA.

[0106] The navigation unit can estimate the user's emotions and adjust the navigation criteria based on the estimated emotions. For example, the navigation unit can estimate the user's emotions and adjust the navigation criteria based on the estimated emotions. For example, if the user is stressed, the navigation unit can provide simple and intuitive navigation. If the user is relaxed, the navigation unit can also provide navigation with detailed information. Furthermore, if the user is in a hurry, the navigation unit can provide concise navigation. This ensures that optimal navigation is provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can use an AI model to estimate the user's emotions and adjust the navigation criteria based on the estimated emotions.

[0107] The navigation unit can improve the accuracy of navigation by considering the relationships between web pages during navigation. For example, the navigation unit can improve the accuracy of navigation by considering the relationships between web pages during navigation. For example, the navigation unit can improve the accuracy of navigation by highlighting links between related pages. The navigation unit can also provide optimal navigation by considering the relationships between pages that the user frequently accesses. Furthermore, the navigation unit can analyze the structure of web pages and propose the optimal navigation route. This improves the accuracy of navigation by considering the relationships between web pages. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to improve the accuracy of navigation by considering the relationships between web pages during navigation.

[0108] The navigation unit can perform navigation while considering the attribute information of the web page provider. For example, the navigation unit can perform navigation while considering the attribute information of the web page provider. For example, if the web page provider provides reliable information, the navigation unit will prioritize that information in the navigation. Furthermore, if the web page provider has specialized knowledge, the navigation unit can also emphasize that information in the navigation. In addition, the navigation unit can propose the optimal navigation route based on the attribute information of the web page provider. This allows for navigation prioritizing reliable information by considering the attribute information of the web page provider. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to perform navigation while considering the attribute information of the web page provider.

[0109] The navigation unit can estimate the user's emotions and adjust the order in which navigation results are displayed based on the estimated emotions. For example, the navigation unit can estimate the user's emotions and adjust the order in which navigation results are displayed based on the estimated emotions. For example, if the user is stressed, the navigation unit can prioritize displaying important information. If the user is relaxed, the navigation unit can also display information considering the overall balance. Furthermore, if the user is in a hurry, the navigation unit can prioritize displaying the most important parts first. This ensures that navigation results are displayed in the optimal order according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use an AI model to estimate the user's emotions and adjust the order in which navigation results are displayed based on the estimated emotions.

[0110] The navigation unit can perform navigation while considering the geographical distribution of web pages. For example, the navigation unit can perform navigation while considering the geographical distribution of web pages. For example, the navigation unit can prioritize navigation to information in the user's current location. The navigation unit can also prioritize navigation to relevant local news and event information based on the user's geographical location. Furthermore, the navigation unit can prioritize navigation to the optimal route guidance and map information based on the user's location. This ensures optimal navigation based on the user's geographical location. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to perform navigation while considering the geographical distribution of web pages.

[0111] The navigation unit can improve the accuracy of navigation by referring to relevant literature on the web page during navigation. For example, the navigation unit can improve the accuracy of navigation by referring to relevant literature on the web page during navigation. The navigation unit can improve the accuracy of navigation by referring to relevant literature. The navigation unit can also provide optimal navigation based on literature that the user frequently accesses. Furthermore, the navigation unit can analyze the content of the web page and suggest a navigation route by referring to relevant literature. This improves the accuracy of navigation by referring to relevant literature. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can use an AI model to improve the accuracy of navigation by referring to relevant literature on the web page during navigation.

[0112] The alternative text generation unit can estimate the user's emotions and adjust the alternative text generation method based on the estimated user emotions. For example, if the user is stressed, the alternative text generation unit can generate concise and intuitive alternative text. If the user is relaxed, the alternative text generation unit can also generate alternative text that includes detailed explanations. Furthermore, if the user is in a hurry, the alternative text generation unit can generate concise alternative text. This ensures that the optimal alternative text is generated according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processes in the alternative text generation unit may be performed using AI, for example, or without AI. For example, the alternative text generation unit can use an AI model to estimate the user's emotions and adjust the alternative text generation method based on the estimated user emotions.

[0113] The alt text generation unit can adjust the level of detail of the alt text based on the importance of the image when generating alt text. For example, the alt text generation unit can adjust the level of detail of the alt text based on the importance of the image when generating alt text. For example, the alt text generation unit can generate detailed alt text for images that contain important information. The alt text generation unit can also generate basic alt text for images that contain general information. Furthermore, the alt text generation unit can generate particularly detailed alt text for images that users frequently access. This ensures that optimal alt text is generated based on the importance of the image. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to adjust the level of detail of the alt text based on the importance of the image when generating alt text.

[0114] The alt text generation unit can apply different generation algorithms depending on the image category when generating alt text. For example, the alt text generation unit can apply different generation algorithms depending on the image category when generating alt text. For example, for news images, the alt text generation unit can generate alt text related to the article's headline and body text. The alt text generation unit can also generate alt text related to product information for images on shopping sites. Furthermore, the alt text generation unit can generate alt text related to the content of social media posts for images on social media. This ensures that the most suitable alt text is generated depending on the image category. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to apply different generation algorithms depending on the image category when generating alt text.

[0115] The alternative text generation unit can estimate the user's emotions and determine the priority of alternative text based on the estimated emotions. For example, if the user is stressed, the alternative text generation unit may prioritize generating alternative text for important images. If the user is relaxed, the alternative text generation unit may also generate alternative text considering the overall balance. Furthermore, if the user is in a hurry, the alternative text generation unit may prioritize generating alternative text for the most important images. This ensures that alternative text is generated with the optimal priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the alternative text generation unit may be performed using AI or not. For example, the alternative text generation unit may use an AI model to estimate the user's emotions and determine the priority of alternative text based on the estimated emotions.

[0116] The alt text generation unit can determine the priority of alt text based on the image submission date when generating alt text. For example, the alt text generation unit can prioritize generating alt text for recently submitted images. The alt text generation unit can also limit the alt text for older images to basic content. Furthermore, the alt text generation unit can prioritize generating alt text for images that users frequently access. This ensures that alt text is generated with the optimal priority based on the image submission date. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to determine the priority of alt text based on the image submission date when generating alt text.

[0117] The alt text generation unit can adjust the order of alt text based on the relevance of images when generating alt text. For example, the alt text generation unit can adjust the order of alt text based on the relevance of images when generating alt text. For example, the alt text generation unit can prioritize generating alt text for relevant images based on the content of the page the user is currently viewing. The alt text generation unit can also highlight alt text for important images based on the user's areas of interest. Furthermore, the alt text generation unit can generate optimal alt text by referring to the user's browsing history. This ensures that alt text is generated in the optimal order based on image relevance. Some or all of the above processing in the alt text generation unit may be performed using AI, for example, or without AI. For example, the alt text generation unit can use an AI model to adjust the order of alt text based on image relevance when generating alt text.

[0118] The labeling unit can estimate the user's emotions and adjust the labeling method based on the estimated emotions. For example, if the user is stressed, the labeling unit can provide a concise and intuitive label. If the user is relaxed, the labeling unit can provide a label with a detailed explanation. Furthermore, if the user is in a hurry, the labeling unit can provide a concise label. This ensures that the labeling is optimal according to 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) or multimodal generation AI. Some or all of the above processing in the labeling unit may be performed using AI or not. For example, the labeling unit can use an AI model to estimate the user's emotions and adjust the labeling method based on the estimated emotions.

[0119] The labeling unit can adjust the level of detail of labels based on the importance of the form fields during labeling. For example, the labeling unit can adjust the level of detail of labels based on the importance of the form fields during labeling. For example, the labeling unit can perform detailed labeling on form fields that contain important information. It can also perform basic labeling on form fields that contain general information. Furthermore, the labeling unit can perform particularly detailed labeling on form fields that users frequently access. This ensures that optimal labeling is performed based on the importance of the form fields. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not using AI. For example, the labeling unit can use an AI model to adjust the level of detail of labels based on the importance of the form fields during labeling.

[0120] The labeling unit can apply different labeling algorithms depending on the category of the form field during labeling. For example, the labeling unit can apply different labeling algorithms depending on the category of the form field during labeling. For example, in a registration form, the labeling unit can apply labels related to user information. In addition, in a shopping cart, the labeling unit can apply labels related to product information. Furthermore, in an inquiry form, the labeling unit can apply labels related to the content of the inquiry. This ensures that the labeling unit applies the most appropriate labels depending on the category of the form field. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit can use an AI model to apply different labeling algorithms depending on the category of the form field during labeling.

[0121] The labeling unit can estimate the user's emotions and determine labeling priorities based on the estimated emotions. For example, the labeling unit might prioritize labeling important form fields if the user is stressed. It might also prioritize labeling based on overall balance if the user is relaxed. Furthermore, if the user is in a hurry, it might prioritize labeling the most important form fields. This ensures that labeling is performed with optimal priority according to 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) or multimodal generation AI. Some or all of the above processing in the labeling unit may be performed using AI or not. For example, the labeling unit can use an AI model to estimate the user's emotions and determine labeling priorities based on the estimated emotions.

[0122] The labeling unit can determine the labeling priority based on the submission date of the form fields during the labeling process. For example, the labeling unit may prioritize labeling of recently submitted form fields. It may also limit the labeling of older form fields to basic labeling. Furthermore, the labeling unit may prioritize labeling of form fields that users frequently access. This ensures that labeling is performed with optimal priority based on the submission date of the form fields. Some or all of the above processing in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit may use an AI model to determine the labeling priority based on the submission date of the form fields during the labeling process.

[0123] The labeling unit can adjust the order of labels based on the relevance of form fields during labeling. For example, the labeling unit can adjust the order of labels based on the relevance of form fields during labeling. For example, the labeling unit can prioritize relevant labels based on the content of the form field the user is currently entering. The labeling unit can also highlight important form field labels based on the user's areas of interest. Furthermore, the labeling unit can perform optimal labeling by referring to the user's browsing history. This ensures that labels are applied in the optimal order based on the relevance of form fields. Some or all of the above processes in the labeling unit may be performed using AI, for example, or not. For example, the labeling unit can use an AI model to adjust the order of labels based on the relevance of form fields during labeling.

[0124] The filter unit can estimate the user's emotions and adjust how the filter is applied based on the estimated emotions. For example, the filter unit can estimate the user's emotions and adjust how the filter is applied based on the estimated emotions. For example, if the user is stressed, the filter unit can apply a concise and intuitive filter. If the user is relaxed, the filter unit can also apply a detailed filter. Furthermore, if the user is in a hurry, the filter unit can apply a concise filter. This ensures that the optimal filter is applied according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filter unit may be performed using AI, for example, or not using AI. For example, the filter unit can use an AI model to estimate the user's emotions and adjust how the filter is applied based on the estimated emotions.

[0125] The filter unit can adjust the level of detail of the filter based on the importance of the web page when applying the filter. For example, the filter unit can adjust the level of detail of the filter based on the importance of the web page when applying the filter. For example, the filter unit can apply a detailed filter to pages that contain important information. The filter unit can also apply a basic filter to pages that contain general information. Furthermore, the filter unit can apply a particularly detailed filter to pages that users frequently access. This ensures that the optimal filter is applied based on the importance of the web page. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to adjust the level of detail of the filter based on the importance of the web page when applying the filter.

[0126] The filter unit can apply different filter algorithms depending on the category of the web page when applying a filter. For example, the filter unit can apply filters related to article headlines and body text on news sites. It can also apply filters related to product information on shopping sites. Furthermore, it can apply filters related to posting and commenting functions on social media sites. This ensures that the most suitable filter is applied depending on the category of the web page. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to apply different filter algorithms depending on the category of the web page when applying a filter.

[0127] The filter unit can estimate the user's emotions and determine the filter priority based on the estimated emotions. For example, if the user is stressed, the filter unit will prioritize filtering important information. If the user is relaxed, the filter unit can also filter considering the overall balance. Furthermore, if the user is in a hurry, the filter unit can prioritize filtering from the most important parts. This ensures that filters are applied with the optimal priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the filter unit may be performed using AI or not. For example, the filter unit can use an AI model to estimate the user's emotions and determine the filter priority based on the estimated emotions.

[0128] The filter unit can determine the priority of filters based on the update frequency of web pages when applying filters. For example, the filter unit can determine the priority of filters based on the update frequency of web pages when applying filters. For example, the filter unit can apply filters preferentially to pages that are frequently updated. The filter unit can also apply basic filters to pages that are not frequently updated. Furthermore, the filter unit can apply particularly detailed filters to pages that users frequently access. This ensures that filters are applied with the optimal priority based on the update frequency of web pages. Some or all of the above processing in the filter unit may be performed using AI, for example, or not. For example, the filter unit can use an AI model to determine the priority of filters based on the update frequency of web pages when applying filters.

[0129] The filter unit can adjust the order of filters based on the relevance of the web pages when applying filters. For example, the filter unit adjusts the order of filters based on the relevance of the web pages when applying filters. For example, the filter unit prioritizes filtering based on the content of the page the user is currently viewing. The filter unit can also filter to highlight important information based on the user's areas of interest. Furthermore, the filter unit can select the optimal filtering method by referring to the user's browsing history. This ensures that filters are applied in the optimal order based on the relevance of the web pages. Some or all of the above processing in the filter unit may be performed using AI, for example, or without AI. For example, the filter unit can use an AI model to adjust the order of filters based on the relevance of the web pages when applying filters.

[0130] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the user is stressed, the summarization unit can provide a concise and intuitive summary. If the user is relaxed, the summarization unit can also provide a summary with more detailed information. Furthermore, if the user is in a hurry, the summarization unit can provide a summary that gets straight to the point. This ensures that the optimal summary is provided according to 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) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can use an AI model to estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions.

[0131] The summarization unit can adjust the level of detail of the summary based on the importance of the content when generating the summary. For example, the summarization unit can adjust the level of detail of the summary based on the importance of the content when generating the summary. For example, the summarization unit can provide a detailed summary for content that contains important information. The summarization unit can also provide a basic summary for content that contains general information. Furthermore, the summarization unit can provide a particularly detailed summary for content that users frequently access. This ensures that the optimal summary is provided based on the importance of the content. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can use an AI model to adjust the level of detail of the summary based on the importance of the content when generating the summary.

[0132] The summarization unit can apply different summarization algorithms depending on the content category when generating summaries. For example, the summarization unit can apply different summarization algorithms depending on the content category when generating summaries. For example, in news articles, the summarization unit can provide summaries related to headlines and body text. In addition, in shopping site content, the summarization unit can provide summaries related to product information. Furthermore, in social media posts, the summarization unit can provide summaries related to the content of the posts. This ensures that the most appropriate summary is provided depending on the content category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can use an AI model to apply different summarization algorithms depending on the content category when generating summaries.

[0133] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, if the user is stressed, the summarization unit can provide a short, concise summary. If the user is relaxed, the summarization unit can provide a longer summary with more detailed explanations. Furthermore, if the user is in a hurry, the summarization unit can provide a brief, intuitive summary. This ensures that the summary is of the optimal length according to 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) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can use an AI model to estimate the user's emotions and adjust the length of the summary based on the estimated emotions.

[0134] The summarization unit can determine the priority of summaries based on the submission date of the content when generating summaries. For example, the summarization unit can prioritize summaries of recently submitted content. The summarization unit can also limit summaries of older content to basic information. Furthermore, the summarization unit can prioritize summaries of content that users frequently access. This ensures that summaries are provided with optimal priority based on the submission date of the content. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can use an AI model to determine the priority of summaries based on the submission date of the content when generating summaries.

[0135] The summarization unit can adjust the order of summaries based on the relevance of the content when generating summaries. For example, the summarization unit can adjust the order of summaries based on the relevance of the content when generating summaries. For example, the summarization unit can prioritize summaries of relevant content based on the content of the page the user is currently viewing. The summarization unit can also highlight summaries of important content based on the user's areas of interest. Furthermore, the summarization unit can provide the most suitable summaries by referring to the user's browsing history. This ensures that summaries are provided in the most appropriate order based on the relevance of the content. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can use an AI model to adjust the order of summaries based on the relevance of the content when generating summaries.

[0136] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0137] Accessibility-supporting browsers or browser extensions can estimate a user's emotions and adjust the reading speed of a webpage based on those emotions. For example, if a user is stressed, the reading speed can be slowed down to make it easier to understand. If the user is relaxed, the reading speed can be normal. Furthermore, if the user is in a hurry, the reading speed can be increased to provide information quickly. This ensures that the optimal reading speed is provided according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, among other things. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Adjusting the reading speed may be done using AI or not.

[0138] Accessibility-supported browsers or browser extensions can analyze a user's past browsing history and suggest the optimal navigation route. For example, they can prioritize pages the user frequently accesses, streamlining navigation. They can also identify the user's areas of interest from past browsing history and prioritize the provision of relevant information. Furthermore, they can analyze the trends of pages accessed at specific times and suggest the optimal navigation route for those times. This provides optimal navigation based on past browsing history. Navigation route suggestions may or may not be performed using AI.

[0139] Accessibility-supporting browsers or browser extensions can estimate a user's emotions and adjust the color scheme of a webpage based on the estimated emotion. For example, if a user is stressed, the color scheme can be changed to a calmer tone to enhance relaxation. If the user is relaxed, the normal color scheme can be maintained. Furthermore, if a user is in a hurry, the color scheme can be changed to highlight important information. This provides the optimal color scheme according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Color scheme adjustment may be performed using AI or not.

[0140] Accessibility-supported browsers or browser extensions can prioritize the display of relevant local news and events information, taking into account the user's geographical location. For example, they can prioritize news and events in the user's current location, providing timely information relevant to the area. They can also provide optimal route guidance and map information based on the user's location. Furthermore, they can prioritize information for areas the user frequently visits. This ensures that the user receives the most relevant information based on their geographical location. The consideration of geographical location may be performed using AI or not.

[0141] Accessibility-supporting browsers or browser extensions can estimate a user's emotions and adjust the font size of a webpage based on those emotions. For example, if a user is stressed, the font size can be increased for easier reading. If the user is relaxed, the normal font size can be maintained. Furthermore, if the user is in a hurry, the font size can be adjusted to highlight important information. This ensures that the optimal font size is provided according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, among other things. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Font size adjustment may be performed using AI or not.

[0142] Accessibility-supported browsers or browser extensions can analyze a user's social media activity and prioritize the display of relevant information. For example, they can prioritize displaying relevant news and articles based on information the user has shared on social media. They can also display relevant content based on the interests of the user's followers and friends. Furthermore, they can analyze a user's social media activity history and provide the most relevant information. This ensures that the information provided is optimal based on the user's social media activity. The analysis of social media activity may be performed using AI or not.

[0143] Accessibility-supporting browsers or browser extensions can estimate a user's emotions and adjust the layout of a webpage based on those emotions. For example, if a user is stressed, the layout can be changed to a simpler, more intuitive one for easier use. If the user is relaxed, the normal layout can be maintained. Furthermore, if the user is in a hurry, the layout can be adjusted to highlight important information. This ensures that the optimal layout is provided according to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, among other things. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Layout adjustments may be performed using AI or not.

[0144] Accessibility-supporting browsers or browser extensions can prioritize the display of reliable information by considering the attribute information of the web page provider. For example, if the web page provider provides reliable information, that information will be displayed preferentially. Furthermore, if the provider possesses specialized knowledge, that information may be highlighted. In addition, the browser can provide the most relevant information based on the provider's attribute information. This ensures that reliable information is provided based on the web page provider's attribute information. The consideration of the provider's attribute information may be performed using AI or not.

[0145] Accessibility-supporting browsers or browser extensions can estimate a user's emotions and adjust the audio guidance of a webpage based on those emotions. For example, if a user is stressed, the audio guidance can be delivered in a slower tone to make it easier to understand. If the user is relaxed, the audio guidance can be delivered in a normal tone. Furthermore, if the user is in a hurry, the tone of the audio guidance can be adjusted to highlight important information. This ensures that the audio guidance is optimally tailored to the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, such as text generation AI (e.g., LLM) or multimodal generation AI, but is not limited to these examples. The adjustment of the audio guidance may be performed using AI or not.

[0146] Accessibility-supported browsers or browser extensions can prioritize the display of important information based on how often a webpage is updated. For example, frequently updated pages can prioritize the display of the most recent information. Pages that are not frequently updated can display basic information. Furthermore, pages that users frequently access can prioritize the display of particularly detailed information. This ensures that the most relevant information is provided based on the webpage's update frequency. The consideration of update frequency may be performed using AI or not.

[0147] The following briefly describes the processing flow for example form 2.

[0148] Step 1: The editorial team dynamically edits the HTML of the web page. The editorial team can, for example, perform real-time editing using JavaScript or server-side editing. The editorial team parses the HTML of the web page and converts it into an accessible format for visually impaired and elderly people. Step 2: The support team will make the HTML edited by the editorial team compliant with the web standard WAI-ARIA. The support team will add appropriate attributes to the HTML according to the specific methods and standards for WAI-ARIA compliance. Step 3: The navigation section provides keyboard navigation based on the HTML handled by the corresponding section. The navigation section adds appropriate tags to links and buttons on the page, enabling keyboard navigation. Step 4: The alternative text generation unit generates alternative text for the image based on the navigation provided by the navigation unit. The alternative text generation unit analyzes the image content and automatically generates appropriate alternative text. Step 5: The labeling unit adds labels to the form fields based on the alternative text generated by the alternative text generation unit. The labeling unit adds appropriate labels to the form fields, making it easier to interact with the interactive elements. Step 6: The filter unit provides a colorblind-friendly filter function based on the labels added by the labeling unit. The filter unit provides a filter function that adjusts the page colors for users with color blindness. Step 7: The summary section summarizes the content based on the filtering functions provided by the filter section. The summary section summarizes the content of long articles or pages, extracting and providing only the important points.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the editing unit, response unit, navigation unit, alternative text generation unit, labeling unit, filter unit, and summarization unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the editing unit is implemented by the processor 46 of the smart device 14 or the processor 28 of the data processing unit 12, and dynamically edits the HTML of the web page. The response unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and makes the edited HTML compatible with WAI-ARIA. The navigation unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and provides keyboard navigation. The alternative text generation unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and generates alternative text for images. The labeling unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12, and adds labels to form fields. The filter unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and provides a filter function that accommodates color blindness. The summarization unit is implemented, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and summarizes the content. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0153] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the editing unit, response unit, navigation unit, alternative text generation unit, labeling unit, filter unit, and summarization unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the editing unit is implemented by the processor 46 of the smart glasses 214 or the processor 28 of the data processing unit 12, and dynamically edits the HTML of a web page. The response unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and makes the edited HTML compatible with WAI-ARIA. The navigation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and provides keyboard navigation. The alternative text generation unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and generates alternative text for images. The labeling unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12, and adds labels to form fields. The filter unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and provides a filter function that accommodates color blindness. The summarization unit is implemented, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and summarizes the content. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0169] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] Each of the multiple elements described above, including the editing unit, response unit, navigation unit, alternative text generation unit, labeling unit, filter unit, and summarization unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the editing unit is implemented by the processor 46 of the headset terminal 314 or the processor 28 of the data processing unit 12, and dynamically edits the HTML of the web page. The response unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and makes the edited HTML compatible with WAI-ARIA. The navigation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and provides keyboard navigation. The alternative text generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and generates alternative text for images. The labeling unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, and adds labels to the form fields. The filtering unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, and provides a filter function that accommodates color blindness. The summarizing unit is implemented, for example, by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12, and summarizes the content. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0185] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.).

[0198] 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.

[0199] 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.

[0200] 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.

[0201] Each of the multiple elements described above, including the editing unit, response unit, navigation unit, alternative text generation unit, labeling unit, filter unit, and summarization unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the editing unit is implemented by the processor 46 of the robot 414 or the processor 28 of the data processing unit 12, and dynamically edits the HTML of a web page. The response unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and makes the edited HTML compatible with WAI-ARIA. The navigation unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and provides keyboard navigation. The alternative text generation unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and generates alternative text for images. The labeling unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and adds labels to form fields. The filter unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and provides a filter function that accommodates color blindness. The summarization unit is implemented, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and summarizes the content. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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."

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] (Note 1) The editorial team dynamically edits the HTML of web pages, The aforementioned editorial department provides a section for adapting the HTML to the web standard WAI-ARIA, and A navigation unit that provides keyboard navigation based on HTML handled by the aforementioned corresponding unit, A replacement text generation unit that generates replacement text for an image based on the navigation provided by the aforementioned navigation unit, A labeling unit adds labels to form fields based on the alternative text generated by the alternative text generation unit, A filter unit that provides a color vision deficiency-compatible filter function based on the labels added by the labeling unit, The system comprises a summarization unit that summarizes content based on the filter function provided by the filter unit. A system characterized by the following features. (Note 2) The aforementioned editorial department, This process involves parsing the HTML of a webpage and converting it into an accessible format for visually impaired and elderly individuals. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned navigation unit is Add appropriate tags to links and buttons on the page to enable keyboard navigation. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned alternative text generation unit, Analyze the content of an image and automatically generate appropriate alternative text. The system described in Appendix 1, characterized by the features described herein. (Note 5) The labeling unit is Add appropriate labels to form fields to facilitate interaction with interactive elements. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned filter section is Provides a filter function to adjust page colors for users with color vision deficiency. The system described in Appendix 1, characterized by the features described herein. (Note 7) The summary section above is, Summarize the content of long articles or pages, extracting and providing only the most important points. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned editorial department, It estimates the user's emotions and adjusts the timing of HTML edits based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned editorial department, Analyze the past access history of a webpage and select the optimal editing method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned editorial department, When editing HTML, filtering is performed based on the user's current browsing status and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned editorial department, It estimates the user's sentiment and determines the priority of HTML to edit based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned editorial department, When editing HTML, the system prioritizes editing content that is highly relevant to the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned editorial department, When editing HTML, the system analyzes the user's social media activity and edits relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 14) The corresponding part is, The system estimates the user's emotions and adjusts the WAI-ARIA response method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The corresponding part is, When implementing WAI-ARIA, 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 16) The corresponding part is, When supporting WAI-ARIA, different mapping algorithms are applied depending on the category of the web page. The system described in Appendix 1, characterized by the features described herein. (Note 17) The corresponding part is, It estimates the user's emotions and determines the priority of responses based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The corresponding part is, When implementing WAI-ARIA, prioritize the implementation based on the frequency of web page updates. The system described in Appendix 1, characterized by the features described herein. (Note 19) The corresponding part is, When implementing WAI-ARIA, the order of implementation is adjusted based on the relevance of the web pages. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned navigation unit is It estimates the user's emotions and adjusts navigation criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned navigation unit is When navigating, improve the accuracy of the navigation by considering the relationships between web pages. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned navigation unit is When navigating, the navigation should take into account the attribute information of the web page provider. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned navigation unit is It estimates the user's sentiment and adjusts the order in which navigation results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned navigation unit is Navigation should take into account the geographical distribution of web pages. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned navigation unit is When navigating, refer to related literature on web pages to improve the accuracy of navigation. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned alternative text generation unit, It estimates the user's sentiment and adjusts how alternative text is generated based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned alternative text generation unit, When generating alt text, adjust the level of detail in the alt text based on the importance of the image. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned alternative text generation unit, When generating alternative text, different generation algorithms are applied depending on the image category. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned alternative text generation unit, It estimates the user's sentiment and determines the priority of alternative text based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned alternative text generation unit, When generating alternative text, prioritize the alternative text based on when the image was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned alternative text generation unit, When generating alternative text, adjust the order of the alternative text based on the relevance of the image. The system described in Appendix 1, characterized by the features described herein. (Note 32) The labeling unit is It estimates the user's emotions and adjusts the labeling method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The labeling unit is When labeling, adjust the level of detail of the label based on the importance of the form field. The system described in Appendix 1, characterized by the features described herein. (Note 34) The labeling unit is When labeling, different labeling algorithms are applied depending on the category of the form field. The system described in Appendix 1, characterized by the features described herein. (Note 35) The labeling unit is It estimates the user's emotions and determines the priority of labeling based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The labeling unit is When labeling, prioritize labeling based on when the form fields were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 37) The labeling unit is When labeling, adjust the labeling order based on the relevance of the form fields. The system according to appended note 1, characterized in that... (Appended note 38) The filter unit... estimates the user's emotion and adjusts the method of applying the filter based on the estimated user emotion The system according to appended note 1, characterized in that... (Appended note 39) The filter unit... adjusts the detail level of the filter based on the importance of the web page when applying the filter The system according to appended note 1, characterized in that... (Appended note 40) The filter unit... applies different filter algorithms according to the category of the web page when applying the filter The system according to appended note 1, characterized in that... (Appended note 41) The filter unit... estimates the user's emotion and determines the priority of the filter based on the estimated user emotion The system according to appended note 1, characterized in that... (Appended note 42) The filter unit... determines the priority of the filter based on the update frequency of the web page when applying the filter The system according to appended note 1, characterized in that... (Appended note 43) The filter unit... adjusts the order of the filter based on the relevance of the web page when applying the filter The system according to appended note 1, characterized in that... (Appended note 44) The summarization unit... estimates the user's emotion and adjusts the expression method of the summary based on the estimated user emotion The system according to appended note 1, characterized in that... (Appended note 45) The summarization unit... When generating an abstract, adjust the detail level of the abstract based on the importance of the content The system according to Appendix 1, characterized in that (Appendix 46) The abstract part When generating an abstract, apply different abstract algorithms according to the category of the content The system according to Appendix 1, characterized in that (Appendix 47) The abstract part Estimate the user's emotion and adjust the length of the abstract based on the estimated user's emotion The system according to Appendix 1, characterized in that (Appendix 48) The abstract part When generating an abstract, determine the priority of the abstract based on the submission time of the content The system according to Appendix 1, characterized in that (Appendix 49) The abstract part When generating an abstract, adjust the order of the abstract based on the relevance of the content The system according to Appendix 1, characterized in that

Explanation of symbols

[0221] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robot

Claims

1. The editorial team dynamically edits the HTML of web pages, The aforementioned editorial department provides a section for adapting the HTML to the web standard WAI-ARIA, and A navigation unit that provides keyboard navigation based on HTML handled by the aforementioned corresponding unit, A replacement text generation unit that generates replacement text for an image based on the navigation provided by the aforementioned navigation unit, A labeling unit adds labels to form fields based on the alternative text generated by the alternative text generation unit, A filter unit that provides a color vision deficiency-compatible filter function based on the labels added by the labeling unit, The system comprises a summarization unit that summarizes content based on the filter function provided by the filter unit. A system characterized by the following features.

2. The aforementioned editorial department, This process involves parsing the HTML of a webpage and converting it into an accessible format for visually impaired and elderly individuals. The system according to feature 1.

3. The aforementioned navigation unit is Add appropriate tags to links and buttons on the page to enable keyboard navigation. The system according to feature 1.

4. The aforementioned alternative text generation unit, Analyze the content of an image and automatically generate appropriate alternative text. The system according to feature 1.

5. The labeling unit is Add appropriate labels to form fields to facilitate interaction with interactive elements. The system according to feature 1.

6. The aforementioned filter section is Provides a filter function to adjust page colors for users with color vision deficiency. The system according to feature 1.

7. The summary section above is, Summarize the content of long articles or pages, extracting and providing only the most important points. The system according to feature 1.

8. The aforementioned editorial department, It estimates the user's emotions and adjusts the timing of HTML edits based on those emotions. The system according to feature 1.

Images