Document navigation display method and apparatus

Abstract

Provided in the present application are a document navigation display method and apparatus, which are used for more intuitively presenting the relationship between document sets, the relationship between a document set and a document, the relationship between documents, tables of contents for documents, etc. to a user on the basis of an interaction operation of the user, thereby providing a more intuitive navigation method to the user, such that the user can efficiently access required content. The method comprises: acquiring a plurality of document sets having an association relationship, and displaying identifiers of the plurality of document sets; in response to a selection operation of a user in respect of an identifier of a first document set among the plurality of document sets, acquiring identifiers of a plurality of documents included in the first document set, and displaying the relationship between the identifiers of the plurality of documents and the identifier of the first document set and the relationship between documents corresponding to the identifiers of the plurality of documents; and in response to an operation of the user in respect of an identifier of a first document among the plurality of documents, acquiring the first document on the basis of the identifier of the first document, and displaying a table of contents for content in the first document.

Description

A document navigation display method and apparatus

[0001] This application claims priority to Chinese Patent Application No. 202410551245.7, filed with the State Intellectual Property Office of China on April 30, 2024, entitled "A Document Navigation Display Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of document parsing, and more particularly to a document navigation display method and apparatus. Background Technology

[0003] Documents are a common type of document for preserving knowledge. For example, contracts are a common application scenario for documents, containing crucial legal documents with detailed information and clauses. Typically, a contract includes one or more documents, which usually require manual review. Routine review processes demand significant manpower for reading and screening. In some scenarios, there are numerous contract documents requiring user review, each with substantial content that necessitates a step-by-step review process. This time-consuming searching and reviewing reduces the overall efficiency of document review. Therefore, improving document review efficiency is a pressing issue. Summary of the Invention

[0004] This application provides a document navigation display method and apparatus, which, based on user interaction, more intuitively displays the relationships between document collections, the relationships between document collections and documents, the relationships between documents, and the document directory, thereby providing users with a more intuitive navigation method and enabling users to efficiently find the content they need.

[0005] In view of the above, firstly, this application provides a document navigation display method, including:

[0006] Retrieves multiple related document collections and displays the identifiers of these document collections, such as their names, IDs, or other identifiers.

[0007] In response to the user's selection operation on the identifier of the first document set among multiple document sets, the identifiers of the multiple documents included in the first document set are obtained, that is, the identifiers of the multiple documents included in the first document set are displayed, and the relationship between the identifiers of the multiple documents and the identifier of the first document set, as well as the relationship between the documents corresponding to the identifiers of the multiple documents, are displayed in the display interface. In other words, in response to the user's selection operation on the first document set, the hierarchical relationship between the multiple documents and the first document set, as well as the relationship between the documents under the first document set (such as subordinate relationship or parallel relationship, etc.) are displayed.

[0008] In response to a user's operation to identify the first document among multiple documents, retrieve the first document based on the identifier and display the table of contents of the first document.

[0009] In this embodiment, the interactive display interface can show the relationships between document collections, the relationships between documents, and the table of contents within documents in a hierarchical manner based on the user's selection. This provides a more intuitive presentation of the hierarchical relationships between document collections or documents. In each level of display, the user can see the selected content and its related content, allowing for further access to the desired information. Therefore, this reduces the time users spend searching for their desired content and significantly improves document retrieval efficiency.

[0010] In one possible implementation, the aforementioned method may further include: identifying multiple document sets from files in a document library using an artificial intelligence model, such as using a large model or a pre-trained language model to identify documents from files in the document library. A collection of multiple documents with related relationships. Therefore, in the embodiments of this application, an artificial intelligence model can be used to identify the files in the file library, thereby eliminating the need for manual identification and outputting a collection of documents with related relationships, greatly improving the efficiency of users reviewing the required document content.

[0011] In one possible implementation, the aforementioned multiple document sets are multiple related contracts, and the first document set includes documents included in a single contract. This application can be applied to contract scenarios, where a single contract typically contains multiple documents. The method provided in this application allows users to quickly find the contract content they need to review, improving the efficiency of contract review.

[0012] In one possible implementation, the aforementioned method may further include: extracting key information based on user input, such as elements in the document that require user review or the main body of the document; identifying the paragraphs containing the key information in the document content; and identifying the table of contents information corresponding to the key information in the table of contents. Therefore, in this embodiment, key information can be identified both in the document content and in the document table of contents, thereby providing a clear visual representation of the location of the key information within the document and in the table of contents, allowing users to more intuitively understand the content and location corresponding to the key information.

[0013] In one possible implementation, the aforementioned method may further include: folding content unrelated to key information within the document. In this application's implementation, when displaying key information, content unrelated to the key information can be folded, allowing for a more concise display of the key information on the interface. This enables users to focus more intently on reviewing content including key information, thereby improving the efficiency of reviewing key information.

[0014] In one possible implementation, the aforementioned method further includes: searching for preset directory information in the directory of the first document; and identifying the searched directory information. In this application embodiment, some preset directory information can be identified. For example, for content that requires special attention from the user, corresponding tags can be added to the document directory, thereby allowing the user to focus on the document content that needs attention and improving the user's reading efficiency.

[0015] Secondly, this application provides a document navigation system, including: a computing device and a display screen, wherein a wired or wireless connection is established between the computing device and the display screen; wherein,

[0016] This display screen is used to display content according to instructions from the computing device;

[0017] This computing device is used to perform the following steps:

[0018] Retrieves multiple related document collections and displays the identifiers of these collections on the screen;

[0019] In response to the user's selection operation of the identifier of the first document set among multiple document sets, the identifiers of the documents included in the first document set are obtained, and the relationship between the multiple document identifiers and the identifier of the first document set, as well as the relationship between the documents corresponding to the multiple document identifiers, are displayed on the screen.

[0020] In response to a user's operation to identify the first document among multiple documents, the system retrieves the first document based on its identifier and displays a table of contents of the first document on the screen.

[0021] The effects achieved by the second aspect and any optional implementation of the second aspect can be referred to the description of the first aspect or any optional implementation of the first aspect, and will not be repeated hereafter.

[0022] In one possible implementation, the aforementioned computing device is also used to: identify multiple document sets from files in a file library using an artificial intelligence model.

[0023] In one possible implementation, the aforementioned multiple document sets are multiple related contracts, and the documents included in the first document set are the documents included in a single contract.

[0024] In one possible implementation, the aforementioned computing device is further configured to: extract key information based on user input; identify the paragraph containing the key information in the document; and identify the directory information of the content corresponding to the key information in the table of contents displayed on the screen.

[0025] In one possible implementation, the aforementioned computing device is also used to: fold content in a document that is not related to key information.

[0026] In one possible implementation, the aforementioned computing device is further configured to: search for preset directory information in the directory of the first document; and identify the searched directory information.

[0027] Thirdly, embodiments of this application provide a computing device, including a processor and a memory; the processor of at least one computing device is configured to execute instructions stored in the memory of at least one computing device, so that the computing device performs method steps as described in the first aspect and any implementation thereof.

[0028] Fourthly, embodiments of this application provide a computing device cluster, including at least one computing device, each computing device including a processor and a memory; the processor of the at least one computing device is used to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster performs the method steps as described in the first aspect and any implementation thereof.

[0029] Fifthly, embodiments of this application provide a computer program product containing instructions that, when executed by a cluster of computing devices, cause the cluster of computing devices to perform a method as described in the first aspect or any implementation thereof.

[0030] In a sixth aspect, embodiments of this application provide a computer-readable storage medium including computer program instructions, which, when executed by a cluster of computing devices, enable the cluster of computing devices to perform a method as described in any of the first, second, third, or fourth aspects.

[0031] In a seventh aspect, embodiments of this application provide a chip including at least one processor and an interface; at least one processor obtains program instructions or data through the interface; at least one processor is used to execute program line instructions to implement the method in the first aspect or any implementation thereof. Attached Figure Description

[0032] Figure 1 is a schematic diagram of a system architecture provided in this application;

[0033] Figure 2 is a flowchart illustrating a document navigation display method provided in this application;

[0034] Figure 3 is a flowchart illustrating another document navigation display method provided in this application;

[0035] Figure 4 is an example diagram of a GUI provided in this application;

[0036] Figure 5 is an example diagram of another GUI provided in this application;

[0037] Figure 6 is an example diagram of another GUI provided in this application;

[0038] Figure 7 is an example diagram of another GUI provided in this application;

[0039] Figure 8 is an example diagram of another GUI provided in this application;

[0040] Figure 9 is an example diagram of another GUI provided in this application;

[0041] Figure 10 is an example diagram of another GUI provided in this application;

[0042] Figure 11 is an example diagram of another GUI provided in this application;

[0043] Figure 12 is a structural schematic diagram of a document navigation display system provided in this application;

[0044] Figure 13 is a schematic diagram of the structure of a computing device provided in this application;

[0045] Figure 14 is a schematic diagram of the structure of a computing device cluster provided in an embodiment of this application;

[0046] Figure 15 is a schematic diagram of another computing device cluster provided in an embodiment of this application. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0048] To facilitate understanding, some terms used in this application will be explained first.

[0049] (1) Large Model

[0050] Large models are large-scale models. The "large" in large models can be reflected in many aspects, such as large data scale, large-scale parallel computing capabilities, and larger model structures.

[0051] (2) Language model (LM)

[0052] Language models play a crucial role in Natural Language Processing (NLP), where their task is to predict the probability of a sentence occurring in a language. For example, a language model is typically constructed as a probability distribution p(s) of a string s, where p(s) attempts to reflect the frequency of string s as a sentence. It can be applied to scenarios such as text recognition or machine translation. In the embodiments of this application, the NLP models mentioned below include language models.

[0053] (3) Large Language Model (LLM)

[0054] A large language model (LLM) refers to a language model containing hundreds of billions (or more) parameters trained on massive amounts of text data. It is a natural language processing model based on deep learning. These models can process large amounts of text data to learn the grammatical and semantic rules of natural language. LLMs can be applied to text generation, machine translation, question answering systems, text summarization, and sentiment analysis, offering advantages such as strong generative capabilities, high adaptability, accurate prediction, and strong scalability. For example, in movie recommendation scenarios, a large language model can generate descriptions of movie scenes, including genre, main actors, and plot, enabling the system to better recommend similar movies. Large language models can also generate recommendation reasons; for example, e-commerce websites can use large language models to generate reasons for recommending products, such as product quality, price, and features, allowing users to better understand the value of the product.

[0055] (4) Contract

[0056] A contract is generally an agreement established between natural persons, legal persons, or other organizations of equal status. Typically, a single contract may contain multiple documents, such as the signing agreement, special contract terms, general contract terms, technical standards, drawings, quotation sheets, supplementary agreements, etc.

[0057] (5) Framework agreement

[0058] A framework agreement refers to a contract entered into by both parties to a contract when they reach an intention on the transaction of the contract subject matter and determine the main contents, and the specific transaction details are further refined into a formal contract based on the framework contract. Each transaction realized during the contract effective period or the agreed period can be operated based on the framework agreement. Usually, a framework agreement may include multiple documents, such as an agreement signing document, an annex, a supplementary agreement or other terms agreements, etc. Usually, when many small repetitive transactions establish a long-term contract, a special contract mechanism is needed to cover such relationship and the needs of individual transactions, that is, a framework agreement. That is to say, the difference between a framework agreement and the aforementioned contract is that a framework agreement may include one or more contracts.

[0059] The method provided by this application can be used in various scenarios where document parsing is required, such as scenarios for document analysis in contracts or analysis of a large number of complex documents.

[0060] A contract is an application scenario of a document. A contract includes very important legal documents, which include a variety of detailed information and terms. Usually, for the documents in a contract, review is required. Conventional review operations require a large amount of manpower for reading and screening, etc. For example, taking a transaction contract as an example, usually contract interpretation, review of business trends, legal risks or financial risks, etc. are carried out. The traditional operation method is time-consuming and laborious, introduces a large number of operations, the process is cumbersome and complex, the efficiency of manual review is low, and there may be omissions in manual screening. Extending to other document review fields, such as data review fields, risk review fields, etc., there are similar problems. Therefore, the demand for intelligent processing of documents is increasing.

[0061] In some existing document retrieval scenarios, users need to gradually check the specific content of the required document from the file. For example, usually the required document of a user may be saved under a multi-layer folder directory. For example, a certain document is under a 5-layer folder directory. For example, the path of this document is expressed as: Area A<12<23<34<B, and B represents this document. If the user needs to open this document, they need to query the specific location where this document is located layer by layer from these 5 layers of directories. However, there may be multiple identifiers of the next-layer files, that is, entrances, under each layer of folder directory. For example, there may be 10 folder entrances under the Area A directory. Therefore, for the user, the workload of checking this document is very large, and the checking efficiency of this document is very low.

[0062] Therefore, this application provides a document navigation display method, which can more intuitively display the relationships between document sets, the relationships between document sets and documents, the relationships between documents, and document directories for users, so as to provide a more intuitive navigation method for users, enabling users to efficiently query the required content and improving the document checking efficiency of users.

[0063] First, the application architecture of the method provided in this application will be introduced.

[0064] The method provided in this application can be deployed in various computing devices, which can be standalone computing devices or server clusters, etc.

[0065] For example, the method provided in this application can be deployed in a server cluster to provide services to users via a client.

[0066] For example, one possible system architecture provided in this application may be as shown in Figure 1. As shown in Figure 1, the cloud service system 10 may include a data center 11, a cloud platform 12, and a client 13.

[0067] The cloud platform 12 may specifically include a server cluster or one or more servers, or the servers may be replaced by other devices with computing capabilities. Optionally, the cloud platform 12 can work with other devices, such as data storage, routers, load balancers, etc. The cloud platform 12 can use data in the data center 11 or call program code in the data center 11 to implement the method steps provided in the embodiments of this application.

[0068] Data center 11 can be used to store data for cloud platform 12 to query or write data. For example, in this embodiment, document data can be stored in data center 11. Specifically, data center 11 may include a data server deployed separately for storing data, or it may include storage media connected to cloud platform 12. The specific deployment form of data center 11 for storing data can be determined according to the actual application scenario.

[0069] The cloud platform 12 can interact with users as a client to provide services. Users can operate on the client 13 to exchange data with the cloud platform 12 or request services from the cloud platform 12. This client can be deployed on devices with displays, such as personal computers, computer workstations, smartphones, tablets, laptops, and smart cars.

[0070] In one implementation, the cloud platform 12 is used to implement the method provided in the embodiments of this application. The user can perform interactive operations with the cloud platform 12 on the client 13, such as performing selection operations on the identifier of the document collection or the identifier of the document mentioned in the following embodiments of this application, and transmit the data generated by the user's operation to the cloud platform. The cloud platform can then extract the corresponding information based on the user's operation and transmit it to the client 13 to update the display interface on the screen of the client 13.

[0071] The method flow provided in this application will be described below in conjunction with the aforementioned system architecture.

[0072] Referring to Figure 2, a flowchart of a document navigation display method provided in this application is shown below.

[0073] 201. Retrieve multiple related document collections and display the identifiers of these document collections.

[0074] The relationships between these multiple document collections can specifically include hierarchical relationships within the document collections, or relationships between document collections at the same level. For example, these multiple document collections may belong to the same business function, or they may belong to the same project.

[0075] The identifiers within these multiple document collections can include the name, ID, number, icon, or other identifiers for each document collection, and can be used to identify each document collection. The identifiers of these multiple document collections displayed in the interface can serve as entry points for users to expand the collection. Users can select any document's identifier to expand the information of the specific documents included in that collection.

[0076] The display methods for the identifiers of these multiple document collections can be varied, including listing them as a list or using a navigation tree. For example, a navigation tree can be used to display the multiple document collections, with the identifiers of the document collections as nodes in the navigation tree. The navigation tree is output based on the relationships between the document collections. For instance, the identifiers of document collections with a subordinate relationship can be used as parent and child nodes (or master and slave nodes), and document collections with a parallel relationship can be used as parallel nodes. This allows for a visual representation of the possible relationships between the document collections using a navigation tree.

[0077] In this embodiment, the identifiers of the multiple document collections with related relationships can be displayed in the interactive interface, allowing users to intuitively understand the relationships between the document collections. These identifiers can serve as entry points to expand specific documents within each document collection, enabling users to expand the document collection to which the content they wish to view belongs based on their actual needs.

[0078] This collection of documents can also be called files, folders, framework agreements, contracts, or other names, depending on the specific application scenario. For example, in one possible application scenario, a collection of documents could include a contract, and each contract could contain one or more documents.

[0079] Optionally, an artificial intelligence model can be used to identify multiple document sets with related relationships from files in a document library. For example, a document library typically contains a large number of documents. An artificial intelligence model, such as a large model or a pre-trained language model, can be used to identify multiple document sets with related relationships from the document library and output the identifiers of these document sets, such as the name, ID, or index of the document set. Each document set may include one or more documents. By leveraging the semantic understanding capabilities of the model, related document sets can be extracted from the document library and displayed to the user, thereby reducing the workload and time spent by the user in searching for document sets in the document library and improving the efficiency of the user's document browsing.

[0080] 202. In response to the user's selection operation of the identifier of the first document set among multiple document sets, obtain the multiple document identifiers included in the first document set, and display the relationship between the multiple document identifiers and the identifier of the first document set, as well as the relationship between the documents corresponding to the multiple document identifiers.

[0081] Based on the aforementioned identifiers of multiple document collections, users can select any one of the document collection identifiers to expand the content under the selected document collection. For example, when a user selects the identifier of the first document collection, in response to the user's selection of the identifier of the first document collection, the system can read the identifiers of the multiple documents included in the first document collection from the storage space storing the specific information of the first document collection, and display the relationship between the identifiers of the multiple documents and the first document collection, as well as the relationship between the multiple documents.

[0082] Specifically, the relationship between the multiple document identifiers and the identifiers of the first document set, as well as the relationship between the documents corresponding to the multiple document identifiers, can be displayed in either a list or a navigation tree format. For example, a navigation tree is used here, with the first document set as the root node, the document identifiers in the first document set as nodes in the navigation tree, the identifiers of documents with subordinate relationships as parent and child nodes (or master and child nodes) in the navigation tree, and nodes with parallel relationships or at the same level as parallel nodes. This allows for a more intuitive display of the relationships between documents within the document set using a navigation tree.

[0083] Optionally, in one possible scenario, based on the aforementioned navigation method for displaying multiple document collections with related relationships, if it is necessary to display the document identifiers under the first document collection using a navigation tree, then on the basis of the document collection navigation tree, nodes corresponding to the documents in the first document collection can be generated on the nodes corresponding to the first document collection. Alternatively, a new navigation tree can be generated with the first document collection as the root node. The specific method can be determined according to the actual application scenario, and this application does not limit it.

[0084] Therefore, in this embodiment, when a user expands any one of the multiple document collections, the system can respond to the user's operation by displaying the relationships between documents within that document collection and the relationships between documents. This allows the user to more intuitively understand the relationships between documents within that document collection, and then select the desired content based on the displayed relationships. This reduces the time spent searching for documents within a document collection and improves the efficiency of the user's document browsing.

[0085] Furthermore, when the aforementioned document set is a contract, the documents in the first document set may include documents under a single contract. Therefore, in this embodiment, the relationships between documents under a contract can be displayed, allowing users to more efficiently browse documents under a contract based on the displayed relationships.

[0086] 203. Respond to the user's operation on the identifier of the first document among multiple documents, obtain the first document according to the identifier of the first document, and display the table of contents of the first document.

[0087] Based on the above-mentioned relationship between multiple document identifiers and the first document set identifier, as well as the relationship between the documents corresponding to the multiple document identifiers, users can operate on the identifier of any document in the display interface. Taking the selection of the identifier of the first document as an example, the system can respond to the user's operation on the identifier of the first document, retrieve the first document according to the identifier of the first document, and display the table of contents of the first document.

[0088] Specifically, the directory can be a directory read from the first document, or it can be a directory generated based on the identified titles after the content of the first document is identified, thereby providing users with navigation to the content within the document through the directory.

[0089] Therefore, in this embodiment, based on user interaction, a collection of documents with related relationships, documents within the collection, the relationships between documents, and document content can be displayed. This eliminates the need for users to search for the collection of documents with related relationships, documents within the collection, the relationships between documents, and the documents themselves, thereby reducing the time required for users to browse documents and improving the efficiency of document browsing.

[0090] Furthermore, when displaying the table of contents of the first document, the content of the first document can also be displayed. For example, a separate document content display window can be set up in the display interface to show the document content to the user. After the user selects the identifier of a document, the content of that document will be displayed in this window, thus quickly displaying the document content that the user needs to view.

[0091] In one possible implementation, key information can be extracted from the first document based on user input, the paragraph containing the key information can be identified in the first document displayed in the display interface, and the table of contents corresponding to the key information can be identified in the table of contents of the first document. For example, the title of the paragraph covering the key information can be identified in the table of contents.

[0092] This key information can specifically be extracted from the first document according to preset rules or using a model (such as a large model or a pre-trained language model). Typically, this key information can include content that requires user review or pre-defined data types that users should focus on. For example, in a contract review scenario, this key information can include elements such as the signing parties, the subject matter, the amount, or the timeline in the contract agreement document. This displays the key information in the document that requires careful review, reducing the time users spend browsing through key information, improving the efficiency of their review, and preventing users from overlooking key information.

[0093] Furthermore, the user input that triggers the extraction of key information from the first document may specifically include the aforementioned selection operation of the first document, or it may include the operation in a separate key information display window.

[0094] For example, in one possible implementation, after a user selects a first document, the system can respond to this selection by retrieving the first document based on its identifier and displaying its table of contents. Simultaneously, it can extract key information from the first document's content and identify the paragraphs containing the key information in the displayed first document, as well as the corresponding table of contents. Therefore, after a user selects a document, the system can proactively display the key information within that document, thereby improving the efficiency of information retrieval from that document.

[0095] In another possible implementation, after the user selects a first document, in response to the user's selection, the first document can be retrieved based on its identifier. While displaying the table of contents of the first document, information on one or more key elements can be extracted from the first document. This extracted information, such as the name, ID, or brief description of the element, can be displayed in a separate window (referred to here as the key element display window). The user can select any key element to extract its key information. For example, if the user selects the identifier of the first element in the key element display window, in response to this selection, key information can be extracted from the first document. The paragraph containing the key information can be identified in the first document displayed on the interface, and the corresponding table of contents information can be identified in the first document's table of contents. Therefore, in this implementation, key elements in a document can be displayed separately to the user, allowing the user to more efficiently learn about the key elements included in the document. The user can also select the desired key elements from the displayed key elements, thereby identifying the information of the desired key elements (i.e., key information) in the document's content and table of contents, thus improving the efficiency of the user in obtaining key information and enhancing the overall document browsing efficiency.

[0096] In addition, to improve the efficiency of users in finding key information from the display interface, content in the first document that is not related to the key information can be collapsed. This allows users to find the key information more intuitively, avoids interference from irrelevant content, and improves the efficiency of users in finding key information.

[0097] Furthermore, to provide a more comprehensive display of document-related information, pre-defined directory information can be searched within the first document's table of contents, and the found information can be identified. For example, the table of contents can be used to search for directory information related to pre-defined data, such as the headings of paragraphs covering the main content or the headings of paragraphs requiring read permissions. This information can then be marked within the table of contents, such as by adding tags or highlighting it. This process effectively identifies the pre-defined data within the document, highlighting the corresponding directory headings and allowing users to more intuitively determine whether each directory is related to the pre-defined data, thus improving their efficiency in accessing relevant content.

[0098] The foregoing has introduced the method and flow provided in this application. To facilitate understanding, the document navigation display method provided in this application will be described in more detail below, with reference to specific example scenarios or GUIs.

[0099] For example, taking multiple contracts with related relationships and each contract containing one or more document parsing as an example, the architecture of the method provided in this application can be as shown in Figure 3. The method provided in this application can be divided into multiple stages based on user interaction operations, including multi-contract relationship modeling, single-contract document association modeling, document paragraph modeling, document element modeling, element mapping to document paragraphs and table of contents, folding irrelevant paragraphs, highlighting elements and paragraphs, and displaying tags, etc.

[0100] in:

[0101] Multi-contract relationship modeling: Modeling the relationships between multiple contracts, that is, constructing the relationships between contracts and outputting a navigation tree formed by the contracts. Typically, one contract corresponds to one node in the navigation tree.

[0102] Single contract document relationship modeling: This involves modeling the relationships between documents within a single contract. For example, it models the relationships between agreement documents, attachments, and other documents within a single contract. Specifically, after a user selects any node in the contract navigation tree in the client's display interface, the directory under that node can be expanded.

[0103] Document paragraph modeling: The document's table of contents can be extracted, and the titles in the table of contents can be mapped to the paragraph nodes in the document. This is equivalent to modeling the paragraph points in a single document and forming a table of contents that maps to the document's paragraph points.

[0104] Document element modeling: Extracting elements from a document to obtain the elements contained in the document, or extracting the relationships between elements, etc.

[0105] Feature mapping to document paragraphs and table of contents: After extracting features, features can be mapped to document paragraphs, and features can be mapped to table of contents titles.

[0106] Collapse irrelevant paragraphs: After a user selects an element, the content of the paragraphs containing that element can be displayed in the scrolling area of ​​the document. Other content in the document that is not related to the element can be collapsed, meaning that the content of paragraphs unrelated to the element will not be displayed.

[0107] Highlight elements and paragraphs: For the element selected by the user, you can display the paragraph containing the element or related content in the paragraph in the document paragraph, and the node related to the element in the navigation tree.

[0108] The following section will introduce each of the aforementioned stages in conjunction with the GUI.

[0109] I. Modeling Multiple Contractual Relationships

[0110] Among them, a contract is one implementation of the aforementioned document set. For example, a contract is a document set. Multiple contracts may have subordinate relationships or parallel relationships at the same level. The specific relationships between contracts can be extracted according to pre-set rules or identified using a large model.

[0111] For example, a large model can be used to extract specific information about each contract from a document library, such as whether there are relationships between contracts, and further, information such as contract name, number, identifier, or readability. For instance, contracts formed at different times within the same business can be considered related contracts, or contracts from different stages of the same project can be considered related contracts, or contracts involving the same entity can be considered related contracts. Furthermore, related contracts may also have subordinate or parallel relationships. For example, for a particular business, there may be one or more sub-businesses; the contracts corresponding to the sub-businesses may be subordinate contracts to the main business's main contract. Therefore, the large model's language understanding capabilities can be used to identify related contracts from the document library and output the relationships between them, thus enabling the construction of a contract navigation tree. This eliminates the need for users to manually mine the relationships between contracts, improving the efficiency of users finding the content they need.

[0112] During the contract navigation tree construction phase, when the identifiers of multiple related contracts are extracted, taking the contract name as an example, the contract navigation tree can be constructed based on these identifiers. For instance, the GUI display interface at this stage can be as shown in Figure 4. There may be contracts named Contract 1, Contract 2, Contract 3, Contract 4, or Contract 5, etc. These contracts may have subordinate relationships, hierarchical relationships, or no relationship. The contract navigation tree can be constructed based on the relationships between these five contracts. For example, Contract 1, Contract 2, Contract 3, Contract 4, and Contract 5 are contracts under the same business, such as the XX business shown in Figure 4, which serves as the root node for Contract 1, Contract 2, Contract 3, Contract 4, and Contract 5. Contract 1, Contract 2, Contract 4, and Contract 5 have a parallel relationship, that is, Contract 1, Contract 2, Contract 4, and Contract 5 are parallel nodes. Contract 2 and Contract 3 have a subordinate relationship, with Contract 3 being a subordinate node under Contract 2. The contract navigation tree is then rendered, and the rendered image of the contract navigation tree is displayed in the corresponding block of the display interface. Users can select any contract to scroll through the information under that contract on the screen, thus performing the steps in Phase Two below.

[0113] Therefore, in this embodiment, modeling can be performed based on the relationships between various contracts to generate a tree-structured navigation method, enabling users to read the required contract information more efficiently based on visualized contract relationships.

[0114] II. Single Contract Document Association Model

[0115] A single contract or framework agreement may include one or more documents, or the one or more documents may form a framework agreement or a contract.

[0116] For a single contract's documents, a document navigation tree can be constructed based on the relationships between multiple documents within that contract. For example, building upon Phase One, after a user selects a contract in the contract navigation tree displayed in the GUI, the system can respond to the user's actions on nodes within the GUI, extracting the contract's directory information, such as the names, IDs, or functional parameters of the documents under that contract. This directory information is then used to construct the document navigation tree. Specifically, each document under the contract can be treated as a node, and the relationships between nodes can be used to build a tree structure, generating the document navigation tree, which is then displayed on the interface.

[0117] For example, the GUI at this stage can be as shown in Figure 5. Taking the Hotel Individual Guest Cooperation Framework Agreement (MPA) as an example, after the user selects the node representing the MPA in the contract navigation tree, the user can read the directory information of the framework and generate a document navigation tree. Each node in the document navigation tree can represent a document. The node can be named according to the document name, a summary of the document's content, or the document number, etc., depending on the actual application scenario. Nodes and child nodes in the tree structure can be used to represent documents with subordinate relationships. For example, the main document can be represented as the main node, and subordinate documents can be represented as child nodes. For instance, document 1 is the main node (or parent node) of documents 2, 3, and 4, while documents 2, 3, and 4 are the subordinate nodes (or child nodes) of document 1. The user can select any node to extract the content and directory of the document corresponding to that node.

[0118] In this embodiment, the relationships between the various documents under the contract are modeled to form and display a navigation tree representing the relationships between the various documents under the contract. This allows users to more intuitively understand the specific documents under the contract and the relationships between the documents, so that users can further select the documents they need to view, thereby improving the efficiency of document review.

[0119] III. Document Paragraph Modeling

[0120] Building upon the document navigation tree displayed in Phase Two, responding to user actions on any document icon within the tree expands the selected document to display its content and corresponding table of contents. This table of contents can include multiple headings, each corresponding to a paragraph within the document. Users can select any heading from the table of contents to display the corresponding paragraph in the document content display window.

[0121] Specifically, the document's table of contents can include the table of contents carried within the document, or it can include a table of contents formed by extracting headings from the document's content using a large model. The table of contents is then displayed so that users can quickly jump to the corresponding paragraphs in the document based on it.

[0122] For example, in one possible implementation, the content of the document could be directly used as input to the large model. Leveraging the model's language understanding capabilities, titles could be extracted or summarized from the document content, and a table of contents could be generated based on the hierarchy of each title in the output title information. This allows for a more efficient and accurate output of the table of contents by utilizing the large model's language understanding capabilities.

[0123] For example, the GUI at this stage is shown in Figure 6. Taking the Hotel Individual Guest Cooperation Framework Agreement (MPA) as an example, after the user selects one of the documents in the MPA, the document's table of contents can be expanded. Specifically, the document's table of contents may include nodes such as 1. Preface, 2. Supplementary Agreements, and 3. Relationship with the Original Agreement. Under the Preface node, there are also sub-nodes such as 1.1 Parties to the Agreement, 1.2 Effective Date, and 1.3 Whereas, etc. For example, node "1. Preface" is the main node of nodes "1.1 Preface", "1.2 Effective Date", and "1.3 Whereas". Users can select various nodes in the document navigation tree to open the corresponding paragraphs. As shown in Figure 7, if the user selects "1.2 Effective Date", the content of the corresponding paragraph can be extracted and displayed in the display window. For example, the content of the "1.2 Effective Date" paragraph can be displayed, such as "This supplementary agreement shall come into effect on

[2023]

[0012] [1] ("Effective Date") after being signed by both parties. If the actual signing date is later than the agreed "Effective Date", both parties confirm that the validity of this agreement is retroactive to the agreed "Effective Date".

[0124] In this embodiment, paragraphs in a document can be modeled to form a navigation tree representing the relationship between paragraph points within the document. This provides users with a navigation method between paragraph points within the document, enabling users to use the navigation tree to more efficiently query the information they need and improve the efficiency of document review.

[0125] Under the aforementioned user interaction processes in stages one, two, and three—that is, in the process of hierarchically displaying related contracts, documents under contracts, the relationships between documents under contracts, and the table of contents under documents based on user interaction operations—users can intuitively understand the related contracts, documents under contracts, the relationships between documents under contracts, and the table of contents under documents based on the displayed content. This allows them to efficiently search for the documents they need, avoiding the need to search through the document library level by level, and greatly improving the efficiency of users searching for the documents they need.

[0126] Building upon the aforementioned display interface, further refinement can be achieved by extracting key information from the document and optimizing its display. For example, refer to stages four and five below, which further enrich the content displayed on the interface based on stages one through three. In other words, stages four and five can serve as supplementary optimizations to the display interfaces of stages one through three, making the content displayed richer and easier for users to access documents, thereby further improving the efficiency of document retrieval.

[0127] IV. Element Mapping Document Paragraphs and Table of Contents

[0128] As a further supplement to the aforementioned display of document content, in this embodiment of the application, key information can be further extracted from the document content for display.

[0129] As a type of key information, elements are used as an example in this embodiment of the application. For instance, an element may include content in a document that the user needs to focus on, and this element is displayed after extraction. Therefore, the display interface can highlight content that the user needs to focus on, allowing the user to more intuitively view the content they need, improving document review efficiency and preventing omissions. The specific process of stage four is described below.

[0130] First, the steps for element extraction will be introduced.

[0131] Elements can include fields or entities extracted from a document. Specifically, elements can be extracted according to pre-defined rules, pre-defined keywords, or a large model. For example, the content of a user-selected document can be used as input to a large model, outputting specific information about one or more elements, thus allowing the large model to extract elements. Specifically, the large model can output the element names, element titles, or content from paragraphs containing elements extracted from the document content.

[0132] For example, in a contract review scenario, the elements requiring user review may include terms, information about Party A, information about Party B, information about the subject matter, price or remuneration, liability for breach of contract, dispute resolution methods, signing date, or attachments. Correspondingly, when extracting elements, keyword extraction or identification can be performed based on the elements requiring user review, thereby extracting elements that meet the user's review needs. This allows the user to intuitively understand the information of the elements, improving review efficiency. That is, the aforementioned elements requiring user review can be used as the elements to be extracted in this application embodiment. Content from paragraphs containing these elements is extracted from the document content and displayed on the display interface. For example, relevant content from paragraphs containing information such as terms, information about Party A, information about Party B, information about the subject matter, price or remuneration, liability for breach of contract, dispute resolution methods, signing date, or attachments can be extracted from the document and displayed on the display interface. For instance, an element display block can be set up on the display screen, displaying the specific content of the extracted elements in this independent block, allowing the user to more intuitively read the key content requiring review.

[0133] For example, the titles in a document can typically summarize the content of one or more paragraphs. Titles that conform to a predefined type can be used as element titles, such as titles that include contract review elements. This allows for the extraction and output of elements that require user review, and the display interface can be set to show these elements in blocks.

[0134] For example, the data included in the document can be input into a large model. Utilizing the large model's language understanding capabilities, information corresponding to the elements can be extracted and output from the document's data, such as element names and specific content. Blocks can then be set up in the display interface to show the information corresponding to the elements. Therefore, in this embodiment, the language understanding capabilities of the large model can be used to more accurately identify element information, thereby displaying key information in the document and improving user review efficiency.

[0135] For example, a GUI containing elements can be shown in Figure 8. Elements and their corresponding information can be displayed in a separate block on the right side of the display interface. For instance, the extracted elements can be displayed in a block titled "Key Information and Structured Result of Clauses." This could include displaying the element name and the information extracted from the document, i.e., the extracted values ​​output in Figure 8.

[0136] For example, taking one of the elements in Figure 8 as an example, the element name can be a summary output using the large model, such as: "Element Name: Effective Date". The content extracted from the document content corresponding to this element can include "Extracted Value: This supplementary agreement shall take effect on December 1, 2023 ("Effective Date") after being signed by both parties...". Therefore, users can intuitively know the effective date of the supplementary agreement through this element.

[0137] For example, taking another element in Figure 8 as an example, the element name can be represented as "Change Journey:", which indicates the time node of the agreement change. The corresponding content extracted from the document content can include:

[0138] 2022 / 12 / 01

[0139] 2022 / 11 / 01

[0140] This is a long journey of changes...

[0141] Therefore, users can intuitively learn about the timeline of changes to the corresponding agreement through this element, thereby promptly knowing the changes in the elements in the document and conducting a more comprehensive review of the document content.

[0142] Therefore, in this embodiment, elements can be extracted from the document and the information of the extracted elements can be displayed to the user, so that the user can browse the elements and their corresponding information more conveniently and intuitively. On the basis of improving the efficiency of the user's document review, this further improves the comprehensiveness of the user's review of the document content and enhances the user experience.

[0143] Secondly, the process of reverse mapping elements to document content and document directory is introduced.

[0144] After extracting the feature information, in addition to displaying the extracted feature information in a separate block, the features can also be mapped to documents and document directories.

[0145] Specifically, it can identify the paragraphs in the document that correspond to the elements, as well as the nodes in the navigation tree that contain the elements.

[0146] For example, the information of an element can include the object and the information corresponding to the object. The object can be mapped to paragraphs in the document; for instance, identifying a paragraph in the document that includes the object and using that paragraph as the corresponding element. Similarly, to facilitate scrolling through the display area, elements can be mapped to nodes in the table of contents; for example, the node corresponding to the paragraph containing the element can be used as the corresponding node for the element.

[0147] When a user selects any element, the system responds to the user's action on that element in the GUI by scrolling the content in the display window to the paragraph corresponding to that element and the corresponding node in the document navigation tree. For example, as shown in Figure 9, after the user selects the area containing the element named "Effective Date," the system scrolls from the current content to the paragraph content corresponding to the selected element in the document content display block. As shown in the marker box 10 in Figure 9, this represents the document content corresponding to the "Effective Date" element. In the document's table of contents display block, the system scrolls from the current node to the node corresponding to the element. As shown in the marker box 11 in Figure 9, this includes the table of contents title of the paragraph node covering the content of the "Effective Date" element, namely "1.2 Effective Date."

[0148] In this embodiment, elements are mapped to paragraphs and the document navigation tree. This allows users to scroll through the document content display area when an element is selected, from the currently displayed content to the paragraph content corresponding to the element in the document. At the same time, the node corresponding to the paragraph containing the element content is also displayed. This makes it easier for users to view the specific content corresponding to the elements in the document, thereby improving the efficiency of element review.

[0149] V. Collapse irrelevant paragraphs, highlight elements and paragraphs, and display tags.

[0150] To further improve users' reading efficiency of document elements, the highlighted elements in the display interface, along with their corresponding content and headings in the table of contents, can be identified. This involves marking the document content and table of contents corresponding to key information and collapsing irrelevant paragraphs. In other words, to improve users' efficiency in reviewing document content, the content displayed in the interface can be further optimized, highlighting the content that users need to focus on and de-emphasizing content irrelevant to the review. This will make users more attentive to the content requiring review, increasing their focus and thus improving the efficiency of document review.

[0151] After back-mapping elements to documents and document directories, paragraphs within the corresponding documents and nodes in the document navigation tree can be highlighted. Specific highlighting methods include bolding, using prominent colors, or a combination of these, making the paragraphs and nodes in the document navigation tree corresponding to the highlighted elements more eye-catching. This allows users to view element-related information more intuitively, improving the efficiency of element review.

[0152] For example, a GUI that highlights element-related information can be shown in Figure 10. It can highlight paragraphs in the document that contain elements, describe elements, or are related to elements, and highlight nodes in the navigation tree that correspond to paragraphs containing elements, paragraphs describing elements, or paragraphs related to elements, thereby highlighting element-related content.

[0153] Furthermore, for content or titles with special attributes, tags can be added to display these attributes. Document attribute information can be read, including whether the document is viewable, whether it is download-only, whether it contains entity-related information, or other attributes that require user notification. Corresponding tags can be generated for these attributes and displayed in the corresponding nodes of the contract navigation tree, document navigation tree, or document directory.

[0154] For example, as shown in Figure 11, taking a music cooperation agreement as an example, the paragraphs in this music cooperation agreement contain various attributes that need to be reminded to the user. For example, labels are added to the "Booking Method" node, "Payment Method" node, "Cancellation or Reduction Terms" node, and "Other Obligations" node. These labels remind the user that the node may contain content that the user needs to pay attention to. For example, in the "Booking Method" node, the label contains information such as "Payment Entity" or "Tax Rate" so that the user can notice these attributes in a timely manner, improving the accuracy and efficiency of the user's review of the content.

[0155] Therefore, in this application's implementation, the interface displays information about the relationships between contracts, the relationships between documents under a contract, the table of contents within a document, and the information of key elements. Corresponding navigation methods are generated and displayed for each part of the content under each contract, allowing users to quickly find the entry point for the content they need, thus navigating to the specific paragraph containing the information they require more quickly and efficiently. Furthermore, the method provided in this application also displays elements and related information, allowing for the separate display of key information in some documents, such as elements in a contract that require user review. This enables users to more conveniently access key information and improves the efficiency of document review.

[0156] The foregoing has described the method flow and GUI provided in this application. The following section describes the structure of the document navigation system provided in this application.

[0157] Referring to Figure 12, which is a schematic diagram of the architecture of a document navigation system provided in this application, the document navigation system may specifically include:

[0158] A computing device 121 and a display screen 122, wherein the computing device is connected to the display screen;

[0159] The display screen can be used to display content according to the instructions of the computing device 121;

[0160] The computing device 121 can be used to execute the processing steps of the methods corresponding to Figures 2 to 11, and the display screen 122 can be used to display the content displayed in the display steps of the methods corresponding to Figures 2 to 11. For example, the computing device can be the cloud platform in Figure 1, and the display screen can be the display screen in the device deployed by the client.

[0161] Specifically, the computing device 121 is used to perform the following steps:

[0162] Retrieve multiple related document collections and display the identifiers of the multiple document collections on display screen 122;

[0163] In response to the user's selection operation of the identifier of the first document set among multiple document sets, the identifiers of the documents included in the first document set are obtained, and the relationship between the multiple document identifiers and the identifier of the first document set, as well as the relationship between the documents corresponding to the multiple document identifiers, are displayed on the display screen 122.

[0164] In response to a user's operation to identify the first document among multiple documents, the system retrieves the first document based on its identifier and displays a table of contents of the first document on the display screen 122.

[0165] In one possible implementation, the aforementioned computing device 121 is also used to: identify multiple document sets from files in a file library using an artificial intelligence model.

[0166] In one possible implementation, the aforementioned multiple document sets are multiple related contracts, and the documents included in the first document set are the documents included in a single contract.

[0167] In one possible implementation, the aforementioned computing device 121 is further configured to: extract key information based on user input; identify the paragraph containing the key information in the document; and identify the directory information of the content corresponding to the key information in the table of contents displayed on the display screen 122.

[0168] In one possible implementation, the aforementioned computing device 121 is also used to: fold content in a document that is not related to key information.

[0169] In one possible implementation, the aforementioned computing device 121 is further configured to: search for preset directory information in the directory of the first document; and identify the searched directory information.

[0170] This application also provides a chip system including a processor and a power supply circuit. The power supply circuit supplies power to the processor, which executes the processing steps corresponding to the method provided in this application. For brevity, further details are omitted here. The processor can be implemented using a GPU, or it can be implemented using computing devices such as a DPU, NPU, XPU, SoC, offload card, or accelerator card.

[0171] This application also provides a computing device 100. As shown in FIG13, the computing device 100 includes: a bus 102, a processor 104, a memory 106, and a communication interface 108. The processor 104, the memory 106, and the communication interface 108 communicate with each other via the bus 102. The computing device 100 may be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device 100.

[0172] Bus 102 can be a Peripheral Component Interconnect Express (PCIe) bus, an Extended Industry Standard Architecture (EISA) bus, a Unified Bus (Ubus or UB), a Compute Express Link (CXL), a Cache Coherent Interconnect for Accelerators (CCIX), etc. The Unified Bus is also known as the Lingqu Bus. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one line is used in Figure 13, but this does not imply that there is only one bus or one type of bus. Bus 104 can include pathways for transmitting information between various components of the computing device 100 (e.g., memory 106, processor 104, communication interface 108). The Unified Bus can also be referred to as the Lingqu Bus.

[0173] The processor 104 may include any one or more of the following computing devices: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP) or digital signal processor (DSP), ASIC, FPGA, CPLD, NPU, SoC, offload card, accelerator card, etc.

[0174] Memory 106 may include volatile memory, such as random access memory (RAM). Processor 104 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD). Furthermore, memory 106 may also be implemented using storage class memory (SCM), phase change memory (PCM), or other types of storage media.

[0175] It is worth noting that the same type of storage medium can be configured in the same computing device to realize the function of memory 106, or two or more types of storage media can be configured to realize the function of memory 106. This application does not limit this.

[0176] The memory 106 stores executable program code, and the processor 104 executes the executable program code to implement the functions of the computing device mentioned in FIG12, thereby implementing the processing steps in the method provided in this application. That is, the memory 106 stores instructions for executing the method provided in this application.

[0177] Alternatively, the memory 106 may store executable code, which the processor 104 executes to implement the functions of the computing device, etc., thereby implementing the method provided in this application. That is, the memory 106 stores instructions for executing the method provided in this application.

[0178] The communication interface 108 uses transceiver modules such as, but not limited to, network interface cards and transceivers to enable communication between the computing device 100 and other devices or communication networks.

[0179] As one possible implementation, the computing device 100 may also include a chip system, which includes a processor and a power supply circuit. The power supply circuit supplies power to the processor, and the processor executes the operation steps corresponding to the method provided in this application. For simplicity, further details are omitted here. The processor can be implemented using a GPU, or it can be implemented using computing devices or AI chips such as a DPU, NPU, XPU, SoC, offload card, or accelerator card.

[0180] As one possible implementation, the computing device 100 may include various types of processors 104, meaning the computing device 100 is a heterogeneous device. For example, the computing device 100 may include a CPU and a GPU, and at least one of the processors 104 may execute the operation steps corresponding to the method provided in this application. For the sake of brevity, further details are omitted here.

[0181] This application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0182] As shown in Figure 14, the computing device cluster includes at least one computing device 100. The memory 106 of one or more computing devices 100 in the computing device cluster may store the same instructions for executing the methods provided in this application.

[0183] In some possible implementations, the memory 106 of one or more computing devices 100 in the computing device cluster may also store partial instructions for executing the methods provided in this application. In other words, a combination of one or more computing devices 100 can jointly execute the instructions for executing the methods provided in this application.

[0184] It should be noted that the memory 106 in different computing devices 100 within the computing device cluster can store different instructions, each used to execute a portion of the document navigation system's functions. That is, the instructions stored in the memory 106 of different computing devices 100 can implement the functions of different processing steps executed by the aforementioned computing devices.

[0185] In some possible implementations, one or more computing devices in a computing device cluster can be connected via a network. This network can be a wide area network (WAN) or a local area network (LAN), etc. Figure 15 illustrates one possible implementation. As shown in Figure 15, two computing devices 100A and 100B are connected via a network. Specifically, they are connected to the network through communication interfaces in each computing device. In this type of possible implementation, the memory 106 in computing device 100A stores instructions for performing a portion of the computing device's functions. Simultaneously, the memory 106 in computing device 100B stores instructions for performing another portion of the computing device's functions, thus enabling computing devices 100A and 100B to jointly implement the aforementioned computing device functions.

[0186] It should be understood that the functions of computing device 100A shown in Figure 15 can also be performed by multiple computing devices 100. Similarly, the functions of computing device 100B can also be performed by multiple computing devices 100.

[0187] The connection method between the computing device clusters shown in Figure 15 can be based on the fact that the method provided in this application requires a large amount of computing power, needs to achieve load balancing, or requires a large amount of data storage. Therefore, different modules are deployed in different computing devices. For example, the implementation of some functions of the computing device is handled by computing device 100A, and the implementation of other functions is handled by computing device 100B.

[0188] This application also provides another computing device cluster. The connection relationship between the computing devices in this computing device cluster can be similarly referred to the connection method of the computing device cluster described in Figures 14 and 15. The difference is that the memory 106 of one or more computing devices 100 in this computing device cluster can store the same instructions for executing the method provided in this application.

[0189] In some possible implementations, the memory 106 of one or more computing devices 100 in the computing device cluster may also store partial instructions for executing the methods provided in this application. In other words, a combination of one or more computing devices 100 can jointly execute the instructions for executing the methods provided in this application.

[0190] It should be noted that the memory 106 in different computing devices 100 within the computing device cluster can store different instructions for executing some functions of the document navigation system provided in this application. That is, the instructions stored in the memory 106 of different computing devices 100 can implement the functions described above for the computing devices.

[0191] This application also provides a computer program product containing instructions. The computer program product may be a software or program product containing instructions, capable of running on a computing device or stored on any usable medium. When the computer program product is run on at least one computing device, it causes the at least one computing device to perform the method provided in this application.

[0192] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium capable of being stored by a computing device, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct a computing device to perform the method provided in this application.

[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A document navigation display method, characterized in that, include: Retrieve multiple related document collections and display the identifiers of the multiple document collections; In response to the user's selection operation of the identifier of the first document set among the plurality of document sets, the identifiers of the plurality of documents included in the first document set are obtained, and the relationship between the identifiers of the plurality of documents and the identifier of the first document set, as well as the relationship between the plurality of documents, are displayed. In response to a user's operation on the identifier of a first document among the plurality of documents, the system retrieves the first document based on the identifier and displays a table of contents of the first document.

2. The method according to claim 1, characterized in that, The method further includes: The multiple document sets are identified from the files in the document library using an artificial intelligence model.

3. The method according to claim 1 or 2, characterized in that, The multiple document sets are multiple contracts that are related, and the documents included in the first document set are the documents included in a single contract.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Extract key information based on user input; The paragraph containing the key information is identified in the first document, and the directory information of the content corresponding to the key information is identified in the directory.

5. The method according to claim 4, characterized in that, The method further includes: Fold content in the first document that is not related to the key information.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Search for the preset directory information in the directory of the first document; Identify the directory information being searched.

7. A document navigation system, characterized in that, include: A computing device and a display screen, wherein the computing device is connected to the display screen; wherein... The display screen is used to display content according to the instructions of the computing device; The computing device is used to perform the following steps: Retrieve multiple related document collections and display the identifiers of the multiple document collections on the display screen; In response to a user's selection operation of the identifier of the first document set among the plurality of document sets, the identifiers of the documents included in the first document set are obtained, and the relationship between the plurality of document identifiers and the identifier of the first document set, as well as the relationship between the documents corresponding to the plurality of document identifiers, are displayed on the display screen; In response to a user's operation on the identifier of a first document among the plurality of documents, the system retrieves the first document based on the identifier and displays a table of contents of the first document on the display screen.

8. The system according to claim 7, characterized in that, The computing device is also used for: The multiple document sets are identified from the files in the document library using an artificial intelligence model.

9. The system according to claim 7 or 8, characterized in that, The multiple document sets are multiple contracts that are related, and the documents included in the first document set are the documents included in a single contract.

10. The system according to any one of claims 7-9, characterized in that, The computing device is also used for: Extract key information based on user input; The document identifies the paragraph containing the key information, and the directory information displayed on the screen identifies the content corresponding to the key information.

11. The system according to any one of claims 7-10, characterized in that, The computing device is also used for: Fold content in the document that is not related to the key information.

12. The system according to any one of claims 7-11, characterized in that, The computing device is also used for: Search for the preset directory information in the directory of the first document; Identify the directory information being searched.

13. A computing device, characterized in that, The computing device includes a processor and memory; The processor is configured to execute instructions stored in the memory to cause the computing device to perform the processing steps of the method as described in any one of claims 1 to 6.

14. A computing device cluster, characterized in that, It includes at least one computing device, each computing device including a processor and memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device to cause the cluster of computing devices to perform the processing steps of the method as described in any one of claims 1 to 6.

15. A computer program product containing instructions, characterized in that, When the instruction is executed by the computing device cluster, the computing device cluster causes the computing device cluster to perform the processing steps of the method as described in any one of claims 1 to 6.

16. A computer-readable storage medium, characterized in that, It includes computer program instructions, which, when executed by a cluster of computing devices, perform the processing steps of the method as described in any one of claims 1 to 6.

Images