Intelligent document display method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application provide an intelligent document display method and apparatus, an electronic device, and a storage medium. The intelligent document display method comprises: displaying a first document in a first window, and displaying in the first window a second window for human-computer interaction; determining first semantics of first input information inputted by a user in the second window, wherein the first input information is used for indicating analysis for the first document; on the basis of the first semantics, analyzing the first document to obtain a full-text analysis result; and displaying the full-text analysis result.

Description

Document intelligent display method, device, electronic device and storage medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application number CN202410253220.9, filed on March 6, 2024, entitled “Document Intelligent Display Method, Device, Electronic Device and Storage Medium”, and Chinese patent application number CN202410555382.8, filed on May 7, 2024, entitled “Document Intelligent Display Method, Device, Electronic Device and Storage Medium”, the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to a method, device, electronic device, and storage medium for intelligent document display. Background Art

[0004] There is a need for patent search throughout the entire life cycle of a patent. For example, before applying for a patent, the applicant needs to conduct a novelty search on the patent; during the examination stage, the examiner needs to use the search results to determine whether the patent can be authorized; during the invalidation stage, the invalidation applicant needs to obtain invalidation evidence through patent search.

[0005] The patent search process requires statistics and analysis of the retrieved patent documents, which often takes a lot of time to read and understand the patent documents, resulting in low search efficiency for users. Summary of the Invention

[0006] In view of this, embodiments of the present application provide a method, device, electronic device, and storage medium for intelligently displaying documents.

[0007] According to a first aspect of an embodiment of the present application, a method for intelligently displaying documents is proposed, the method comprising:

[0008] Displaying a first document in a first window, and displaying a second window for human-computer interaction within the first window;

[0009] determining a first semantic meaning of first input information input by a user in the second window, wherein the first input information is used to indicate an analysis of the first document;

[0010] Analyze the first document based on the first semantics to obtain a full-text analysis result;

[0011] The full text analysis results are displayed.

[0012] In some embodiments, the method further comprises:

[0013] At least one piece of position information is displayed in at least one of the first window and the second window, wherein the position information is used to indicate a position of the document content associated with the full-text analysis result in the first document.

[0014] In some embodiments, the method further comprises:

[0015] In response to displaying the at least one location information, the first document is associated with at least one location indicated by the location information in the first window.

[0016] In some embodiments, the location information is provided for selection so as to associate the location indicated by the location information with the first document within the first window.

[0017] In some embodiments, analyzing the first document based on the first semantics and obtaining a full-text analysis result includes:

[0018] Analyzing the first document based on the target content category indicated by the first semantics to obtain at least one full-text analysis result associated with the target content category;

[0019] The display of the full-text analysis results includes:

[0020] Each of the full-text analysis results is displayed in a classified manner based on at least one sub-category attribute included in the target content category.

[0021] In some embodiments, the sub-category attributes included in the target content category are pre-set; and / or

[0022] The sub-category attributes included in the target content category are set based on the full-text analysis result.

[0023] In some embodiments, the method further comprises:

[0024] Determine N candidate documents that meet the search conditions, and display the associated information corresponding to the N candidate documents in the third window;

[0025] Displaying a fourth window for human-computer interaction within the third window;

[0026] determining a second semantic meaning of second input information input by the user in the fourth window, wherein the second input information is used to indicate a statistical analysis of the candidate document;

[0027] Analyze the N candidate documents based on the second semantics and obtain statistical analysis results;

[0028] The statistical analysis results are displayed.

[0029] In some embodiments, analyzing the first document based on the second semantics and obtaining a full-text analysis result includes:

[0030] Analyzing the N candidate documents based on a first statistical analysis parameter indicated by the second semantics to obtain a statistical number of candidate documents corresponding to each of the I first sub-analysis parameters associated with the first statistical analysis parameter;

[0031] The displaying of the statistical analysis results includes:

[0032] Display the statistical quantities corresponding to the I first sub-analysis parameters respectively.

[0033] In some embodiments, the displaying of the statistical quantities corresponding to the I first sub-analysis parameters includes:

[0034] The statistical quantities are classified and displayed according to the first classification parameter.

[0035] In some embodiments, the statistical quantities are provided for selection, so that the fifth window displays the associated information corresponding to the candidate documents corresponding to the selected statistical quantities.

[0036] In some embodiments, displaying the statistical quantities corresponding to the I first sub-analysis parameters includes:

[0037] Displaying the statistical quantities corresponding to the I first sub-analysis parameters respectively in a first form;

[0038] The statistical quantities displayed in the first form are provided for selection, and the statistical quantities corresponding to the first sub-analysis parameters are displayed in a second form; wherein the display area of ​​the second form is larger than that of the first form;

[0039] The statistical quantity displayed in the second form is provided for selection, so that the associated information of the candidate document corresponding to the selected statistical quantity displayed in the second form is displayed in the fifth window.

[0040] In some embodiments, the associated information corresponding to the N candidate documents displayed in the third window is provided for selection, so that the candidate document corresponding to the selected associated information is displayed in the first window.

[0041] In some embodiments, the analyzing the first document based on the first semantics to obtain a full-text analysis result includes:

[0042] Based on the first semantics, the selected portion of the first document is analyzed to obtain a full-text analysis result corresponding to the selected portion of the first document.

[0043] According to a second aspect of the embodiments of the present application, a document intelligent display device is provided, wherein the device includes: a processing module; the processing module is configured to:

[0044] Displaying a first document in a first window, and displaying a second window for human-computer interaction within the first window;

[0045] determining a first semantic meaning of first input information input by a user in the second window, wherein the first input information is used to indicate an analysis of the first document;

[0046] Analyze the first document based on the first semantics to obtain a full-text analysis result;

[0047] The full text analysis results are displayed.

[0048] In some embodiments, the processing module is further configured to:

[0049] At least one piece of position information is displayed in at least one of the first window and the second window, wherein the position information is used to indicate a position of the document content associated with the full-text analysis result in the first document.

[0050] In some embodiments, the processing module is further configured to:

[0051] In response to displaying the at least one location information, the first document is associated with at least one location indicated by the location information in the first window.

[0052] In some embodiments, the location information is provided for selection so as to associate the location indicated by the location information with the first document within the first window.

[0053] In some embodiments, the processing module is specifically configured to:

[0054] Analyzing the first document based on the target content category indicated by the first semantics to obtain at least one full-text analysis result associated with the target content category;

[0055] Each of the full-text analysis results is displayed in a classified manner based on at least one sub-category attribute included in the target content category.

[0056] In some embodiments, the sub-category attributes included in the target content category are pre-set; and / or

[0057] The sub-category attributes included in the target content category are set based on the full-text analysis result.

[0058] In some embodiments, the processing module is further configured to:

[0059] Determine N candidate documents that meet the search conditions, and display the associated information corresponding to the N candidate documents in the third window;

[0060] Displaying a fourth window for human-computer interaction within the third window;

[0061] determining a second semantic meaning of second input information input by the user in the fourth window, wherein the second input information is used to indicate a statistical analysis of the candidate document;

[0062] Analyze the N candidate documents based on the second semantics and obtain statistical analysis results;

[0063] The statistical analysis results are displayed.

[0064] In some embodiments, the processing module is specifically configured to:

[0065] Analyzing the N candidate documents based on a first statistical analysis parameter indicated by the second semantics to obtain a statistical number of candidate documents corresponding to each of the I first sub-analysis parameters associated with the first statistical analysis parameter;

[0066] Display the statistical quantities corresponding to the I first sub-analysis parameters respectively.

[0067] In some embodiments, the processing module is specifically configured to:

[0068] The statistical quantities are classified and displayed according to the first classification parameter.

[0069] In some embodiments, the statistical quantities are provided for selection, so that the fifth window displays the associated information corresponding to the candidate documents corresponding to the selected statistical quantities.

[0070] In some embodiments, the processing module is specifically configured to:

[0071] Displaying the statistical quantities corresponding to the I first sub-analysis parameters respectively in a first form;

[0072] The statistical quantities displayed in the first form are provided for selection, and the statistical quantities corresponding to the first sub-analysis parameters are displayed in a second form; wherein the display area of ​​the second form is larger than that of the first form;

[0073] The statistical quantity displayed in the second form is provided for selection, so that the associated information of the candidate document corresponding to the selected statistical quantity displayed in the second form is displayed in the fifth window.

[0074] In some embodiments, the associated information corresponding to the N candidate documents displayed in the third window is provided for selection, so that the candidate document corresponding to the selected associated information is displayed in the first window.

[0075] In some embodiments, the processing module is specifically configured to:

[0076] Based on the first semantics, the selected portion of the first document is analyzed to obtain a full-text analysis result corresponding to the selected portion of the first document.

[0077] According to a third aspect of the embodiments of the present application, an electronic device is provided, comprising:

[0078] one or more processors;

[0079] Wherein, the processor is configured to call instructions to enable the electronic device to execute the document intelligent display method described in the first aspect.

[0080] According to a fourth aspect of an embodiment of the present application, a storage medium is proposed, which stores instructions. When the instructions are executed on an electronic device, the electronic device executes the document intelligent display method described in the first aspect.

[0081] According to an embodiment of the present application, the method includes displaying a first document in a first window, displaying a second window for human-computer interaction within the first window; determining a first semantic of first input information input by a user within the second window, wherein the first input information is used to indicate an analysis of the first document; analyzing the first document based on the first semantic to obtain a full-text analysis result; and displaying the full-text analysis result. In this way, the first document is displayed within the first window within the first window, and the interaction of document analysis is achieved through the second window within the first window displaying the first document, and the analysis of the first patent document is further achieved through the language model. On the one hand, the user can interact directly within the first window, which improves convenience. On the other hand, because the language model uses a machine to analyze documents at a faster speed, the time for manual reading and analysis is reduced, and the efficiency of analyzing the first document is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] FIG1 is a schematic diagram showing a flow chart of a method for intelligently displaying documents according to an exemplary embodiment;

[0083] FIG2 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0084] FIG3 is a schematic diagram showing a flow chart of a method for intelligently displaying documents according to an exemplary embodiment;

[0085] FIG4 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0086] FIG5 is a schematic diagram showing a flow chart of a method for intelligently displaying documents according to an exemplary embodiment;

[0087] FIG6 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0088] FIG7 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0089] FIG8 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0090] FIG9 is a flow chart showing a method for intelligently displaying documents according to an exemplary embodiment;

[0091] FIG10 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0092] FIG11 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0093] FIG12 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0094] FIG13 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0095] FIG14 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0096] FIG15 is a schematic diagram of a document intelligent display window according to an exemplary embodiment;

[0097] FIG16 is a schematic diagram showing the structure of a document intelligent display device according to an exemplary embodiment;

[0098] Fig. 17 is a schematic diagram showing the structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0099] To make the technical solutions and beneficial effects of this application more clearly understood, the following detailed description is given by way of specific embodiments. The accompanying drawings are not necessarily drawn to scale, and local features may be enlarged or reduced to more clearly illustrate the details of the local features. Unless otherwise defined, the technical and scientific terms used herein have the same meanings as those in the technical field to which this application belongs.

[0100] The embodiments of the present application are not exhaustive, but are merely illustrative of some embodiments and are not intended to be a specific limitation on the scope of protection of the present application. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementations in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all of the steps in different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementations of other embodiments.

[0101] In each embodiment of the present application, unless otherwise specified or there is any logical conflict, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0102] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0103] In the embodiments of the present application, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., can mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article can be understood as a singular expression or a plural expression.

[0104] In the embodiments of the present application, "plurality" refers to two or more.

[0105] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0106] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "in one case A, in another case B," or "in one case A, in another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, and C.

[0107] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0108] The prefixes such as "first" and "second" in the embodiments of the present application are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, value or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the description object is a "field", the ordinal number before the "field" in "first field" and "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and "second field". For another example, if the description object is a "level", the ordinal number before the "level" in "first level" and "second level" does not limit the priority between the "levels". For another example, the value of the description object is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the value of "device" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0109] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0110] In some embodiments, terms such as "...", "determine...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0111] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0112] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0113] In addition, each element, each row, or each column in the table of the embodiments of the present application can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0114] As shown in FIG1 , the embodiment of the present application relates to a method for intelligently displaying documents, which includes:

[0115] Step 101: Displaying a first document in a first window, and displaying a second window for human-computer interaction within the first window;

[0116] Step 102: Determine a first semantic meaning of first input information input by a user in the second window, wherein the first input information is used to indicate an analysis of the first document;

[0117] Step 103: Analyze the first document based on the first semantics to obtain a full-text analysis result;

[0118] Step 104: Display the full-text analysis result.

[0119] In one possible implementation, the document intelligent display method may be executed by a local computer or a remote server.

[0120] In one possible implementation, the document intelligent display method can be performed by a local computer and a remote server in combination. For example, steps 101, 102, and 104 can be performed by the local computer, while step 103 can be performed by the remote server. For another example, steps 101 and 104 can be performed by the local computer, while steps 102 and 103 can be performed by the remote server, but the present invention is not limited thereto.

[0121] In a possible implementation, the first document may include: a patent document.

[0122] Here, the first document may be obtained through a search, or may be directly opened by the user.

[0123] In a possible implementation, displaying the first document in the first window may include displaying the full text of the first document. For example, the first window may display the full text of the first document in a split screen, and the user may select the content to be browsed by means of a slider or the like.

[0124] In one possible implementation, displaying the first document in the first window may include displaying different sections of the first document separately. For example, the first window may include tabs for each of the five sections of the patent document (abstract, claims, specification, drawings, and abstract drawings), allowing the user to select the desired content through the tabs.

[0125] In one possible implementation, the first window may further display related information associated with the first document, such as the patent document's legal information, citation confidence, and patent families, which are not limited here. The first window may also display operation icons for adding, translating, and saving the first document, which are also not limited here.

[0126] In one possible implementation, the first window may include a browser window.

[0127] In a possible implementation, the second window may include one of the following: a partial space divided from the first window; a plug-in window within the first window; or a card window suspended on the first window.

[0128] The way in which the user inputs the first input information in the second window may include one of the following: keyboard input, handwriting input, and voice recognition input.

[0129] In one possible implementation, the method of the user inputting the first input information in the second window may further include: selecting the first input information from at least one first candidate input information preset in the second window. Here, the first candidate input information may include: preset input information having a user input frequency exceeding a frequency threshold based on historical input information statistics; and preset input information based on the analysis capabilities of a language model.

[0130] The first input information may include input text information, voice information, etc. The first semantics may be the meaning expressed by the first input information obtained through machine analysis of the first input information. Text information and / or voice information are carriers of language. Text is meaningless to computers, etc. Computers (language models), etc., need to assign meaning, i.e., semantics, to text information and / or voice information in order for the computer to understand and further process it.

[0131] In one possible implementation, step 103 may include analyzing the first document using a language model based on the first semantics to obtain a full-text analysis result. Here, the language model may include a machine learning model. The language model may be pre-trained to perform at least one of the following: determining the semantics of input information, understanding the semantics, and analyzing the document.

[0132] In one possible implementation, the language model may include a Generative Pre-trained Transformer (GPT). Here, the full-text analysis results may not be obtained by extracting textual information from the first document, but rather by summarizing and / or performing secondary inference on the first document based on the language model's prior training, enabling the language model to understand the first document. This can reduce the time it takes for users to understand the first document and arrive at the full-text analysis results, thereby improving the efficiency of user comprehension of the first document.

[0133] In specific applications, language models can use generative artificial intelligence (AI) models such as ChatGPT 3.5turbo, ChatGPT 4.0, and llama2. Generative AI models can perform secondary reasoning, reducing the time users spend summarizing and reasoning, and improving reading efficiency.

[0134] In a possible implementation, the semantics of the entire document content or the semantics of part of the document content of the first document may be summarized to obtain a full-text analysis result.

[0135] In one possible implementation, the entire document content or a portion of the document content of the first document may be secondary inferred to obtain a full-text analysis result. In one possible implementation, determining the first semantic meaning of the first input information entered by the user in the second window may include: using a speech model to determine the first semantic meaning of the first input information entered by the user in the second window.

[0136] The first input information may indicate analyzing and understanding the full text of the first document from different perspectives.

[0137] For example, taking the case where the first document is a patent document, the first input information may indicate to analyze at least one of the following items of the full text of the patent document: technical solution, beneficial effect, technical problem, implementation method, and example.

[0138] The language model can perform full text analysis based on the first semantics to obtain a full text analysis result for the analysis item indicated by the first input information. In one possible implementation, the full text analysis result can be displayed in at least one of the first window and the second window.

[0139] In one possible implementation, the full-text analysis result may be displayed in a window different from the first window and the second window.

[0140] In a possible implementation, the second window may display the first input information and the full text analysis result of the first input information in the form of human-computer dialogue.

[0141] For example, as shown in FIG2 , assuming the first document is a patent document, a portion of the first window is used to display the full text of the patent document. The first window may include tabs for five patent documents, allowing users to browse patent documents using these tabs. A second window may be located to the side of the first window. The position and size of the second window may be freely adjustable by the user. The second window includes a dialog display space and an input space. Users may enter first input information into the input space at the bottom of the second window. A language model may determine the semantics of the first input information and analyze the patent document. The display space may display the first input information and the full-text analysis results in a dialog format.

[0142] In a possible implementation, at least one of the position and size of the second window can be adaptively adjusted based on the content displayed in the second window, thereby meeting the display requirements of the content displayed in the second window.

[0143] In this way, the first document is displayed in the first window, and interactive document analysis is performed in the second window within the first window displaying the first document, thereby completing the analysis of the first document. On the one hand, users can interact directly within the first window, improving convenience. On the other hand, because machine analysis is faster, it reduces the time required for manual reading and analysis, thereby improving the efficiency of analyzing the first document.

[0144] In some embodiments, analyzing the first document based on the first semantics to obtain a full-text analysis result includes: analyzing a selected portion of the first document based on the first semantics to obtain a full-text analysis result corresponding to the selected portion of the first document.

[0145] The selected portion of the first document may be selected by at least one of the following: the user directly selects the portion in the first document by using a mouse, touch, or the like;

[0146] Specifying by first input information; for example, selecting a selected portion by specifying position information such as a paragraph;

[0147] The text information of the first document displayed in the first window is identified as the selected portion.

[0148] The language model or the like can analyze the selected portion of the first document, for example, performing secondary inference on the selected portion of the first document.

[0149] For example, a user can use a mouse or other tool to select a portion of the first document as the selected portion and enter first input information in the second window, such as an instruction to summarize. The language model can summarize the selected portion and obtain a summary result for the selected portion. As shown in Figure 2, the [00N] segment in Figure 2 is the selected portion, and the first input information indicates "summary." Therefore, the full-text analysis result in Figure 2 is the summary result for the [00N] segment.

[0150] In this way, the analysis of the first document is not limited to the entire text, but selected parts can also be analyzed, thereby increasing the flexibility of the analysis of the first document.

[0151] As shown in FIG3 , the embodiment of the present application relates to a method for intelligently displaying documents, which includes:

[0152] Step 301: Display at least one piece of position information in at least one of the first window and the second window, wherein the position information is used to indicate the position of the document content associated with the full-text analysis result in the first document.

[0153] Step 301 may be implemented alone or in combination with any one of steps 101 to 104 .

[0154] The full-text analysis result can be obtained by summarizing and / or re-inferring the language model based on part or all of the content in the first document. The full-text analysis result may not include the original text in the first document, or it may include content that is not present in the original text of the first document, or a portion of the full-text analysis result may include the original text in the first document. The location of the document content associated with the full-text analysis result in the first document can be displayed for the user to review. The user can browse the document content to further verify the full-text analysis result and determine its accuracy.

[0155] In one possible implementation, the document content associated with the full-text analysis results may include at least one of the following:

[0156] Content in the first article that supports the results of the full-text analysis;

[0157] The content in the first document used to infer the results of the full text analysis;

[0158] The basis for the full text analysis results is summarized in the first document.

[0159] This allows users to quickly locate documents related to the full-text analysis results within the first document using location information, making it easier for users to access related documents and improving their efficiency. Furthermore, users can browse the document content to further verify the full-text analysis results, assessing their accuracy and improving the efficiency of assessing their credibility.

[0160] The location information may indicate at least one of the following:

[0161] The paragraph where the document content is located;

[0162] The page number where the document content is located.

[0163] For example, as shown in FIG4 , the second window may display the full-text analysis results. Location information may be displayed at the bottom of the full-text analysis results. In FIG4 , Segment X, Segment Y, and Segment Z respectively indicate the paragraphs containing the document content supporting the full-text analysis results. The content in Segment X, Segment Y, and Segment Z may be the same or different.

[0164] As shown in FIG5 , the embodiment of the present application relates to a method for intelligently displaying documents, which includes:

[0165] Step 501: In response to displaying the at least one location information, in the first window, associating the first document with at least one location indicated by the location information.

[0166] Step 501 may be implemented independently or in combination with any one of steps 101 to 104 and step 301. In one possible implementation, in response to displaying the at least one location information, associating the first document with the at least one location indicated by the location information in the first window may include: displaying, in the first window display, the document content at the at least one location indicated by the location information during adjustment of the first document.

[0167] In one possible implementation, the first document is associated with the location indicated by the location information, and the document content at the location indicated by the location information in the first document can be linked to the location indicated by the location information. For example, the location information can include a link that can directly link to the document content at the location indicated by the location information; when the location information is triggered, the document content at the location indicated by the location information can be displayed. Here, triggering the location information can include at least one of the following: the location information is displayed, an operation is performed on the location information, or the location of the location information satisfies a predetermined condition when multiple location information are displayed simultaneously.

[0168] In order to facilitate users to browse the document content supporting the full-text analysis results, the first window can display the document content at the location indicated by at least one position information. For example, the display content of the first window can be switched to the location of the document content containing the at least one position information indicating the location.

[0169] Exemplarily, as shown in FIG4 , the second window can display the full-text analysis results. Position information can be displayed at the bottom of the full-text analysis results. In FIG4 , segment X, segment Y, and segment Z respectively indicate the paragraphs where the document content supporting the full-text analysis results is located. The contents of segment X, segment Y, and segment Z can be the same or different. The location of the first document displayed in the first window can display the document content at the location indicated by the position information. For example, the first window can display the document content of segment X and the document content of segment Y.

[0170] In one possible implementation, the position corresponding to the document content displayed in the first window may be predetermined. Specifically, the first window may prioritize displaying the document content based on the order of the multiple positions in the first document. For example, the first window may prioritize displaying the document content whose position information indicates a preceding position in the first document.

[0171] In a possible implementation, for the locations respectively indicated by multiple pieces of location information, the user can customize the location to be displayed first.

[0172] By associating the first document with the location indicated by at least one piece of location information, the convenience for users to browse the document content can be improved, and the efficiency of document reading can be improved.

[0173] In some embodiments, the location information is provided for selection so as to associate the location indicated by the location information with the first document within the first window.

[0174] In one possible implementation, associating the position indicated by the position information with the first document in the first window may include: adjusting the first document to display the position indicated by the position information corresponding to the selection operation in the first window display.

[0175] In one possible implementation, selecting the location information may include applying a selection operation (such as hovering a mouse, single-clicking, double-clicking, long pressing, etc.) to the location information.

[0176] The location information display position can be set with a hyperlink or command statement, etc. When a selection operation is detected, the hyperlink or command statement can be executed, so that the first window displays the document content at the location indicated by the location information corresponding to the selection operation, so as to increase the speed at which users can directly browse to the document content, improve convenience and efficiency of browsing document content.

[0177] As shown in FIG6 , when the user clicks the position information “Z section” in the second window with the mouse, the first window can display the document content of Z section.

[0178] In some embodiments, analyzing the first document based on the first semantics and obtaining a full-text analysis result includes:

[0179] Analyzing the first document based on the target content category indicated by the first semantics to obtain at least one full-text analysis result associated with the target content category;

[0180] The display of the full-text analysis results includes:

[0181] Each of the full-text analysis results is displayed in a classified manner based on at least one sub-category attribute included in the target content category.

[0182] Here, the content classification can be based on the content of the first document. For example, a patent document can contain content from different categories. For example, the content of the patent specification can generally include: background technology, summary of the invention, and embodiments. The full-text analysis results of the target content classification can be a summary and / or analysis of the content of the document corresponding to the target content classification.

[0183] In a possible implementation, there may be multiple full-text analysis results corresponding to one target content category. For example, a patent document may generally have multiple embodiments.

[0184] When determining the full text analysis results, the language model can determine the content corresponding to the sub-category attributes in each full text analysis result and display the full text analysis results based on the sub-category attributes. The sub-category attributes may include: the necessary elements that constitute the full text analysis results. For example, in the same patent document, the specific implementation methods of each embodiment are different, that is, the sub-category attributes of each embodiment are not exactly the same.

[0185] For example, as shown in Figure 7, two full-text analysis results are obtained for the target content category indicated by the first input information: Full-text Analysis Result 1 and Full-text Analysis Result 2. The full-text analysis results list the results corresponding to each sub-category attribute. This allows users to more intuitively understand the full-text analysis results and more easily compare the two full-text analysis results, improving document interpretation efficiency.

[0186] For example, an embodiment in a patent document has various constituent elements. For example, for a circuit embodiment, it includes: electronic components, electronic component connection methods, working timing, etc. For another example: for a mechanical structure embodiment, it includes: component structure, component materials, etc. For example: for a chemical material preparation embodiment, it includes: raw materials, ratios, preparation processes, etc. For example, as shown in Figure 8, in a chemical material preparation patent document, based on the target content classification (embodiment), a full-text analysis is performed, and two full-text analysis results (i.e., two embodiments) can be obtained. Each embodiment is classified and displayed by sub-classification attributes (i.e., materials, ratios, and processes). On the one hand, users can understand the embodiments more intuitively; on the other hand, it is more convenient to compare the two embodiments, thereby improving the efficiency of document interpretation.

[0187] In some embodiments, the sub-category attributes included in the target content category are pre-set; and / or

[0188] The sub-category attributes included in the target content category are set based on the full-text analysis result.

[0189] In one possible implementation, sub-category attributes can be predetermined based on the type of full-text analysis results. For example, corresponding sub-category attributes can be pre-set for circuit embodiments, mechanical structure embodiments, and chemical material preparation embodiments. After obtaining the full-text analysis results using a language model, the language model can be used to determine the sub-category attributes to be displayed based on the type of full-text analysis results, and the full-text analysis results can be displayed using the sub-category attributes.

[0190] In a possible implementation, for the portion of the full-text analysis result other than the content corresponding to the sub-category attribute, the language model may further set sub-category attributes other than the preset sub-category attributes for classification display.

[0191] For example, if X full-text analysis results are obtained, and the X full-text analysis results contain content of the same category in addition to the preset sub-category attributes, the language model may further set corresponding sub-category attributes for the content of the same category and display them when displaying the X full-text analysis results. X is an integer greater than or equal to 2.

[0192] As shown in FIG9 , the embodiment of the present application relates to a method for intelligently displaying documents, which includes:

[0193] Step 901: Determine N candidate documents that meet the search criteria, and display the associated information corresponding to the N candidate documents in a third window;

[0194] Step 902: Displaying a fourth window for human-computer interaction in the third window;

[0195] Step 903: Determine a second semantic meaning of second input information input by the user in the fourth window, wherein the second input information is used to indicate a statistical analysis of the candidate document;

[0196] Step 904: Analyze the N candidate documents based on the second semantics and obtain statistical analysis results;

[0197] Step 905: Display the statistical analysis results.

[0198] Steps 901 to 905 may be implemented independently, or in combination with any one of steps 101 to 104 , step 301 , and step 501 .

[0199] In one possible implementation, the document intelligent display method may be executed by a local computer or a remote server.

[0200] In one possible implementation, the document intelligent display method can be performed by a local computer and a remote server in combination. For example, steps 901, 902, 903, and 905 can be performed by the local computer, while step 904 can be performed by the remote server. For another example, steps 901, 902, and 905 can be performed by the local computer, while steps 903 and 904 can be performed by the remote server, but the present invention is not limited thereto.

[0201] In a possible implementation, the candidate documents may include: candidate patent documents.

[0202] For example, a search condition may be input into the patent document search system, and the patent document search system performs a search to obtain N candidate documents that meet the search condition, where N is an integer greater than or equal to 1.

[0203] In one possible implementation, the associated information corresponding to the candidate document may partially or uniquely identify the candidate document.

[0204] In one possible implementation, the associated information of each candidate document may include at least one of the following: an identifier of the candidate document (such as the application number and / or publication number of the patent document, etc.); a name of the candidate document (such as the name of the patent document, etc.); persons associated with the candidate document (such as the applicant, right holder and / or inventor of the patent document, etc.); associated images of the candidate document (such as drawings and / or abstract drawings of the patent document, etc.), and the status of the candidate document (such as the legal status of the patent document, etc.).

[0205] For example, the third window can display the associated information corresponding to N candidate documents in a split screen, and the user can select the content to be browsed by means of a sliding block or the like.

[0206] In a possible implementation, the third window may also include conditions for screening N candidate documents. For example, the user can further screen N candidate documents using the screening conditions.

[0207] In a possible implementation, the fourth window may include one of the following: a partial space divided from the third window; a plug-in window within the third window; or a card window suspended on the third window.

[0208] The way in which the user inputs the second input information in the third window may include one of the following: keyboard input, handwriting input, and voice recognition input.

[0209] In one possible implementation, the method for the user to input the second input information in the third window may further include: selecting the second input information from at least one second candidate input information preset in the third window. Here, the second candidate input information may include: preset input information having a user input frequency exceeding a frequency threshold based on historical input information statistics; and input information preset based on the analysis capabilities of a language model.

[0210] In a possible implementation, step 904 may include: analyzing the N candidate documents using a language model based on the second semantics, and obtaining statistical analysis results.

[0211] Here, the language model may include a machine learning model. The language model may implement at least one of the following based on pre-training: determining the semantics of input information, understanding the semantics, and analyzing literature.

[0212] In one possible implementation, the language model may include a generative pre-trained language model (GPT).

[0213] Here, the statistical analysis result can be obtained by the language model through summarization and / or secondary inference based on the candidate documents. In one possible implementation, determining the second semantics of the second input information entered by the user in the third window may include: using a speech model to determine the second semantics of the second input information entered by the user in the third window.

[0214] The second input information may indicate that a summary analysis is to be performed on N candidate documents.

[0215] For example, taking the candidate document as a patent document, the second input information may indicate summarizing at least one of the following items of N candidate documents: the type of technical solution adopted, the associated right holder, the field involved, the number of patent documents for specific statistical items, etc.

[0216] The language model may perform full text analysis based on the second semantics to obtain statistical analysis results for the analysis items indicated by the second input information.

[0217] In one possible implementation, the statistical analysis result may be displayed in at least one of the third window and the fourth window.

[0218] In one possible implementation, the statistical analysis result may be displayed in a window different from the third window and the fourth window.

[0219] In a possible implementation, the third window may display the second input information and the statistical analysis result of the second input information in the form of human-computer dialogue.

[0220] For example, as shown in FIG10 , assuming the candidate document is a patent document, a portion of the third window is used to display the associated information corresponding to each of the N candidate documents. A fourth window can be located to the side of the third window. The position and size of the fourth window can be freely adjusted by the user. The fourth window includes a dialog display space and an input space. The user can enter second input information in the input space at the bottom of the fourth window. The language model can determine the semantics of the second input information and analyze the N candidate documents. The display space can display the second input information and statistical analysis results in a dialog format.

[0221] In a possible implementation, at least one of the position and size of the fourth window can be adaptively adjusted based on the content displayed in the fourth window, thereby meeting the display requirements of the content displayed in the fourth window.

[0222] In this way, within the third window displaying N candidate documents, interactive statistical analysis of these N candidate documents is achieved through the fourth window, and statistical analysis of multiple candidate documents is performed using a language model. On the one hand, users can interact directly within the third window, improving convenience. On the other hand, the faster machine analysis reduces the time required for manual reading and statistical analysis, improving the efficiency of statistical analysis of N candidate documents.

[0223] In some embodiments, analyzing the first document based on the second semantics and obtaining a full-text analysis result includes:

[0224] Analyzing the N candidate documents based on a first statistical analysis parameter indicated by the second semantics to obtain a statistical number of candidate documents corresponding to each of the I first sub-analysis parameters associated with the first statistical analysis parameter;

[0225] The displaying of the statistical analysis results includes:

[0226] Display the statistical quantities corresponding to the I first sub-analysis parameters respectively.

[0227] Here, the first statistical analysis parameter may be an item for which statistics are required.

[0228] In one possible implementation, the first sub-analysis parameter is the analysis result obtained by analyzing each candidate document using the speech model. The first sub-analysis parameters obtained by statistically analyzing different candidate documents using the first statistical analysis parameter can be different or the same. A candidate document can have one or more associated first sub-analysis parameters.

[0229] As shown in Figure 11, an analysis of N candidate documents yields four first sub-analysis parameters associated with the first statistical analysis parameter: first sub-analysis parameter 1 through first sub-analysis parameter 4. Each first sub-analysis parameter corresponds to one or more candidate documents. The statistical quantity corresponding to each first sub-analysis parameter can be displayed in a fourth window. In Figure 11, XXX, YYY, ZZZ, and AAA represent statistical quantities.

[0230] Exemplarily, as shown in FIG12 , the candidate document is a patent document. The first statistical analysis parameter may be “beneficial effect”, that is, the speech model needs to statistically analyze the beneficial effects of N patent documents. The beneficial effects of each patent document may be the same or different. A patent document may have one or more beneficial effects. The beneficial effects (first sub-analysis parameter) obtained through statistical analysis include: improving stability, improving sealing, reducing power consumption, and reducing wear. Then, the statistical number of patent documents corresponding to each beneficial effect is obtained.

[0231] In one possible implementation, if the fourth window cannot display the statistical quantities corresponding to all first sub-analysis parameters, the statistical quantities may be displayed based on a predetermined priority. For example, first sub-analysis parameters with larger statistical quantities have a higher priority.

[0232] In some embodiments, the displaying of the statistical quantities corresponding to the I first sub-analysis parameters includes:

[0233] The statistical quantities are classified and displayed according to the first classification parameter.

[0234] The first classification parameter may be a classification for the candidate document, so that the statistical quantity of the first classification parameter for the subdivided type of the candidate document can be calculated.

[0235] As shown in Figure 13 , the statistical quantities in Figure 11 may be subdivided and counted according to first classification parameters 1 to 3. In Figure 13 , X, Y, Z, XX, YY, ZZ, and AA represent statistical quantities.

[0236] For example, as shown in FIG14 , for the statistical analysis results of the beneficial effects shown in FIG12 , the statistical analysis can be subdivided by the year of application of the candidate patent application, so as to obtain the statistical number of patent documents corresponding to different beneficial effects in different years.

[0237] In some embodiments, the statistical quantities are provided for selection, so that the fifth window displays the associated information corresponding to the candidate documents corresponding to the selected statistical quantities.

[0238] Here, selecting a statistical quantity may apply a first operation (such as hovering a mouse, single-clicking, double-clicking, long pressing, etc.) to the displayed statistical quantity.

[0239] Each statistical quantity may be provided with a hyperlink or command statement, etc. When a selection operation for a statistical quantity is detected, the hyperlink or command statement may be executed, and the associated information corresponding to the candidate documents corresponding to the statistical quantity may be displayed in the fifth window.

[0240] In one possible implementation, the third window and the fifth window may be the same window.

[0241] In one possible implementation, the third window and the fifth window may be different windows.

[0242] For example, in the patent document statistics shown in FIG14 , you can click any statistical quantity to display the associated information corresponding to the candidate document in the fifth window. The fifth window displays the associated information corresponding to the candidate documents in the same manner as the first window. From another perspective, displaying the candidate documents in the fifth window is equivalent to displaying the candidate documents in the first window.

[0243] In a possible implementation, the fifth window may display a seventh window for human-computer interaction within the third window. The function of the window is similar to that of the fourth window, and is used to perform statistical analysis on the candidate documents displayed in the fifth window.

[0244] In some embodiments, displaying the statistical quantities corresponding to the I first sub-analysis parameters includes:

[0245] Displaying the statistical quantities corresponding to the I first sub-analysis parameters respectively in a first form;

[0246] The statistical quantities displayed in the first form are provided for selection, and the statistical quantities corresponding to the first sub-analysis parameters are displayed in a second form; wherein the display area of ​​the second form is larger than that of the first form;

[0247] The statistical quantity displayed in the second form is provided for selection, so that the associated information of the candidate document corresponding to the selected statistical quantity displayed in the second form is displayed in the fifth window.

[0248] In a possible implementation, the first form may include a table display, a graph display, a pie chart display, or the like.

[0249] In a possible implementation, the second form and the first form may be the same in display mode, but have different display areas.

[0250] The method for selecting the statistical quantity is as described above and will not be repeated here.

[0251] In a possible implementation, the second form of statistical quantity may be displayed in the sixth window.

[0252] The sixth window may be different from the third window and the fourth window, or may be the same window as the third window or the fourth window.

[0253] As shown in FIG15 , the first form is to use the first table to display statistical quantities. After the selection operation is performed, the second table may be displayed in the sixth window instead of the fifth window. The display area of ​​the sixth window may be the same as that of the third window, so as to accommodate the second table with a larger display area.

[0254] In one possible implementation, the text in the second form is larger than the text in the first form, so as to be more convenient for users to observe.

[0255] In a possible implementation, the second form can display the statistical quantity corresponding to the first sub-analysis parameter that cannot be displayed in the first form, thereby improving the completeness of the statistical analysis result display.

[0256] In one possible implementation, the sixth window may be provided with a format conversion option for converting the display mode of the second form of the statistical quantity. Exemplarily, the statistical quantity displayed in the second form may be converted to a third form. For example, the statistical quantity displayed in a table may be converted to be displayed in a curve chart, a bar chart, or the like.

[0257] In some embodiments, the associated information corresponding to the N candidate documents displayed in the third window is provided for selection, so that the candidate document corresponding to the selected associated information is displayed in the first window.

[0258] In a possible implementation, the third window and the first window are the same window.

[0259] In one possible implementation, the third window and the first window are different windows.

[0260] In one possible implementation, the embodiment shown in FIG. 9 may be implemented before the embodiment shown in FIG. 1 .

[0261] Here, the selection operation may include one of the following: mouse hover, single click, double click, long press.

[0262] Each associated information may be provided with a hyperlink or command statement. When a selection operation for a certain associated information is detected, the hyperlink or command statement may be executed, and the candidate document corresponding to the associated information may be displayed in the first window. This is equivalent to displaying the first document in the first window.

[0263] FIG16 shows an embodiment of the present application providing a document intelligent display device 10, the device comprising: a processing module 11, the processing module being configured to:

[0264] Displaying a first document in a first window, and displaying a second window for human-computer interaction within the first window;

[0265] determining a first semantic meaning of first input information input by a user in the second window, wherein the first input information is used to indicate an analysis of the first document;

[0266] Analyze the first document based on the first semantics to obtain a full-text analysis result;

[0267] The full text analysis results are displayed.

[0268] In some embodiments, the processing module is further configured to:

[0269] At least one piece of position information is displayed in at least one of the first window and the second window, wherein the position information is used to indicate a position of the document content associated with the full-text analysis result in the first document.

[0270] In some embodiments, the processing module is further configured to:

[0271] In response to displaying the at least one location information, the first document is associated with at least one location indicated by the location information in the first window.

[0272] In some embodiments, the location information is provided for selection so as to associate the location indicated by the location information with the first document within the first window.

[0273] In some embodiments, the processing module is specifically configured to:

[0274] Analyzing the first document based on the target content category indicated by the first semantics to obtain at least one full-text analysis result associated with the target content category;

[0275] Each of the full-text analysis results is displayed in a classified manner based on at least one sub-category attribute included in the target content category.

[0276] In some embodiments, the sub-category attributes included in the target content category are pre-set; and / or

[0277] The sub-category attributes included in the target content category are set based on the full-text analysis result.

[0278] In some embodiments, the processing module is further configured to:

[0279] Determine N candidate documents that meet the search conditions, and display the associated information corresponding to the N candidate documents in the third window;

[0280] Displaying a fourth window for human-computer interaction within the third window;

[0281] determining a second semantic meaning of second input information input by the user in the fourth window, wherein the second input information is used to indicate a statistical analysis of the candidate document;

[0282] Analyze the N candidate documents based on the second semantics and obtain statistical analysis results;

[0283] The statistical analysis results are displayed.

[0284] In some embodiments, the processing module is specifically configured to:

[0285] Analyzing the N candidate documents based on a first statistical analysis parameter indicated by the second semantics to obtain a statistical number of candidate documents corresponding to each of the I first sub-analysis parameters associated with the first statistical analysis parameter;

[0286] Display the statistical quantities corresponding to the I first sub-analysis parameters respectively.

[0287] In some embodiments, the processing module is specifically configured to:

[0288] The statistical quantities are classified and displayed according to the first classification parameter.

[0289] In some embodiments, the statistical quantities are provided for selection, so that the fifth window displays the associated information corresponding to the candidate documents corresponding to the selected statistical quantities.

[0290] In some embodiments, the processing module is specifically configured to:

[0291] Displaying the statistical quantities corresponding to the I first sub-analysis parameters respectively in a first form;

[0292] The statistical quantities displayed in the first form are provided for selection, and the statistical quantities corresponding to the first sub-analysis parameters are displayed in a second form; wherein the display area of ​​the second form is larger than that of the first form;

[0293] The statistical quantity displayed in the second form is provided for selection, so that the associated information of the candidate document corresponding to the selected statistical quantity displayed in the second form is displayed in the fifth window.

[0294] In some embodiments, the associated information corresponding to the N candidate documents displayed in the third window is provided for selection, so that the candidate document corresponding to the selected associated information is displayed in the first window.

[0295] In some embodiments, the processing module is specifically configured to:

[0296] Based on the first semantics, the selected portion of the first document is analyzed to obtain a full-text analysis result corresponding to the selected portion of the first document.

[0297] It should be understood that the division of the various units or modules in the above devices is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above devices, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), and the functions of some or all of the above units or modules are realized by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the remaining part by the form of hardware circuits.

[0298] In an embodiment of the present application, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of a hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0299] Figure 17 is a schematic diagram of the structure of an electronic device 9100 provided in an embodiment of the present application. Electronic device 9100 can be a computer terminal, a server, a chip, a chip system, or a processor that supports implementation of any of the above methods, or a chip, a chip system, or a processor that supports a terminal to implement any of the above information transmission methods. Electronic device 9100 can be used to implement the document intelligent display method described in the above method embodiment. For details, please refer to the description of the above method embodiment.

[0300] As shown in Figure 17, the electronic device 9100 includes one or more processors 9101. The processor 9101 can be a general-purpose processor or a dedicated processor, etc. The processor 9101 is used to call instructions to enable the electronic device 9100 to execute any of the above document intelligent display methods.

[0301] In some embodiments, the electronic device 9100 further includes one or more memories 9102 for storing instructions. Optionally, all or part of the memories 9102 may be located outside the electronic device 9100.

[0302] In some embodiments, the electronic device 9100 further includes one or more transceivers 9103. When the electronic device 9100 includes one or more transceivers 9103, the steps of sending, receiving, and / or acquiring in the above method are performed by the transceiver 9103, and the other steps are performed by the processor 9101.

[0303] In some embodiments, the steps of obtaining and the like in the above method may also be executed by the processor 9101 , for example, obtaining information from the memory 9102 .

[0304] Optionally, the electronic device 9100 further includes one or more interface circuits 9104, which are connected to the memory 9102. The interface circuits 9104 can be used to receive signals from the memory 9102 or other devices, and can be used to send signals to the memory 9102 or other devices. For example, the interface circuits 9104 can read instructions stored in the memory 9102 and send the instructions to the processor 9101.

[0305] The electronic device 9100 described in the above embodiments may be a network device or a terminal, but the scope of the electronic device 9100 described in this application is not limited thereto, and the structure of the electronic device 9100 may not be limited to Figure 17. The electronic device may be an independent device or may be part of a larger device.

[0306] Those skilled in the art will appreciate that all or part of the steps of the above method embodiments may be implemented by hardware related to program commands, and the aforementioned program may be stored in a storage medium, including various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0307] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes several commands to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0308] It should be understood that the above embodiments are exemplary and are not intended to encompass all possible implementations of the claims. Various modifications and variations may be made to the above embodiments without departing from the scope of this application. Similarly, the various technical features of the above embodiments may be arbitrarily combined to form additional embodiments of the present application that may not be explicitly described. Therefore, the above embodiments merely illustrate several implementations of the present application and do not limit the scope of protection of the patent application.

Claims

1. A method for intelligent document display, wherein: The method comprises: Displaying a first document in a first window, and displaying a second window for human-computer interaction within the first window; determining a first semantic meaning of first input information input by a user in the second window, wherein the first input information is used to indicate an analysis of the first document; Analyze the first document based on the first semantics to obtain a full-text analysis result; The full text analysis results are displayed.

2. The method according to claim 1, wherein The method further comprises: At least one piece of position information is displayed in at least one of the first window and the second window, wherein the position information is used to indicate a position of the document content associated with the full-text analysis result in the first document.

3. The method according to claim 2, wherein: The method further comprises: In response to displaying the at least one location information, the first document is associated with at least one location indicated by the location information in the first window.

4. The method according to claim 2, wherein: The position information is provided for selection, so as to associate the position indicated by the position information with the first document within the first window.

5. The method according to claim 1, wherein The first document is analyzed based on the first semantics, and a full-text analysis result is obtained, including: Analyzing the first document based on the target content category indicated by the first semantics to obtain at least one full-text analysis result associated with the target content category; The display of the full-text analysis results includes: Each of the full-text analysis results is displayed in a classified manner based on at least one sub-category attribute included in the target content category.

6. The method according to claim 5, wherein: The sub-category attributes included in the target content category are pre-set; and / or The sub-category attributes included in the target content category are set based on the full-text analysis result.

7. The method according to claim 1, wherein The method further comprises: Determine N candidate documents that meet the search conditions, and display the associated information corresponding to the N candidate documents in the third window; Displaying a fourth window for human-computer interaction within the third window; determining a second semantic meaning of second input information input by the user in the fourth window, wherein the second input information is used to indicate a statistical analysis of the candidate document; Analyze the N candidate documents based on the second semantics and obtain statistical analysis results; The statistical analysis results are displayed.

8. The method according to claim 7, wherein: The first document is analyzed based on the second semantics, and a full-text analysis result is obtained, including: Analyzing the N candidate documents based on a first statistical analysis parameter indicated by the second semantics to obtain a statistical number of candidate documents corresponding to each of the I first sub-analysis parameters associated with the first statistical analysis parameter; The displaying of the statistical analysis results includes: Display the statistical quantities corresponding to the I first sub-analysis parameters respectively.

9. The method according to claim 8, wherein The displaying of the statistical quantities corresponding to the I first sub-analysis parameters respectively includes: The statistical quantities are classified and displayed according to the first classification parameter.

10. The method according to claim 8, wherein The statistical quantities are provided for selection, so that the fifth window displays the associated information corresponding to the candidate documents corresponding to the selected statistical quantities.

11. The method according to claim 10, wherein: The displaying of the statistical quantities corresponding to the I first sub-analysis parameters respectively includes: Displaying the statistical quantities corresponding to the I first sub-analysis parameters respectively in a first form; The statistical quantities displayed in the first form are provided for selection, and the statistical quantities corresponding to the first sub-analysis parameters are displayed in a second form; wherein the display area of ​​the second form is larger than that of the first form; The statistical quantity displayed in the second form is provided for selection, so that the associated information of the candidate document corresponding to the selected statistical quantity displayed in the second form is displayed in the fifth window.

12. The method according to any one of claims 7 to 11, wherein: The associated information corresponding to the N candidate documents displayed in the third window is provided for selection, so that the candidate document corresponding to the selected associated information is displayed in the first window.

13. The method according to any one of claims 7 to 11, wherein: The first document is analyzed based on the first semantics to obtain a full-text analysis result, including: Based on the first semantics, the selected portion of the first document is analyzed to obtain a full-text analysis result corresponding to the selected portion of the first document.

14. A document intelligent display device, wherein: The device includes: a processing module; the processing module is configured to: Displaying a first document in a first window, and displaying a second window for human-computer interaction within the first window; determining a first semantic meaning of first input information input by a user in the second window, wherein the first input information is used to indicate an analysis of the first document; Analyze the first document based on the first semantics to obtain a full-text analysis result; The full text analysis results are displayed.

15. An electronic device, wherein: The electronic device comprises: one or more processors; The processor is configured to call instructions to enable the electronic device to execute the document intelligent display method according to any one of claims 1 to 13.

16. A storage medium, wherein: The storage medium stores instructions, and when the instructions are executed on the electronic device, the electronic device executes the document intelligent display method according to any one of claims 1 to 13.

Images