Method, system, device and medium for simplifying and complementing page information of mobile device

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to a method, a system and equipment for simplifying and complementing page information of mobile equipment and a storage medium, and the method comprises the following steps: 1) obtaining an original XML (Extensible Markup Language) of a page of the mobile equipment; 2) judging whether nodes outside a screen need to be reserved or not, if not, entering step 3), and if so, entering step 4); 3) deleting nodes outside the screen; 4) deleting redundant nodes; 5) judging whether the page is a special page, if so, entering 6), otherwise, entering 7); 6) performing information deletion or information supplement processing on the special page; 7) identifying all texts and the positions of the texts by using an optical character identification method, comparing the texts identified by the optical character identification method with the texts in the XML, removing repeated texts, and inserting the rest texts into the XML; and 8) simplifying attributes in the inserted XML. According to the method, the XML can be simplified, and post-complementation processing can be carried out aiming at missing of page information, so that the processing capability of a large language model is improved.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology and relates to a method, system, device and storage medium for simplifying and completing page information of a mobile device. Background Art

[0002] Large Language Models (LLMs) have shown great potential in understanding implicit intent and commonsense reasoning, which enables LLMs to be used as intelligent agents that can make decisions and perform actions based on the perceived state of the environment. For example, LLMs can interact with domain-specific software such as databases, games, and browsers to complete various tasks.

[0003] In recent years, new LLMs-based agents have begun to emerge, capable of interacting with general software systems (such as operating systems and their installed applications) to complete more complex and open-domain tasks. These tasks range from simple operations (such as setting reminders) to complex activities (such as financial management or interacting with loved ones). The inventors of the present invention explored an application scenario that is both interesting and challenging, designing an agent system that can control any smartphone application in a mobile operating system. Unlike existing smart assistants (such as Siri) that access and call functions through the system background, the agent takes a completely new approach and interacts with the application directly on the human-computer interface (GUI) through low-level operations such as clicking and sliding. This approach brings many advantages. First, it does not rely on system background access, so the agent can be widely used in various applications. In addition, since no deep system-level integration is required, this method also has significant advantages in improving security and protecting privacy. More importantly, by operating at the GUI level, the agent can adapt to changes and updates in the application interface, thereby ensuring its long-term adaptability and flexibility.

[0004] LLMs are used to predict interactive operations, thereby utilizing the powerful reading comprehension and reasoning capabilities of LLMs, and using the XML corresponding to the page as a carrier of page information to input into a large language model. The current mainstream LLMs generally have an effective input length between 8k tokens and 16k tokens. The performance of large language models will drop significantly after exceeding this length. However, the original XML obtained through the method provided by Google Andoird often requires tens of thousands of tokens after conversion into tokens, so the XML information needs to be simplified before input into a large language model. In addition, the XML of some pages does not fully display the text information on the page, or some page information is missing in the XML due to different models. Therefore, in order to input complete page information into the large language model, this information needs to be supplemented during the simplification process.

[0005] However, some existing XML simplification algorithms still retain a lot of original XML structure information and some descriptive representations, and the simplified XML obtained in many complex pages will still be much longer than 16k tokens. At the same time, they do not consider the situation where page information is missing in the XML.

[0006] Therefore, in view of the defects existing in the above-mentioned prior art, it is necessary to develop a method, system, device and storage medium for simplifying and completing page information of a mobile device. Summary of the invention

[0007] In order to overcome the defects of the prior art, the present invention proposes a method, system, device and storage medium for simplifying and completing page information of a mobile device, which can perform post-processing for missing page information while simplifying XML, thereby improving the performance of a large language model.

[0008] In order to achieve the above object, the present invention provides the following technical solutions:

[0009] A method for simplifying and completing page information of a mobile device, characterized by comprising the following steps:

[0010] 1) Get the original XML of the mobile device page;

[0011] 2) Determine whether it is necessary to retain the off-screen nodes in the original XML, if not, proceed to step 3), if yes, proceed to step 4);

[0012] 3) Delete the off-screen nodes in the original XML;

[0013] 4) Deleting redundant nodes in the original XML;

[0014] 5) Determine whether the mobile device page is a special page, if yes, proceed to step 6), if no, proceed to step 7);

[0015] 6) Delete or supplement information on special pages;

[0016] 7) using an optical character recognition method to identify all text and the location of the text in the mobile device page, comparing the text recognized by the optical character recognition method with the text in the XML, removing the text in the text recognized by the optical character recognition method that is repeated with the text in the XML, and inserting the remaining text into the XML;

[0017] 8) Simplify the attributes in the inserted XML.

[0018] Preferably, in step 2), for the need to summarize the information of the entire mobile device page, the off-screen nodes in the original XML need to be retained; for the need related to operation simulation, the off-screen nodes in the original XML do not need to be retained.

[0019] Preferably, in step 3), all nodes within the screen are determined based on whether the bounds attribute of the current node is included by its parent node, thereby facilitating the deletion of nodes outside the screen in the original XML.

[0020] Preferably, in step 4), whether a node is redundant is determined based on the attribute information of the node.

[0021] Preferably, in step 5), whether the mobile device page is a special page is determined based on the page content included in the XML.

[0022] Preferably, in step 6), for special pages of deleted information, first select a text node that is fixed in the current page as a marker node, and then find the top level of the node tree to be deleted based on the position of this node and delete it; for special pages of supplementary information, first select a text node that is fixed in the current page as a marker node, and then find the node to be supplemented with information based on the position of this node and supplement the information.

[0023] Preferably, in step 7), a MinHash-based algorithm and Levenshtein edit distance are used to compare whether the text recognized by the optical character recognition method and the text in the XML are duplicate texts.

[0024] In addition, the present invention also provides a mobile device page information simplification and completion system, which is characterized by comprising:

[0025] The acquisition module is used to obtain the original XML of the mobile device page;

[0026] An off-screen node retention judgment module, which is used to judge whether it is necessary to retain the off-screen nodes in the original XML;

[0027] An off-screen node deletion module, which is used to delete off-screen nodes in the original XML;

[0028] A redundant node deletion module, which is used to delete redundant nodes in the original XML;

[0029] A special page determination module, which is used to determine whether the mobile device page is a special page;

[0030] A special page processing module, which is used to delete information or supplement information on special pages;

[0031] An OCR processing module, which is used to use an optical character recognition method to recognize all texts and text locations in the mobile device page, compare the text recognized by the optical character recognition method with the text in the XML, remove the text in the text recognized by the optical character recognition method that is repeated with the text in the XML, and insert the remaining text into the XML;

[0032] The attribute simplification module is used to simplify the attributes in the inserted XML.

[0033] Moreover, the present invention also provides a mobile device page information simplification and completion device, which is characterized by comprising:

[0034] one or more processors;

[0035] A memory for storing one or more programs;

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement the mobile device page information simplification and completion method as described above.

[0037] Finally, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the steps of the mobile device page information simplification and completion method as described above are implemented.

[0038] Compared with the prior art, the method, system, device and storage medium for simplifying and completing page information of a mobile device of the present invention have one or more of the following beneficial technical effects:

[0039] 1. The present invention simplifies XML more thoroughly, and the simplified tokens are shorter, with an average token length of about 6k, while the average length of other methods is about 10k, and some complex pages with more content will exceed the effective length limit of 16k. Therefore, the present invention can make the reasoning efficiency of large language models higher, and more content, such as multiple pages, can be added to the input of large language models.

[0040] 2. The simplified XML obtained by the present invention contains more complete page information. By introducing OCR technology to supplement the text information on the page that is not included in the XML, a more complete page description is provided for the large language model.

[0041] 3. For some special pages (some pages' XMLs have some special problems that will cause troubles to large language models), the present invention designs separate processing logic for special pages, which can improve the processing capability of large language models. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of the method for simplifying and completing page information of a mobile device of the present invention.

[0043] Figure 2 It is a schematic diagram of the structure of the mobile device page information simplification and completion system of the present invention. DETAILED DESCRIPTION

[0044] Before describing in detail any embodiment of the present invention, it should be understood that the present invention is not limited in its application to the construction and arrangement details of the components described below or illustrated in the following figures. The present invention can have other embodiments and can be practiced or carried out in various ways. In addition, it should be understood that the words and terms used here are for descriptive purposes and should not be considered restrictive. The use of "including" or "having" and its variations herein is intended to cover the items and their equivalents and additional items displayed below. Unless otherwise specified or limited, the terms "install", "connect", "support" and "couple" and their variations are widely used and cover direct installation and indirect installation, connection, support and connection. In addition, "connect" and "couple" are not limited to physical or mechanical connections or connections.

[0045] Furthermore, on the first aspect, in the disclosure of the present invention, the orientation or positional relationship indicated by terms such as "longitudinal", "transverse", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" are based on the orientation or positional relationship shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore the above terms cannot be understood as limitations on the present invention; on the second aspect, the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" cannot be understood as a limitation on the quantity.

[0046] Before introducing the specific content of the present invention, some technical terms used in the present invention are briefly introduced to help those skilled in the art to better understand the present invention.

[0047] 1. XML: It usually represents page information in the Android mobile device scenario and is used to define the layout and elements of the user interface. In the present invention, it specifically refers to the XML obtained by the method provided by Google Android, which is usually displayed in a tree structure. Each node in the XML tree represents a page component or layout. Each node contains multiple attributes, indicating the function of the component or layout, such as "clickable = True" means that this component is clickable.

[0048] 2. Attributes of XML nodes: The attributes of each XML node represent the function of the component corresponding to this node. Among them, index represents the index of the node under its parent node; text and content-desc represent the text content of the node on the page; class represents the class name of the element; package represents the package name of the application to which this node belongs; checkable represents whether this element can be selected or checked; checked represents that if the element is selectable, it indicates whether the current element is in the selected state; clickable represents whether the element is clickable; enabled represents whether the element is enabled, which is generally True; focusable represents whether the element can get focus; focused represents whether the element is currently in the state of getting focus; scrollable represents whether the element is scrollable; long-clickable represents whether the element supports long-press operation; password represents whether the element is a password field; selected represents whether the element has been selected; bounds represents the position and size of the element on the screen.

[0049] 3. OCR: OCR (Optical Character Recognition) is a text recognition technology used to convert text in images into editable and searchable text.

[0050] 4. LLMs: Large Language Models (LLMs) are deep learning-based AI models that are specifically designed to understand and generate natural language. They learn the structure, meaning, and context of language by analyzing large amounts of text data, enabling them to perform a variety of language-related tasks such as translation, question answering, and text generation.

[0051] 5. Tokens: A token is a basic unit of text data, which can be a word, a character, or even a subword. When processing text, large language models (LLMs) usually do not directly process complete sentences or paragraphs, but break the text into multiple tokens, which makes it easier for large language models to understand and generate language.

[0052] 6. Levenshtein edit distance: Levenshtein edit distance is a measure of the difference between two strings. Specifically, it represents the minimum number of single-character editing operations required to convert one string into another. The allowed editing operations usually include inserting a character, deleting a character, or replacing a character.

[0053] 7. MinHash algorithm: MinHash is a hash algorithm used to quickly evaluate the similarity between two sets, and is particularly suitable for dealing with similarity problems in large-scale data sets. It is mainly used for approximate set similarity queries, such as text similarity detection, document deduplication, web page deduplication, and other tasks. The core idea of ​​MinHash is to estimate their Jaccard similarity by generating multiple hash values ​​for the set.

[0054] Figure 1 The flowchart of the method for simplifying and completing the mobile device page information of the present invention is shown. Figure 1 As shown, the mobile device page information simplification and completion method of the present invention includes the following steps:

[0055] 1. Get the original XML of the mobile device page.

[0056] The method of obtaining the original XML of the mobile device page is not the inventive point of the present invention, and it can be obtained by using existing technologies. For example, using the Accessibility Service provided in the Android development tool, it is relatively convenient to obtain Accessibility Node Info, and the original XML of the mobile device page can be obtained by parsing the Accessibility Node Info.

[0057] 2. Determine whether it is necessary to retain the off-screen nodes in the original XML. If not, proceed to step 3; if yes, proceed to step 4.

[0058] Since the original XML is used to define the layout and elements of the mobile device page, it contains all the components in a page, so the original XML contains a large number of nodes that only exist for structure and layout. These nodes do not contain actual useful page information, which is also the main reason why the original XML is too long. In addition, a page often contains more nodes than the part displayed on the screen, such as some swiping pages, so the original XML also contains many nodes outside the screen.

[0059] Whether to retain off-screen nodes is controlled by an entry parameter remain_nodes (retain nodes when remain_nodes=True), which can be selected by yourself. In the present invention, if the need is to summarize the entire page information, in order to save the number of operation steps (such as sliding the screen to see the complete text), the off-screen nodes can be retained, so that the text information of the entire page can be directly obtained without additional operations. If the need is related to operation simulation, such as simulating the need to click on elements or slide, you can choose to delete the off-screen nodes to prevent interference with large language models.

[0060] 3. Delete the off-screen nodes in the original XML.

[0061] In the original XML, the bounds attribute of all nodes on the screen must be within the range of [0,0][Window_Height,Window_Width] and must be included by its parent node. Therefore, you only need to determine whether the bounds of the current node is included by its parent node to determine all nodes within the screen range. If you need to delete nodes outside the screen, after determining all nodes within the screen range, delete other nodes that are not within the screen range.

[0062] 4. Delete the redundant nodes in the original XML.

[0063] The original XML also contains a large number of nodes that exist only for structural and layout needs. These nodes do not contain useful page information, so the present invention will delete these redundant nodes. The present invention will determine whether a node is redundant based on the attribute information of the node. If at least one of the attributes of a node such as "checkable", "checked", "clickable", "focusable", "scrollable", "long-clickable", "password" and "selected" is True, or the text and content-desc attributes are not empty, then the node is considered to be a functional node, and nodes that do not meet this requirement are redundant nodes. The present invention will delete all nodes that do not meet this requirement.

[0064] 5. Determine whether the mobile device page is a special page. If yes, proceed to step 6; if no, proceed to step 7.

[0065] Due to different ideas of APP developers during development or different models, some pages will get some original XML with different structures or even information, which will easily confuse large language models. At the same time, for components such as pop-up windows and drop-down boxes, it will cause overlapping between different components. However, in XML, these components are displayed in a tiled manner, which means that it is impossible to tell which component is on the top and which one is on the bottom only through the original XML (in actual operation, the components overlapping below will not be triggered by any operation), which is also easy to cause confusion to large language models. Therefore, the present invention designs processing logic separately for special pages. The present invention will determine whether it is a special page based on the fixed text content of each page, and then execute the processing logic of the special page.

[0066] In the present invention, whether it is a special page will be determined based on the page content contained in the XML. Specifically, the corresponding text information can be preset for all special pages in advance. For example, for pages containing drop-down boxes in various APPs, the preset text information can be selected according to the specific information contained in the drop-down box in the page. In this way, when the text or content-desc attributes of some nodes in the XML contain text information preset for special pages, the current page is considered to be a special page.

[0067] 6. Delete or supplement information on special pages;

[0068] Special pages can be divided into two categories: special pages for deleting information and special pages for supplementing information.

[0069] Deleting special pages of information is mainly aimed at the situation where multiple components overlap in some pages, where the components on the top can be operated, but the components on the bottom cannot be operated (covered by the components on the top). At this time, the nodes of the components on the bottom still exist in XML, which will confuse the large language model. For example, when the pop-up window and various pages containing drop-down boxes appear when selecting specifications for ordering takeaway APP, the components originally in this position will be covered, resulting in overlapping phenomena. When the present invention processes these special pages of information deletion, it will first select a text node that is fixed and unchanged on the current page as a marker node (information that is not changed by time or network changes), and then find the top-level position of the node tree to be deleted according to the position of this node and delete it (XML is displayed in a tree structure, so it is only necessary to delete the root node of the subtree where all nodes to be deleted are located).

[0070] The special page of supplementary information is mainly aimed at some pages, which may not exist in XML for some information (some attributes of a node are missing) or nodes corresponding to some operable components due to the implementation logic. For example, the button for liking a circle of friends in WeChat Moments does not have a specific node corresponding in XML, and a node needs to be added through special processing. Similar to the processing method in the special page of deleted information, for the special page of supplementary information, the present invention will also select a marker node, find the node that needs supplementary information according to its position, and supplement the information (supplement the missing attributes or add a new node under this node).

[0071] 7. Use an optical character recognition method to identify all text and the location of the text in the mobile device page, compare the text recognized by the optical character recognition method with the text in the XML, remove the text in the text recognized by the optical character recognition method that is repeated with the text in the XML, and insert the remaining text into the XML.

[0072] In many pages, the original XML does not contain all the text information in the page, but in many cases, this text information is critical for large language models to understand the page information. The present invention will introduce OCR (optical character recognition) technology to supplement the missing text information in XML. Specifically, OCR will first be used to identify all the text and the location (bounds) of the text in the mobile device page. Then compare the text recognized by OCR with the text contained in XML (text and content-desc), remove duplicate text and insert the remaining text into XML.

[0073] Specifically, we use a MinHash-based algorithm to compare text similarity and try to determine whether a given OCR text contains the same or most of the information as the text in the existing XML (sometimes due to the accuracy of OCR, the text recognized by OCR may not be completely consistent with the XML). We use technologies such as MinHash and Levenshtein edit distance to process text matching, and determine the coverage of matching under a certain threshold. First, we create a MinHashLSH object for locality sensitive hash (LSH) query, and generate MinHash for all XML descriptions and insert LSH, while removing punctuation and spaces and saving them in the dictionary. Then, we generate MinHash for each OCR text and perform LSH query. If the specific threshold is reached, it is considered a successful match (parameter of the MinHash algorithm). If the match fails, we further process it according to the length of the text: for texts with a length of 2 to 4 characters, we use Levenshtein edit distance to compare, and if the distance is less than or equal to 1, it is considered a match; for single-character text, we directly perform character matching. Finally, we get all non-duplicate texts. For these non-repeated texts, they will be inserted into the XML as a node according to their corresponding position information (bounds). According to the aforementioned fact that the bounds of a parent node must contain child nodes, the present invention will select the smallest bounds of all OCR-recognized texts as its parent node for insertion.

[0074] The following is an example. Suppose all XML descriptions correspond to a text list ["How!","document."], and the text list recognized by OCR is ["HoW!","丶document."]. First, remove all punctuation and special symbols to obtain the text list ["How","document"] for XML descriptions and the text list ["HoW","document"] for OCR recognition. Then, generate MinHash values for each element in the text list of XML descriptions and insert them into the LSH. After that, for each element in the text list recognized by OCR, generate MinHash values as well and match them with the elements in the LSH (the MinHash corresponding to the XML list). Finally, "document" can be successfully matched, indicating that "document." and "丶document." correspond to the same content. Therefore, this piece of text does not need to be added to the XML again. However, HoW and How do not match, so proceed to the next step of judgment. Since the Levenshtein edit distance between How and HoW is 1, it means they match, and it is also considered that the text recognized by OCR and the text in the XML are duplicates.

[0075] VIII. Simplify the attributes in the inserted XML.

[0076] The descriptions of each attribute in the original XML are too redundant and will occupy a large number of Tokens. Finally, the present invention will simplify the descriptions of these attributes. For functional attributes such as "checkable", "checked", "clickable", "focusable", "scrollable", "long-clickable", "password", and "selected", since in most cases, most of them are False, only the attributes with the value of True will be shown. The three attributes "index", "resource-id", and "package" are not helpful for large language models to understand the page and will be directly deleted. The "class" attribute also represents the main function of the node to a certain extent, so the last part will be retained (the "class" must be in the format of x.x.x.x, and the number of dots is variable. The present invention only retains the content after the last dot. For example, in android.widget.FrameLayout, only FrameLayout is retained). The two attributes "text" and "content-desc" represent the text information of the node, and they will be merged and shown separately.

[0077] The "bounds" attribute represents the position of the node on the page and is one of the most critical attributes, and it will also be shown separately.

[0078] Finally, for the following nodes:

[0079] <node index="0"text="Steamed sweat bath"resource-id=""class="android.view.View"

[0080] package="com.autonavi.minimap"content-desc=""checkable="false"checked="false"

[0081] clickable="false"enabled="true"focusable="false"focused="false"scrollable="false"

[0082] long-clickable="false"password="false"selected="false"bounds="[290,844][346,885]" / >

[0083] It will be simplified to:

[0084] [n42]View;;; Steamed sweat bath; [290, 844][346, 885]

[0085] The present invention obtains a more concise XML by deleting redundant nodes and nodes not within the screen through node deletion, and simplifying the attribute expressions of the nodes, rewriting the XML into a new format. At the same time, by performing special processing on the page and using OCR technology to delete or supplement information for specific pages, the processing ability of the large language model can be improved.

[0086] Figure 2 The schematic diagram of the composition of the mobile device page information simplification and supplementation system of the present invention is shown. As Figure 2 shown, the mobile device page information simplification and supplementation system of the present invention includes:

[0087] 1. An acquisition module, which is used to acquire the original XML of the mobile device page.

[0088] 2. An off-screen node retention judgment module, which is used to judge whether it is necessary to retain the off-screen nodes in the original XML.

[0089] 3. An off-screen node deletion module, which is used to delete the off-screen nodes in the original XML.

[0090] 4. A redundant node deletion module, which is used to delete the redundant nodes in the original XML.

[0091] 5. A special page determination module, which is used to determine whether the mobile device page is a special page.

[0092] 6. A special page processing module, which is used to delete information or supplement information on special pages.

[0093] 7. An OCR processing module, which is used to use an optical character recognition method to recognize all texts and text locations in the mobile device page, compare the text recognized by the optical character recognition method with the text in XML, remove the text in the text recognized by the optical character recognition method that is repeated with the text in XML, and insert the remaining text into XML.

[0094] 8. Attribute simplification module, which is used to simplify the attributes in the inserted XML.

[0095] In addition, the present invention also provides a mobile device page information simplification and completion device, which includes: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the mobile device page information simplification and completion method as described above.

[0096] Finally, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the steps of the mobile device page information simplification and completion method as described above are implemented.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Those skilled in the art can modify or replace the technical solution of the present invention according to the idea of ​​the present invention without departing from the essence and scope of the technical solution of the present invention.

Claims

1. A method for simplifying and completing page information of a mobile device, characterized in that: The following steps are involved: 1) Get the original XML of the mobile device page; 2) Determine whether it is necessary to retain the off-screen nodes in the original XML, if not, proceed to step 3), if yes, proceed to step 4); 3) Delete the off-screen nodes in the original XML; 4) Deleting redundant nodes in the original XML; 5) Determine whether the mobile device page is a special page, if yes, proceed to step 6), if no, proceed to step 7); 6) Delete or supplement information on special pages; 7) using an optical character recognition method to identify all text and the location of the text in the mobile device page, comparing the text recognized by the optical character recognition method with the text in the XML, removing the text in the text recognized by the optical character recognition method that is repeated with the text in the XML, and inserting the remaining text into the XML; 8) Simplify the attributes in the inserted XML.

2. The method for simplifying and completing mobile device page information according to claim 1, characterized in that: In the step 2), for the need to summarize the information of the entire mobile device page, the off-screen nodes in the original XML need to be retained; for the need related to operation simulation, the off-screen nodes in the original XML do not need to be retained.

3. The method for simplifying and completing mobile device page information according to claim 2, characterized in that: In the step 3), all nodes within the screen are determined based on whether the bounds attribute of the current node is included by its parent node, thereby facilitating the deletion of nodes outside the screen in the original XML.

4. The method for simplifying and completing mobile device page information according to claim 3, characterized in that: In the step 4), whether a node is redundant is determined based on the attribute information of the node.

5. The method for simplifying and completing page information of a mobile device according to claim 4, characterized in that: In the step 5), whether the mobile device page is a special page is determined based on the page content included in the XML.

6. The method for simplifying and completing mobile device page information according to claim 5, characterized in that: In the step 6), for special pages of deleted information, first select a text node that is fixed in the current page as a marker node, and then find the top level of the node tree to be deleted based on the position of this node and delete it; for special pages of supplementary information, first select a text node that is fixed in the current page as a marker node, and then find the node to be supplemented with information based on the position of this node and supplement the information.

7. The method for simplifying and completing mobile device page information according to claim 6, characterized in that: In the step 7), a MinHash-based algorithm and Levenshtein edit distance are used to compare whether the text recognized by the optical character recognition method and the text in the XML are duplicate texts.

8. A mobile device page information simplification and completion system, characterized in that: include: The acquisition module is used to obtain the original XML of the mobile device page; An off-screen node retention judgment module, which is used to judge whether it is necessary to retain the off-screen nodes in the original XML; An off-screen node deletion module, which is used to delete off-screen nodes in the original XML; A redundant node deletion module, which is used to delete redundant nodes in the original XML; A special page determination module, which is used to determine whether the mobile device page is a special page; A special page processing module, which is used to delete information or supplement information on special pages; An OCR processing module is used to use an optical character recognition method to recognize all texts and text locations in the mobile device page, compare the text recognized by the optical character recognition method with the text in the XML, remove the text in the text recognized by the optical character recognition method that is repeated with the text in the XML, and insert the remaining text into the XML; The attribute simplification module is used to simplify the attributes in the inserted XML.

9. A device for simplifying and completing page information on a mobile device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the mobile device page information simplification and completion method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the mobile device page information simplification and completion method as described in any one of claims 1 to 7 are implemented.

Images