A page processing method, device, equipment and medium

Abstract

The embodiments of the present application provide a page processing method, apparatus, device and medium, which support, in the process of displaying a target page, when the target page contains an image, the image can be processed into a templated content description text in combination with the image pattern recognition technology to describe the semantics of the image, so that the content contained in the image and the meaning expressed can be provided more accurately, and the complete page information of the target page can be delivered in combination with the barrier-free reading capability. The embodiments of the present application can effectively read the image (non-text content) in the target page, improving the integrity of the page information reading.

Description

Technical Field

[0001] The present application relates to the field of computer technology, specifically to the field of artificial intelligence, and more particularly to a page processing method, apparatus, device, and medium. Background Art

[0002] The massive amount of information on the Internet is usually presented in a visual way. It is difficult for visually impaired people to browse information on the Internet like healthy people, which makes it impossible for visually impaired people to use the Internet for office work or communication.

[0003] Currently, some smart devices (or applications deployed on them) provide accessible screen readers to help visually impaired people read information on web pages. This so-called accessible screen reader function allows the smart device to read the information on a web page and then announce it using voice, allowing the visually impaired to hear it. However, in practice, it has been found that existing accessible screen readers only support a limited range of information types. They can typically only read text content on a web page, while some non-text content is often unreadable or read incorrectly. This results in the loss of some information on the page and prevents the visually impaired from providing a more complete page information. Summary of the Invention

[0004] The embodiments of the present application provide a page processing method, apparatus, device, and medium, which can effectively read images (non-text content) in a target page and improve the integrity of page information reading.

[0005] On the one hand, an embodiment of the present application proposes a page processing method, which includes:

[0006] Display the target page;

[0007] If the target page contains an image, obtain the semantic description information of the image;

[0008] Play audio prompts that match the semantic description of the image.

[0009] On the other hand, an embodiment of the present application provides a page processing device, which includes:

[0010] A display unit, configured to display a target page;

[0011] A processing unit, configured to obtain semantic description information of an image if the target page contains an image;

[0012] The processing unit is further configured to play prompt audio that matches the semantic description information of the image.

[0013] In one implementation, the semantic description information of the image is used to describe the image semantically;

[0014] The semantic description information includes at least one of the following: description information of a target color presented by the image, description information of textual content contained in the image, description information of the source of the image, description information of the author of the image, description information of objects contained in the image, and description information of actions performed by objects contained in the image;

[0015] The prompt audio is used to prompt at least one of the following: used to prompt the target color presented by the image, used to prompt the text content contained in the image, used to prompt the source of the image, used to prompt the author of the image, used to prompt the object contained in the image, and used to prompt the behavior performed by the object contained in the image.

[0016] In one implementation, the processing unit is further configured to start a screen reading mode;

[0017] The processing unit is used to play the prompt audio that matches the semantic description information of the image, specifically to: play the prompt audio that matches the semantic description information of the image in the screen reading mode.

[0018] In one implementation, the target page further includes other content, and the other content includes at least one of the following: text, rich text, and an icon; and the processing unit is further configured to:

[0019] In screen reading mode, the audio that matches each content will be read aloud in the order in which the content is arranged on the target page.

[0020] In one implementation, the target page further includes operation information, which includes at least one of the following: information about the operator, the operated object, the type of the operated object, information about the operation item, feedback presented when the operation item is selected, and changes to the target page caused by the operation information; the processing unit is further configured to:

[0021] In screen reading mode, the operation information on the target page is converted into operation audio for playback output.

[0022] In one implementation, the target page refers to any service page in the target application; the target application supports the screen reader mode and provides an entry to the screen reader mode; and the processing unit, when activating the screen reader mode, is specifically configured to:

[0023] When the screen reading mode entry is triggered, the screen reading mode is started;

[0024] The entry to the screen reading mode includes any of the following: a button, an icon, a menu item, or a voice command.

[0025] In one implementation, if the target page is the first page, and the image is a native image in the first page and does not support editing, the processing unit, when obtaining the semantic description information of the image, is specifically configured to:

[0026] During the process of loading the first page, obtaining semantic description information of the image;

[0027] The first page includes any one of the following: a web page, a service page of an application, a page of a mini-program, or a multimedia playback page.

[0028] In one implementation, if the target page is the second page and the image is added to the second page through an editing operation, the processing unit, when being configured to obtain the semantic description information of the image, is specifically configured to:

[0029] When adding an image to the second page, obtain the semantic description information of the image;

[0030] The second page includes any one of the following: a document editing page, an online document editing page, and a social conversation page.

[0031] In one implementation, the semantic description information includes description information of a target color presented by the image; and the processing unit, when used to obtain the semantic description information of the image, is specifically configured to:

[0032] Identify S colors from the image, where S is an integer greater than 1;

[0033] Get the number of pixels and saturation of each color in S colors;

[0034] Multiply the number of pixels of each color by the saturation to get the color score of each color;

[0035] The color corresponding to the maximum color score among the S colors is determined as the target color of the image;

[0036] Generates description information for describing the target color.

[0037] In one implementation, the semantic description information includes description information of text content contained in the image; and the processing unit, when used to obtain the semantic description information of the image, is specifically configured to:

[0038] Preprocess the image;

[0039] Perform image feature extraction on the preprocessed image to obtain image features;

[0040] Use a classifier to classify image features to identify the text content contained in the image;

[0041] Generates description information for describing the text content contained in the image.

[0042] In one implementation, the semantic description information includes description information of the source of the image and description information of the author of the image; and the processing unit, when used to obtain the semantic description information of the image, is specifically configured to:

[0043] Get the source of the image;

[0044] If the image's origin indicates that the image is from the local space, the image's author is read from the local space;

[0045] If the source of the image indicates that the image comes from a network file, then obtain the link of the image and read the author of the image according to the link;

[0046] Generates a description of the image's origin and the image's author.

[0047] In one implementation, the semantic description information includes description information of objects contained in the image and description information of actions performed by the objects contained in the image; and the processing unit, when used to obtain the semantic description information of the image, is specifically configured to:

[0048] Call the visual vocabulary model to perform object recognition processing on the image, identify the objects contained in the image and the behavioral sentences associated with the objects;

[0049] Descriptive information of an object contained in the image is generated, and descriptive information of an action performed by the object contained in the image is generated based on the object and an action sentence associated with the object.

[0050] In one implementation, the processing unit, when used to play the prompt audio that matches the semantic description information of the image, is specifically used to:

[0051] Create a hidden document object node for the target page and set auxiliary properties for the hidden document object node;

[0052] Process the semantic description information of the image into template text in a templated form;

[0053] Write the template text into the hidden document object node;

[0054] When a write operation is detected, the prompt audio is matched to the written template text; and

[0055] Play the prompt audio.

[0056] In one implementation, the target page is rendered in a Canvas manner; the processing unit is further configured to:

[0057] Create a hidden document object node for the target page and set auxiliary properties for the hidden document object node;

[0058] Write the contents of the Canvas node into the hidden document object node;

[0059] When a write operation is detected, content audio is matched to the written content; and the content audio is played.

[0060] In one implementation, the processing unit is further configured to:

[0061] Monitor the operation events and feedback results of the operation events on the Canvas node;

[0062] Write the operation events and feedback results into the hidden document object node;

[0063] When a write operation is detected, an operation audio is matched with the written operation event and the feedback result; and the operation audio is played.

[0064] In another aspect, the present application provides a computer device, comprising:

[0065] a processor for loading and executing computer programs;

[0066] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the page processing method is implemented.

[0067] On the one hand, the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is suitable for being loaded by a processor and executing the above-mentioned page processing method.

[0068] In one aspect, the present application provides a computer program product or computer program, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the above-described page processing method.

[0069] In an embodiment of the present application, for the displayed target page, if the target page contains an image, the semantic description information of the image can be obtained, and then a prompt audio that matches the semantic description information of the image can be played. In the above scheme, the semantic description information can semantically describe the content expressed by the image, and the semantic description information is then converted into a matching prompt audio for broadcast, which realizes the effective screen reading of the image (non-text content) in the target page and improves the integrity of the page information reading; in addition, by playing the prompt audio, the content expressed by the image can be expressed more accurately and completely, thereby assisting in understanding the semantics of the image, so that more abundant page information can be provided in the process of reading the target page, thereby improving the intelligence of the page reading process. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0071] Figure 1a A schematic diagram showing a page processing scenario provided by an exemplary embodiment of the present application is shown;

[0072] Figure 1b A schematic diagram of a target page provided by an exemplary embodiment of the present application is shown;

[0073] Figure 2 A schematic flow chart of a page processing method provided by an exemplary embodiment of the present application is shown;

[0074] Figure 3 A schematic diagram showing a target page including images and other contents provided by an exemplary embodiment of the present application is shown;

[0075] Figure 4a A schematic diagram of a process for starting a screen reading mode provided by an exemplary embodiment of the present application is shown;

[0076] Figure 4b A schematic diagram of a confirmation window provided by an exemplary embodiment of the present application is shown;

[0077] Figure 5a A schematic diagram showing content indicated by audio provided by an exemplary embodiment of the present application is shown;

[0078] Figure 5b A schematic diagram showing content indicated by audio provided by an exemplary embodiment of the present application is shown;

[0079] Figure 5c A schematic diagram showing content indicated by audio provided by an exemplary embodiment of the present application is shown;

[0080] Figure 6 A schematic flow chart of a page processing method provided by an exemplary embodiment of the present application is shown;

[0081] Figure 7 A schematic diagram of an HSL color mode provided by an exemplary embodiment of the present application is shown;

[0082] Figure 8 A schematic diagram of a target page provided by an exemplary embodiment of the present application is shown;

[0083] Figure 9 A schematic diagram of a process for obtaining text content contained in an image provided by an exemplary embodiment of the present application is shown;

[0084] Figure 10 A schematic diagram of a process for obtaining description information of the source and author of an image provided by an exemplary embodiment of the present application is shown;

[0085] Figure 11a A schematic diagram of a visual vocabulary model provided by an exemplary embodiment of the present application is shown;

[0086] Figure 11b A schematic diagram of a visual vocabulary model provided by an exemplary embodiment of the present application is shown;

[0087] Figure 12 A schematic diagram of a process for monitoring canvas node content provided by an exemplary embodiment of the present application is shown;

[0088] Figure 13 A schematic structural diagram of a page processing device provided by an exemplary embodiment of the present application is shown;

[0089] Figure 14 A structural diagram of a computer device provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0090] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0091] The embodiments of the present application relate to barrier-free screen reading, which is a screen reading method that uses voice (or audio) to broadcast the content contained in a page. The process of barrier-free screen reading may include: identifying the content contained in the page, and outputting a voice that matches the identified content using voice broadcasting, and the voice can be used to describe the semantics of the identified content. Since most of the information on the Internet is presented in a visual way, the barrier-free screen reading function is of great significance to the visually impaired. For example: in a scenario where a visually impaired person browses a web page using a browser, the barrier-free screen reading function can read the web page content on the web page and play the web page content through voice broadcasting, which can help the visually impaired person easily obtain the web page content contained in the web page; wherein, a language description method for constructing a web page (or web page) is HTML5 (Hypertext 5.0). For example, when visually impaired people use online documents for collaborative work, they can read the document content in the online document based on the barrier-free screen reading function and have the document content spoken aloud, which makes it convenient for visually impaired people to work and communicate through the Internet. Among them, online documents are a document tool that can be edited, viewed, and collaborated with multiple people online.

[0092] The aforementioned accessible screen reader technology involves speech processing technology in the field of artificial intelligence (AI). Specifically, speech processing technology enables the spoken output of page content identified by the accessible screen reader. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive field of computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making. AI technology is an interdisciplinary discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Basic AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning. Key speech processing technologies include automatic speech recognition (ASR), text-to-speech (TTS), and voiceprint recognition. Enabling computers to hear, see, speak, and feel is the future direction of human-computer interaction, with speech becoming one of the most promising methods of human-computer interaction.

[0093] Specifically, accessible screen reading can be achieved by using a target application (or simply referred to as an application, such as any application) with an accessible screen reading function, where an application refers to a computer program for completing one or more specific tasks; for example, the target application may include a document application with an accessible screen reading function, which can be used to open online documents, such as the Tencent document application. According to the operation mode of the target application, the target application may include but is not limited to: ① Applications installed and running in the terminal; the terminal may include but is not limited to: PC (Personal Computer), PDA (tablet computer), mobile phone, wearable device, smart car and other smart devices. ② Installation-free applications, that is, applications that can be used without downloading and installing. Such applications are also commonly known as mini-programs, which usually run as sub-programs in the client. ③ Web applications opened through a browser; and so on.

[0094] The embodiment of the present application proposes a page processing solution, which not only supports the recognition of the text content (such as the text content contained in the DOM node) of the text in the target page (such as any service page) and the output of voice prompts; it also supports the acquisition of the semantic description information of the image when the target page contains an image, and then plays the prompt audio that matches the semantic description information of the image. The semantic description information mentioned above can describe the content expressed by the image from a semantic point of view, and then convert the semantic description information into a matching prompt audio for playback, so as to achieve effective screen reading of the image in the target page and improve the integrity of the page information reading. In addition, by playing the prompt audio, the content expressed by the image can be expressed more accurately and completely, thereby assisting in understanding the semantics of the image, so that more abundant page information can be provided in the process of reading the target page, thereby improving the intelligence of the page reading processing.

[0095] The page processing scheme proposed in the embodiment of the present application can be executed by a computer device, or by a target application (such as a document application) running in the computer device. Among them, the computer device can be any smart device with barrier-free screen reading function, and the smart terminal may include but is not limited to: smart phones (such as Android phones, iOS phones, etc.), tablet computers, personal computers, portable personal computers, mobile Internet devices (Mobile Internet Devices, referred to as MID), smart TVs, car-mounted devices, head-mounted devices, and other smart devices that can touch the screen. The embodiment of the present application does not limit the type of computer device, which is explained here. A schematic diagram of an exemplary page processing scenario can be found in Figure 1a ,like Figure 1aAs shown, assuming that a target page is displayed in the computer device 101, the target page may belong to a document application; if the target page contains an image, the image may be visually semantically read to obtain semantic description information of the image, and then a voice prompt matching the semantic description information of the image may be output. Of course, the embodiment of the present application also includes a computer device 102, which is a background server of the document application or the computer device 101, and may provide service support for the computer device 101 or the document application; under this implementation mode, the operation of visually semantically reading the image mentioned in the embodiment of the present application may be performed by the computer device 102, which sends the semantic description information of the recognized image to the computer device 101 or the document application running in the computer device 101, so that the computer device 101 may convert the semantic description information into a matching prompt audio for playback; as Figure 1a The content of the prompt audio 1011 played is "There are words on the picture: My pet; The background color of the picture is light gray; There is a gray cat in the picture; The cat is licking its paw; The picture comes from XX; The author of the picture is XX"; This embodiment of the application does not limit the execution subject of this embodiment of the application, which is explained here. It is worth mentioning that the above-mentioned image can be an image frame contained in a video stream; in actual application scenarios, when a visually impaired person selects an image frame of the video while playing the video, the page processing method provided by the embodiment of the application can be used to process the selected image frame; and play a prompt audio that matches the semantic description information of the image frame.

[0096] It has been found in practice that the page processing solution provided by the embodiment of the present application has obvious advantages in barrier-free screen reading of the target page. The advantages of the embodiment of the present application are described below by comparing the present application solution with the existing mainstream barrier-free screen reading function. The existing mainstream barrier-free screen reading function can only recognize the text content of the target page and voice broadcast it; when the target page contains content such as images, it can only simply voice broadcast the format of the content; such as Figure 1b In the first picture shown, the target page is a slide page, which contains text and images. When the existing mainstream barrier-free screen reading function is used to read the slide page, the output prompt audio is "My pet, [image]"; if the text "My pet" is text in the image, the output prompt audio is simpler, that is, "[image]". For the visually impaired, they cannot obtain the specific content of the image, but only know that the slide page contains an image, which results in the visually impaired being unable to obtain the complete information of the page. The page processing solution provided by the embodiment of the present application is Figure 1bWhen the slide page shown is read for barrier-free screen reading, not only can the text "My Pet" in the slide page be read out, but the objects contained in the image, the behavior of the objects, and other information of the image can also be obtained and voice broadcasted; Figure 1b In the second image shown, the prompt audio played by the embodiment of the present application is "The image has text written on it: My pet; The background color of the image is light gray; There is a gray cat in the image; The cat is licking its paw; The image is from XX; The image author is XX..." Based on this, the embodiment of the present application can obtain the semantic description information of the image on the target page and convert the semantic description information into a matching prompt audio. This method of playing the prompt audio can more accurately and completely express the content of the image, thereby assisting in understanding the semantics of the image and improving the intelligence of the page screen reading process.

[0097] Based on the page processing scheme described above, the embodiment of the present application proposes a more detailed page processing method. The page processing method proposed in the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0098] Figure 2 A flow chart of a page processing method provided by an exemplary embodiment of the present application is shown; the page processing method can be executed by a computer device (such as the computer device 101 mentioned above), and the page processing method may include but is not limited to steps S201-S203:

[0099] S201: Display the target page.

[0100] When the target user (such as a user using the computer device 101) opens and uses the computer device (such as a smart device), the target page can be displayed on the display screen of the computer device. Optionally, the target page can be an operating system page of the computer device, such as a configuration page for configuring the functions of the computer device. Optionally, the target page can also refer to any service page in the target application running in the computer device (such as a smart terminal); for example: the target application is a document application running in the computer device and having a document editing function, then any service page in the target application can include a document page of any document contained in the document application, and the any document can be an online document (such as an online table, online text, and online slides, etc.), which can realize a document that can be collaboratively edited by multiple people. For the sake of convenience, the following introduction will be based on the example of a document application running in the computer device and the target page being a document page of any document contained in the document application.

[0101] The target page may include images and other content, and the other content may include at least one of the following: text, rich text, icons, video, and audio, etc. Among them, text, or plain text, refers to a form of expression of a written language; the text may include multiple characters, one or more characters form a string, and the characters may include at least one of the following: Chinese characters (i.e., Chinese characters), English characters (i.e., letters), numbers, and punctuation marks (such as commas "," , periods ".", square brackets "[ ]"); for example, the target page contains the following text "My Pets", which contains multiple characters, such as the characters "I", "raise", "of", etc. Rich text, or rich text format, is relative to plain text. Simply put, it means that multiple formats can be used in the text, such as font color, pictures, tables, animations, emoticons, etc. Icons may include but are not limited to: functional icons and non-functional icons; so-called functional icons may refer to icons that can be triggered to achieve a certain function, such as an insert icon, which can insert content into the target page when the insert icon is clicked; non-functional icons may refer to icons that cannot be triggered and only serve as prompts or for viewing.

[0102] It should be noted that the above is only an exemplary introduction to the content that may be included in the target page. In actual application scenarios, the target page may also include content not mentioned above. The embodiment of this application does not limit the number and type of content included in the target page.

[0103] S202: If the target page contains an image, obtain semantic description information of the image.

[0104] The semantic description information of an image is used to describe the image semantically; the semantic description information of an image may include at least one of the following: description information of the target color presented by the image, description information of the text content contained in the image, description information of the source of the image, description information of the author of the image, description information of the objects contained in the image, and description information of the behaviors performed by the objects contained in the image. Among them, the objects contained in the image refer to the category individuals contained in the image, such as the image contains a cat, a person, an umbrella, a sofa, etc.; the behaviors performed by the objects contained in the image refer to: the actions performed by the objects. Figure 3 As shown, the target page 301 includes an image 3011, and the target color presented by the image 3011 is gray. For example, the target color of the image refers to the background color, and the background color of the image is gray; the text content contained in the image is "My Pet"; the image comes from XX; the author of the image is XX; the object contained in the image is a cat; and the behavior performed by the object contained in the image - the cat - is "licking cat paws."

[0105] It is understandable that when the target page also contains other content, the embodiment of the present application supports obtaining the description information of other content when obtaining the semantic description information of the image; for example, if the target page also contains text, the description information of the text can be obtained. This facilitates the subsequent voice broadcast of all the content contained in the target page. Figure 3 ,like Figure 3 As shown, in addition to image 3011, target page 301 also includes text 3012. Therefore, the text content of text 3012 can be recognized to obtain description information of text 3012. The description information of text 3012 is actually the text content. For example, if the text content of text 3012 is "Title: XXXX", the description information of recognized text 3012 is "Title: XXXX". It is worth mentioning that the process of obtaining semantic description information of the image shown in step S202 is the process of performing pattern recognition on the image. The so-called pattern recognition is to use a computational method to classify samples into certain categories based on the characteristics of the samples. In the embodiment of the present application, the samples are the images mentioned in the embodiment of the present application.

[0106] S203: Play prompt audio that matches the semantic description information of the image.

[0107] Prompt audio that matches the semantic description information of the image is played in the form of voice broadcast, so that visually impaired people can understand the semantics that the image intends to express through hearing. Among them, the prompt audio that matches (or corresponds to) the semantic description information can be used to prompt at least one of the following: used to prompt the target color presented by the image (the corresponding semantic description information includes description information of the target color presented by the image); used to prompt the text content contained in the image; (the corresponding semantic description information includes description information of the text content contained in the image); used to prompt the source of the image (the corresponding semantic description information includes description information of the source of the image); used to prompt the author of the image (the corresponding semantic description information includes description information of the author of the image); used to prompt the objects contained in the image (the corresponding semantic description information includes description information of the objects contained in the image); and used to prompt the actions performed by the objects contained in the image (the corresponding semantic description information includes description information of the actions performed by the objects contained in the image).

[0108] It is not difficult to understand that the above steps S201-S203 are implemented after the screen reading mode is started; in other words, the barrier-free screen reading function has a switch item, and the barrier-free screen reading function is turned on only when the screen reading mode is started, so that the screen reading mode can be turned off for people without visual impairments. In a specific implementation, the embodiment of the present application supports the start of the screen reading mode, so that the prompt audio that matches the semantic description information of the image shown in step S203 includes: in the screen reading mode, the prompt audio that matches the semantic description information of the image is played. When the target page refers to any service page in the target application, it means that the target application supports the screen reading mode; when the target page refers to any service page in the smart terminal, it means that the smart terminal supports the screen reading mode; the embodiment of the present application takes the target application supporting the screen reading mode as an example for explanation. The target application provides an entry to the screen reading mode, and when the entry to the target application is triggered, the screen reading mode of the target application is started; wherein, the entry to the screen reading mode of the target application may include any of the following: a button, an icon, a menu item, and a voice command. The following is a brief introduction to several implementation methods of starting the screen reading mode, wherein:

[0109] (1) Start the screen reading mode through the menu item. In the specific implementation, a menu control (or component, option, etc.) is displayed on the target page; when the menu control is triggered, the option window is triggered to display, and the option window contains one or more options, one or more options including the screen reading option; if the screen reading option is triggered, a notification message is displayed on the target page, and the notification message is used to notify that the screen reading mode is successfully started. Combined with Figure 4a The flowchart of starting the screen reading mode is shown in FIG. Figure 4a As shown, a menu control 401 is displayed in the target page. When the menu control 401 is triggered, an option window 402 is displayed, and the option window 402 includes a screen reading option 4021. If the screen reading option 4021 is triggered, it means that the user wants to turn on the barrier-free screen reading function of the target application, then a notification message 403 is displayed in the target page, and the notification message 403 indicates to start the screen reading mode of the target application.

[0110] It should be noted that the above is only an exemplary implementation method of starting the screen reading mode of the target application; it is understandable that the implementation method of starting the screen reading mode of the target application in the actual application scenario may also change; for example: the embodiment of the present application supports outputting a confirmation window after the screen reading option is triggered to notify the user again to confirm whether to start the screen reading mode of the target application. The confirmation window contains a confirmation option and a cancel option; when the confirmation option is triggered, it indicates that the user is determined to start the screen reading mode of the target application, and when the cancel option is triggered, it indicates that the user cancels the start of the screen reading mode of the target application. An exemplary schematic diagram of the confirmation window can be seen Figure 4b ,like Figure 4b As shown, confirmation window 404 includes a confirmation option 4041 and a cancel option 4042. In addition, the above description is based on the example of the option window and confirmation window being displayed overlaid on the target page, but they can also be displayed in the form of separate pages. The embodiment of the present application does not limit the display form of the option window and confirmation window.

[0111] (2) Start the screen reading mode through voice commands. In the specific implementation, when the smart terminal turns on the voice input function, the smart terminal can collect the audio in its physical environment. In this way, the user can say a sentence similar to "turn on barrier-free screen reading" when the smart terminal turns on the voice input function; after the smart terminal receives the sentence, it can automatically start the screen reading mode. Among them, the smart terminal collects the audio in its physical environment through the microphone deployed by the smart terminal.

[0112] (3) Start the screen reading mode through a shortcut key. In a specific implementation, the embodiment of the present application supports quickly starting the screen reading mode through a shortcut key, such as the shortcut key ctrl+XX; in this way, the user can quickly start the screen reading mode when entering the shortcut key. Optionally, the user can enter the shortcut key in the virtual keyboard displayed on the display screen of the smart terminal; optionally, the smart terminal can be connected to a physical keyboard, so that the user enters the shortcut key on the physical keyboard. In summary, the embodiment of the present application supports multiple ways to start the screen reading mode, enriches the ways to start the screen reading mode, helps visually impaired people to quickly start the screen reading mode of the target application or smart terminal, and improves the speed and simplicity of starting the screen reading mode.

[0113] In addition, the embodiment of the present application supports playing audio that matches each content when the target page contains images and other content (such as text, icons, etc.). In one implementation, in screen reading mode, the audio that matches each content can be read aloud in the order in which the content is arranged in the target page. For example, continue to see Figure 3 ,exist Figure 3In the target page 301 shown, the first row displays, from left to right, a return option 302, an application icon 303 of the target application, an application name 304 of the target application, and a favorite option 305, etc. Audio matching each content can be read aloud in sequence to inform the visually impaired person of the content contained in the target page 301. In another implementation, in screen reading mode, audio matching the selected content can be played based on the user's selection operation on the target page (such as a trigger operation, a long press operation, a drag operation, a double-click operation, etc.). In other implementations, in screen reading mode, audio matching the selected content can be read aloud in sequence according to the order in which the content is arranged on the target page. When any content on the target page is triggered, the current audio is stopped and audio matching the triggered content is played. For example, in screen reading mode, the audio of the first content, the second content, and the third content are read aloud in sequence. When the audio of the second content is read aloud, if a triggering action for the first content is detected on the target page, the reading of the second content stops and the audio matching the first content is played. This meets the user's demand for click-to-play and improves the user's barrier-free screen reading experience.

[0114] The audio that matches the target content can be used to prompt the basic content of the target content, operation information related to the target content, content format of the target content, and structure and location of the target content; the target content is any one of the multiple contents contained in the target page. Figure 5a 、 Figure 5b as well as Figure 5c Briefly introduce the content indicated by the audio (such as basic content, operation information, etc.):

[0115] (1) Figure 5a As shown, audio is used to prompt content-based and operation information of each content in the target page.

[0116] Depending on the type of content contained in the target page, the corresponding basic content may vary. For example, if the target page contains an image, the basic content of the image may include, but is not limited to, the following: the target color presented by the image, the text content contained in the image, the image source, the image author, the objects contained in the image, and the actions performed by the objects contained in the image; for another example, if the target page contains text, the basic content of the text may include, but is not limited to, the characters that make up the text, the font used by the characters, the color of the characters, etc.

[0117] The operation information may include at least one of the following: information of the operator, the object being operated, the type of the object being operated, information of the operation item, feedback presented when the operation item is selected, and changes to the target page caused by the operation information. That is, the embodiment of the present application supports converting the operation information in the target page into operation audio for playback output in screen reading mode. For example, if the user selects an operation item (such as an option) in the target page, the feedback presented when the operation item is selected can be played, such as the operation item being highlighted; the changes to the target page caused by the operation item being selected can also be played, such as after the operation item is selected, the content associated with the operation item is displayed in the target page; and so on. For another example, assuming that the target application is a document application with multi-person collaborative editing of documents, when any collaborator participating in the collaborative editing edits the target page, the visually impaired person can immediately play the operation information related to any collaborator, such as information of any collaborator (i.e., operator), the object being operated, the type of the object being operated, information of the operation item, feedback presented when the operation item is selected, and changes to the target page caused by the operation information. This can help the visually impaired understand the operation information of their collaborators in real time, and enable the visually impaired to participate in normal work and life communication.

[0118] To sum up, the embodiment of the present application can play the basic content of each content in the target page, as well as all user operations (such as selection, addition, deletion, modification, etc.) and system feedback (such as changes in the target page based on user operations, etc.) in the target page. Through this instant playback of changes in the target page, the visually impaired can instantly perceive the interaction between themselves and the target application, thereby improving the sense of security of the visually impaired when using the target application.

[0119] (2) Figure 5b As shown, audio is used to prompt the content format of each content in the target page.

[0120] It is understandable that the format of the content on the target page may have an impact on user perception; see Figure 3 As shown, the content format of the first line of text is text. If only the basic content of the text is played during voice broadcast, the format information of the text will be lost, which will affect the visually impaired person's cognition and understanding of the text; therefore, the embodiment of the present application supports broadcasting the format of the text together with the voice broadcast of the text. For example, a shape with a text label can be read as "square", "circle", etc.; for another example, a link with a text label can be read as "link". Among them, an optional principle of the content format of the played content may include: for the text in the target page, the format of the text is broadcast during broadcast; for the non-text content in the target page, it is "textualized" as much as possible to facilitate the visually impaired person to understand the non-text content.

[0121] (3) Figure 5c As shown, audio is used to prompt the structure and location of each content in the target page.

[0122] The structure and position of the content in the target page are "graphical" concepts, such as where the function menu is in the target page, whether the function menu is a list or a grid, etc., all of which require visual perception. If the output audio loses the structure and position of the content, it may cause the visually impaired person to be unable to understand the content in the target page more accurately. Based on this, the embodiment of the present application supports reading out the current state of the target page, which is to enter or leave a certain area (or content, function area, etc.), and also supports reading out the position of the current cursor (such as the mouse cursor) in the target page, so as to help the visually impaired person locate their position in the target page in real time, help the visually impaired person understand the target page, and avoid getting lost in the target page. For example, when a visually impaired person enters the toolbar through a shortcut key, it is necessary to read out "Enter Toolbar"; when entering a specific menu from the toolbar, it is necessary to read out "Enter Menu"; after entering the menu, it is also necessary to read out which item position the current cursor is located in the menu, etc.

[0123] In an embodiment of the present application, if the displayed target page contains an image, the semantic description information of the image can be obtained, and then the prompt audio that matches the semantic description information of the image can be played. The semantic description information of the image can semantically describe the content expressed by the image, and the semantic description information is also converted into a matching prompt audio for broadcast, thereby achieving effective screen reading of the image (i.e., non-text content) in the target page and improving the integrity of the page information reading. In addition, the prompt audio that matches the semantic description information of the image played at the time of voice broadcast can more accurately and completely express the content expressed by the image, thereby assisting visually impaired people to understand the semantics of the image, and can provide richer page information in the process of reading the target page, thereby improving the intelligence of the page reading process.

[0124] Figure 6 A flow chart of a page processing method provided by an exemplary embodiment of the present application is shown; the page processing method may be executed by a computer device (such as the computer device 101 mentioned above), and the page processing method may include but is not limited to steps S601-S606:

[0125] S601: Display the target page.

[0126] Depending on the page type of the target page, the method of obtaining the semantic description information of the image is different. In one implementation, the target page is a first page, and the first page is a page that does not support users to edit the content in the page. The first page may include any of the following: a web page, a service page of an application, a service page of a mini-program, and a multimedia playback page; when the target page is the first page, the image contained in the target page is a native image in the first page (such as an image not added by the user) and does not support editing, then the implementation method of obtaining the semantic description information of the image may include: obtaining the semantic description information of the image during the process of loading the first page. In other words, when the target page is the first page, the operation of obtaining the semantic description information of the image is triggered during the process of loading (or rendering) the first page in the background. For example, the target page is any web page displayed in a browser, and the web page only supports users to browse the content contained in the web page. Then, during the process of loading the web page in the background, the semantic description information of the image in the web page can be triggered.

[0127] In other implementations, the target page is a second page that supports user editing of content within the page. The second page may include any of the following: a document editing page, an online document editing page, a social conversation page, a questionnaire page, etc. When the target page is the second page, and an image within the target page is added to the second page through an editing operation, the implementation method for obtaining the semantic description information of the image may include obtaining the semantic description information of the image when the image is added to the second page. Of course, if the second page also includes a native image, the semantic description information of the native image is obtained during the loading of the second page.

[0128] As mentioned above Figure 2As described in the illustrated embodiment, the semantic description information of the acquired image may include at least one of the following: description information of the target color presented by the image, description information of the text content contained in the image, description information of the source of the image, description information of the author of the image, description information of the objects contained in the image, and description information of the behavior performed by the objects contained in the image. Since the semantic description information includes the recognition of the color of the image and related information such as the objects contained therein; it is not difficult to find that the embodiment of the present application involves computer vision technology (Computer Vision, CV) in the field of artificial intelligence. Computer vision technology is a science that studies how to make machines "see". More specifically, it refers to machine vision that uses cameras and computers to replace human eyes to identify, track and measure targets, and further performs graphic processing so that the computer processing becomes an image that is more suitable for human eye observation or transmission to instruments for detection. As a scientific discipline, computer vision studies related theories and technologies, and attempts to establish an artificial intelligence system that can obtain information from images or multidimensional data. Computer vision technology generally includes image processing, image recognition, image semantic understanding, image retrieval, optical character recognition (OCR), video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, and simultaneous localization and mapping. Specifically, the method for obtaining semantic description information of an image based on computer vision technology can be found in the description of the specific implementation method shown in steps S602-S605 below. The present embodiment does not limit the order in which steps S602-S605 are executed, but this description is provided here.

[0129] S602: If the target page includes an image, obtain description information of the target color presented by the image.

[0130] The target color may refer to the color with the largest display area in the image, or the target color may refer to the color of the object contained in the image, or the target color may refer to the background color of the image, and so on; the target color may be specifically defined according to business needs, and the embodiments of the present application do not limit this. The embodiment of the present application can determine the target color of the image based on the HSL color model. The HSL color model is a color representation method that represents points in the RGB (red, green, and blue) color model in a cylindrical coordinate system; wherein, H represents hue (i.e., color), and the value range of H is [0,360]. When H=0 or 360, the hue (i.e., color) is red, when H=120, the hue is green, and when H=240, the hue is blue; S represents saturation, and the value range of S is [0%, 100%]. When S=0%, the saturation is gray, and when S=100%, the saturation is transparent; L represents lightness, and the value range of L is [0%, 100%]. When L=0%, the lightness is dark, when L=50%, the lightness is normal, and when L=100%, the lightness is white. A schematic diagram of using a cylindrical coordinate system to represent color can be found in Figure 7 .

[0131] The embodiment of the present application takes the target color as the color with the largest display area in the image as an example to illustrate the descriptive information of the target color presented by the image; specifically, first, S colors are identified from the image, where S is an integer greater than 1. These S colors can be the colors corresponding to different objects in the image (such as a person, a hat, a sofa, etc.). Of course, the same object can correspond to different colors. For example, if the object is a person, the top worn by the person can be red, and the pants worn by the person can be black; the number of pixels and saturation of each color in the S colors are obtained, and then the number of pixels of each color is multiplied by the saturation to obtain the color score of each color; finally, the color corresponding to the maximum color score in the S colors is determined as the target color of the image, and descriptive information for describing the target color is generated. That is, the saturation and number of pixels of each color contained in the image are used to evaluate the color score of a color, and the color corresponding to the highest color score is determined as the target color of the image; wherein, the formula for calculating the color score of each color is as follows:

[0132] score = pixel nums * saturation

[0133] score represents the color score, pixel nums represents the number of pixels, and saturation represents the saturation.

[0134] For example, an image contains three colors, namely red, yellow and blue; among them, the number of red pixels is 40 and the saturation is 40%, the number of yellow pixels is 70 and the saturation is 64%, and the number of blue pixels is 80 and the saturation is 49%; then the color scores of the three colors are calculated respectively, and the results are: red color score = 40*40% = 16, yellow color score = 70*64% = 44.8 and blue color score = 80*49% = 39.2. It is determined that yellow has the highest color score, so yellow is determined as the target color of the image.

[0135] It is understandable that the embodiment of the present application also supports sorting the S color scores corresponding to the S colors contained in the image in descending order, and determining multiple colors whose sorting positions are before the position threshold as target colors; when playing audio that matches the color, the color and the object corresponding to the color can be played together. Figure 8 , the objects contained in the image include: a little boy 801, a skateboard 802, and a hat 803. Hat 803 is black, and skateboard 802 is white. The audio that matches the image may be "a boy wearing a black hat and riding a white skateboard." It should be noted that the location threshold can be set by business personnel based on business needs, and this embodiment of the application does not limit the specific value of the location threshold.

[0136] S603: Obtain description information of the text content contained in the image.

[0137] Figure 9 FIG. 1 shows a flow chart of obtaining text content contained in an image provided by an exemplary embodiment of the present application; FIG. Figure 9 As shown, the process of obtaining the text content contained in the image may include:

[0138] ①Preprocess the image.

[0139] Image preprocessing can reduce useless information in the image, facilitating subsequent feature extraction and learning. Preprocessing can include, but is not limited to, grayscaling, noise reduction, binarization, character segmentation, and normalization. Grayscaling an image (e.g., a color image) can reduce the amount of raw image data, reducing subsequent processing time and computational complexity. Noise reduction can eliminate or suppress noise, improving image quality. The effectiveness of noise reduction significantly impacts subsequent feature extraction. Binarization involves setting the grayscale value of each pixel in the image to 0 or 255, resulting in a distinct black and white image. Character segmentation involves segmenting the text in an image into individual characters, allowing for subsequent character recognition. Of course, if the text in the image is tilted, it is often necessary to correct the tilt to facilitate subsequent processing. Normalization involves regularizing individual characters in an image to a consistent size and pattern, facilitating subsequent processing using the same algorithm. In other embodiments, the text in the image may be segmented into words so that the text can be recognized word by word later.

[0140] ② Perform image feature extraction on the preprocessed image to obtain image features.

[0141] Image features are key information used to identify the text content in an image. Each different text in an image can be distinguished from other text through image features. The embodiment of the present application supports the use of multiple feature extraction algorithms to extract features from images in the target page. Feature extraction algorithms may include but are not limited to: histogram of oriented gradient (HOG), scale-invariant features transform (SIFT), and difference of Gaussians (difference of gaussians) and other algorithms; the embodiment of the present application does not limit the specific feature extraction algorithm used to extract the image features of the image. Of course, if the dimension of the extracted image features is too high, it will affect the subsequent recognition efficiency and quality of the image features. Therefore, the embodiment of the present application also supports dimensionality reduction processing of image features with higher dimensions to facilitate subsequent recognition.

[0142] ③ Use a classifier to classify image features to identify the text content contained in the image.

[0143] A classifier is a general term for methods of classifying data. A classifier can be used to receive image features and classify them to identify the text content that the image features represent. Common classifiers include, but are not limited to, decision trees, logistic regression, naive Bayesian, and neural network algorithms. The present application does not limit the specific classifier used.

[0144] ④ Generate description information for describing the text content contained in the image.

[0145] S604: Obtain description information of the image source and description information of the image author.

[0146] This embodiment of the application takes the case where an image originates from a local space or a network file as an example to introduce the implementation method of obtaining the description information of the image source and the description information of the image author. Figure 10 , Figure 10 FIG. 1 shows a flow chart of an exemplary embodiment of the present application for obtaining description information of the source of an image and description information of the author of the image; FIG. Figure 10 As shown: First, the source of the image is obtained, which indicates that the image comes from a local space or a network file. Secondly, if the source of the image indicates that the image comes from a local space, the author of the image is read from the local space, for example, the image information is read from the file properties in the operating system of the smart device, and the image information includes the author of the image; if the source of the image indicates that the image comes from a network file, the link of the image is obtained, and the author of the image is read based on the link; wherein the link of the image can be a hyperlink, which supports jumping directly to the web page containing the image after being clicked. Finally, a description of the source of the image and a description of the author of the image are generated.

[0147] S605: Obtain description information of the object contained in the image and description information of the behavior performed on the object contained in the image.

[0148] In a specific implementation, a visual vocabulary model can be called to perform object recognition processing on an image, and identify the objects contained in the image and the behavioral sentences associated with the objects; then generate description information of the objects contained in the image, and, based on the objects and the behavioral sentences associated with the objects, generate description information of the behaviors performed on the objects contained in the image. Among them, the visual vocabulary model can include a transformer model (or machine translation model) based on an attention mechanism; for a given image and candidate objects (i.e., pre-set identifiable objects), the visual vocabulary model can use autoregression (i.e., a form of regression analysis) to generate a series of characters, and then generate a sentence (i.e., a character string) describing the image based on the behavioral sentence. The following is combined with Figure 11a and Figure 11bLet's give a more detailed introduction to the training and application of the visual vocabulary model:

[0149] The embodiment of the present application adopts a visual vocabulary pre-training method to train the visual vocabulary model; wherein, the process of training the visual vocabulary model may include a pre-training stage and a fine-tuning stage. Specifically, the visual vocabulary pre-training method supports multimodal pre-training of images and texts even in the absence of text annotations (such as text that annotates the semantics of the sample image to be expressed). The so-called multimodality may refer to different forms of expression of an object, such as using images, text, and animations to represent the same object. This makes the training of the visual vocabulary model no longer dependent on paired image and text annotations, but can utilize a large number of computer vision data sets, such as category labels (tags) for image recognition; with the help of the visual vocabulary pre-training method, the visual vocabulary model can establish the connection between the visual appearance and semantic names of multiple objects (or objects) through large-scale data learning, that is, a visual vocabulary. The visual vocabulary can be defined as a joint feature space (joint embedding space) of images and texts, in which semantically similar texts (or characters) can be mapped to feature vectors that are closer. The pre-training stage and the fine-tuning stage are introduced below, wherein:

[0150] ① Pre-training stage. In the pre-training stage, semantically similar category labels (or texts) and corresponding image features can be mapped to feature vectors with closer distances; for example Figure 11a As shown, assuming that the semantics of image 1 describes a yellow dog, and the semantics of image 2 describes a black dog, since the semantics of image 1 and image 2 both represent the same category - dog, the image features of image 1 and the corresponding category label (yellow dog), as well as the image features of image 2 and the corresponding category label (black dog) can be mapped to the feature vector in the upper left corner of the visual vocabulary; assuming that the semantics of image 3 describes a musical instrument, and the semantics of image 4 describes an accordion, the image features of image 3 and the corresponding category label (musical instrument), as well as the image features of image 4 and the corresponding category label (accordion) can be mapped to the feature vector in the lower left corner of the visual vocabulary, and so on; then, a visual vocabulary is established in the pre-training stage, and the category labels and corresponding image features with similar semantics in the visual vocabulary will be mapped to feature vectors with closer distances. More specifically, as Figure 11b As shown in the figure, a multi-layer visual vocabulary model can be used to predict the classification of images in the pre-training stage. Specifically, a plurality of sample images and the category labels corresponding to each sample image are given first, and then some category labels are randomly erased. The visual vocabulary model is then used to predict these erased category labels, thereby training the visual vocabulary model to predict the objects contained in the image. Figure 11bAs shown, the category label "slide" can be erased and the visual vocabulary model can be used to predict the category label. Of course, since the order of multiple category labels is interchangeable, the embodiment of the present application can use the Hungarian matching algorithm to find the one-to-one correspondence between the predicted category results and the category labels, and then calculate the cross entropy loss function to evaluate whether the visual vocabulary model is successfully optimized. Among them, the Hungarian algorithm is a combinatorial optimization algorithm, which can match the predicted category results with the category labels.

[0151] ② Fine-tuning stage. After the visual vocabulary is generated in the pre-training stage, the embodiment of the present application also supports fine-tuning the visual vocabulary model using sample images paired with text annotations, so that the visual vocabulary model can have the function of generating a universal behavior sentence template based on the sample images and the identified objects. In this way, the description information describing the behavior of the object in the image can be obtained by filling the identified objects into the behavior sentence template. It should be noted that during fine-tuning, the category label corresponding to the sample image can be an annotation from the sample data set (i.e., a collection of multiple sample images paired with text annotations) itself, or it can be automatically generated by other trained image classification or object recognition models. The embodiment of the present application does not limit this. Figure 11a As shown in the figure, during the fine-tuning phase, a sample image is labeled "a boy wearing a hat and skateboarding." This text label includes the objects "hat," "skateboard," and "boy." If the visual vocabulary model is used to identify the sample image and the predicted text content is "a boy wearing a hat," then the visual vocabulary model is determined to have failed to predict the object "skateboard," and further training is required. Otherwise, an optimized visual vocabulary model is determined. In summary, fine-tuning the visual vocabulary model can train the visual vocabulary model to generate sentences that describe the semantics of an image.

[0152] In summary, pre-training and fine-tuning the visual vocabulary model enables the trained visual vocabulary model to more accurately identify information such as the objects contained in the image and the behaviors performed by the objects, which can improve the recognition performance and efficiency of the visual vocabulary model.

[0153] S606: Play prompt audio that matches the semantic description information of the image.

[0154] In a specific implementation, after obtaining the semantic description information of the image, a hidden document object node can be created for the target page. The document object node is an application programming interface (API) that is independent of the platform and language. The document object node can dynamically access programs and scripts, update its content, structure and style of the www document, and set auxiliary attributes (such as the aria-live attribute) for the hidden document object node; the semantic description information of the image is processed into template text in a templated form; the template text is written into the hidden document object node; when a write operation is detected, a prompt audio is matched for the written template text; and the prompt audio is played.

[0155] It should be noted that the target page can be rendered using a canvas method, and the above-mentioned image can be rendered using a canvas method. Among them, the canvas tag is a tag in hypertext, and graphics can be dynamically drawn by scripts (such as JavaScript). When the target page is rendered by a canvas tag, the implementation method of playing the prompt audio that matches the semantic description information of the image shown in step S606 may include: creating a hidden document object node for the target page, and setting auxiliary attributes for the hidden document object node; writing the content in the canvas node to the hidden document object node; and when a write operation is detected, matching content audio for the written content, and playing the content audio. In other words, when the target page is rendered using a canvas tag, the embodiment of the present application supports identifying the content rendered by the canvas tag, and playing the content audio corresponding to the content.

[0156] The following combination Figure 12 Taking the operation event (such as the all-select event) on the canvas node as an example, the implementation method of playing the content audio that matches the content contained in the canvas node is introduced exemplarily. Figure 12 As shown, ① monitor the user's operation events on the canvas node, such as the user selects all the content on the canvas node through the keyboard (such as a physical keyboard), such as selecting all the content on the canvas node through the select all shortcut key (ctrl+A). ② Get the feedback result of the canvas node on the operation event; such as the monitoring component (accessibility component) monitors the operation event on the canvas node, and the monitoring component sends the operation event to the user operation category, so as to obtain the feedback result after judging the user operation. ③ Send the feedback result to the hidden document object node, so that the hidden document object node will change the feedback result to the node content. ④ When the node content of the document object node is monitored to change, the operation audio is matched with the written operation event and the feedback result, and the operation audio is played.

[0157] In an embodiment of the present application, for the displayed target page, if the target page contains an image, the semantic description information of the image can be obtained, and then the prompt audio that matches the semantic description information of the image can be played; wherein, the semantic description information can describe the content expressed by the image from a semantic point of view, and the semantic description information is then converted into a matching prompt audio for broadcast. In addition, if the target page is rendered in a canvas manner, the embodiment of the present application can also identify the content contained in the canvas node and play the content audio that matches the content contained in the canvas node. This achieves effective screen reading of the image or canvas node (non-text content) in the target page, and improves the integrity of the page information reading; and, by playing the prompt audio, the content expressed by the image or canvas node can be expressed more accurately and completely, thereby assisting in understanding the semantics of the image or canvas node, so that more abundant page information can be provided in the process of screen reading the target page, thereby improving the intelligence of the page screen reading processing.

[0158] The above describes in detail the method of the embodiment of the present application. In order to facilitate better implementation of the above scheme of the embodiment of the present application, the device of the embodiment of the present application is provided below accordingly.

[0159] Figure 13 A schematic diagram of the structure of a page processing device provided by an exemplary embodiment of the present application is shown; the page processing device can be used as a computer program (including program code) running on a computer device, for example, the page processing device can be an application program (such as Tencent Documents) in the computer device; the page processing device can be used to execute Figure 2 as well as Figure 6 Some or all of the steps in the method embodiment shown. Figure 13 , the page processing device includes the following units:

[0160] Display unit 1301, used to display the target page;

[0161] The processing unit 1302 is configured to obtain semantic description information of the image if the target page contains an image;

[0162] The processing unit 1302 is further configured to play prompt audio that matches the semantic description information of the image.

[0163] In one implementation, the semantic description information of the image is used to describe the image semantically;

[0164] The semantic description information includes at least one of the following: description information of a target color presented by the image, description information of textual content contained in the image, description information of the source of the image, description information of the author of the image, description information of objects contained in the image, and description information of actions performed by objects contained in the image;

[0165] The prompt audio is used to prompt at least one of the following: used to prompt the target color presented by the image, used to prompt the text content contained in the image, used to prompt the source of the image, used to prompt the author of the image, used to prompt the object contained in the image, and used to prompt the behavior performed by the object contained in the image.

[0166] In one implementation, the processing unit 1302 is further configured to start a screen reading mode;

[0167] The processing unit 1302 is configured to play the prompt audio that matches the semantic description information of the image, specifically to play the prompt audio that matches the semantic description information of the image in the screen reading mode.

[0168] In one implementation, the target page further includes other content, and the other content includes at least one of the following: text, rich text, and an icon; the processing unit 1302 is further configured to:

[0169] In screen reading mode, the audio that matches each content will be read aloud in the order in which the content is arranged on the target page.

[0170] In one implementation, the target page further includes operation information, which includes at least one of the following: operator information, an operated object, the type of the operated object, information about the operation item, feedback presented when the operation item is selected, and changes to the target page caused by the operation information. The processing unit 1302 is further configured to:

[0171] In screen reading mode, the operation information on the target page is converted into operation audio for playback output.

[0172] In one implementation, the target page refers to any service page in the target application; the target application supports the screen reader mode and provides an entry to the screen reader mode; the processing unit 1302 is configured to activate the screen reader mode by:

[0173] When the screen reading mode entry is triggered, the screen reading mode is started;

[0174] The entry to the screen reading mode includes any of the following: a button, an icon, a menu item, or a voice command.

[0175] In one implementation, if the target page is the first page, and the image is a native image in the first page and does not support editing, the processing unit 1302, when configured to obtain semantic description information of the image, is specifically configured to:

[0176] During the process of loading the first page, obtaining semantic description information of the image;

[0177] The first page includes any one of the following: a web page, a service page of an application, a page of a mini-program, or a multimedia playback page.

[0178] In one implementation, if the target page is the second page and the image is added to the second page through an editing operation, the processing unit 1302 is configured to obtain the semantic description information of the image by:

[0179] When adding an image to the second page, obtain the semantic description information of the image;

[0180] The second page includes any one of the following: a document editing page, an online document editing page, and a social conversation page.

[0181] In one implementation, the semantic description information includes description information of a target color presented by the image; and the processing unit 1302, when configured to obtain the semantic description information of the image, is specifically configured to:

[0182] Identify S colors from the image, where S is an integer greater than 1;

[0183] Get the number of pixels and saturation of each color in S colors;

[0184] Multiply the number of pixels of each color by the saturation to get the color score of each color;

[0185] The color corresponding to the maximum color score among the S colors is determined as the target color of the image;

[0186] Generates description information for describing the target color.

[0187] In one implementation, the semantic description information includes description information of text content contained in the image; the processing unit 1302, when configured to obtain the semantic description information of the image, is specifically configured to:

[0188] Preprocess the image;

[0189] Perform image feature extraction on the preprocessed image to obtain image features;

[0190] Use a classifier to classify image features to identify the text content contained in the image;

[0191] Generates description information for describing the text content contained in the image.

[0192] In one implementation, the semantic description information includes description information of the source of the image and description information of the author of the image. When the processing unit 1302 is configured to obtain the semantic description information of the image, it is specifically configured to:

[0193] Get the source of the image;

[0194] If the image's origin indicates that the image is from the local space, the image's author is read from the local space;

[0195] If the source of the image indicates that the image comes from a network file, then obtain the link of the image and read the author of the image according to the link;

[0196] Generates a description of the image's origin and the image's author.

[0197] In one implementation, the semantic description information includes description information of objects contained in the image and description information of actions performed by the objects contained in the image. When the processing unit 1302 is configured to obtain the semantic description information of the image, it is specifically configured to:

[0198] Call the visual vocabulary model to perform object recognition processing on the image, identify the objects contained in the image and the behavioral sentences associated with the objects;

[0199] Descriptive information of an object contained in the image is generated, and descriptive information of an action performed by the object contained in the image is generated based on the object and an action sentence associated with the object.

[0200] In one implementation, the processing unit 1302, when configured to play the prompt audio that matches the semantic description information of the image, is specifically configured to:

[0201] Create a hidden document object node for the target page and set auxiliary properties for the hidden document object node;

[0202] Process the semantic description information of the image into template text in a templated form;

[0203] Write the template text into the hidden document object node;

[0204] When a write operation is detected, the prompt audio is matched to the written template text; and

[0205] Play the prompt audio.

[0206] In one implementation, the target page is rendered in a Canvas manner; the processing unit 1302 is further configured to:

[0207] Create a hidden document object node for the target page and set auxiliary properties for the hidden document object node;

[0208] Write the contents of the Canvas node into the hidden document object node;

[0209] When a write operation is detected, content audio is matched to the written content; and the content audio is played.

[0210] In one implementation, the processing unit 1302 is further configured to:

[0211] Monitor the operation events and feedback results of the operation events on the Canvas node;

[0212] Write the operation events and feedback results into the hidden document object node;

[0213] When a write operation is detected, an operation audio is matched with the written operation event and the feedback result; and the operation audio is played.

[0214] According to one embodiment of the present application, Figure 13 The various units in the page processing device shown can be individually or completely combined into one or several other units to form a whole, or one (or some) of the units can be further divided into multiple functionally smaller units to form a whole, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In actual applications, the function of one unit can also be realized by multiple units, or the functions of multiple units can be realized by one unit. In other embodiments of the present application, the page processing device may also include other units. In actual applications, these functions can also be implemented with the assistance of other units and can be implemented by the collaboration of multiple units. According to another embodiment of the present application, the following can be executed by running on a general-purpose computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), a random access storage medium (RAM), and a read-only storage medium (ROM). Figure 2 and Figure 6 A computer program (including program code) for each step of the corresponding method shown in FIG. Figure 13 The page processing device shown in and the page processing method of the embodiment of the present application are implemented. The computer program can be recorded on a computer readable recording medium, for example, and loaded into the above-mentioned computing device through the computer readable recording medium and run therein.

[0215] In an embodiment of the present application, for the displayed target page, if the target page contains an image, the processing unit 1302 can obtain the semantic description information of the image, and then play the prompt audio that matches the semantic description information of the image. In the above scheme, the semantic description information can describe the content expressed by the image from a semantic point of view, and the semantic description information is then converted into a matching prompt audio for broadcast, which realizes the effective screen reading of the image (non-text content) in the target page and improves the integrity of the page information reading; in addition, by playing the prompt audio, the content expressed by the image can be expressed more accurately and completely, thereby assisting in understanding the semantics of the image, so that more abundant page information can be provided in the process of reading the target page, thereby improving the intelligence of the page reading processing.

[0216] Figure 14 FIG2 shows a schematic diagram of a computer device provided by an exemplary embodiment of the present application. Figure 14 , the computer device includes a processor 1401, a communication interface 1402 and a computer-readable storage medium 1403. The processor 1401, the communication interface 1402 and the computer-readable storage medium 1403 can be connected via a bus or other means. The communication interface 1402 is used to receive and send data. The computer-readable storage medium 1403 can be stored in the memory of the computer device. The computer-readable storage medium 1403 is used to store computer programs. The computer programs include program instructions. The processor 1401 is used to execute the program instructions stored in the computer-readable storage medium 1403. The processor 1401 (or CPU (Central Processing Unit)) is the computing core and control core of the computer device, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function.

[0217] The embodiment of the present application also provides a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space that stores the processing system of the computer device. In addition, one or more instructions suitable for being loaded and executed by the processor 1401 are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk storage; optionally, it can also be at least one computer-readable storage medium located away from the aforementioned processor.

[0218] In one embodiment, the computer device may be the smart device mentioned in the aforementioned embodiment; the computer-readable storage medium stores one or more instructions; the processor 1401 loads and executes the one or more instructions stored in the computer-readable storage medium to implement the corresponding steps in the aforementioned page processing method embodiment; in a specific implementation, the processor 1401 loads the one or more instructions in the computer-readable storage medium and executes the following steps:

[0219] Display the target page;

[0220] If the target page contains an image, obtain the semantic description information of the image;

[0221] Play audio prompts that match the semantic description of the image.

[0222] In one implementation, the semantic description information of the image is used to describe the image semantically;

[0223] The semantic description information includes at least one of the following: description information of a target color presented by the image, description information of textual content contained in the image, description information of the source of the image, description information of the author of the image, description information of objects contained in the image, and description information of actions performed by objects contained in the image;

[0224] The prompt audio is used to prompt at least one of the following: used to prompt the target color presented by the image, used to prompt the text content contained in the image, used to prompt the source of the image, used to prompt the author of the image, used to prompt the object contained in the image, and used to prompt the behavior performed by the object contained in the image.

[0225] In one implementation, the one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and further perform the following steps: initiating screen reader mode;

[0226] The one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when playing the prompt audio that matches the semantic description information of the image, specifically perform the following steps:

[0227] In screen reader mode, play prompt audio that matches the semantic description of the image.

[0228] In one implementation, the target page further includes other content, the other content including at least one of the following: text, rich text, and an icon; the processor 1401 loads one or more instructions in the computer-readable storage medium and further performs the following steps:

[0229] In screen reading mode, the audio that matches each content will be read aloud in the order in which the content is arranged on the target page.

[0230] In one implementation, the target page further includes operation information, where the operation information includes at least one of the following: information about the operator, the operated object, the type of the operated object, information about the operation item, feedback presented when the operation item is selected, and changes to the target page caused by the operation information. The processor 1401 loads one or more instructions in the computer-readable storage medium and further executes the following steps:

[0231] In screen reading mode, the operation information on the target page is converted into operation audio for playback output.

[0232] In one implementation, the target page refers to any service page in the target application; the target application supports the screen reader mode and provides an entry to the screen reader mode; one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when executing to initiate the screen reader mode, specifically perform the following steps:

[0233] When the screen reading mode entry is triggered, the screen reading mode is started;

[0234] The entry to the screen reading mode includes any of the following: a button, an icon, a menu item, or a voice command.

[0235] In one implementation, if the target page is the first page, and the image is a native image in the first page and does not support editing, then one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when executing to obtain semantic description information of the image, specifically perform the following steps:

[0236] During the process of loading the first page, obtaining semantic description information of the image;

[0237] The first page includes any one of the following: a web page, a service page of an application, a page of a mini-program, or a multimedia playback page.

[0238] In one implementation, if the target page is the second page and the image is added to the second page through an editing operation, one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when executing to obtain semantic description information of the image, specifically perform the following steps:

[0239] When adding an image to the second page, obtain the semantic description information of the image;

[0240] The second page includes any one of the following: a document editing page, an online document editing page, and a social conversation page.

[0241] In one implementation, the semantic description information includes description information of a target color presented in an image; one or more instructions in a computer-readable storage medium are loaded by the processor 1401 and, when executing to obtain the semantic description information of the image, specifically perform the following steps:

[0242] Identify S colors from the image, where S is an integer greater than 1;

[0243] Get the number of pixels and saturation of each color in S colors;

[0244] Multiply the number of pixels of each color by the saturation to get the color score of each color;

[0245] The color corresponding to the maximum color score among the S colors is determined as the target color of the image;

[0246] Generates description information for describing the target color.

[0247] In one implementation, the semantic description information includes description information of textual content contained in the image; one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when executing to obtain the semantic description information of the image, specifically perform the following steps:

[0248] Preprocess the image;

[0249] Perform image feature extraction on the preprocessed image to obtain image features;

[0250] Use a classifier to classify image features to identify the text content contained in the image;

[0251] Generates description information for describing the text content contained in the image.

[0252] In one implementation, the semantic description information includes description information of the source of the image and description information of the author of the image; one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when executing to obtain the semantic description information of the image, specifically perform the following steps:

[0253] Get the source of the image;

[0254] If the image's origin indicates that the image is from the local space, the image's author is read from the local space;

[0255] If the source of the image indicates that the image comes from a network file, then obtain the link of the image and read the author of the image according to the link;

[0256] Generates a description of the image's origin and the image's author.

[0257] In one implementation, the semantic description information includes description information of objects contained in the image and description information of actions performed by the objects contained in the image; one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when executing to obtain the semantic description information of the image, specifically perform the following steps:

[0258] Call the visual vocabulary model to perform object recognition processing on the image, identify the objects contained in the image and the behavioral sentences associated with the objects;

[0259] Descriptive information of an object contained in the image is generated, and descriptive information of an action performed by the object contained in the image is generated based on the object and an action sentence associated with the object.

[0260] In one implementation, one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and, when playing the prompt audio that matches the semantic description information of the image, specifically perform the following steps:

[0261] Create a hidden document object node for the target page and set auxiliary properties for the hidden document object node;

[0262] Process the semantic description information of the image into template text in a templated form;

[0263] Write the template text into the hidden document object node;

[0264] When a write operation is detected, the prompt audio is matched to the written template text; and

[0265] Play the prompt audio.

[0266] In one implementation, the target page is rendered using a Canvas method; one or more instructions in a computer-readable storage medium are loaded by the processor 1401 and the processor 1401 further executes the following steps:

[0267] Create a hidden document object node for the target page and set auxiliary properties for the hidden document object node;

[0268] Write the contents of the Canvas node into the hidden document object node;

[0269] When a write operation is detected, content audio is matched to the written content; and the content audio is played.

[0270] In one implementation, one or more instructions in the computer-readable storage medium are loaded by the processor 1401 and further perform the following steps:

[0271] Monitor the operation events and feedback results of the operation events on the Canvas node;

[0272] Write the operation events and feedback results into the hidden document object node;

[0273] When a write operation is detected, an operation audio is matched with the written operation event and the feedback result; and the operation audio is played.

[0274] In an embodiment of the present application, for the displayed target page, if the target page contains an image, the processor 1401 can obtain the semantic description information of the image, and then play the prompt audio that matches the semantic description information of the image. In the above scheme, the semantic description information can describe the content expressed by the image from a semantic point of view, and the semantic description information is then converted into a matching prompt audio for broadcast, which realizes the effective screen reading of the image (non-text content) in the target page and improves the integrity of the page information reading; in addition, by playing the prompt audio, the content expressed by the image can be expressed more accurately and completely, thereby assisting in understanding the semantics of the image, so that more abundant page information can be provided in the process of reading the target page, thereby improving the intelligence of the page reading processing.

[0275] The present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the above-described page processing method.

[0276] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0277] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0278] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A page processing method, characterized in that: include: Display the target page; The target page is the first page or the second page; If the target page includes an image, and the target page is the first page, and the image is a native image in the first page and does not support editing, then in the process of loading the first page, identifying semantic description information of the image; or, If the target page includes an image, and the target page is the second page, and the image is added to the second page through an editing operation, then when the image is added to the second page, identifying semantic description information of the image; Creating a hidden document object node for the target page, and setting auxiliary attributes for the hidden document object node; Processing the semantic description information of the image into a template text in a templated form, writing the template text into the hidden document object node, and matching a prompt audio for the written template text when a write operation is detected; and playing the prompt audio; When the page content, structure and style of the target page are updated, the document object node is dynamically refreshed according to the auxiliary attribute and plays the updated audio of the target page.

2. The method according to claim 1, characterized in that The semantic description information of the image is used to describe the image semantically; The semantic description information includes at least one of the following: description information of a target color presented by the image, description information of text content contained in the image, description information of a source of the image, description information of an author of the image, description information of an object contained in the image, and description information of an action performed by an object contained in the image; The prompt audio is used to prompt at least one of the following: used to prompt the target color presented by the image, used to prompt the text content contained in the image, used to prompt the source of the image, used to prompt the author of the image, used to prompt the object contained in the image, and used to prompt the behavior performed by the object contained in the image.

3. The method according to claim 1, characterized in that The method further includes: starting a screen reading mode; The playing of the prompt audio includes: in the screen reading mode, playing the prompt audio matching the semantic description information of the image.

4. The method according to claim 3, characterized in that The target page also includes other content, and the other content includes at least one of the following: text, rich text, and icon; the method further includes: In the screen reading mode, the audios matching the contents in the target page are read aloud in sequence according to the arrangement order of the contents in the target page.

5. The method according to claim 3, characterized in that The target page also includes operation information, which includes at least one of the following: information about the operator, the object being operated, the type of the object being operated, information about the operation item, feedback presented when the operation item is selected, and changes to the target page caused by the operation information; The method further comprises: In the screen reading mode, the operation information in the target page is converted into operation audio for playback output.

6. The method according to claim 3, characterized in that The target page refers to any service page in the target application; the target application supports the screen reading mode and provides an entry to the screen reading mode; The starting screen reading mode includes: When the entrance to the screen reading mode is triggered, starting the screen reading mode; The entry to the screen reading mode includes any of the following: a button, an icon, a menu item, or a voice command.

7. The method according to claim 1, characterized in that The first page includes any one of the following: a web page, a service page of an application, a page of a mini-program, or a multimedia playback page.

8. The method according to claim 1, characterized in that The second page includes any one of the following: a document editing page, an online document editing page, and a social conversation page.

9. The method according to claim 1 or 2, characterized in that: The semantic description information includes description information of a target color presented by the image; the semantic description information for identifying the image includes: Identify S colors from the image, where S is an integer greater than 1; Obtain the number of pixels and saturation of each color in the S colors; Multiply the number of pixels of each color by the saturation to obtain the color score of each color; Determine the color corresponding to the maximum color score among the S colors as the target color of the image; Generate description information for describing the target color.

10. The method according to claim 1 or 2, characterized in that: The semantic description information includes description information of text content contained in the image; the semantic description information for identifying the image includes: Preprocessing the image; Perform image feature extraction on the preprocessed image to obtain image features; Using a classifier to classify the image features to identify text content contained in the image; Generate description information for describing text content contained in the image.

11. The method according to claim 1 or 2, characterized in that: The semantic description information includes description information of the source of the image and description information of the author of the image; the semantic description information for identifying the image includes: Obtaining the source of the image; If the source of the image indicates that the image comes from a local space, reading the author of the image from the local space; If the source of the image indicates that the image comes from a network file, obtaining a link to the image, and reading the author of the image according to the link; Generate the description information of the source of the image and the description information of the author of the image.

12. The method according to claim 1 or 2, characterized in that: The semantic description information includes description information of objects contained in the image and description information of behaviors performed by the objects contained in the image; The identifying semantic description information of the image includes: Calling a visual vocabulary model to perform object recognition processing on the image, and identifying the object contained in the image and the behavior sentence pattern associated with the object; Generate description information of an object contained in the image, and generate description information of a behavior performed by the object contained in the image based on the object and a behavior sentence associated with the object.

13. The method according to claim 1, characterized in that The target page is rendered in Canvas mode; the method further includes: Write the content in the Canvas node into the hidden document object node; When a writing operation is monitored, matching content audio for the written content; and playing the content audio.

14. The method according to claim 13, characterized in that The method further comprises: Monitor the operation events on the Canvas node and the feedback results of the operation events; Writing the operation event and the feedback result into the hidden document object node; When a write operation is monitored, an operation audio is matched for the written operation event and the feedback result; and the operation audio is played.

15. A page processing device, characterized in that: include: A display unit, used for displaying a target page; The target page is the first page or the second page; A processing unit, for, if the target page contains an image and the target page is the first page, and the image is a native image in the first page and does not support editing, identifying the semantic description information of the image during the process of loading the first page; or, if the target page contains an image and the target page is the second page, and the image is added to the second page through an editing operation, identifying the semantic description information of the image when adding the image to the second page; creating a hidden document object node for the target page and setting auxiliary attributes for the hidden document object node; processing the semantic description information of the image into a template text in a templated form, writing the template text into the hidden document object node, and matching the written template text with a prompt audio when a write operation is detected; and playing the prompt audio; wherein, when the page content, structure and style of the target page are updated, the document object node is dynamically refreshed according to the auxiliary attributes and plays the updated audio of the target page.

16. A computer device, characterized in that: include: a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the page processing method according to any one of claims 1 to 14 is implemented.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the page processing method according to any one of claims 1 to 14.

18. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device implements the page processing method according to any one of claims 1 to 14.

Images