A document intelligent navigation method, system, electronic device, and storage medium

Abstract

This application provides a document intelligent navigation method, system, electronic device, and storage medium, relating to the field of document processing technology. The method includes: acquiring a target document, wherein the target document includes one of the following document types: XML document, HTML document; extracting document structure information of the target document using XPath rules, and performing semantic parsing of the content of the target document using Natural Language Processing (NLP) to obtain a parsing result, wherein the parsing result is used to represent the relationships between different structural parts in the document structure information; and generating a target navigation directory based on the document structure information and the parsing result, wherein the target navigation directory is used for intelligent navigation. Implementing the technical solution provided in this application achieves the effect of improving the user reading experience.

Description

Technical Field

[0001] This application relates to the field of document processing technology, specifically to a document intelligent navigation method, system, electronic device, and storage medium. Background Technology

[0002] Currently, with the rapid development of internet technology and big data, massive amounts of text resources are being digitally stored. How to efficiently manage and quickly retrieve these documents has become an urgent problem to solve. While existing text processing technologies can support basic keyword searches and simple document categorization, they are generally limited to fixed category menus. Traditional document navigation typically relies on manually constructed indexes or simple linear browsing modes, lacking in-depth analysis of the document's internal hierarchy and semantic structure. Users must browse according to preset paths, and if the content they want to find is not in the expected category, it is difficult to discover, affecting user search efficiency and reading experience. Summary of the Invention

[0003] To address the aforementioned technical problems, this application provides a document intelligent navigation method, system, electronic device, and storage medium.

[0004] In a first aspect, this application provides a document intelligent navigation method, comprising: obtaining a target document, wherein the target document includes one of the following document types: XML document, HTML document; extracting document structure information of the target document using XPath rules, and performing semantic parsing of the content of the target document using Natural Language Processing (NLP) to obtain a parsing result, wherein the parsing result is used to represent the association between different structural parts in the document structure information; generating a target navigation directory based on the document structure information and the parsing result, wherein the target navigation directory is used for intelligent navigation.

[0005] By employing the aforementioned technical solution, utilizing XPath rules to extract document structure information, and combining it with Natural Language Processing (NLP) for content semantic parsing, a comprehensive understanding and expression of the document's internal hierarchy and semantic structure is achieved, laying the foundation for subsequent intelligent navigation. The target navigation directory generated based on the parsing results accurately reflects the document's actual organization and core content, helping users quickly locate the information they need and significantly improving the speed and accuracy of document retrieval. This method efficiently acquires and parses the structural information and semantic content of target documents, generating an intelligent target navigation directory. It not only supports various document formats but also improves user search efficiency and reading experience in complex document environments through in-depth analysis of the document's internal structure and semantic relationships.

[0006] Optionally, the document structure information of the target document can be extracted using XPath rules, including: extracting metadata from the target document using XPath rules to obtain document structure information, wherein the metadata includes headings, paragraph IDs and keyword data.

[0007] By employing the above technical solution, metadata from the target document can be accurately extracted, including headings, paragraph IDs, and keyword data, thus ensuring that the generated document structure information is more detailed and accurate. This not only aids the subsequent semantic parsing process but also improves the quality of the final generated target navigation directory, enabling users to more easily locate the specific document content they need.

[0008] Optionally, Natural Language Processing (NLP) is used to perform semantic parsing on the content of the target document to obtain the parsing results, including: using NLP to identify the key entity set in the target document, wherein the key entity set includes keywords, topics, and authors; using NLP to analyze the conceptual relationships in the target document to generate a semantic tag set; and obtaining the parsing results based on the key entity set and the semantic tag set.

[0009] By adopting the above technical solutions, the key content of target documents can be extracted and parsed more accurately. Specifically: using NLP to identify the key entity set (including keywords, topics, and authors) in the target document ensures a comprehensive capture of the document's core information, improving the accuracy of information extraction; using NLP to analyze the conceptual relationships in the target document and generate a semantic tag set further enhances the understanding of the document's internal structure, making the connections between different parts clearer. The parsing results obtained by combining the key entity set and the semantic tag set not only enrich the document's information hierarchy but also provide a reliable foundation for subsequent target navigation directory generation, improving the intelligence level of navigation.

[0010] Optionally, a target navigation directory can be generated based on the document structure information and the parsing results, including: obtaining an initial directory based on the document structure information; and adjusting the initial directory based on the parsing results to obtain the target navigation directory.

[0011] By adopting the above technical solutions, the level of intelligence in document management and user experience can be effectively improved. Specifically: the initial table of contents is generated based on document structure information, ensuring the basic accuracy of the navigation directory and making it easy for users to quickly locate the parts of interest; the initial table of contents is adjusted based on the parsing results, making the navigation directory more consistent with the actual content and logical structure of the document, enhancing the accuracy and convenience of navigation, and improving the user's search efficiency and reading experience.

[0012] Optionally, the initial directory is adjusted based on the parsing results to obtain the target navigation directory, including: if the parsing results indicate that there is a relationship between the first heading and the second heading, adjusting the positions of the first heading and the second heading, and adding a link to jump to the document content corresponding to the second heading at the position of the first heading to obtain the target navigation directory, wherein the initial directory includes the first heading and the second heading.

[0013] By employing the above technical solution, the initial table of contents is adjusted using semantic information from the parsing results, allowing related headings to be arranged logically within the navigation menu, thus improving user search efficiency. Adding jump links at the first heading position to the document content corresponding to the second heading facilitates quick location of the relevant sections, enhancing the user experience. This technical solution more accurately reflects the relationships between different parts within a document.

[0014] Optionally, a target navigation directory can be generated based on the document structure information and parsing results, including: obtaining an initial navigation directory based on the document structure information and parsing results; dynamically adjusting the initial navigation directory based on the user's historical query records and reading habits to obtain a target navigation directory, wherein the target navigation directory includes popular topic tags added based on the user's historical query records and reading habits.

[0015] By adopting the above technical solution, the initial navigation directory is generated based on document structure information and parsing results, ensuring its basic accuracy and comprehensiveness. The dynamic adjustment process considers users' historical query records and reading habits, making the final target navigation directory more closely match users' actual needs, improving search efficiency and user experience. The addition of popular topic tags not only enriches the content of the navigation directory but also provides users with a new way of exploration, helping them find documents of interest more quickly. This technical solution can dynamically generate a target navigation directory according to users' personalized needs.

[0016] Optionally, after generating the target navigation directory based on the document structure information and parsing results, the above method may further include at least one of the following: setting a search box in the target navigation directory to support keyword search, so as to find matching document content; allowing users to jump to the target document content section through the target navigation directory to achieve accurate positioning of the target document content section.

[0017] By adopting the above technical solution, a search box can be set in the generated target navigation directory to support keyword search, thereby improving the efficiency of users finding matching document content; at the same time, users can directly jump to the specific content of the target document through the target navigation directory, realizing accurate positioning of document content and further improving the user's browsing experience and ease of use.

[0018] In a second aspect of this application, a document intelligent navigation system is also provided, comprising: an acquisition module for acquiring a target document, wherein the target document includes one of the following document types: XML document, HTML document; a processing module for extracting document structure information of the target document using XPath rules, and performing semantic parsing of the content of the target document using Natural Language Processing (NLP) to obtain a parsing result, wherein the parsing result is used to represent the association between different structural parts in the document structure information; and a generation module for generating a target navigation directory based on the document structure information and the parsing result, wherein the target navigation directory is used for intelligent navigation.

[0019] In a third aspect of this application, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the program to implement the method steps of any of the above claims.

[0020] In a fourth aspect of this application, a computer-readable storage medium is also provided, which stores instructions that, when executed, perform the method steps of any of the above claims.

[0021] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages:

[0022] 1. It can efficiently acquire and parse the structural information and semantic content of target documents, and generate an intelligent target navigation directory; through in-depth analysis of the internal structure and semantic relationships of documents, it improves the user's search efficiency and reading experience in complex document environments;

[0023] 2. The initial table of contents is generated based on the document structure information, ensuring the basic accuracy of the navigation table of contents and making it easy for users to quickly locate the parts of interest; the initial table of contents is adjusted based on the parsing results, making the navigation table of contents more consistent with the actual content and logical structure of the document, thus enhancing the accuracy and convenience of navigation;

[0024] 3. It can more accurately reflect the relationships between different parts of a document; it can dynamically generate a target navigation directory based on the user's personalized needs. Attached Figure Description

[0025] Figure 1 This is a flowchart of a document intelligent navigation method provided in an embodiment of this application;

[0026] Figure 2 This is an example diagram of a navigation directory provided in an embodiment of this application;

[0027] Figure 3 This is a structural block diagram of a document intelligent navigation system provided in an embodiment of this application;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application.

[0029] Explanation of reference numerals in the attached drawings: 400 - Electronic device; 401 - Processor; 402 - Communication bus; 403 - User interface; 404 - Network interface; 405 - Memory. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0031] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0032] In the description of the embodiments of this application, the term "multiple" means two or more. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0033] The following is in conjunction with the appendix Figures 1-4 The embodiments of this application will be described.

[0034] This application provides a document intelligent navigation method, referring to... Figure 1 , Figure 1 This is a flowchart of a document intelligent navigation method provided in an embodiment of this application. The method includes:

[0035] Step S101: Obtain the target document, wherein the target document includes one of the following document types: XML document, HTML document;

[0036] Step S102: Extract the document structure information of the target document using XPath rules, and perform semantic parsing on the content of the target document using Natural Language Processing (NLP) to obtain the parsing result, wherein the parsing result is used to represent the relationship between different structural parts in the document structure information;

[0037] Step S103: Generate a target navigation directory based on the document structure information and parsing results, wherein the target navigation directory is used for intelligent navigation.

[0038] Through the above steps, document structure information is extracted using XPath rules, and content semantic parsing is performed using Natural Language Processing (NLP). This achieves a comprehensive understanding and expression of the document's internal hierarchy and semantic structure, laying the foundation for subsequent intelligent navigation. The target navigation directory generated based on the parsing results accurately reflects the document's actual organization and core content, helping users quickly locate the information they need and significantly improving the speed and accuracy of document retrieval. This method efficiently acquires and parses the structural information and semantic content of target documents, generating an intelligent target navigation directory. It not only supports various document formats but also improves user search efficiency and reading experience in complex document environments through in-depth analysis of the document's internal structure and semantic relationships.

[0039] The target document can be an XML or HTML document. XPath rules are used to extract the document's structural information. XPath is a language for finding information in XML and HTML documents. It uses path expressions to select nodes or sets of nodes in the document. By writing appropriate XPath expressions, structured information can be extracted from the document. For example, in an HTML document, the XPath expression " / / div[@class='article']" can be used to select all div elements with the class attribute "article". XPath rules clearly reveal the hierarchical structure of the document, such as the nesting relationships of elements like head, body, div, and span in an HTML document, and the parent-child and sibling relationships of tags in an XML document. This provides a structural foundation for building a navigation directory. Natural Language Processing (NLP) techniques are then used to semantically analyze the content of the target document. NLP can analyze lexical, grammatical, and semantic information in text. For example, it can identify parts of speech (nouns, verbs, etc.) through part-of-speech tagging, determine sentence components through syntactic analysis, and understand the role of each component in a sentence through semantic role tagging. The parsing results represent the relationships between different structural parts of a document. For example, in an HTML document, NLP analysis can reveal semantic inclusion relationships between a heading and its paragraphs, the heading summarizing the main content of the paragraph, or causal relationships between the content of a heading and the content of other headings. Based on the extracted document structure information and semantic parsing results, a target navigation directory is generated. This directory is organized according to the document's structure and semantic hierarchy, visually displaying the various parts of the document and their interrelationships. For instance, for an HTML document, the target navigation directory might be organized by heading level, considering the semantic relationships between paragraph content and headings, categorizing related content under the corresponding headings. Users can quickly jump to any part of the document using this target navigation directory, achieving intelligent navigation. Alternatively, if there is a causal or referential relationship between the content of heading x and the content of heading y, a link to heading 2 can be placed at heading 1 in the target navigation directory. This semantic relationship helps to construct a more accurate navigation directory, allowing users to quickly locate content of interest based on semantics. The target navigation directory is organized according to the document's structure and semantic hierarchy, which helps users better understand the overall structure of the document. During the reading process, users can clearly understand the relationship between the various parts. For example, when reading an XML document of an academic paper, the navigation directory can help users quickly understand the logical order and content relationship of the paper's abstract, introduction, methods, results, discussion, and other parts, making reading smoother and improving the reading experience.In related technologies, manual indexing requires significant manpower and time, and is prone to omissions and errors. Linear browsing requires users to view document content sequentially, making it difficult to find content outside the expected browsing path. This method utilizes XPath rules and NLP technology to automatically extract document structure and semantic information, automatically generating a target navigation directory. Users no longer need to rely on manual indexing or browse documents in a linear order. The intelligent navigation directory allows users to quickly locate relevant sections of the document, greatly improving search efficiency and enhancing the reading experience. Furthermore, the target document can also be a Word document, which can be converted to XML before the target navigation directory is automatically generated using the above method. Through this embodiment, by deeply mining the hierarchical structure and semantic information of the document, this method can generate a more accurate and intelligent navigation directory, thereby improving navigation accuracy. Using the intelligent navigation directory, users can quickly locate the required content, reducing search time and improving search efficiency.

[0040] In an optional embodiment, the document structure information of the target document is extracted using XPath rules, including: extracting metadata from the target document using XPath rules to obtain document structure information, wherein the metadata includes title, paragraph ID and keyword data.

[0041] In the above embodiments, metadata from the target document can be accurately extracted, including titles, paragraph IDs, and keyword data, thereby ensuring that the generated document structure information is more detailed and accurate. This not only helps the subsequent semantic parsing process but also improves the quality of the final generated target navigation directory, enabling users to more easily locate the specific document content they need.

[0042] XPath rules are used to precisely extract key metadata from target documents. This metadata forms an important part of the document's structural information, including titles, paragraph IDs, and keyword data. It reflects the document's hierarchical structure and key content, providing a foundation for subsequent semantic parsing and navigation table of contents generation. XPath is a language for locating nodes in XML documents, and it is also applicable to markup languages ​​such as HTML. By writing specific XPath expressions, the required metadata can be precisely extracted from the document. XPath is a language for finding information in XML and HTML documents, using path expressions to locate nodes, attributes, and text content. For example, the XPath expression " / / h1" can be used to extract all h1 headings in the document, " / / p[@id='specific-paragraph']" can be used to extract paragraphs with a specific ID, and " / / meta[@name='keywords'] / @content" can be used to extract keyword data. This metadata is an important part of the document's structural information and helps build a detailed navigation table of contents. By using XPath rules to accurately extract document metadata, the accuracy of document structure information extraction can be greatly improved, providing a reliable foundation for subsequent intelligent navigation. The complete metadata set makes the generated navigation directory more practical and accurate. Accurate document structure information and a complete metadata set make the intelligent navigation directory easier to use and understand, thereby improving the user's reading experience and search efficiency.

[0043] In an optional embodiment, natural language processing (NLP) is used to perform semantic parsing on the content of the target document to obtain the parsing result, including: using NLP to identify a set of key entities in the target document, wherein the set of key entities includes keywords, topics, and authors; using NLP to analyze the conceptual relationships in the target document to generate a set of semantic tags; and obtaining the parsing result based on the set of key entities and the set of semantic tags.

[0044] In the above embodiments, the key content of the target document can be extracted and parsed more accurately. Specifically: using NLP to identify the key entity set (including keywords, topics, and authors) in the target document ensures a comprehensive capture of the document's core information, improving the accuracy of information extraction; using NLP to analyze the conceptual relationships in the target document and generate a semantic tag set further enhances the understanding of the document's internal structure, making the connections between different parts clearer. The parsing results obtained by combining the key entity set and the semantic tag set not only enrich the document's information hierarchy but also provide a reliable foundation for the subsequent generation of the target navigation directory, improving the intelligence level of the navigation.

[0045] Natural Language Processing (NLP) techniques are used to identify key entity sets in target documents. These key entity sets include keywords, topics, and authors. Named Entity Recognition (NER) technology in NLP can be used to identify entities such as keywords and authors in a document. For example, a well-trained NER model can identify proper nouns (such as names of people, places, and organizations) in a document as key entities. Simultaneously, topic recognition technology can be used to extract the topic of a document. This can be achieved through methods such as analyzing high-frequency words in the document and using term frequency-inverse document frequency (TF-IDF). For example, in a document about "artificial intelligence," NLP analysis can identify keywords such as "machine learning," "deep learning," and "neural network" as topic-related keywords. NLP analysis can also be used to analyze conceptual relationships in target documents and generate semantic tag sets. This can be achieved through techniques such as dependency parsing and semantic role labeling. Dependency parsing can identify dependency relationships between words in a sentence, such as subject-verb relationships and verb-object relationships. For example, in the sentence "Scientists have discovered a new drug," dependency parsing can identify the subject-verb relationship between "scientists" and "discovery," and the verb-object relationship between "discovery" and "drug." Based on these conceptual relationships, a semantic tag set is generated. Semantic tags can represent the associations between different concepts in the document, such as "causal relationship," "parallel relationship," and "inclusion relationship." For example, for a document about historical events, semantic tags such as "event-cause-effect" can be generated to represent the causal relationship between events. The parsing results are obtained based on the key entity set and the semantic tag set. The parsing results integrate the key entities and conceptual relationships in the document, comprehensively reflecting the document's semantic structure. By identifying the key entity set and analyzing conceptual relationships, the generated navigation menu will more accurately reflect the document's semantic structure. Users can not only see the document's keywords and themes but also understand the relationships between concepts through semantic tags; for example, in a document about literary works, the navigation menu can display the work's keywords (such as "love," "tragedy"), themes (such as "exploration of love tragedies"), and the relationships between concepts (such as "love leads to tragedy"), allowing users to more accurately navigate to the parts of the document that interest them. The generation of semantic tag sets greatly enhances document comprehensibility. Users can quickly understand the main content and structure of a document through semantic tags without having to read every part of the document. At the same time, semantic tags also help improve document searchability. For example, in an enterprise's internal knowledge base, semantic tags can quickly retrieve documents related to "project management - risk assessment - response strategies," rather than just documents containing these keywords, thus improving the accuracy and efficiency of retrieval.

[0046] Semantic parsing, through Natural Language Processing (NLP) techniques, goes beyond simple keyword matching, delving into the semantic level of text. This includes identifying entities, concepts, and their relationships; understanding implicit information within the context; and capturing the connections between different text fragments. Here are some specific methods:

[0047] Topic Modeling: Used to discover whether the topics discussed in different parts of a document are consistent or related; Causal Reasoning: Identifies causal relationships described in the text, such as one event causing another; Citation Resolution: Detects citation markers in the text and tracks the specific locations these citations point to; Step Sequence: For operation guidelines or process descriptions, organizes the steps in chronological or logical order; Comparative Analysis: Identifies paragraphs that compare two or more viewpoints, methods, or cases.

[0048] Suppose we are working on a research paper on diabetes treatment, here are a few examples of possible logical relationships:

[0049] Thematic consistency: Both the "Introduction" and "Background" sections introduce the basics of diabetes, so these two sections should be linked to each other in the navigation.

[0050] Causal Relationship: If the "Experimental Results" show that a certain drug lowers blood sugar levels and the "Discussion" section explains the mechanism behind this effect, then there is a causal relationship between the two. You can set up a shortcut from the results to the discussion in the navigation.

[0051] Reference relationship: If the "Materials and Methods" section mentions the use of a specific measuring device, and the "Appendix" contains the operating manual for that device, then a small icon pointing to the "Appendix" can be provided next to "Materials and Methods".

[0052] Step sequence: If the paper includes the design process of a clinical trial, then the various experimental phases (patient recruitment, group assignment, intervention administration, data collection) should be organized into a multi-level navigation path in chronological order;

[0053] Comparison: When a paper compares two different treatment methods, a dedicated comparison view can be created in the navigation menu, allowing users to easily switch between viewing the efficacy evaluations of different treatments;

[0054] In this way, this embodiment can not only improve the speed and accuracy of document retrieval, but also greatly improve the user's reading experience.

[0055] In an optional embodiment, generating a target navigation directory based on document structure information and parsing results includes: obtaining an initial directory based on document structure information; and adjusting the initial directory based on the parsing results to obtain the target navigation directory.

[0056] The above embodiments effectively improve the intelligence level of document management and user experience. Specifically: the initial directory is generated based on document structure information, ensuring the basic accuracy of the navigation directory and making it easy for users to quickly locate the parts of interest; the initial directory is adjusted based on the parsing results, making the navigation directory more consistent with the actual content and logical structure of the document, enhancing the accuracy and convenience of navigation, and improving the user's search efficiency and reading experience.

[0057] An initial table of contents is generated based on the document's structure information. This structure includes the document's hierarchical structure, such as headings and paragraphs. For example, extracting headings (h1, h2, h3, etc.) and paragraph IDs using XPath rules can generate a basic table of contents. This initial table of contents is generated based on the document's physical structure, reflecting the document's various parts and their hierarchical relationships. For instance, for an HTML document, the XPath expression " / / h1 | / / h2 | / / h3" can be used to extract all headings, and then an initial table of contents can be generated based on these headings. The initial table of contents is then adjusted using the parsing results from Natural Language Processing (NLP). These results include key entity sets (such as keywords, topics, and authors) and semantic tag sets (such as conceptual relationships). This information allows for optimization of the initial table of contents to better align with the document's semantic structure. For example, if NLP analysis reveals that a paragraph, while physically belonging to "Heading 1.1," is more relevant to "Heading 2," the table of contents can be adjusted using semantic tag sets to reclassify the paragraph under "Heading 2." The adjustment steps following semantic parsing ensure that the navigation directory not only reflects the document's physical structure but also the inherent connections between content, helping users find the information they need more intuitively. This embodiment adjusts the initial directory based on the parsing results, generating a target navigation directory that more accurately reflects the document's semantic structure. Users can quickly find content of interest through the directory without having to examine every part of the document individually. The dynamic adjustment mechanism of the directory makes document maintenance more convenient. When the document content changes, the directory can be automatically updated, reducing the workload and error probability of manual maintenance.

[0058] In an optional embodiment, adjusting the initial directory based on the parsing results to obtain the target navigation directory includes: if the parsing results indicate a relationship between the first title and the second title, adjusting the positions of the first title and the second title, and adding a link to the document content corresponding to the second title at the position of the first title to obtain the target navigation directory, wherein the initial directory includes the first title and the second title.

[0059] In the above embodiment, the semantic information in the parsing results is used to adjust the initial directory, so that related titles can be arranged reasonably in the navigation directory, improving the user's search efficiency. Adding a jump link to the document content corresponding to the second title at the first title position allows users to quickly locate the part of interest, enhancing the user experience. This embodiment can more accurately reflect the relationships between different parts within a document.

[0060] This embodiment identifies the relationships between different headings (such as the first heading and the second heading) in a document through parsing results, and adjusts the heading positions in the initial table of contents based on these relationships. Specifically, when the parsing results indicate a logical or content-related relationship between the first heading and the second heading, the method adds a jump link at the position of the first heading, pointing to the document content corresponding to the second heading. This allows readers to directly jump to the content related to the second heading by clicking the jump link under the first heading, thus more conveniently obtaining the required information. By adding a jump link at the position of the first heading, this method allows readers to directly jump to the content related to the second heading while browsing the table of contents, thereby enhancing the flexibility of the table of contents navigation. By identifying and adjusting the relationships between headings, this method enables readers to more intuitively see the logical and content connections in the document and quickly locate relevant content, improving the accessibility of related information. The flexible navigation mechanism and intuitive information display method help improve the user's reading experience, making it easier for readers to understand and browse document content. The intelligently adjusted navigation table of contents not only makes the document structure clearly visible but also provides users with a smoother and more convenient browsing environment, enhancing user satisfaction. Figure 2 This is an example diagram of a navigation directory provided in an embodiment of this application. Figure 2 The left side of the diagram shows the initial directory, and the right side shows the target navigation directory after adjustment. This diagram is only an example.

[0061] In an optional embodiment, generating a target navigation directory based on document structure information and parsing results includes: obtaining an initial navigation directory based on document structure information and parsing results; dynamically adjusting the initial navigation directory based on the user's historical query records and reading habits to obtain a target navigation directory, wherein the target navigation directory includes popular topic tags added based on the user's historical query records and reading habits.

[0062] In the above embodiments, the initial navigation directory is generated based on document structure information and parsing results, ensuring its basic accuracy and comprehensiveness. The dynamic adjustment process considers the user's historical query records and reading habits, making the final target navigation directory more closely match the user's actual needs, improving search efficiency and user experience. The addition of popular topic tags not only enriches the content of the navigation directory but also provides users with a new way of exploration, helping them find documents of interest more quickly. This embodiment can dynamically generate a target navigation directory according to the user's personalized needs.

[0063] An initial navigation directory is generated based on document structure information and parsing results. Document structure information includes the document's hierarchical structure, such as headings and paragraphs. Parsing results use Natural Language Processing (NLP) technology to identify key entity sets and conceptual relationships within the document, generating semantic tag sets. For example, XPath rules are used to extract headings (h1, h2, h3, etc.) and paragraph IDs from the document, combined with NLP parsing results to generate the initial directory. The initial navigation directory is then dynamically adjusted based on the user's historical query history and reading habits. The system can understand user interests and usage habits by analyzing historical behavioral data, such as search keywords, click records, and dwell time. By analyzing users' historical query history and reading habits, the system can provide customized navigation directories to better meet the specific needs of individual users. Adding trending topic tags makes related topics more prominent, helping to guide users to discover new content or explore areas of interest, promoting knowledge dissemination and learning. As more user behavior data accumulates, the system can continuously optimize the navigation directory adjustment strategy through machine learning algorithms, making it more intelligent and efficient.

[0064] In an optional embodiment, after generating the target navigation directory based on the document structure information and the parsing results, the above method further includes at least one of the following: setting a search box in the target navigation directory to support keyword search, so as to find matching document content; allowing users to jump to the target document content section through the target navigation directory to achieve accurate positioning of the target document content section.

[0065] In the above embodiments, a search box can be set in the generated target navigation directory to support keyword search, thereby improving the efficiency of users finding matching document content; at the same time, users can directly jump to the specific content of the target document through the target navigation directory, realizing accurate positioning of document content and further improving the user's browsing experience and ease of use.

[0066] By embedding a search box in the target navigation directory, users can enter keywords to search the entire document or the navigation directory. The system will match the entered keywords within the document or navigation directory, returning document content or navigation items related to the keywords, thus helping users quickly locate the information they need. Each navigation item in the target navigation directory is associated with a specific content section in the document. When a user clicks on a navigation item, the system will directly jump to that section of content based on the correspondence between the navigation item and the document content section, achieving accurate location of the target document content section. The introduction of the search box allows users to quickly search and locate the information they need by entering keywords, greatly improving the efficiency of information retrieval. At the same time, allowing users to directly jump to the target content section through the navigation directory also reduces the time spent on manual browsing. By adding a search box and jump functionality, the target navigation directory not only provides the hierarchical structure of the document but also supports users to perform keyword searches and quick location. This enhances the functionality of the navigation directory and improves the user experience.

[0067] In an optional embodiment, after generating the target navigation directory based on the document structure information and the parsing results, the method further includes: pushing target document fragments to the user based on the matching degree between user preferences and the target navigation directory.

[0068] In the above embodiment, a target navigation directory is first constructed using the document's structural information and parsing results. This directory reflects the document's content structure and theme. Then, the system analyzes user history, interests, and other data to assess the degree of matching between the user and various parts of the target navigation directory. Finally, based on the degree of matching, the system selects the target document segment that best matches the user's preferences and pushes it to the user. By matching user preferences with the target navigation directory, this method can accurately push content segments that users are interested in, improving the user's reading experience and satisfaction. Because the pushed content highly matches user preferences, users are more likely to continue reading and explore the document content in depth, thereby increasing engagement.

[0069] By analyzing users' historical behavioral data, such as browsing history, search records, and click behavior, a user profile is constructed. This profile includes information such as the user's interests, preferences, and behavioral patterns. For example, by analyzing frequently searched keywords and clicked document sections, the system understands the user's interest in specific topics. The system calculates the matching degree between user preferences and the target navigation directory. This can be achieved by analyzing the similarity between document fragments in the target navigation directory and points of interest in the user profile. For example, cosine similarity can be used to calculate the similarity between the user preference vector and the document fragment vector. Based on the matching degree, the system pushes target document fragments to the user. These fragments represent content that the user may be interested in, and by highlighting them or directly jumping to relevant sections, the system helps the user quickly find the information they need. For example, if a user is interested in "data encryption," the system can push document fragments containing the keyword "data encryption." This personalized recommendation system enables users to find the content they need faster, reduces search time, and improves user satisfaction. By pushing content that users are interested in, the system can improve user engagement and retention rates.

[0070] In an optional embodiment, generating a target navigation directory based on document structure information and parsing results includes: obtaining an initial navigation directory based on document structure information and parsing results; adjusting the initial navigation directory based on preset cross-document associations to obtain the target navigation directory, wherein the preset cross-document associations are used to indicate the establishment of logical relationships between multiple documents, including the target document.

[0071] In the above embodiments, preset cross-document associations are used to establish logical relationships between multiple documents. These logical relationships can be topic-related, citation-related, or complementary, for example, one document may cite content from another document, or two documents may discuss the same topic. The initial navigation directory is adjusted based on the preset cross-document associations to obtain the target navigation directory. For example, if both document A and document B discuss the topic of "data encryption," a link can be added to document A's navigation directory pointing to the relevant content in document B. Through preset cross-document associations, users can quickly jump to content in related documents without manual searching. For example, when viewing content related to "data encryption," a user can directly jump to the relevant content in other documents via links in the navigation directory, greatly improving search efficiency. Cross-document associations enable users to gain a more comprehensive understanding of related topics, reducing search time and improving user satisfaction. For example, when reading technical documents, users can quickly find supplementary content in other documents via links in the navigation directory, making the reading experience smoother.

[0072] Obviously, the embodiments described above are only some embodiments of this application, and not all embodiments. The present application will be specifically described below with reference to specific embodiments.

[0073] This application provides a multi-level intelligent document navigation method based on XPath rules. It adopts a document parsing scheme that integrates XPath rules and natural language processing technology, so it can automatically construct a multi-level navigation directory that accurately reflects the document structure characteristics, which greatly improves the speed and accuracy of document retrieval.

[0074] The specific plan is as follows:

[0075] A multi-level intelligent document navigation method based on XPath rules is proposed. This method combines XPath rules with semantic recognition technology to automatically parse the document structure of complex documents and generate a visual multi-level document navigation directory. The corresponding document content can be located based on the multi-level document navigation directory, and the document content can be pushed in a targeted manner based on user preferences and the multi-level document navigation directory.

[0076] Specifically, this can be achieved by collecting a target document set, automatically extracting tags and attributes from the documents using XPath rules to form a document tree structure model; applying natural language processing technology to perform semantic analysis on the document content, identifying key entities and conceptual relationships, and enhancing the depth of understanding of the document structure; dynamically generating a visual multi-level document navigation directory by combining user historical behavior data and personal preference settings; developing a real-time update mechanism based on the multi-level document navigation directory to ensure the latest and accurate information of the document content; achieving precise positioning of document content, allowing users to quickly jump to sections of interest through the navigation directory, improving browsing efficiency; and integrating a recommendation engine to proactively push relevant document snippets based on the matching degree between user preferences and the multi-level document navigation directory, enhancing the user experience.

[0077] In a specific implementation scenario, such as a legal document retrieval system, the system first collects a large number of legal documents and uses XPath rules to automatically extract metadata such as titles, paragraph IDs, and keywords from the documents, constructing a detailed document structure graph. Second, leveraging advanced natural language understanding and machine learning algorithms, it delves into the core issues, key figures, time and location of each document, enhancing the understanding of its content. Third, based on each user's historical query records and reading habits, the system intelligently calculates individual interests and dynamically adjusts the presentation of the navigation menu, such as adding popular topic tags and highlighting frequently cited clauses. Finally, combining the above technologies, the system not only achieves highly structured parsing of complex legal documents but also responds instantly to changes in user needs, intelligently pushing highly relevant cases or legal interpretations, significantly improving retrieval efficiency and user satisfaction.

[0078] Compared with related technologies, the embodiments of this application have at least the following technical effects: a document parsing scheme that integrates XPath rules and natural language processing technology is adopted, so it can automatically construct a multi-level navigation directory that accurately reflects the document structure characteristics, which greatly improves the speed and accuracy of document retrieval.

[0079] This application also provides a document intelligent navigation system, such as Figure 3 As shown, Figure 3 This is a structural block diagram of a document intelligent navigation system provided in an embodiment of this application. The system includes:

[0080] The acquisition module 301 is used to acquire the target document, wherein the target document includes one of the following document types: XML document, HTML document;

[0081] The processing module 302 is used to extract the document structure information of the target document using XPath rules, and to perform semantic parsing on the content of the target document using Natural Language Processing (NLP) to obtain the parsing result, wherein the parsing result is used to represent the relationship between different structural parts in the document structure information;

[0082] The generation module 303 is used to generate a target navigation directory based on the document structure information and the parsing results, wherein the target navigation directory is used for intelligent navigation.

[0083] In an optional embodiment, the processing module 302 includes an extraction unit, configured to extract metadata from the target document using XPath rules to obtain document structure information, wherein the metadata includes title, paragraph ID and keyword data.

[0084] In an optional embodiment, the processing module 302 includes: an identification unit, configured to identify a set of key entities in a target document using NLP, wherein the set of key entities includes keywords, topics, and authors; an analysis unit, configured to analyze conceptual relationships in the target document using NLP and generate a set of semantic tags; and a first obtaining unit, configured to obtain parsing results based on the set of key entities and the set of semantic tags.

[0085] In an optional embodiment, the generation module 303 includes: a second obtaining unit, configured to obtain an initial directory based on document structure information; and a third obtaining unit, configured to adjust the initial directory based on the parsing results to obtain a target navigation directory.

[0086] In an optional embodiment, the third obtaining unit includes: an adjustment subunit, configured to adjust the positions of the first title and the second title when the parsing result indicates that there is a relationship between the first title and the second title, and add a link to the document content corresponding to the second title at the position of the first title to obtain a target navigation directory, wherein the initial directory includes the first title and the second title.

[0087] In an optional embodiment, the generation module 303 includes: a fourth obtaining unit, configured to obtain an initial navigation directory based on document structure information and parsing results; and an adjusting unit, configured to dynamically adjust the initial navigation directory based on the user's historical query records and reading habits to obtain a target navigation directory, wherein the target navigation directory includes popular topic tags added based on the user's historical query records and reading habits.

[0088] In an optional embodiment, the system further includes at least one of the following: a search module, configured to set a search box in the target navigation directory after generating the target navigation directory based on the document structure information and parsing results, supporting keyword search to facilitate finding matching document content; and a jump module, configured to allow users to jump to the target document content section through the target navigation directory, thereby achieving accurate positioning of the target document content section.

[0089] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided above belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0090] This application also provides a computer-readable storage medium storing instructions that, when executed, perform the steps of any of the methods described above.

[0091] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0092] This application also discloses an electronic device. For example... Figure 4 As shown, Figure 4This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 400 may include: at least one processor 401, at least one communication bus 402, a user interface 403, at least one network interface 404, and a memory 405.

[0093] The communication bus 402 is used to enable communication between these components.

[0094] The user interface 403 may include a display screen and a camera. Optionally, the user interface 403 may also include a standard wired interface and a wireless interface.

[0095] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0096] The processor 401 may include one or more processing cores. The processor 401 connects to various parts of the electronic device (such as a server) using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 405, and by calling data stored in memory 405. Optionally, the processor 401 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 401 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 401.

[0097] The memory 405 may include random access memory (RAM) or read-only memory. Optionally, the memory 405 may include a non-transitory computer-readable storage medium. The memory 405 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 405 may also be at least one storage device located remotely from the aforementioned processor 401. (Refer to...) Figure 4 The memory 405, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a document intelligent navigation method.

[0098] exist Figure 4 In the illustrated electronic device 400, the user interface 403 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 401 can be used to call an application program of a document intelligent navigation method stored in the memory 405. When executed by one or more processors 401, the electronic device 400 performs one or more of the methods described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0099] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0100] In the various embodiments provided in this application, it should be understood that the disclosed apparatus or system can be implemented in other ways. For example, the apparatus or system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0101] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0103] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0104] The above description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the disclosure herein.

[0105] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art that are not described in this disclosure.

Claims

1. A document intelligent navigation method, characterized in that, include: Obtain the target document, wherein the target document includes one of the following document types: XML document, HTML document; The document structure information of the target document is extracted using XPath rules, and the content of the target document is semantically parsed using Natural Language Processing (NLP) to obtain the parsing result, wherein the parsing result is used to represent the relationship between different structural parts in the document structure information; A target navigation directory is generated based on the document structure information and the parsing results, wherein the target navigation directory is used for intelligent navigation; The semantic parsing of the target document's content using Natural Language Processing (NLP) to obtain the parsing result includes: using NLP to identify a set of key entities in the target document, wherein the set of key entities includes keywords, topics, and authors; using NLP to analyze conceptual relationships in the target document and generate a set of semantic tags; obtaining the parsing result based on the set of key entities and the set of semantic tags; the parsing result is used to represent the associations between different structural parts in the document's structural information, including topic consistency, causal relationships, citation relationships, step order, or comparison relationships; Generating a target navigation directory based on the document structure information and the parsing result includes: obtaining an initial directory based on the document structure information; and adjusting the initial directory based on the parsing result to obtain the target navigation directory. The adjustment of the initial directory based on the parsing result to obtain the target navigation directory includes: when the parsing result indicates that there is a relationship between the first title and the second title, adjusting the positions of the first title and the second title, and adding a link to the document content corresponding to the second title at the position of the first title to obtain the target navigation directory, wherein the initial directory includes the first title and the second title.

2. The method according to claim 1, characterized in that, The document structure information of the target document is extracted using XPath rules, including: Metadata from the target document is extracted using the XPath rules to obtain the document structure information, wherein the metadata includes title, paragraph ID, and keyword data.

3. The method according to claim 1, characterized in that, Generate a target navigation directory based on the document structure information and the parsing results, including: The initial navigation directory is obtained based on the document structure information and the parsing results; The initial navigation directory is dynamically adjusted based on the user's historical query records and reading habits to obtain the target navigation directory, wherein the target navigation directory includes popular topic tags added based on the user's historical query records and reading habits.

4. The method according to claim 1, characterized in that, After generating the target navigation directory based on the document structure information and the parsing results, the method further includes at least one of the following: A search box is set in the target navigation directory to support keyword search, so as to find matching document content; Users can navigate to the target document content section through the target navigation directory, enabling accurate location of the target document content section.

5. A document intelligent navigation system, characterized in that, include: The acquisition module is used to acquire a target document, wherein the target document includes one of the following document types: XML document, HTML document; The processing module is used to extract the document structure information of the target document using XPath rules, and to perform semantic parsing on the content of the target document using Natural Language Processing (NLP) to obtain the parsing result, wherein the parsing result is used to represent the relationship between different structural parts in the document structure information; A generation module is used to generate a target navigation directory based on the document structure information and the parsing result, wherein the target navigation directory is used for intelligent navigation; The processing module includes: an identification unit for identifying a set of key entities in a target document using NLP, wherein the set of key entities includes keywords, topics, and authors; an analysis unit for analyzing conceptual relationships in the target document using NLP to generate a set of semantic tags; and a first obtaining unit for obtaining a parsing result based on the set of key entities and the set of semantic tags. The parsing result is used to represent the associations between different structural parts in the document's structural information, wherein the associations include topic consistency, causal relationships, citation relationships, step order, or comparison relationships. The generation module includes: a second obtaining unit, used to obtain an initial directory based on document structure information; and a third obtaining unit, used to adjust the initial directory based on the parsing results to obtain a target navigation directory. The third obtaining unit includes an adjustment subunit, used to adjust the positions of the first and second headings when the parsing result indicates a relationship between the first heading and the second heading, and to add a link to the document content corresponding to the second heading at the position of the first heading to obtain the target navigation directory, wherein the initial directory includes the first heading and the second heading.

6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 4.

Images