Document information recommendation methods, related equipment, and computer programs

Abstract

This provides an improved document information recommendation method. [Solution] The document information recommendation method of this disclosure includes determining one or more questions related to a document in response to a user's access operation to a document satisfying predetermined conditions, and displaying the one or more questions in a predetermined area of ​​the document, wherein the one or more questions are generated based on the content of one or more target documents related to the document.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and particularly to a method for recommending document information and related devices.

Background Art

[0002] With the development of computer science and technology, in some scenarios, documents can be viewed using software, application programs, or web page browsers.

[0003] However, the inventors of the present disclosure have discovered that in related technologies, after a user views a document, the user may have some questions about the content of the document, and at this time, the user can only search for the answers to the questions by himself, resulting in relatively low working efficiency.

Summary of the Invention

Problems to be Solved by the Invention

[0004] In view of this, an object of the present disclosure is to propose a method for recommending document information and related devices for solving or partially solving the above technical problems.

Means for Solving the Problems

[0005] According to a first aspect of the present disclosure, a method for recommending document information is provided, the method comprising: determining one or more questions related to the document in response to an access operation by a user to the document satisfying a predetermined condition; and displaying the one or more questions in a preset area of the document, wherein the one or more questions are generated based on the content of one or more target documents related to the document.

[0006] According to a second aspect of the present disclosure, a document information recommendation device is provided, the device comprising: A decision module configured to determine one or more questions related to a document in response to a user's access operation to the document meeting predetermined conditions, The document includes a display module configured to display one or more of the questions in a pre-defined area of ​​the document, The aforementioned one or more questions are generated based on the content of one or more target documents related to the aforementioned document.

[0007] A third aspect of this disclosure provides a computer device comprising memory, a processor, and a computer program stored in the memory and operable on the processor, wherein when the processor executes the program, the method of the first aspect is realized.

[0008] According to a fourth aspect of the present disclosure, a non-temporary computer-readable storage medium is provided, the non-temporary computer-readable storage medium storing computer instructions, the computer instructions are used to cause a computer to perform the method described in the first aspect.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, which includes computer program instructions, and which, when the computer program instructions are run on a computer, cause the computer to perform the method described in the first aspect. [Effects of the Invention]

[0010] As can be seen from the above, the document information recommendation method and related equipment disclosed herein can, in the process of viewing a document, display document-related questions in a pre-set area of ​​the document when the operation of viewing the document meets certain conditions, thereby further searching for document-related information based on these questions, eliminating much of the work that would otherwise be required to organize and summarize, and significantly improving the user's work efficiency. [Brief explanation of the drawing]

[0011] To more clearly illustrate the technical concepts in this disclosure or related technologies, the following briefly introduces the drawings that may be used in the descriptions of the embodiments or related technologies. Obviously, the drawings in the following descriptions are merely embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any creative effort. [Figure 1] A schematic diagram of an exemplary system according to an embodiment of the present disclosure is shown. [Figure 2A] A schematic diagram of one exemplary page according to an embodiment of this disclosure is shown. [Figure 2B] A schematic diagram of another exemplary page according to an embodiment of this disclosure is shown. [Figure 3A] A schematic diagram of one exemplary page according to an embodiment of this disclosure is shown. [Figure 3B] A schematic diagram of another exemplary page according to an embodiment of this disclosure is shown. [Figure 4] A schematic diagram of one exemplary page according to an embodiment of this disclosure is shown. [Figure 5] A flowchart illustrating an exemplary method according to the embodiments of this disclosure is shown. [Figure 6] A schematic diagram of the structure of an exemplary apparatus according to an embodiment of the present disclosure is shown. [Figure 7] A schematic diagram of the hardware structure of an exemplary electronic device according to an embodiment of this disclosure is shown. [Modes for carrying out the invention]

[0012] To make the purpose, technical proposal, and advantages of this disclosure clearer, this disclosure will be described in more detail below with reference to the drawings, along with specific examples.

[0013] Unless otherwise defined, technical or scientific terms used in the embodiments of this disclosure should have the general meaning understood by a person of general skill in the art to which this disclosure belongs. The terms “first,” “second,” and similar terms used in the embodiments of this disclosure do not indicate any order, number, or importance, but are used solely to distinguish different components. Similar terms such as “include” or “incorporate” mean that the element or substance appearing before it includes the enumerated elements or substances and their equivalents appearing after it, but do not exclude other elements or substances. Similar terms such as “connection” or “link” are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Terms such as “up,” “down,” “left,” and “right” are used solely to describe relative positional relationships, and these relative positional relationships change accordingly as the absolute position of the object being described changes.

[0014] Before using any of the technical proposals in each embodiment of this disclosure, it is understood that the user will be informed in an appropriate manner of the type of personal information involved, the scope of use, and the usage scenario, and that the user's permission will be obtained.

[0015] For example, when responding to a user's voluntary request, prompt information is sent to the user to clearly prompt the user that it is necessary to obtain and use the user's personal information in order to perform the requested operation. This allows the user to autonomously choose whether or not to provide personal information to software or hardware such as electronic devices, application programs, servers, or storage media that perform the operation of the proposed technical method of this disclosure based on the prompt information.

[0016] As a selective but non-limiting implementation form, the method of sending prompt information to the user in response to receiving the user's spontaneous request may be, for example, in the form of a pop-up window. In the pop-up window, the prompt information may be presented in text form. In addition, the pop-up window may further carry a selection control for the user to select whether to "agree" or "disagree" to provide personal information to the electronic device.

[0017] The above notification and user permission acquisition process is only schematic and does not limit the implementation forms of the present disclosure. It can be understood that other methods that comply with relevant laws and regulations are also applicable to the implementation forms of the present disclosure.

[0018] FIG. 1 shows a schematic diagram of an exemplary system 100 according to an embodiment of the present disclosure.

[0019] As shown in FIG. 1, the system 100 may be used to provide functions for online or offline viewing and editing documents, and may include a terminal device 102, a service side 106, and a database server 108. A medium (e.g., a network) providing a communication link may be included among the terminal device 102, the service side 106, and the database server 108. This network may include various connection types, such as wired, wireless communication links, or optical fiber cables.

[0020] The terminal device 102 may have various software or application programs (APPs) installed on it, such as collaborative office software or application programs, image processing software or application programs, video conferencing software or application programs, reading software or application programs, video software or application programs, social software or application programs, payment software or application programs, a web page browser and instant messaging tools, etc. In some embodiments, these software or application programs may all be used to present and edit documents.

[0021] The terminal device 102 here may be hardware or software. If the terminal device 102 is hardware, it may be various electronic devices having a display screen, including but not limited to smartphones, tablet computers, e-book readers, MP3 players, laptop computers (Laptops) and desktop computers (PCs). If the terminal device 102 is software, it may be installed on any of the electronic devices listed above. It may be implemented as multiple software or software modules (for example, used to provide distributed services), or as a single software or software module. This is not specifically limited here.

[0022] The service side 106 may be a server that provides various services, for example, a backend server that provides support for various applications displayed on terminal device 102. The database server 108 may be a database server that provides various services. It can be understood that if the service side 106 can implement the related functions of the database server 108, then it is not necessary to install the database server 108 in system 100.

[0023] Here, the service side 106 and the database server 108 may be hardware or software. If they are hardware, they may be implemented as a distributed server cluster consisting of multiple servers or as a single server. If they are software, they may be implemented as multiple software or software modules (for example, used to provide a distributed service) or as a single software or software module. There are no specific limitations here.

[0024] The method for recommending questions for the documentation according to the embodiments of this disclosure may be performed by terminal device 102 or by system 100. It should be understood that the number of terminal devices, users, servers and database servers in Figure 1 is approximate. Any number of terminal devices, users, servers and database servers may be used as required by implementation.

[0025] In some embodiments, the terminal device 102 may have a shared office application program or software installed on it, and the user 104 can use this application program or software installed on the terminal device 102 to perform office work. For example, browsing documents.

[0026] However, in some scenarios, for example, user 104 may have several questions about the document's content after viewing it, and at this point, the user can only seek answers to their questions themselves, for example, by researching and viewing other documents related to the current document. In some specific scenarios, if user 104 needs to research materials related to this document within their company, they may need to ask other colleagues for help or search for related materials in the company's internal library themselves. Furthermore, after obtaining the materials, the user may need to further acquire information by viewing the materials and find answers to their questions from there.

[0027] In view of this, according to one embodiment of the present disclosure, a document information recommendation method is provided.

[0028] Figure 2A shows a schematic diagram of an exemplary page 200 according to an embodiment of the present disclosure. This page 200 may be used to present and edit the document.

[0029] As shown in Figure 2A, in some embodiments, user 104 can use terminal device 102 to open collaborative office software or use a web page browser to open a collaborative office webpage, open a document using this software or webpage, and further present page 200 to terminal device 102, and display the document 202 opened on page 200.

[0030] Selectively, if user 104 only has permission to view document 202, they can only view document 202 on page 200. If user 104 also has permission to edit document 202, they can edit document 202 on page 200. If user 104 has other permissions for document 202, they can also perform operations on document 202 corresponding to those other permissions.

[0031] As mentioned above, after finishing viewing document 202, user 104 may need to look up and view other related materials to obtain more information. However, this operation is relatively inconvenient.

[0032] In view of this, in some embodiments, several questions can be generated for user 104 based on this document 202, and by further generating answers corresponding to the questions, time can also be saved for user 104 in searching for and summarizing the material.

[0033] As one selective embodiment, the timing for triggering this question generation mechanism may be when document 202 is opened, when document 202 has been browsed up to page n (where n is 1 or greater), or when browsing of document 202 is complete. Here, when document 202 is opened, the question generation mechanism is triggered, thereby giving system 100 more time to complete various operations related to question generation, and furthermore, enabling a faster response when the question is finally present on page 200. When document 202 has been browsed up to page n, the question generation mechanism is triggered, meaning that various operations related to question generation can be completed only when page n of document 202 is displayed on page 200, thereby avoiding unnecessary resource consumption due to user 104 accidentally opening document 202. When viewing document 202 is complete, the question generation mechanism is triggered. This means that various operations related to question generation can only be completed when the last page of document 202 is displayed on page 200. This allows the relevant questions to be generated after user 104 has finished viewing document 202, avoiding unnecessary resource consumption caused by user 104 exiting the viewing process prematurely.

[0034] Furthermore, in some embodiments, questions may be generated based on the content of one or more target documents related to document 202, thereby ensuring a high degree of relevance between the questions and the content of document 202, and further enhancing the user experience. For this reason, when the question generation mechanism is triggered, the target documents associated with document 202 may be determined first.

[0035] Selectively, one or more target documents related to document 202 are: Document 202 itself, One or more other documents cited by Document 202, If one or more other documents cite Document 202, Other documents listed in the bidirectional links section of Document 202, Document 202 includes at least one of one or more other documents associated with the keywords of Document 202.

[0036] For illustrative purposes, the other documents mentioned above may refer to documents different from Document 202. Here, other documents that are cited or referenced by Document 202 are highly relevant to the content of Document 202, and by generating questions based on these documents, questions related to Document 202 can be better recommended. Other documents associated with keywords in Document 202 are also relatively highly relevant to Document 202, and by generating questions based on these documents, questions related to Document 202 can be relatively better recommended. By generating questions based on Document 202 itself, it is possible to help User 104 summarize the essence or important content of Document 202, and questions related to Document 202 can be relatively better recommended.

[0037] Selectively, the determination of whether Document 202 cites another document may be based on whether Document 202 includes information such as a link and title of that other document. Conversely, the determination of whether Document 202 is cited by another document may be based on whether the other document includes information such as a link and title of Document 202.

[0038] For illustrative purposes, referring to Figure 2B, page 200 may further include a bidirectional link area 200A. Bidirectional links may refer to forward links and reverse links, where a forward link may refer to other documents linked by document 202 (which may be understood as other documents cited by document 202), and a reverse link may refer to other documents linking to document 202 (which may be understood as other documents citing document 202). By having these forward and reverse links present on page 200 via the bidirectional link area 200A, user 104 can directly find other documents with a strong relevance to document 202 from the bidirectional link area 200A, eliminating the need for user 104 to search for bidirectional linked documents themselves and improving user efficiency.

[0039] Based on this, when determining target documents related to document 202, the documents with forward and reverse links can be directly found in the bidirectional link area 200A, and the target documents can be filtered from among them. Since these bidirectional link documents have a strong relationship with document 202, recommendations based on these bidirectional link documents can yield better results. On the other hand, the documents present in the bidirectional link area 200A may be those obtained through preprocessing, and by directly obtaining the documents with forward and reverse links from among them, the process of traversing document 202 to obtain documents with citation and cited relationships can be omitted, thereby improving processing speed.

[0040] As one selective implementation, keywords may be extracted from document 202, and then documents may be searched in the database based on the extracted keywords. The documents in the search results may be other documents associated with the keywords in document 202. Selectively, these keywords may be terms in the title of document 202, for example, the title may be "Development Outlook for Artificial Intelligence," and the keyword may be "Artificial Intelligence." Selectively, these keywords may be terms that appear relatively frequently in document 202 (e.g., appearing 10 or more times), such as "Natural Language Model" or "Large-Scale Language Model." By extracting keywords and searching for documents that match the keywords, the target document may be determined based on these documents, strengthening the relationship between the target document and document 202, and obtaining a better recommendation effect.

[0041] In some embodiments, in order to further personalize the recommended questions, when retrieving other documents in the above embodiments, documents that satisfy the requirements of the above embodiments may be retrieved from a target database. This target database may be a private database of the company where user 104 works. In this way, the documents retrieved from this database will reflect the characteristics or individuality of the company where user 104 works, allowing the recommended related questions to be better suited to the actual situation of the company where user 104 works, and further improving user 104's office work efficiency.

[0042] When selectively determining one or more target documents related to document 202 in order to improve the relevance between the generated questions and document 202, the system first retrieves one or more first documents cited by document 202 and one or more second documents that cite document 202. If the sum of the number of first and second documents is less than a predetermined number (e.g., 10), it may further retrieve one or more third documents associated with keywords in document 202. This predetermined number is used to limit the total number of target documents and to avoid a situation where a small number of target documents results in an insufficient number of generated questions, or where a large number of targets results in too many questions (including many impurities), further weakening the relevance between the questions and document 202.

[0043] Accordingly, if the sum of the number of first documents and second documents is greater than or equal to a predetermined number (for example, 10 documents), one or more target documents related to the documents may be determined based on the one or more first documents and the one or more second documents. If the sum of the number of first documents and second documents is less than a predetermined number, one or more target documents related to the documents may be determined based on the one or more first documents, the one or more second documents and the one or more third documents.

[0044] In some embodiments, when retrieving other documents cited by document 202, other documents citing document 202, or other documents associated with keywords in document 202 from the database, these documents may be filtered to obtain a final first, second, and third document so that the first, second, and third documents satisfy some specific requirements.

[0045] Specifically, the system may selectively retrieve one or more first candidate documents that are cited by document 202 from the target database, and then filter the one or more first candidate documents based on the user's viewing permissions, the number of times the first candidate documents are clicked, and the number of characters in the first candidate documents.

[0046] If, in some embodiments, other documents corresponding to the document links and titles contained in document 202 do not exist in the target database, it can be understood that such documents should not be considered the first document and should be filtered out to ensure the personalization of the question.

[0047] Here, filtering based on user viewing permissions may result in the first candidate document being filtered out if user 104 does not have viewing permissions for that document. Filtering based on the number of times a first candidate document is clicked may also result in the document being filtered out if it is clicked infrequently (e.g., less than 10 times), as this may indicate that the document is relatively unpopular and of relatively poor quality. Continuing to filter based on the number of characters in a first candidate document may also result in the document being filtered out if it has a small number of characters (e.g., less than 10 words or characters), as this may indicate that the document is of relatively poor quality.

[0048] In this way, the effectiveness of recommendation questions can be improved by obtaining the target document after filtering candidate documents.

[0049] Similarly, determining one or more second documents to cite document 202 may involve first determining one or more candidate second documents cited by document 202, and then filtering those one or more candidate second documents based on user access rights, the number of times the candidate second documents are clicked, and the number of characters in the candidate second documents. Specific implementations refer to the previous embodiment and will not be described further here.

[0050] Similarly, determining one or more third documents associated with the keywords of document 202 may involve first determining one or more candidate third documents associated with the keywords of document 202, and then filtering the one or more candidate third documents based on the user's viewing permissions, the number of times the candidate third documents are clicked, and the number of characters in the candidate third documents. Specific implementations will be described in reference to the previously mentioned examples and will not be explained further here.

[0051] This allows us to filter and obtain a certain number of first, second, and third documents.

[0052] The target document may then be determined based on these first, second, and third documents.

[0053] As mentioned above, if the sum of the numbers of the first and second documents is greater than or equal to a predetermined number, the target document may be determined based on the first and second documents. Specifically, if the sum of the numbers of the first and second documents is equal to a predetermined number, these first and second documents may be directly used as the target documents. If the sum of the numbers of the first and second documents is greater than a predetermined number, in some embodiments, these first and second documents may be rearranged, and the target document may be obtained by filtering based on the rearrangement result.

[0054] As one selective implementation, considering the greater relevance between Document 202 and other documents cited by Document 202, the first document may be placed before the second document. If the number of first documents is equal to a predetermined number, the first document may be directly designated as the target document, and all second documents may be filtered out. If the number of first documents is greater than the predetermined number, each first document may be sorted according to the chronological order in which it was cited by Document 202 (earlier cited documents are placed later, and later cited documents are placed earlier), and the target document may be selected in that order. If the number of first documents is less than the predetermined number, documents are filtered and supplemented from the second document. The method for filtering the second document is the same as the method for filtering the first document and will not be described further here.

[0055] As described above, in some other embodiments, if the sum of the number of first documents and second documents is less than a predetermined number, the one or more target documents associated with the documents may be determined based on the one or more first documents, the one or more second documents, and the one or more third documents. Specifically, the number of target documents may be supplemented by filtering documents from the third documents based on a difference value obtained by subtracting the sum of the number of first documents and second documents from a predetermined number.

[0056] Alternatively, the third document may be selectively sorted based on its degree of matching with document 202, then filtered in descending order of matching degree, and those with the highest matching degree may be added to the target document.

[0057] In this way, a predetermined number of target documents are obtained.

[0058] It should be understood that the above embodiments are merely illustrative. When comparing with a predetermined number, in addition to comparing with a predetermined number based on the sum of the number of the first document and the second document, in some embodiments, the number of the first document may be used to compare with a predetermined number, and if the number of the first document satisfies the requirements, questions that are more relevant to the background information of document 202 may be recommended due to a stronger citation relationship between the obtained target document and document 202. In some other embodiments, the number of the second document may be used to compare with a predetermined number, and if the number of the second document satisfies the requirements, questions that are more relevant to the information of further development of document 202 may be recommended due to a stronger citation relationship between the obtained target document and document 202. Furthermore, after filtering the first and second documents, when determining one or more target documents related to the said documents based on the one or more first documents and / or the one or more second documents, it is possible to choose to determine the target documents based on either the first or second document, depending on the differences in actual needs, thereby relating the recommendation questions with background information or with information on further development of document 202. When determining multiple target documents, a ratio of the number of first and second documents may be assigned among them, and the recommendation effect may be related with background information or with information on further development of document 202.

[0059] Similarly, when determining one or more target documents related to the said documents based on the said one or more first documents, the said one or more second documents and / or the said one or more third documents, it should be understood that the target documents may be filtered from the first, second and third documents based on the embodiments described above, and that by assigning numerical ratios to the first, second and third documents, the recommended questions may be more relevant to certain aspects or to broader questions.

[0060] Next, one or more candidate questions may be generated based on the content of each target document.

[0061] As one optional embodiment, candidate questions may be generated based on a target document using a pre-trained first model. This first model may be a machine learning model based on natural language processing and may be trained on a document that serves as training text. Optionally, this training text may be tagged with questions (these tags may be questions extracted based on the content of the training text), and the model may be subjected to supervised learning based on the tagged training text to obtain the aforementioned pre-trained first model.

[0062] Therefore, it is also possible to selectively use each target document as input to the first model and output a certain number (for example, 3) candidate questions.

[0063] In this way, several candidate questions can be obtained. For example, if the number of target documents is 10, 30 candidate questions can be obtained.

[0064] In some embodiments, when inputting a target document, the first model may be provided with context or prompts to guide the model's predictions, either as part of the model input data or as constraints on the model, thereby clarifying the question, strengthening guidance, and helping the user understand the question.

[0065] Selectively, this prompt, To generate only questions directly related to the document content, The title should be used as important context to supplement the question, The question should be specific and highly directional, and the use of vague pronouns such as "this" and "the" should be avoided and replaced with specific terminology from the document. This may include at least one of the following pieces of information: ensuring that the question includes contextual specificity when the content is broad or general, and ensuring that the expression of the subject is complete and clear.

[0066] By using the above information as a prompt to constrain the model's predictions, clearer and more guiding questions can be obtained.

[0067] As one optional embodiment, this prompt may further include prompt information that outputs a symbol or icon associated with the question. For example, "Add a symbol or icon appropriate to the theme of each question to enhance its expressive effect." In this way, the model can output a symbol or icon appropriate to the theme of the question, which may then be displayed with subsequent questions to enhance the visual effect and improve the user experience.

[0068] In some embodiments, candidate questions may be in JSON (JavaScript Object Notation) format, so that when subsequent questions are displayed, they can be rendered directly based on the JSON format text, improving processing efficiency.

[0069] After obtaining multiple candidate questions, one or more questions to recommend to user 104 may be determined based on these candidate questions generated by these target documents.

[0070] Selectively, the questions may be filtered from the candidate questions based on the number of characters in each candidate question.

[0071] You may selectively filter out questions that are too long (e.g., more than 18 characters) or too short (e.g., less than 10 characters). Filtering out questions with too many characters can help present them better when they are displayed, and filtering out questions with too few characters can help avoid questions that are too short, lack sufficient information, and therefore have relatively low reference value.

[0072] In some embodiments, if, after filtering based on character count, the number of remaining candidate questions is greater than a predetermined number of questions that need to be presented (e.g., 10), the remaining candidate questions may be further filtered. For example, the remaining candidate questions may be reordered based on the priority of the target document from which they are generated. For example, if the target document is the first document, the corresponding candidate questions are listed first, followed by candidate questions for which the target document is the second document, and finally candidate questions for which the target document is the third document. Here, the candidate questions for which the target document is the third document may be further reordered based on the degree of matching between the target document and document 202. Then, according to the order, one or more questions related to the aforementioned document are filtered from the candidate questions to obtain.

[0073] Thus, several questions related to Document 202 can be raised.

[0074] Furthermore, when the user's operation to access document 202 satisfies predetermined conditions (for example, when user 104 scrolls document 202 to the last page), terminal device 102 may determine one or more questions related to document 202. For example, one or more questions may be determined from the questions generated in the previous embodiment. Then, the one or more questions may be displayed in a pre-set area of ​​document 202. In this way, when user 104's operation to view document 202 satisfies specific conditions, they can see questions related to document 202, thereby further exploring information related to document 202 based on these questions, saving a lot of work that would otherwise require organizing and summarizing the information themselves, and significantly improving user 104's work efficiency.

[0075] Figure 2B shows another schematic diagram of page 200, which is an example of an embodiment of the present disclosure.

[0076] As shown in Figure 2B, in some embodiments, the operation for a user to access document 202 may be defined as the user 104 scrolling to the end of document 202. At this point, it is possible that user 104 has already finished viewing document 202 and may continue with subsequent operations, such as researching other materials related to document 202. Therefore, in this case, relevant questions may be recommended to user 104, and recommending questions at this time has relatively little impact on user 104's browsing experience.

[0077] In addition to this embodiment, it can be understood that there may be many more of these pre-set conditions. For example, if, in the process of user 104 viewing document 202, user 104 leaves the current page 200 and returns to page 200 after a certain period of time to continue viewing document 202, it can be explained that user 104 may have looked at other materials during the process of leaving page 200. Therefore, the operation of a user accessing document 202 satisfying a predetermined condition may refer to the time difference between user 104 leaving document 202 and returning to document 202 exceeding a pre-set time length. In this case, by recommending relevant questions to user 104, user 104 can understand the relevant information more conveniently and the time user 104 spends looking at other materials can be reduced as much as possible. Also, for example, if document 202 has multiple chapters, relevant questions may be recommended to user 104 when each chapter ends. By inserting relevant questions between chapters in this way, user 104 can be clarified in a timely manner, and the user experience can be enhanced. In this case, the operation by which the user accesses document 202 may satisfy the predetermined conditions, which may refer to the period before the content of each chapter enters the visible area of ​​page 200.

[0078] Selectively, the aforementioned pre-set region is The adjacent area of ​​the editable region of document 202, The adjacent area of ​​the "Like" section in document 202, The adjacent region of the bidirectional link area in document 202, This may be at least one of the newly added areas within the bidirectional link area of ​​document 202.

[0079] Here, as shown in Figure 2B, the editable area of ​​document 202 may refer to the area where document 202 is located, and user 104 can edit document 202 in this area if they have editing privileges for document 202. In one optional embodiment, the pre-configured area for displaying one or more questions may be an area adjacent to the editable area of ​​document 202, for example, located to the left or right of the editable area of ​​document 202, or, when document 202 is scrolled to the end, located below and close to the editable area of ​​document 202. In this way, user 104 can view related questions from an area adjacent to the editable area of ​​document 202 during the process of viewing document 202, making the operation more convenient.

[0080] As shown in Figure 2B, in some embodiments, when the document 202 is scrolled to the end, a Like button 210 may be displayed on page 200, and the user 104 can Like the document 202 by triggering this button 210. In one optional embodiment, the pre-configured area for displaying one or more questions may be an area adjacent to the area where the Like button 210 of the document 202 is located (e.g., above, below, to the left, or to the right of the Like area), and since both Like and question searching belong to operations other than viewing the document 202, setting the pre-configured area adjacent to the Like area makes user operation easier, while setting the pre-configured area adjacent to the Like area, since the Like area is generally located at the end of the document, setting the pre-configured area adjacent to the Like area ensures the completeness of the viewing experience by allowing the user 104 to see the questions and Likes after finishing viewing the document 202.

[0081] As described above, as shown in Figure 2B, in some embodiments, page 200 may further include a bidirectional link area 200A, which may be used to present bidirectional links (including forward and reverse links), and user 104 can trigger these links to jump to the corresponding document pages, and user 104 can further view the documents corresponding to these links, provided that they have viewing privileges. In one optional embodiment, the pre-configured area for displaying one or more questions is an adjacent area of ​​the bidirectional link area 200A of document 202 (e.g., above, below, to the left, or to the right of the bidirectional link area 200A). By displaying one or more questions in this way adjacent to the bidirectional link area 200A, user 104 can see the bidirectional links and recommended questions simultaneously, making it easier to view them in contrast and more in line with user habits.

[0082] In some embodiments, a new area may be added to the bidirectional link area 200A of document 202 as a pre-configured area for displaying the one or more questions, thereby utilizing the bidirectional link area 200A to configure the pre-configured area and further saving page space.

[0083] As shown in Figure 2B, in one optional embodiment, the bidirectional link region 200A may further include three tabs, where the first tab corresponds to the pre-configured region for displaying the one or more questions, the second tab corresponds to a forward link for displaying one or more other documents referenced by the document, and the third tab corresponds to a reverse link for displaying one or more other documents referenced by the document.

[0084] In some embodiments, as shown in Figure 2B, a first tag 208A corresponding to the first tab may be displayed at a relevant location (e.g., the top) in the bidirectional link area 200A, and by triggering this tag 208A, one or more of the aforementioned questions may be displayed in the bidirectional link area 200A. Selectively, the information on this tag 208A may be, for example, "question and answer," thereby prompting the user 104 to answer the questions based on these questions recommended in the first tab, thereby obtaining the appropriate answers and further improving work efficiency.

[0085] Selectively, as shown in Figure 2B, the second tag 208B corresponding to the second tab and the third tag 208C corresponding to the third tab may be displayed at the relevant location in the bidirectional link region 200A (for example, the top of region 200A, one side of the first tag 208A). Selectively, since the first tab is currently displayed in the bidirectional link region 200A, the corresponding first tag 208A may be highlighted to enhance the visual effect.

[0086] In some embodiments, the corresponding second and third tabs may be presented by triggering a second tag 208B and a third tag 208C. For example, when the second tag 208B is triggered (for example, by clicking the second tag 208B), terminal device 102 may display information from one or more other documents cited by document 202, such as the title and thumbnail content of the first document which is the target document (e.g., highlighted content, fragments of important content in the document) in the bidirectional link area 200A. Alternatively, for example, when the third tag 208C is triggered (for example, by clicking the third tag 208C), terminal device 102 may display the title and thumbnail content of one or more other documents that quote document 202, such as the title and thumbnail content of the second document which is the target document (e.g., highlighted content, fragments of important content in the document) in the bidirectional link area 200A. In this way, by switching tags, user 104 can see document information that corresponds to document 202, which is cited or referenced to generate questions, and can further explore these documents.

[0087] If there are no other documents that cite or are cited by document 202, it can be understood that the second tag 208B and the third tag 208C may not be displayed in the bidirectional link area 200A.

[0088] In some embodiments, the timing for triggering the question generation mechanism may be when the first tag 208A enters the visible area of ​​page 200. In this way, by generating the question immediately before presenting it, it is possible to generate the question early but avoid wasting resources due to the user leaving the document midway. Furthermore, when the number of pages in the document is relatively small, it is possible to avoid the problem that the question generation mechanism cannot be fully triggered if page n does not exist.

[0089] As shown in Figure 2B, in some embodiments, one or more of the questions, for example, questions 204A to 204D, may be displayed on the first tab of the bidirectional link area 200A on page 200. Here, the bidirectional link area 200A is located at the end of document 202. By displaying the questions at the end of document 202 in this way, it is possible to avoid the questions appearing too early and affecting the user 104's viewing of document 202, thereby better aligning with the user's usage habits and improving the user experience.

[0090] In some embodiments, as shown in Figure 2B, symbols or icons associated with questions 204A to 204D may be displayed on page 200 in a relevant position (e.g., before) the questions 204A to 204D, thereby enhancing the visual effect.

[0091] As one selective implementation, to enhance the user experience, questions 204A-204D may be displayed as close to the end of document 202 as possible. As shown in Figure 2B, there is no other interface content (e.g., a like button 210, a comment area (not shown), etc.) between questions 204A-204D and the last paragraph of document 202. In this way, user 104 can improve their work efficiency by finding the recommended questions sooner.

[0092] Selectively, the arrangement of questions 204A to 204D on page 200 may differ based on the different types of terminal devices 102.

[0093] As one optional embodiment, if the terminal device 102 is a personal computer (PC) or tablet PC, questions 204A to 204D may be arranged in an array format, as shown in Figure 2B. In this case, since the horizontal space of page 200 is relatively large, questions 204A to 204D may be arranged in a left-to-right and top-to-bottom order, linking the lengths of the questions themselves, in order to make page 200 more compact and aesthetically pleasing.

[0094] As another optional embodiment, if the terminal device 102 is a mobile phone, as shown in Figure 3A, the horizontal space on page 300 is relatively small, so questions 302A to 302D may be arranged in a top-to-bottom order to make page 300 more aesthetically pleasing.

[0095] In some embodiments, as shown in Figure 3A, the available space on page 300 is relatively small, so instead of displaying the tags in the embodiments described above, prompt information 304 may be displayed to prompt the user 104 to answer the questions based on questions 302A to 302D, thereby enabling quicker access to the relevant answers.

[0096] As one optional embodiment, if there is a possibility that question retrieval will fail due to network or server issues, questions 204A-204D and 302A-302D may not be presented on pages 200 and 300 to avoid the display of tags or prompt information affecting the page's appearance because the questions are not presented. The first tag 208A, the second tag 208B, the third tag 208C, and prompt information 304 may also not be presented. Selectively, user 104 may re-retrieve the questions by refreshing pages 200 and 300, and if the questions can be retrieved, they may be presented normally according to the above embodiment.

[0097] Furthermore, in some embodiments, when user 104 triggers a question on page 200 or 300, the system may generate a corresponding answer based on this question, thereby allowing user 104 to quickly understand the relevant information by viewing the answer, saving time on summarization and improving work efficiency.

[0098] In some embodiments, a target application may be invoked in response to a trigger command for a target question among the one or more questions to generate a target answer corresponding to the target question.

[0099] As one selective embodiment, for example, terminal device 102 is a personal computer or tablet PC, and page 200 is displayed by a web page browser. Since the web page browser may not generate a target answer based on this target question, a target application may be called to generate a target answer corresponding to this target question.

[0100] Figure 4 shows a schematic diagram of another exemplary page 400 according to an embodiment of the present disclosure.

[0101] As shown in Figure 4, in some embodiments, in response to a trigger command for a target question (e.g., question 204A) among the one or more questions, a target application (e.g., collaborative office software) may be invoked, and the system may jump from page 200 to page 400, where page 400 further includes a window for question answers, in which the target question may be submitted and the target application may generate an answer corresponding to the target question. The target question 402 and the answer 404 corresponding to the target question 402 may then be displayed on page 400.

[0102] In some embodiments, the answer 404 may be generated based on the target question 402 using a pre-trained second model. Selectively, this second model may be a large-scale language model obtained by pre-training on a question-answering mechanism. In one selective embodiment, when the terminal device 102 invokes the target application, it sends the target question 402 to the server 106, and the second model deployed on the server 106 generates the answer 404 and returns it to the terminal device 102 for display.

[0103] Selectively, just before jumping from page 200 to page 400, prompt information may be displayed to prompt user 104 that it is now necessary to jump to another software. In another selective embodiment, if page 200 itself is a document page of the target application, the target application may switch to a question-answer page 400 and generate an answer 404 using a second model based on a second model module in the target application. Selectively, this second model module may send a target question 402 to the server 106 so that the second model deployed on the server 106 generates and returns an answer based on the question, and then receive and present the answer 404 returned from the server 106.

[0104] Figure 3B shows another schematic diagram of page 300, which is an example of an embodiment of the present disclosure.

[0105] As shown in Figure 3B, in some embodiments, if the terminal device 102 is a mobile phone, a first window 306 may be displayed on page 300 in response to a trigger command for a target question (e.g., question 302A) among the one or more questions, and the target question 3062 and the answer 3064 corresponding to the target question 3062 may be displayed in the first window 306.

[0106] In some embodiments, the answer 3064 may be generated based on the target question 3062 using a pre-trained second model. Selectively, this second model may be a large-scale language model obtained by pre-training on a question-answering mechanism. In one selective embodiment, when terminal device 102 opens window 306, it may send the target question 3062 to server 106, and the second model deployed on server 106 generates the answer 3064 and returns it to terminal device 102 for display.

[0107] Selectively, as shown in Figure 3B, window 306 may be displayed on page 300 in half-screen mode, thereby creating a visual effect of the window popping up from the bottom, and enhancing the user experience by allowing users to continue other operations after closing window 306 and returning to the document page.

[0108] As can be seen from the embodiments described above, the document recommendation question method according to the embodiments of this disclosure can improve work efficiency by eliminating the need for the user to summarize questions themselves, by recommending and presenting questions generated based on documents related to the currently viewed document at the bottom of the document after the user has finished viewing the document. In some embodiments, after clicking on a question to view details, intelligently narrowed-down answers to the questions are displayed, further improving work efficiency by eliminating the need to search for and organize answers.

[0109] The methods of the embodiments of this disclosure may be performed by a single device, such as a single computer or server. The methods of the embodiments may also be used in a distributed scenario in which multiple devices cooperate to complete the process. In such a distributed scenario, one of these multiple devices may perform only one or more steps of the methods of the embodiments of this disclosure, and these multiple devices may interact with each other to complete the method.

[0110] The above describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the operations or steps described in the claims may be performed in a different order than those in the embodiments above, and the desired results can still be achieved. Furthermore, the processes depicted in the drawings do not necessarily require a specific order or sequence shown to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0111] Based on essentially the same inventive concept, embodiments of this disclosure further provide a document information recommendation method.

[0112] Figure 5 shows a flowchart of an exemplary method 500 according to an embodiment of the present disclosure. This method 500 may be carried out by the terminal device 102 in Figure 1, or by the system 100 in Figure 1, and this method 500 may be used to recommend document information. This method 500 may further include the following steps.

[0113] In step 502, in response to the user's access operation to the document meeting certain conditions, one or more questions related to the document are determined.

[0114] In step 504, one or more of the questions (for example, questions 204A to 204D in Figure 2B, and questions 302A to 302D in Figure 3A) are displayed in a pre-defined area of ​​the document.

[0115] Here, the one or more questions mentioned above are generated based on the content of one or more target documents related to the said document.

[0116] The document information recommendation method disclosed herein allows users to view questions related to a document in a pre-defined area of ​​the document when certain conditions are met during the document viewing process. This enables users to further explore and organize information related to the document based on these questions, significantly improving user efficiency by eliminating much of the work required for summarization.

[0117] In some embodiments, one or more target documents related to the said document are: The aforementioned document itself, One or more other documents cited by the aforementioned document, One or more other documents that cite the aforementioned document, Other documents listed in the bidirectional link area of ​​the aforementioned document, The document includes at least one of one or more other documents associated with the keywords of the aforementioned document.

[0118] Here, other documents that have a citation or cited relationship with the document have a high relevance to the content of the document, and by generating questions based on these documents, questions related to the document can be recommended more effectively. Other documents associated with the keywords of the document also have a relatively high relevance to the document, and by generating questions based on these documents, questions related to the document can be recommended relatively effectively. Generating questions based on the document itself can help the user summarize the essence or important content of the document, and questions related to the document can be recommended relatively effectively. When determining target documents related to the document, the documents with forward and reverse links can be directly found in the bidirectional link area, and the target document can be filtered from among them. Since these bidirectional link documents have a strong relevance to the document, recommending based on these bidirectional link documents can yield better results. On the other hand, the documents present in the bidirectional link area may be those obtained through preprocessing, and by directly obtaining the documents with forward and reverse links from among them, the process of traversing the document to obtain documents with citation and cited relationships with it can be omitted, thereby improving processing speed. Furthermore, by extracting keywords and searching for documents that match those keywords, the target document is determined based on these documents, strengthening the relationship between the target document and document 202, and obtaining a better recommendation effect.

[0119] In some embodiments, the method 500 is, Determining one or more target documents related to the aforementioned document, Based on the content of each of the aforementioned target documents, one or more candidate questions are generated. The further includes determining the one or more candidate questions based on the one or more candidate questions corresponding to each of the target documents.

[0120] In this way, question recommendation can be better achieved by generating candidate questions based on the content of one or more target documents related to the aforementioned document, and by filtering the one or more questions from the candidate questions.

[0121] In some embodiments, the method 500 is, To determine one or more first documents cited by the said document and one or more second documents that cite the said document, In response to the determination that the number of the first document and / or the second document is greater than or equal to a predetermined number, one or more target documents related to the document are determined based on the one or more first documents and / or the one or more second documents, or In response to the determination that the number of the first document and / or the second document is smaller than a predetermined number, one or more third documents associated with the keywords of the document are determined, The further includes determining one or more target documents related to the said documents based on the said one or more first documents, the said one or more second documents and / or the said one or more third documents.

[0122] In this way, by prioritizing the selection of documents that are cited or cited by the aforementioned documents as target documents for question generation, the relevance between recommendation questions and documents can be increased, resulting in better recommendation effectiveness.

[0123] In some embodiments, the method 500 is, To determine one or more first candidate documents to be cited by the aforementioned document, The further includes filtering one or more first documents from the one or more first candidate documents based on the user's viewing permissions, the number of times the first candidate document is clicked, and / or the number of characters in the first candidate document, and / or Determining one or more second documents that cite the aforementioned document is: To determine one or more second candidate documents to be cited by the aforementioned document, This includes filtering one or more second documents from the one or more second candidate documents based on the user's viewing permissions, the number of times the second candidate document is clicked, and / or the number of characters in the second candidate document, and / or Determining one or more third documents associated with the keywords of the aforementioned document is: To determine one or more third candidate documents associated with the keywords of the aforementioned document, This includes filtering one or more third documents from the one or more third candidate documents based on the user's viewing permissions, the number of times the third candidate document is clicked, and / or the number of characters in the third candidate document.

[0124] In this way, the effectiveness of recommendation questions can be improved by obtaining the target document after filtering candidate documents.

[0125] In some embodiments, determining the one or more candidate questions based on the one or more candidate questions corresponding to each of the target documents is: This includes filtering one or more candidate questions based on the number of characters in each candidate question.

[0126] You may selectively filter out questions that are too long (e.g., more than 18 characters) or too short (e.g., less than 10 characters). Filtering out questions with too many characters can help present them better when they are displayed, and filtering out questions with too few characters can avoid the problem of questions having too little information and therefore relatively low reference value.

[0127] In some embodiments, displaying the document includes displaying the document on a first page (for example, page 200 in Figure 2A, page 300 in Figure 3A), Displaying the one or more questions at the end of the document includes displaying the one or more questions in a first area of ​​the first page (for example, area 200A in Figure 2B), the first area being located at the end of the document.

[0128] By displaying questions at the end of the document in this way, it is possible to avoid questions appearing too early and interfering with the user's viewing of the document, thereby better aligning with the user's usage habits and improving the user experience.

[0129] In some embodiments, the predetermined region is Adjacent areas of the editable area of ​​the aforementioned document, The adjacent area to the "Like" area of ​​the aforementioned document, The adjacent area of ​​the bidirectional link area of ​​the aforementioned document, or This includes a newly added area within the bidirectional link area of ​​the aforementioned document.

[0130] Here, the editable area of ​​the document may refer to the area where the document is located, and the user can edit the document in this area if they have editing privileges for the document. In one optional embodiment, the pre-configured area for displaying one or more questions may be an area adjacent to the editable area of ​​the document, for example, located to the left or right of the editable area of ​​the document, or, when the document is scrolled to the end, located below and close to the editable area of ​​the document. In this way, the user can view related questions from an area adjacent to the editable area of ​​document 202 during the process of viewing the document, making the operation more convenient.

[0131] As one optional embodiment, the pre-configured area for displaying one or more questions may be an area adjacent to the area where the document's "Like" button is located (for example, above, below, to the left of, or to the right of the "Like" area). Since both "Like" and question searching belong to operations other than viewing the document, setting the pre-configured area adjacent to the "Like" area can facilitate user operation. Furthermore, because the "Like" area is generally located at the end of the document, setting the pre-configured area adjacent to the "Like" area ensures the completeness of the viewing experience by allowing the user to view the questions and "Like" after finishing viewing the document.

[0132] As one optional embodiment, the pre-configured area for displaying the one or more questions may be an area adjacent to the bidirectional link area of ​​the document (for example, above, below, to the left of, or to the right of the bidirectional link area). By displaying the one or more questions in this way, adjacent to the bidirectional link area, the user can see the bidirectional links and the recommended questions simultaneously, making it easier to view them in contrast and more in line with user habits.

[0133] Displaying one or more of the aforementioned questions in a newly added area within the bidirectional link area of ​​the aforementioned document is, Displaying one or more of the questions in the first tab of the aforementioned bidirectional link area, Displaying one or more other documents cited by the document in the second tab of the aforementioned bidirectional link area, This includes at least one of the following: displaying one or more other documents that reference the aforementioned document in a third tab of the aforementioned bidirectional link area.

[0134] In this way, by adding a new tab to the bidirectional link area of ​​the document as a pre-configured area for displaying one or more of the aforementioned questions, the pre-configured area can be set using the bidirectional link area, and further page space can be saved.

[0135] In some embodiments, displaying one or more of the questions in the first area of ​​the first page is: This includes displaying a first tag corresponding to one or more questions (e.g., the first tag 208A in Figure 2B), a second tag corresponding to one or more other documents cited by the document (e.g., the second tag 208B in Figure 2B), and a third tag corresponding to one or more other documents citing the document (e.g., the third tag 208C in Figure 2B) at the relevant location in the first area, wherein the first tag is highlighted.

[0136] Since the currently displayed item is a question, the corresponding first tag is highlighted, thereby enhancing the visual effect.

[0137] In some embodiments, the above method is In response to a trigger command for the second tag, display one or more other documents referenced by the document in the first area, or The further includes displaying one or more other documents that reference the document in the first area in response to a trigger command for the third tag.

[0138] In this way, users can be presented with corresponding document information by triggering the second and third tags, making the operation more convenient.

[0139] In some embodiments, the above method is In response to a trigger command for a target question among the one or more of the aforementioned questions, a target application is invoked, the target question (for example, question 402 in Figure 4) is sent in the window of the target application, and the target application generates an answer corresponding to the target question (for example, answer 404 in Figure 4), or In response to a trigger command for a target question among the one or more questions, the first page is further to display a first window (e.g., window 306 in Figure 3B) and the first window displays the target question (e.g., question 3062 in Figure 3B) and the answer corresponding to the target question (e.g., answer 3064 in Figure 3B).

[0140] By presenting different pages on different types of devices, the page layout can be better adapted to the device type, enhancing the visual effect. Furthermore, by utilizing the question-answering capabilities of the target application to generate answers to questions, processing efficiency can be further improved, and resources can be saved.

[0141] In some embodiments, displaying one or more questions in a predetermined area of ​​the document further includes displaying symbols or icons associated with the questions (e.g., symbols or icons 206A-206D in Figure 2B) at the relevant location of the questions, thereby enhancing the visual effect.

[0142] The methods of the embodiments of this disclosure may be performed by a single device, such as a single computer or server. The methods of the embodiments may also be used in a distributed scenario in which multiple devices cooperate to complete the process. In such a distributed scenario, one of these multiple devices may perform only one or more steps of the methods of the embodiments of this disclosure, and these multiple devices may interact with each other to complete the method.

[0143] The above describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the operations or steps described in the claims may be performed in a different order than those in the embodiments above, and the desired results can still be achieved. Furthermore, the processes depicted in the drawings do not necessarily require a specific order or sequence shown to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0144] Based on essentially the same inventive concept and corresponding to the methods of any of the above embodiments, the present disclosure further provides a document information recommendation device. Figure 6 shows a schematic diagram of the structure of an exemplary device 600 according to an embodiment of the present disclosure.

[0145] Referring to Figure 6, the document information recommendation device 600 is, A decision module 602 is configured to determine one or more questions related to a document in response to a user's access operation to the document meeting predetermined conditions, The document may also include a display module 604 configured to display one or more of the questions in a pre-defined area of ​​the document, Here, the one or more questions mentioned above are generated based on the content of one or more target documents related to the said document.

[0146] In some embodiments, one or more target documents related to the said document are: The aforementioned document itself, One or more other documents cited by the aforementioned document, One or more other documents that cite the aforementioned document, Other documents listed in the bidirectional link area of ​​the aforementioned document, The document includes at least one of one or more other documents associated with the keywords of the aforementioned document.

[0147] In some embodiments, the decision module 602 is Determine one or more target documents related to the aforementioned document, Based on the content of each target document, one or more candidate questions are generated. The system is configured to determine one or more questions based on one or more candidate questions corresponding to each of the target documents.

[0148] In some embodiments, the decision module 602 is Determine one or more first documents cited by the said document and one or more second documents that cite the said document. In response to the determination that the number of the first document and / or the second document is greater than or equal to a predetermined number, one or more target documents related to the document are determined based on the one or more first documents and / or the one or more second documents, or In response to the determination that the number of the first and / or second documents is less than a predetermined number, one or more third documents associated with the keywords of the documents are determined. The system is configured to determine one or more target documents related to the said documents based on the said one or more first documents, the said one or more second documents, and / or the said one or more third documents.

[0149] In some embodiments, the decision module 602 is Determine one or more first candidate documents to be cited by the aforementioned document, The system is configured to filter and obtain one or more first documents from one or more first candidate documents based on the user's viewing permissions, the number of times the first candidate document is clicked, and / or the number of characters in the first candidate document.

[0150] In some embodiments, the decision module 602 is Determine one or more second candidate documents to be cited by the aforementioned document, The system is configured to filter and obtain one or more second documents from the one or more second candidate documents based on the user's viewing permissions, the number of times the second candidate document is clicked, and / or the number of characters in the second candidate document.

[0151] In some embodiments, the decision module 602 is Determine one or more third candidate documents that are associated with the keywords of the aforementioned document, The system is configured to filter and obtain one or more third documents from the one or more third candidate documents based on the user's viewing permissions, the number of times the third candidate document is clicked, and / or the number of characters in the third candidate document.

[0152] In some embodiments, the decision module 602 is configured to filter out one or more candidate questions based on the number of characters in each candidate question.

[0153] In some embodiments, the predetermined region is Adjacent areas of the editable area of ​​the aforementioned document, The adjacent area to the "Like" area of ​​the aforementioned document, The adjacent area of ​​the bidirectional link area of ​​the aforementioned document, or This includes a newly added area within the bidirectional link area of ​​the aforementioned document.

[0154] In some embodiments, the display module 604 is Displaying one or more of the questions in the first tab of the aforementioned bidirectional link area, Displaying one or more other documents cited by the document in the second tab of the aforementioned bidirectional link area, The system is configured to perform at least one of the following: display one or more other documents that reference the aforementioned document in the third tab of the bidirectional link area.

[0155] In some embodiments, the display module 604 is configured to respond to a trigger command for a target question among the one or more questions by calling a target application, sending the target question in the window of the target application, and having the target application generate an answer corresponding to the target question.

[0156] In some embodiments, the display module 604 is configured to display a first window on the document page in response to a trigger command for a target question among the one or more questions, and to display the target question and the answer corresponding to the target question in the first window.

[0157] In some embodiments, the display module 604 is configured to display a symbol or icon associated with the question at the relevant location of the question.

[0158] For the sake of convenience in description, the above device will be described by dividing it into various modules according to its function. Of course, when implementing this disclosure, the functions of each module may be implemented in the same or multiple software and / or hardware.

[0159] The apparatus of the above embodiment is used to implement the corresponding method 500 in any one of the embodiments described above, and has the beneficial effects of the embodiment of the corresponding method, which will not be described further here.

[0160] Based on essentially the same inventive concept, embodiments of the present disclosure further provide computer equipment for realizing the above-described method 500. Figure 7 shows a schematic diagram of the hardware structure of an exemplary computer equipment 700 according to an embodiment of the present disclosure. The computer equipment 700 may be used to realize the terminal equipment 102 in Figure 1. In some scenarios, the computer equipment 700 may be used to realize the server 106 and database server 108 in Figure 1.

[0161] As shown in Figure 7, the computer device 700 may include a processor 702, memory 704, a network module 706, a peripheral interface 708, and a bus 710. Here, the processor 702, memory 704, network module 706, and peripheral interface 708 enable internal communication between the computer device 700 via the bus 710.

[0162] The processor 702 may be a central processing unit (CPU), an image processor, a neural network processor (NPU), a microcontroller (MCU), a programmable logic device, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or one or more integrated circuits. The processor 702 may be used to perform functions related to the technologies described herein. In some embodiments, the processor 702 may further include multiple processors integrated into a single logic assembly. For example, as shown in Figure 7, the processor 702 may include multiple processors 702a, 702b, and 702c.

[0163] The memory 704 may be configured to store data (e.g., instructions, computer code, etc.). As shown in Figure 7, the data stored in the memory 704 may include program instructions (e.g., program instructions for implementing method 500 of the embodiments of this disclosure) and data to be processed (e.g., the memory may also store configuration files for other modules, etc.). The processor 702 may access the program instructions and data stored in the memory 704 and may execute the program instructions to manipulate the data to be processed. The memory 704 may include volatile or non-volatile storage devices. In some embodiments, the memory 704 may include random access memory (RAM), read-only memory (ROM), optical disks, magnetic disks, hard disks, solid-state drives (SSDs), flash memory, memory sticks, etc.

[0164] The network interface 706 may be configured to provide the computer device 700 with communication with other external devices via a network. This network may be any wired or wireless network capable of transmitting and receiving data. For example, this network may be a wired network, a local wireless network (e.g., Bluetooth®, Wi-Fi, Near Field Communication (NFC), etc.), a cellular network, the Internet, or a combination of the above. It should be understood that the type of network is not limited to the specific examples given above.

[0165] The peripheral interface 708 may be configured to connect the computer equipment 700 with one or more peripheral devices to enable information input and output. For example, the peripheral devices may include input devices such as keyboards, mice, touchpads, touchscreens, microphones, and various sensors, and output devices such as displays, speakers, vibrators, and indicator lights.

[0166] The bus 710 may be configured to transmit information between each assembly of the computer equipment 700 (e.g., processor 702, memory 704, network interface 706, and peripheral interface 708), for example, via an internal bus (e.g., processor-memory bus), an external bus (USB port, PCI-E bus), etc.

[0167] Although the architecture of the computer device 700 described above shows only the processor 702, memory 704, network interface 706, peripheral interface 708, and bus 710, in a specific implementation process, the architecture of this computer device 700 may further include other assemblies necessary to achieve normal operation. A person skilled in the art will understand that the architecture of the computer device 700 may include only the assemblies necessary to implement the embodiment of the present disclosure, and does not necessarily have to include all the assemblies shown in the figure.

[0168] Based on essentially the same inventive concept and corresponding to the methods of any of the above embodiments, the present disclosure further provides a non-temporary computer-readable storage medium on which computer instructions are stored, and which are used to cause the computer to execute the method 500 of any one of the above embodiments.

[0169] The computer-readable media of this embodiment include persistent and non-persistent, removable and non-removable media, and information can be stored by any method or technique. The information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random-access memory (SRAM), dynamic random-access memory (DRAM), other types of random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only disk memory (CD-ROM), digital multipurpose disk (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that may be used to store information accessible by computing equipment.

[0170] The computer instructions stored in the storage medium of the above embodiment are used to have the computer execute the method 500 of any one of the above embodiments, and have the beneficial effects of the embodiment of the applicable method, which will not be described further here.

[0171] Based on the same inventive concept, and corresponding to Method 500 of any of the above embodiments, the present disclosure further provides a computer program product including a computer program. In some embodiments, the computer program is executable by one or more of the processors in order to cause the processors to execute Method 500. Corresponding to the execution body corresponding to each step in each embodiment of Method 500, the processor that performs the corresponding step may belong to the corresponding execution body.

[0172] The computer program product of the above embodiment is used to cause a processor to execute the method 500 of any one of the above embodiments, and has the beneficial effects of the embodiment of the applicable method, which will not be described further here.

[0173] Those skilled in the art will understand that the consideration of the above-described examples is illustrative and not intended to imply that the scope of the Disclosure (including the claims) is limited to these examples, that in the spirit of the Disclosure, technical features in the above-described examples or different examples can be combined, that the steps can be carried out in any order, and that many other variations of different embodiments of the embodiments of the Disclosure described above exist, which are not provided in detail for the sake of simplicity.

[0174] Furthermore, in order to simplify the explanation and discussion, and to avoid making it difficult to understand the embodiments of this disclosure, the provided drawings may or may not show known power / ground connections of integrated circuit (IC) chips and other components. Also, in order to avoid making it difficult to understand the embodiments of this disclosure, the apparatus may be shown in the form of a block diagram, taking into consideration the following fact: the details of the embodiments of the apparatus in these block diagrams depend heavily on the platform on which the embodiments of this disclosure are carried out (i.e., these details should be fully within the understanding of those skilled in the art). Where specific details (e.g., circuits) are described to describe exemplary embodiments of this disclosure, it will be obvious to those skilled in the art that the embodiments of this disclosure can be carried out even if these specific details are absent or changed. Therefore, these descriptions should be considered descriptive, not restrictive.

[0175] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art as described herein. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used in the embodiments discussed.

[0176] The embodiments of this disclosure are intended to include all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for recommending document information, In response to a user's access operation to the document meeting certain conditions, one or more questions related to the document are determined. This includes displaying one or more of the questions in a pre-configured area of ​​the document, A document information recommendation method wherein the one or more of the aforementioned questions are generated based on the content of one or more target documents related to the aforementioned document.

2. One or more target documents related to the aforementioned document are: The aforementioned document itself, One or more other documents cited by the aforementioned document, One or more other documents that cite the aforementioned document, Other documents listed in the bidirectional link area of ​​the aforementioned document, The method according to claim 1, comprising at least one document among one or more other documents associated with the keywords of the aforementioned document.

3. Determining one or more target documents related to the aforementioned document, Based on the content of each of the aforementioned target documents, one or more candidate questions are generated. The method according to claim 1, further comprising determining the one or more candidate questions based on the one or more candidate questions corresponding to each of the target documents.

4. To determine one or more first documents cited by the said document and one or more second documents that cite the said document, In response to the determination that the number of the first document and / or the second document is greater than or equal to a predetermined number, one or more target documents related to the document are determined based on the one or more first documents and / or the one or more second documents, or In response to the determination that the number of the first document and / or the second document is smaller than a predetermined number, one or more third documents associated with the keywords of the document are determined, The method according to claim 1, further comprising determining one or more target documents related to the said documents based on the said one or more first documents, the said one or more second documents and / or the said one or more third documents.

5. To determine one or more first candidate documents to be cited by the aforementioned document, To filter one or more first documents from one or more first candidate documents based on the user's viewing permissions, the number of times the first candidate document is clicked, and / or the number of characters in the first candidate document, and / or To determine one or more second documents that reference the aforementioned document, To determine one or more second candidate documents to be cited by the aforementioned document, This includes filtering one or more second documents from the one or more second candidate documents based on the user's viewing permissions, the number of times the second candidate document is clicked, and / or the number of characters in the second candidate document, and / or Determining one or more third documents associated with the keywords of the aforementioned document, To determine one or more third candidate documents associated with the keywords of the aforementioned document, The method according to claim 3, further comprising filtering one or more third documents from one or more third candidate documents based on the user's viewing permissions, the number of times the third candidate document is clicked, and / or the number of characters in the third candidate document.

6. Determining one or more questions based on one or more candidate questions corresponding to each of the target documents is: The method according to claim 3, further comprising filtering one or more candidate questions from one or more candidate questions based on the number of characters in each candidate question.

7. The aforementioned pre-set area is Adjacent areas of the editable area of ​​the aforementioned document, The adjacent area to the "Like" area of ​​the aforementioned document, The adjacent area of ​​the bidirectional link area of ​​the aforementioned document, or The method according to claim 1, further comprising a newly added area within the bidirectional link area of ​​the aforementioned document.

8. Displaying one or more of the aforementioned questions in a newly added area within the bidirectional link area of ​​the aforementioned document is, Displaying one or more of the questions in the first tab of the aforementioned bidirectional link area, Displaying one or more other documents cited by the document in the second tab of the aforementioned bidirectional link area, The method according to claim 7, further comprising displaying one or more other documents referencing the document in a third tab of the bidirectional link area.

9. In response to a trigger command for a target question among the one or more of the aforementioned questions, a target application is invoked, the target question is sent in the window of the target application, and the target application generates an answer corresponding to the target question, or The method according to claim 1, further comprising displaying a first window on a document page in response to a trigger command for a target question among the one or more questions, and displaying the target question and the answer corresponding to the target question in the first window.

10. Displaying one or more of the aforementioned questions in a pre-configured area of ​​the aforementioned document is, The method according to claim 1, further comprising displaying a symbol or icon associated with the question at the relevant location of the question.

11. A document information recommendation device, A decision module configured to determine one or more questions related to a document in response to a user's access operation to the document meeting predetermined conditions, The document includes a display module configured to display one or more of the questions in a pre-defined area of ​​the document, A document information recommendation device in which the one or more questions are generated based on the content of one or more target documents related to the said document.

12. A computer device comprising memory, a processor, and a computer program stored in memory and operable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 10 is realized.

13. A non-temporary computer-readable storage medium for storing computer instructions, wherein the computer instructions are used to cause a computer to perform the method according to any one of claims 1 to 10.

14. A computer program that causes a computer to perform the method described in any one of claims 1 to 10.

Images