Information generation method and apparatus, and electronic device and computer-readable medium

Abstract

The present disclosure relates to the technical field of artificial intelligence, specifically the technical fields such as natural language processing, computer vision and deep learning. Provided are an information generation method and apparatus. The specific implementation solution comprises: acquiring a selected file obtained after a user has selected at least one type of file; in response to detecting that there is a graph carrier document on a current display interface, acquiring operation information of the user on the selected file in real time; on the basis of the operation information, determining a falling position of the selected file relative to a file upload hotspot, wherein the file upload hotspot is an area where the graph carrier document is displayed; and on the basis of the falling position and the selected file, optimizing the graph carrier document to obtain an optimized graph carrier document. The embodiment improves user experience.

Description

Information generation method and device, electronic device, and computer-readable medium

[0001] Cross-references

[0002] This patent application claims priority to the Chinese patent application filed on February 21, 2024, with application number 202410193556.0 and invention name “Information generation method and device, electronic device, computer-readable medium”, the full text of which is incorporated by reference into this application. Technical Field

[0003] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as natural language processing, computer vision, and deep learning, and in particular to an information generation method and device, an electronic device, a computer-readable medium, and a computer program product. Background Art

[0004] For information collection and organization in daily life, study, and work, a wide variety of information carriers are currently available, including Word, Excel, PDF (Portable Document Format), PPT (Microsoft Office PowerPoint), TXT (text files), and other file formats. Currently, when acquiring information, users must manually organize files, reading through different files and spending considerable time manually deduplicating and merging information. They also need to analyze the relationships between different elements and between elements and the overall picture to ultimately identify the desired information. This process is extremely time-consuming and labor-intensive, and can easily lead to information omissions.

[0005] Summary of the Invention

[0006] Provided are an information generation method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

[0007] According to a first aspect, an information generation method is provided, which includes: obtaining a selected file after a user selects at least one type of file; in response to detecting that there is a graph carrier document on the current display interface, obtaining the user's operation information on the selected file in real time; based on the operation information, determining the falling position of the selected file relative to the file upload hot zone, the file upload hot zone is the area where the graph carrier document is displayed; based on the falling position and the selected file, optimizing the graph carrier document to obtain an optimized graph carrier document.

[0008] According to the second aspect, an information generating device is provided, which includes: a file acquisition unit, configured to acquire a selected file after a user selects at least one type of file; an information acquisition unit, configured to acquire the user's operation information on the selected file in real time in response to detecting that there is a graph carrier document on the current display interface; a determination unit, configured to determine the falling position of the selected file relative to the file upload hot zone based on the operation information, and the file upload hot zone is the area where the graph carrier document is displayed; an optimization unit, configured to optimize the graph carrier document based on the falling position and the selected file to obtain an optimized graph carrier document.

[0009] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any implementation manner of the first aspect.

[0010] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method as described in any implementation of the first aspect.

[0011] According to a fifth aspect, a computer program product is provided, comprising a computer program, which implements the method described in any implementation manner of the first aspect when executed by a processor.

[0012] The information generation method and device provided by the embodiments of the present disclosure first obtain the selected file after the user selects at least one type of file; secondly, in response to detecting that there is a graph carrier document on the current display interface, the user's operation information on the selected file is obtained in real time; thirdly, based on the operation information, the falling position of the selected file relative to the file upload hot zone is determined, and the file upload hot zone is the area where the graph carrier document is displayed; finally, based on the falling position and the selected file, the graph carrier document is optimized to obtain the optimized graph carrier document. Thus, by selecting the falling position of the file relative to the file upload hot zone and selecting the file, the pre-generated graph carrier document is optimized, thereby summarizing the information of multiple types of files, improving the richness of the optimized graph carrier document, and ensuring the comprehensiveness of the generation of the graph carrier document information.

[0013] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0015] FIG1 is a flow chart of an embodiment of a method for generating information according to the present disclosure;

[0016] FIG2 is a schematic diagram of a structure of a graph carrier document generated by the present disclosure;

[0017] FIG3 a is a schematic diagram of a structure of a selection file associated with a display node according to the present disclosure;

[0018] FIG3 b is another schematic diagram showing the structure of a selection file associated with a display node according to the present disclosure;

[0019] FIG4 is a schematic structural diagram of an embodiment of an information generating device according to the present disclosure;

[0020] FIG5 is a block diagram of an electronic device for implementing the information generating method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0022] In this embodiment, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0023] For information collection and organization scenarios in daily life, study, and work, there is currently no one-stop information extraction method that merges the contents of multiple files across file types, and intelligently optimizes mind maps, flow charts, document summaries, or PPTs. Traditional technologies require users to manually manage different file materials and extract and organize information by manually reading, comparing, merging, and sorting different file types. This operation is time-consuming and labor-intensive, and can easily lead to omissions of key information.

[0024] To address the problem of poor user experience in traditional technologies, the present disclosure provides an information generation method. FIG1 shows a process 100 according to an embodiment of the information generation method of the present disclosure. The information generation method includes the following steps:

[0025] Step 101: Obtain a selected file after the user selects at least one type of file.

[0026] In this embodiment, the execution subject on which the information generation method runs can monitor the file display area on the display interface, wherein the file, determine the user's selection operation (such as clicking or selecting) on ​​at least one type of file in the file display area, and determine the selected file based on the selection operation. The selected file can be a single type of file or multiple types of files. The selected file can be a single file or multiple files.

[0027] In this embodiment, the user uploads at least one file of different types, such as Word, Excel, PDF, PPT or TXT, to the file display area; then checks multiple files that need to be merged to obtain selected files.

[0028] Alternatively, in addition to the aforementioned method for obtaining selected files, the information generation method and its execution entity can also support users inserting links to online public documents in the library to participate in multi-file merging. After the user adds the public document link to the merged multi-file, the execution entity will first parse and extract the information content in the link, and then aggregate all the information to be merged to obtain the selected file.

[0029] Step 102: In response to detecting that there is a graph carrier document on the current display interface, obtaining user operation information on the selected file in real time.

[0030] In this embodiment, the graph carrier document is a document related to the knowledge graph and is also a graph carrier document. The current display interface is used to display the content of the graph carrier document. Specifically, the graph carrier document includes: mind map, flow chart, document summary or PPT, etc.

[0031] In this embodiment, the operation information includes: a drag operation, a release operation, and a release area corresponding to the release operation. The above step 102 includes: in response to detecting that there is a map carrier document on the current display interface, detecting whether the operation information contains a drag operation for selecting a file; in response to the operation information containing a drag operation, detecting whether there is a release operation after the drag operation; in response to detecting a release operation after the drag operation, determining the release area corresponding to the release operation.

[0032] Step 103: Based on the operation information, determine the location of the selected file relative to the file upload hot zone.

[0033] In this embodiment, the file upload hot zone is the area where the atlas carrier document is displayed.

[0034] In this embodiment, the above-mentioned operation information includes: the release area of ​​the file selected when operating to select a file, and the above-mentioned step 103 includes: detecting whether the release area is located in the file upload hot area; in response to the release area being located in the file upload hot area, determining that the falling position of the selected file relative to the file upload hot area is within the file upload hot area.

[0035] The above step 103 may further include: in response to the release area not being located in the file upload hot zone, determining that the falling position of the selected file relative to the file upload hot zone is not within the file upload hot zone.

[0036] Step 104: Optimize the atlas carrier document based on the falling position and the selected file to obtain an optimized atlas carrier document.

[0037] In this embodiment, the above step 104 includes: in response to the falling position being within the file upload hot zone, node information of the selected file is extracted, and the nodes or node information related to the graph carrier document in the extracted information are added to the graph carrier document to obtain an optimized graph carrier document.

[0038] The information generation method provided by the embodiment of the present disclosure first obtains the selected file after the user selects at least one type of file; secondly, in response to detecting that there is a graph carrier document on the current display interface, the user's operation information on the selected file is obtained in real time; thirdly, based on the operation information, the falling position of the selected file relative to the file upload hot zone is determined, and the file upload hot zone is the area where the graph carrier document is displayed; finally, based on the falling position and the selected file, the graph carrier document is optimized to obtain the optimized graph carrier document. Thus, by selecting the falling position of the file relative to the file upload hot zone and selecting the file, the pre-generated graph carrier document is optimized, thereby summarizing the information of multiple types of files, improving the richness of the optimized graph carrier document, and ensuring the comprehensiveness of the generation of the graph carrier document information.

[0039] In some embodiments of the present disclosure, the above-mentioned information generation method also includes: in response to detecting that there is no graph carrier document on the current display interface, generating a file upload hot zone on the current display interface; obtaining the user's operation information on the selected file in real time; based on the operation information, determining the falling area of ​​the selected file relative to the file upload hot zone; in response to detecting that the falling area matches the area where the file upload hot zone is located, generating a graph carrier document based on the selected file; and displaying the graph carrier document in the file upload hot zone.

[0040] In this embodiment, the file upload hot zone is the area for displaying the graph carrier document. The execution entity on which the information generation method runs extracts information, merges, and generates document format for the selected file to obtain the graph carrier document, and displays the graph carrier document in the file upload hot zone.

[0041] In this embodiment, the operation information includes: selecting the falling area of ​​the file, comparing the falling area of ​​the selected file with the area where the file upload hot zone is located, and when the falling area of ​​the selected file overlaps with the area where the file upload hot zone is located, determining that the falling area matches the area where the file upload hot zone is located. At this time, it is determined that the user expects to place the selected file into the file upload hot zone, thereby generating a map carrier document.

[0042] The information generation method provided by the present disclosure generates a file upload hot zone on the current display interface when the current display interface does not have a graph carrier document. When it is determined through the user's operation information that the falling area corresponding to the selected file matches the file upload hot zone, the graph carrier document is generated and displayed based on the selected file, thereby realizing content analysis and merging of different types of files, and finally intelligently generating a graph carrier document from the analyzed and summarized information, providing a reliable implementation method for the generation of graph carrier documents.

[0043] Optionally, in some embodiments of the present disclosure, the above-mentioned information generation method further includes: associating each node in the graph carrier document with a selection file, and displaying the selection file associated with the node when operating the information source tracking tag for the node.

[0044] Optionally, in some embodiments of the present disclosure, the above-mentioned information generation method also includes: when the user operates the intelligent recommendation tag of the node's information, displaying a search information box to the user; and obtaining the user's to-be-queried information through the search information box, searching for search results from all types of files based on the to-be-queried information, and displaying the search results.

[0045] Optionally, in some embodiments of the present disclosure, the above-mentioned information generation method also includes: displaying a search information box to the user when the user performs a real-time online search on the node; and obtaining the user's online query information through the search information box, searching the Internet for online results based on the online query information, and displaying the online results.

[0046] In some embodiments of the present disclosure, in response to detecting that the fallen area matches the area where the file upload hot zone is located, generating a graph carrier document based on the selected file includes: in response to detecting that the fallen area matches the area where the file upload hot zone is located, inputting the selected file and the carrier guide word into the large language model to obtain the graph carrier document output by the large language model.

[0047] In this optional implementation, the carrier guide word is a guide word generated for the large language model to inform the large language model to generate a graph carrier document. Optionally, the carrier guide word can be generated based on user needs. For example, when the user needs to generate a mind map, a carrier guide word can be generated to inform the large language model to generate a mind map.

[0048] In this optional implementation, the carrier guide words include: words that preset the identity role of the large language model (such as a senior text research expert with strong knowledge acquisition and integration capabilities), and task goal description words, among which the task goal description words are used to propose requirements such as information retention, overlap, relevance, structured output, and logical rigor for document merging for the large language model.

[0049] In this optional implementation, after the large language model obtains the carrier guide word, it analyzes the selected file according to the instruction of the carrier guide word, determines and generates the atlas carrier document guided by the carrier guide word.

[0050] The method for obtaining a graph carrier document provided in this embodiment obtains a graph carrier document by selecting files, carrier guide words and a large language model, thereby improving the stability of the generation of the graph carrier document.

[0051] Optionally, in response to detecting that the fallen area matches the area where the file upload hot zone is located, before generating the atlas carrier document based on the selected file, the above information generation method also includes: performing data preprocessing on the selected file, wherein the data preprocessing includes: extracting file information to be merged in the selected file; removing illegal character strings and meaningless characters in the extracted information and merging them into the same document format, such as markdown (a lightweight markup language).

[0052] Optionally, in response to detecting that the fallen area matches the area where the file upload hot zone is located, generating a graph carrier document based on the selected file includes: in response to detecting that the fallen area matches the area where the file upload hot zone is located, extracting the nodes of the image carrier document and the relationship information between the nodes of the selected file, combining the extracted nodes and relationship information according to the format of the graph carrier document to obtain the graph carrier document.

[0053] In some optional implementations of the present disclosure, in response to detecting that the fallen area matches the area where the file upload hot zone is located, generating a graph carrier document based on the selected file includes: in response to detecting that the fallen area matches the area where the file upload hot zone is located, inputting the selected file and the graph guide word into the large language model to obtain the knowledge graph output by the large language model; obtaining the carrier demand information input by the user; and generating the graph carrier document based on the knowledge graph and the carrier demand information.

[0054] In this optional implementation, the execution subject on which the information generation method runs calls the large language model to perform information analysis and knowledge extraction on the content of the selected file, remove duplicates and merge them into a unified information set (such as H in Figure 2); the large language model extracts the association logic between different entity elements in the information set (such as T in Figure 2), and reorganizes the information set in a systematic way (such as Z in Figure 2). Among them, organizing the information set in a systematic way includes: making the large language model determine whether there is a logical conflict. If so, making the large language model evaluate the information reliability, authenticity, logical rigor, etc. When there is a significant difference in the scores, the information with a high score is selected and the information with a low score is deleted; if there is no significant difference in the scores, the large language model evaluates the overall quality score of the original file corresponding to the information source and selects the one with a high score.

[0055] In this embodiment, when the association logic for different file information items is inconsistent, the large language model scores their credibility and quality, ultimately selecting the one with the higher score. The large language model's scoring is primarily based on its existing knowledge base. Specifically, the large language model's scoring process involves first determining whether the information is time-sensitive. If so, it utilizes some online real-time search capabilities. If not, it makes a judgment based on the large language model's knowledge base.

[0056] The logic for extracting associations between different entity elements in the information set involves extracting entities, attributes, and relationships from the information set, organizing these knowledge elements, and gradually abstracting them into concepts to form a model layer. The system then conducts a quality assessment of the integrated knowledge (some of which requires manual screening), ultimately adding qualified content to the knowledge graph.

[0057] After the above information processing, the large language model can intelligently generate different types of graph carrier documents based on the knowledge graph and carrier demand information.

[0058] In this optional implementation, the carrier requirement information is information related to the graph carrier document. The type of the graph carrier document can be determined through the carrier requirement information. For example, if the carrier requirement information requires that the graph carrier document be generated as a mind map, then the carrier requirement information is information instructing the generation of a mind map. For another example, if the carrier requirement information requires that a flowchart be generated, then the carrier requirement information is information instructing the generation of a flowchart.

[0059] As shown in Figure 2, based on the large language model, all file contents of the selected file X are understood and analyzed, and the data is intelligently organized to generate a knowledge graph S of multiple file information sets, and a mind map, flow chart, document summary or PPT is intelligently generated.

[0060] The method for generating a graph carrier document provided by this optional implementation method first obtains a knowledge graph through a large language model when the area falls into matches the area where the file upload hot zone is located, and then generates a graph carrier document based on the carrier demand information and knowledge graph input by the user. This allows the large language model to have the relationship information of each node in the corresponding graph carrier document through the knowledge graph, thereby improving the reliability of the generation of the graph carrier document and providing another reliable implementation method for the generation of the graph carrier document.

[0061] Optionally, before inputting the selected file and graph guide words into the large language model to obtain the knowledge graph output by the large language model, the above-mentioned information generation method also includes: performing data preprocessing on the selected file, wherein the data preprocessing includes: extracting file information to be merged from the selected file; removing illegal character strings and meaningless characters in the extracted information and merging them into the same document format.

[0062] In some optional implementations of the present disclosure, the above-mentioned generation of a graph carrier document based on the knowledge graph and carrier demand information includes: generating demand guide words based on the carrier demand information; inputting the demand guide words and the knowledge graph into the large language model to obtain the graph carrier document output by the large language model.

[0063] In this optional implementation, the carrier requirement information is the demand information for the graph carrier document uploaded by the user. For example, the carrier requirement information is that the graph carrier document to be generated is a mind map; for another example, the carrier requirement information is that the graph carrier document to be generated is a flowchart.

[0064] The method for generating a graph carrier document provided by this optional implementation generates demand guiding words based on carrier demand information, and inputs the demand guiding words and the knowledge graph into a large language model. This allows the large language model to reorganize the knowledge graph based on understanding user needs to obtain a graph carrier document, thereby improving the reliability of obtaining the graph carrier document.

[0065] Optionally, the above-mentioned generation of a graph carrier document based on the knowledge graph and carrier requirement information includes: inputting the carrier requirement information and the knowledge graph into a large language model to obtain a graph carrier document output by the large language model.

[0066] In some optional implementations of the present disclosure, the above-mentioned optimization of the atlas carrier document based on the falling position and the selected file to obtain the optimized atlas carrier document includes: in response to detecting that the falling position is located in a blank area of ​​the file upload hot zone, based on the selected file, supplementing the entire document information of the atlas carrier document to obtain the optimized atlas carrier document.

[0067] In this optional implementation, the file upload hotspot includes: a document display area for the graph carrier document and a blank area. The document display area is the area containing the existing graph carrier document and is used to display the various nodes, node information, and relationships between nodes in the graph carrier document to the user. The blank area is the area in the file upload hotspot where the graph carrier document is not displayed. When a position falls into the blank area, it indicates that the entire graph carrier document needs to be supplemented with information to obtain an optimized graph carrier document.

[0068] In this optional implementation, supplementing the entire document information of the graph carrier document means expanding the information of each information unit in the graph carrier document. For example, the graph carrier document is a mind map, and supplementing the entire document information of the graph carrier document means expanding the nodes or node information in the mind map so that the expanded graph carrier document is an optimized graph carrier document.

[0069] The method for obtaining an optimized graph carrier document provided by this optional implementation method, upon detecting that the location falls into a blank area located in the file upload hot zone, supplements the entire document information of the graph carrier document based on the selected file to obtain the optimized graph carrier document, thereby improving the optimization effect of the graph carrier document.

[0070] Optionally, the above-mentioned optimization of the atlas carrier document based on the falling position and the selected file to obtain the optimized atlas carrier document includes: in response to detecting that the falling position is located in an area outside the file upload hot zone, based on the selected file, supplementing the entire document information of the atlas carrier document to obtain the optimized atlas carrier document.

[0071] Optionally, the above-mentioned optimization of the graph carrier document based on the falling position and the selected file to obtain the optimized graph carrier document includes: in response to detecting that the falling position is located at a non-node position of the graph carrier document (for example, on the edge between nodes), based on the selected file, supplementing the entire document information of the graph carrier document to obtain the optimized graph carrier document.

[0072] In some embodiments of the present disclosure, the above-mentioned response to detecting that the falling position is located in a blank area of ​​the file upload hot zone, based on the selected file, supplementing the entire document information of the graph carrier document to obtain the optimized graph carrier document includes: in response to detecting that the falling position is located in a blank area of ​​the file upload hot zone, based on the selected file, performing node expansion on all original nodes on the graph carrier document to obtain expanded nodes of each original node; based on the information of each original node, deduplicating the expanded nodes of all original nodes to obtain deduplicated nodes of all original nodes; in response to the fact that the number of deduplicated nodes with original nodes is the largest and the quality is the highest, adding the deduplicated nodes of the original node to the graph carrier document to obtain the optimized graph carrier document.

[0073] In this optional implementation, the original node on the graph carrier document is an information unit of the graph carrier document. For example, if the graph carrier document is a mind map, the original node can be a central node, node 1, node 2, node 3, etc. with a connection relationship, where the central node to node 1 is a branch, and the central node to node 2 is another branch.

[0074] In this optional implementation, expanding the original node refers to expanding the child nodes of any node in the graph carrier document to obtain the expanded branches of the node; the above-mentioned deduplication of the expanded nodes of all original nodes based on the information of each original node refers to: for each node that undergoes child node expansion, whether the child nodes on all expanded branches of the node and the nodes on the currently expanded graph carrier document have duplicate nodes or duplicate node information, and in response to the duplicate nodes or duplicate node information in the expanded child nodes, removing the duplicate nodes or duplicate node information.

[0075] In this optional implementation, the deduplicated nodes are the latest expanded nodes related to the original nodes, and the deduplicated nodes are nodes whose nodes or node information are not repeated. The number of deduplicated nodes of the original node is obtained by accumulating the deduplicated nodes on the same branch of the original node; the quality of the deduplicated nodes of the original node is calculated by the corresponding quality formula (such as the information entropy formula), and the number and quality of the deduplicated nodes of each original node can be determined. The deduplicated nodes with the largest number and highest quality in the branch where the original node is located are added to the graph carrier document to obtain the optimized graph carrier document.

[0076] This embodiment provides a method for supplementing the entire document information of a graph carrier document, performing node expansion on all original nodes on the graph carrier document to obtain expanded nodes, deduplicating the expanded nodes, and when the number of deduplicated nodes with original nodes is the largest and the quality is the highest, adding the deduplicated nodes of the original nodes to the graph carrier document to obtain an optimized graph carrier document.

[0077] Optionally, in response to detecting that the location falls in a blank area of ​​the file upload hot zone, based on the selected file, the entire document information of the graph carrier document is supplemented to obtain an optimized graph carrier document, including: in response to detecting that the location falls in a blank area of ​​the file upload hot zone, based on the selected file, all original nodes on the graph carrier document are expanded to obtain expanded nodes of each original node; based on the information of each original node, the expanded nodes of all original nodes are deduplicated to obtain deduplicated nodes of all original nodes; and the deduplicated nodes of all original nodes are added to the graph carrier document to obtain an optimized graph carrier document.

[0078] In some optional implementations of the present disclosure, the above-mentioned optimization of the graph carrier document based on the falling position and the selected file to obtain the optimized graph carrier document includes: in response to detecting that the falling position is located at the position of the node of the graph carrier document in the file upload hot zone, based on the selected file, adding a corresponding child node to the node to obtain the optimized graph carrier document.

[0079] In this optional implementation, the optimized graph carrier document includes at least one node and the relationships between each node. The graph carrier document displayed in the file upload hotspot can display all nodes of the graph carrier document. To this end, each node has a corresponding node position. When the falling position is equal to the position of the node, it can be determined that the user only wants to expand the information of the node at the position of the node. To this end, the execution entity can analyze the information related to the node in the selected file, refine the subnodes in the information related to the node, and add corresponding subnodes to the node.

[0080] In this optional implementation, the above-mentioned adding corresponding child nodes to the node based on the selected file to obtain the optimized graph carrier document includes: based on the selected file, determining the file information related to the information of the node, performing node information processing on the file information to obtain child nodes, adding child nodes to the branch connected to the node, and obtaining the optimized graph carrier document.

[0081] The method for obtaining an optimized graph carrier document provided by this optional implementation method, when falling into the position of a node of the graph carrier document in the file upload hot zone, adds a child node to the node based on the selected file, thereby providing a reliable implementation method for obtaining the optimized graph carrier document.

[0082] In some embodiments of the present disclosure, the above-mentioned information generation method also includes: associating each node in the optimized graph carrier document with a selection file; when the user operates the information source tracking tag of the node, the selection file associated with the node is displayed.

[0083] In this embodiment, associating a node with a selection file refers to determining the selection file from which the node information comes, and associating the node with the selection file.

[0084] In this embodiment, when the type of the optimized graph carrier document is different, the way in which the node is associated with the selected file is different. As shown in Figures 3a and 3b, the user selects different nodes and performs different operations on different tags of the node. The selected file associated with the node is displayed through the operation (not shown in the figure), thereby achieving the purpose of information source tracking. Specifically, the graph carrier document shown in Figure 3a is a mind map, and the nodes in the mind map include: central node, node 1, node 2, node 3, node 1.1, node 1.2, node 1.3, node 2.1, node 2.2, node 3.1, node 3.2, wherein node 1, node 2, and node 3 are child nodes of the central node, node 1.1, node 1.2, and node 1.3 are child nodes of node 1, node 2.1 and node 2.2 are child nodes of node 2, and node 3.1 and node 3.2 are child nodes of node 3. In Figure 3a, the user clicks (e.g., single-clicks or double-clicks) node 1.3 to select it, and the information source tracking label a is displayed. The graph carrier document shown in Figure 3b is a flowchart, and the nodes in the flowchart include: Start, Node 1', Node 2', Node 3', Judgment, and End. In Figure 3b, the user clicks node 3' to select it, and the information source tracking label a for that node 3' is displayed.

[0085] In this embodiment, the above-mentioned operation on the information source tracking tag of the node includes: in response to receiving the user's operation on the node, displaying the information source tracking tag of the node (such as a in Figure 3a and Figure 3b); in response to receiving the user's operation on the information source tracking tag, determining that the user has operated the information source tracking tag of the node.

[0086] The information generation method provided by the embodiments of the present disclosure associates each node in the optimized graph carrier document with a selected file. When the user operates the information source tracking tag of the node, the selected file associated with the node is displayed, thereby improving the comprehensiveness of the user's information acquisition.

[0087] Optionally, while displaying the information source tracking tag, the data intelligent recommendation tag of each node is also displayed synchronously. The above information generation method also includes: when the user operates the data intelligent recommendation tag of the node (such as b in Figure 3a and Figure 3b), a search information box is displayed to the user; and the user's to-be-queried information is obtained through the search information box. Based on the to-be-queried information, search results are obtained from all types of files and the search results are displayed.

[0088] Optionally, while displaying the information source tracking tag, the real-time online search tag of each node is also displayed synchronously. The above information generation method also includes: when the user performs a real-time online search for the node (such as c in Figure 3a and Figure 3b), a search information box is displayed to the user; and the user's online query information is obtained through the search information box, and based on the online query information, online results are searched from the Internet and displayed.

[0089] The information generation method provided by this disclosure allows users to view the reference source of a node's information through a dual-link function and jump to the information details page to view the node's context. Furthermore, users can request the document library platform to intelligently recommend resources for the node and conduct real-time, online searches across the entire network, providing more real-time and comprehensive supplementary information for the node.

[0090] The information generation method provided by the present disclosure can quickly realize the reading, information merging, element extraction, information sorting and visual map presentation of multiple documents of multiple types. Take the summary of 6 document information as an example: the manual reading time is calculated as every 20 minutes, and the full-link operation takes 20*6=120 minutes, that is, 2 hours; the comparative analysis takes 1 hour; and finally, manual typing and reorganization of the information takes more than 2 hours. The whole process takes at least 5 hours. Using the information generation method disclosed in the present disclosure, the operation time required for file uploading and final content generation is less than 2 minutes, which saves information processing time. At the same time, the convenient data recommendation capability and real-time retrieval capability can expand richer and more effective information for users and bring more inspiration.

[0091] Further referring to FIG4 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an information generating device. This device embodiment corresponds to the method embodiment shown in FIG1 , and the device can be specifically applied to various electronic devices.

[0092] As shown in Figure 4, the information generation device 400 provided in this embodiment includes: a file acquisition unit 401, an information acquisition unit 402, a determination unit 403, and an optimization unit 404. The file acquisition unit 401 can be configured to obtain a selected file after the user selects at least one type of file. The information acquisition unit 402 can be configured to obtain the user's operation information on the selected file in real time in response to detecting that there is a graph carrier document on the current display interface. The determination unit 403 can be configured to determine the falling position of the selected file relative to the file upload hot zone based on the operation information. The file upload hot zone is the area where the graph carrier document is displayed. The optimization unit 404 can be configured to optimize the graph carrier document based on the falling position and the selected file to obtain an optimized graph carrier document.

[0093] In this embodiment, the specific processing of the file acquisition unit 401, the information acquisition unit 402, the determination unit 403, and the optimization unit 404 in the information generating device 400 and the technical effects brought about by them can be referred to the relevant descriptions of step 101, step 102, step 103, and step 104 in the corresponding embodiment of Figure 1, and will not be repeated here.

[0094] In some optional implementations of this embodiment, the above-mentioned device also includes: a generation unit (not shown in the figure), the above-mentioned generation unit is configured to generate a file upload hot zone on the current display interface in response to detecting that there is no graph carrier document on the current display interface; obtain the user's operation information on the selected file in real time; determine the falling area of ​​the selected file relative to the file upload hot zone based on the operation information; in response to detecting that the falling area matches the area where the file upload hot zone is located, generate a graph carrier document based on the selected file; and display the graph carrier document in the file upload hot zone.

[0095] In some optional implementations of this embodiment, the above-mentioned generation unit is further configured to: in response to detecting that the fallen area matches the area where the file upload hot zone is located, input the selected file and carrier guide word into the large language model to obtain the graph carrier document output by the large language model.

[0096] In some optional implementations of this embodiment, the above-mentioned generation unit is further configured to: in response to detecting that the fallen area matches the area where the initial upload area is located, input the selected file and graph guide words into the large language model to obtain the knowledge graph output by the large language model; obtain the carrier requirement information input by the user; and generate a graph carrier document based on the knowledge graph and the carrier requirement information.

[0097] In some optional implementations of this embodiment, the above-mentioned generation unit is further configured to: generate demand guide words based on carrier demand information; input the demand guide words and the knowledge graph into the large language model to obtain the graph carrier document output by the large language model.

[0098] In some optional implementations of the present disclosure, the above-mentioned optimization unit is configured to: in response to detecting that the position falls into a blank area located in the file upload hot zone, based on the selected file, supplement the entire document information of the atlas carrier document to obtain an optimized atlas carrier document.

[0099] In some optional implementations of the present disclosure, the above-mentioned optimization unit is further configured to: in response to detecting that the position falls into a blank area located in the file upload hot zone, based on the selected file, all original nodes on the graph carrier document are expanded to obtain expanded nodes of each original node; based on the information of each original node, all expanded nodes of the original nodes are deduplicated to obtain deduplicated nodes of all original nodes; in response to the fact that the number of deduplicated nodes of the original node is the largest and the quality is the highest, the deduplicated nodes of the original node are added to the graph carrier document to obtain an optimized graph carrier document.

[0100] In some optional implementations of the present disclosure, the above-mentioned optimization unit is configured to: in response to detecting the position of a node of a graph carrier document that falls into a file upload hot zone, add a corresponding child node to the node based on the selected file to obtain an optimized graph carrier document.

[0101] In some optional implementations of the present disclosure, the above-mentioned device 400 also includes: an association unit (not shown in the figure), which is configured to: associate each node in the optimized graph carrier document with a selection file; and display the selection file associated with the node when the user operates the information source tracking tag of the node.

[0102] The information generation device provided by the embodiment of the present disclosure is as follows: first, the file acquisition unit 401 acquires the selected file after the user selects at least one type of file; second, the information acquisition unit 402 acquires the user's operation information on the selected file in real time in response to detecting that there is a graph carrier document on the current display interface; third, the determination unit 403 determines the falling position of the selected file relative to the file upload hot zone based on the operation information, and the file upload hot zone is the area where the graph carrier document is displayed; finally, the optimization unit 404 optimizes the graph carrier document based on the falling position and the selected file to obtain the optimized graph carrier document. Thus, by selecting the falling position of the file relative to the file upload hot zone and selecting the file, the pre-generated graph carrier document is optimized, thereby summarizing the information of multiple types of files, improving the richness of the optimized graph carrier document, and ensuring the comprehensiveness of the generation of the graph carrier document information.

[0103] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0104] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0105] FIG5 shows a schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0106] As shown in Figure 5, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0107] Various components in device 500 are connected to I / O interface 505, including: an input unit 506, such as a keyboard, mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, optical disk, etc.; and a communication unit 509, such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0108] The computing unit 501 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the information generation method. For example, in some embodiments, the information generation method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the information generation method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the information generation method by any other appropriate means (e.g., by means of firmware).

[0109] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable information generating device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic input, voice input, or tactile input.

[0113] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0114] Computer systems may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The client and server relationship arises through computer programs running on the respective computers and having a client-server relationship to each other.

[0115] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0116] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for generating information, the method comprising: Obtaining a selected file after the user selects at least one type of file; In response to detecting that a map carrier document is present on the current display interface, obtaining user operation information on the selected file in real time; Based on the operation information, determining the position of the selected file relative to a file upload hot zone, wherein the file upload hot zone is an area where the atlas carrier document is displayed; Based on the falling position and the selected file, the atlas carrier document is optimized to obtain an optimized atlas carrier document.

2. The method according to claim 1, further comprising: In response to detecting that there is no atlas carrier document on the current display interface, generating the file upload hot zone on the current display interface; Acquiring user operation information on the selected file in real time; Based on the operation information, determining an area where the selected file falls relative to the file upload hot zone; In response to detecting that the falling area matches the area where the file uploading hot zone is located, generating a map carrier document based on the selected file; The atlas carrier document is displayed in the file upload hot zone.

3. The method according to claim 2, wherein: In response to detecting that the falling area matches the area where the file uploading hot zone is located, generating a graph carrier document based on the selected file includes: In response to detecting that the falling area matches the area where the file uploading hot zone is located, the selected file and the carrier guide word are input into the large language model to obtain the graph carrier document output by the large language model.

4. The method according to claim 2, wherein: In response to detecting that the falling area matches the area where the file uploading hot zone is located, generating a graph carrier document based on the selected file includes: In response to detecting that the falling area matches the area where the file uploading hot zone is located, inputting the selected file and the graph guide word into a large language model to obtain a knowledge graph output by the large language model; Obtain carrier requirement information input by the user; Based on the knowledge graph and the carrier requirement information, a graph carrier document is generated.

5. The method according to claim 4, wherein The generating of a graph carrier document based on the knowledge graph and the carrier requirement information includes: generating demand guiding words based on the carrier demand information; The demand guiding words and the knowledge graph are input into the large language model to obtain a graph carrier document output by the large language model.

6. The method according to any one of claims 1 to 5, wherein: The optimizing the atlas carrier document based on the falling position and the selected file to obtain the optimized atlas carrier document includes: In response to detecting that the falling position is located in a blank area of ​​the file upload hot zone, based on the selected file, the entire document information of the atlas carrier document is supplemented to obtain an optimized atlas carrier document.

7. The method according to claim 6, wherein: In response to detecting that the falling position is located in a blank area of ​​the file upload hot zone, supplementing the entire document information of the atlas carrier document based on the selected file to obtain an optimized atlas carrier document includes: In response to detecting that the falling position is located in a blank area of ​​the hot upload zone in the file, based on the selected file, all original nodes on the graph carrier document are expanded to obtain expanded nodes of each original node; Based on the information of each original node, the expanded nodes of all original nodes are deduplicated to obtain the deduplicated nodes of all original nodes; In response to the fact that the number of deduplicated nodes of the original node is the largest and the quality is the highest, the deduplicated nodes of the original node are added to the graph carrier document to obtain an optimized graph carrier document.

8. The method according to any one of claims 1 to 5, wherein: The optimizing the atlas carrier document based on the falling position and the selected file to obtain the optimized atlas carrier document includes: In response to detecting that the falling position is located at the position of the node of the graph carrier document in the file upload hot zone, based on the selected file, a corresponding child node is added to the node to obtain an optimized graph carrier document.

9. The method according to claim 1, further comprising: Associating each node in the optimized graph carrier document with the selected file; When the user operates the information source tracking tag of the node, the selection file associated with the node is displayed.

10. An information generating device, comprising: A file acquisition unit is configured to acquire a selected file after the user selects at least one type of file; An information acquisition unit is configured to, in response to detecting that a graph carrier document is present on the current display interface, acquire in real time user operation information on the selected file; A determining unit configured to determine, based on the operation information, a position where the selected file falls relative to a file upload hot zone, the file upload hot zone being an area where the atlas carrier document is displayed; The optimization unit is configured to optimize the atlas carrier document based on the falling position and the selected file to obtain an optimized atlas carrier document.

11. The apparatus according to claim 10, further comprising: a generating unit configured to generate the file upload hot zone on the current display interface in response to detecting that there is no atlas carrier document on the current display interface; Acquiring user operation information on the selected file in real time; Based on the operation information, determine the falling area of ​​the selected file relative to the file upload hot zone; in response to detecting that the falling area matches the area where the file upload hot zone is located, generate a map carrier document based on the selected file; and display the map carrier document in the file upload hot zone.

12. The device according to claim 11, wherein The generation unit is further configured to: in response to detecting that the falling area matches the area where the file upload hot zone is located, input the selected file and the carrier guide word into the large language model to obtain the graph carrier document output by the large language model.

13. The device according to claim 11, wherein The generation unit is further configured to: in response to detecting that the fallen area matches the area where the initial upload area is located, input the selected file and the graph guide word into the large language model to obtain the knowledge graph output by the large language model; obtain the carrier requirement information input by the user; and generate a graph carrier document based on the knowledge graph and the carrier requirement information.

14. The device according to claim 13, wherein The generation unit is further configured to: generate demand guiding words based on the carrier demand information; input the demand guiding words and the knowledge graph into the large language model to obtain the graph carrier document output by the large language model.

15. The device according to any one of claims 10 to 14, wherein: The optimization unit is configured to: in response to detecting that the falling position is located in a blank area of ​​the file upload hot zone, supplement the entire document information of the atlas carrier document based on the selected file to obtain an optimized atlas carrier document.

16. The device according to claim 15, wherein The optimization unit is further configured to: in response to detecting that the falling position is located in a blank area of ​​the file upload hot zone, based on the selected file, perform node expansion on all original nodes on the graph carrier document to obtain expanded nodes of each original node; based on information of each original node, perform deduplication on the expanded nodes of all original nodes to obtain deduplication nodes of all original nodes; In response to the fact that the number of deduplicated nodes of the original node is the largest and the quality is the highest, the deduplicated nodes of the original node are added to the graph carrier document to obtain an optimized graph carrier document.

17. The device according to any one of claims 10 to 14, wherein: The optimization unit is configured to: in response to detecting that the falling position is located at the position of the node of the graph carrier document in the file upload hot zone, add a corresponding child node to the node based on the selected file to obtain an optimized graph carrier document.

18. The apparatus according to claim 10, further comprising: an associating unit, the associating unit being configured to: associate each node in the optimized graph carrier document with the selected file; When the user operates the information source tracking tag of the node, the selection file associated with the node is displayed.

19. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

20. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 9.

21. A computer program product comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 9.

Images