Document information recommendation method and related equipment

Abstract

The invention provides a document information recommendation method and related equipment. The method comprises the following steps: determining one or more questions associated with a document in response to the situation that the operation of accessing the document by a user meets a predetermined condition; displaying the one or more questions in a preset area of the document; wherein the one or more questions are generated according to contents of one or more target documents associated with the document.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a document information recommendation method and related equipment. Background Art

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

[0003] However, the inventors of the present disclosure have discovered that in the related art, after reading a document, users may have some questions about the content of the document. At this time, the users can only search for answers to the questions by themselves, resulting in low work efficiency. Summary of the invention

[0004] In view of this, the purpose of the present disclosure is to propose a document information recommendation method and related devices to solve or partially solve the above technical problems.

[0005] In a first aspect of the present disclosure, a document information recommendation method is provided, comprising:

[0006] In response to a user's operation of accessing a document satisfying a predetermined condition, determining one or more issues associated with the document;

[0007] displaying the one or more questions in a predetermined area of ​​the document;

[0008] The one or more questions are generated based on the content of one or more target documents associated with the document.

[0009] A second aspect of the present disclosure provides a document information recommendation device, comprising:

[0010] A determination module, configured to: in response to a user's operation of accessing a document satisfying a predetermined condition, determine one or more issues associated with the document;

[0011] A display module, configured to: display the one or more questions in a preset area of ​​the document;

[0012] The one or more questions are generated based on the content of one or more target documents associated with the document.

[0013] In a third aspect of the present disclosure, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the first aspect is implemented.

[0014] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable a computer to execute the method described in the first aspect.

[0015] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer program instructions, which, when executed on a computer, cause the computer to execute the method described in the first aspect.

[0016] From the above description, it can be seen that the document information recommendation method and related equipment provided by the present disclosure, during the process of reading a document, when the operation of reading the document meets specific conditions, questions related to the document can be seen in a preset area of ​​the document, so that information related to the document can be further explored based on the questions, thereby eliminating a lot of work that needs to be sorted and summarized, and greatly improving the user's work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of an exemplary system according to an embodiment of the present disclosure is shown.

[0019] Figure 2A A schematic diagram of an exemplary page according to an embodiment of the present disclosure is shown.

[0020] Figure 2B A schematic diagram showing another exemplary page according to an embodiment of the present disclosure is shown.

[0021] Figure 3A A schematic diagram of an exemplary page according to an embodiment of the present disclosure is shown.

[0022] Figure 3B A schematic diagram showing another exemplary page according to an embodiment of the present disclosure is shown.

[0023] Figure 4 A schematic diagram of an exemplary page according to an embodiment of the present disclosure is shown.

[0024] Figure 5 A flowchart of an exemplary method provided by an embodiment of the present disclosure is shown.

[0025] Figure 6 A schematic diagram of the structure of an exemplary device provided by an embodiment of the present disclosure is shown.

[0026] Figure 7 A schematic diagram of the hardware structure of an exemplary electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0027] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0028] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0029] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0030] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0031] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0032] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0033] Figure 1 A schematic diagram of an exemplary system 100 provided by an embodiment of the present disclosure is shown.

[0034] like Figure 1 As shown, the system 100 can be used to provide online or offline reading and editing document functions, and can include a terminal device 102, a server 106, and a database server 108. A medium (e.g., a network) providing a communication link may be included between the terminal device 102 and the server 106 and the database server 108. The network may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0035] Various software or applications (APPs) may be installed on the terminal device 102, such as collaborative office software or applications, image processing software or applications, video conferencing software or applications, reading software or applications, video software or applications, social software or applications, payment software or applications, web browsers, and instant messaging tools, etc. In some embodiments, these software or applications may be used to display and edit documents.

[0036] The terminal device 102 here can be hardware or software. When the terminal device 102 is hardware, it can be various electronic devices with a display screen, including but not limited to smart phones, tablet computers, e-book readers, MP3 players, laptop computers (Laptops) and desktop computers (PCs), etc. When the terminal device 102 is software, it can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0037] The server 106 may be a server that provides various services, such as a background server that provides support for various applications displayed on the terminal device 102. The database server 108 may also be a database server that provides various services. It is understood that if the server 106 can implement the relevant functions of the database server 108, the database server 108 may not be set in the system 100.

[0038] Here, the server 106 and the database server 108 can also be hardware or software. When they are hardware, they can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When they are software, they can be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module. No specific limitation is made here.

[0039] It should be noted that the method for document recommendation provided in the embodiment of the present disclosure may be executed by the terminal device 102 or by the system 100. It should be understood that Figure 1 The number of terminal devices, users, servers and database servers in the embodiment is only for illustration. Any number of terminal devices, users, servers and database servers may be provided as required.

[0040] In some embodiments, a collaborative office application or software may be installed in the terminal device 102, and the user 104 may use the application or software installed in the terminal device 102 to perform office work, such as reading documents.

[0041] However, in some scenarios, for example, after reading a document, the user 104 may have some questions about the content of the document. In this case, the user can only search for answers to the questions by himself, for example, he may need to consult other documents related to the current document for further reading. In some special scenarios, when the user 104 needs to consult materials related to the document within his company, he may need to ask other colleagues for help, or search for relevant materials in the company's internal database. In addition, after obtaining the materials, the user also needs to obtain further information by reading the materials to obtain answers to the questions.

[0042] In view of this, one aspect of an embodiment of the present disclosure provides a document information recommendation method.

[0043] Figure 2A A schematic diagram of an exemplary page 200 according to an embodiment of the present disclosure is shown. The page 200 can be used to display and edit documents.

[0044] like Figure 2A As shown, in some embodiments, user 104 can use terminal device 102 to open collaborative office software or use a web browser to open a collaborative office webpage, and use the software or webpage to open a document, and then page 200 can be displayed in terminal device 102, and the opened document 202 can be displayed in page 200.

[0045] Optionally, when the user 104 only has the permission to view the document 202, the user can only read the document 202 in the page 200. If the user 104 also has the permission to edit the document 202, the user can edit the document 202 in the page 200. It is understood that when the user 104 has other permissions on the document 202, the user can also perform operations corresponding to other permissions on the document 202.

[0046] As mentioned above, after the user 104 finishes reading the document 202, he may need to search for other related materials to read in order to obtain more information. However, such operation is relatively inconvenient.

[0047] In view of this, in some embodiments, some questions can be generated for the user 104 based on the document 202, and answers corresponding to the questions can be further generated, thereby saving the user 104 time in searching for information and sorting and summarizing.

[0048] As an optional embodiment, the timing of triggering the question generation mechanism may be when the document 202 is opened, when the document 202 is browsed to the nth page (n is greater than or equal to 1), or when the document 202 is completely read. Among them, triggering the question generation mechanism when the document 202 is opened can allow the system 100 to have more time to complete various tasks related to generating questions, and thus the response when the questions are finally presented in the page 200 can be faster. Triggering the question generation mechanism when the document 202 is browsed to the nth page, that is, various tasks related to generating questions can be completed when the nth page of the document 202 is displayed in the page 200, thereby avoiding unnecessary resource consumption caused by the user 104 opening the document 202 by mistake. Triggering the question generation mechanism when the document 202 is completely read, that is, various tasks related to generating questions can be completed when the last page of the document 202 is displayed in the page 200, thereby generating relevant questions after the user 104 finishes reading the document 202, thereby avoiding unnecessary resource consumption caused by the user 104 quitting reading midway.

[0049] Furthermore, in some embodiments, questions may be generated based on the content of one or more target documents associated with the document 202, thereby ensuring that the questions are highly relevant to the content of the document 202, thereby improving the user experience. Therefore, when triggering the question generation mechanism, the target document associated with the document 202 may be determined first.

[0050] Optionally, the one or more target documents associated with the document 202 include at least one of the following documents:

[0051] The document 202 itself;

[0052] One or more other documents referenced by document 202;

[0053] One or more other documents that reference document 202;

[0054] Other documents recorded in the bidirectional link area of ​​the document 202;

[0055] One or more other documents associated with the keywords of document 202 .

[0056] Exemplarily, the other documents mentioned above may refer to documents different from document 202. Among them, other documents that have a reference or reference relationship with document 202 have a high relevance to the content of document 202. Generating questions based on these documents can better recommend questions related to document 202. Other documents associated with the keywords of document 202 also have a high relevance to document 202. Generating questions based on these documents can also better recommend questions related to document 202. Generating questions based on document 202 itself can play a role in summarizing the essence or key content of document 202 for user 104, and can also better recommend questions related to document 202.

[0057] Optionally, whether the document 202 refers to other documents can be determined based on whether the document 202 contains information such as a link or title of the other document. Conversely, whether the document 202 is referenced by other documents can be determined based on whether the other documents contain information such as a link or title of the document 202.

[0058] For example, reference Figure 2B As shown, the page 200 may also include a bidirectional link area 200A. Bidirectional links may refer to forward links and reverse links, wherein forward links may refer to other documents linked by the document 202 (which may also be understood as other documents referenced by the document 202), and reverse links may refer to other documents linking to the document 202 (which may also be understood as other documents that reference the document 202). The page 200 presents these forward links and reverse links through the bidirectional link area 200A, so that the user 104 can directly find other documents that are highly related to the document 202 from the bidirectional link area 200A, eliminating the process of the user 104 searching for bidirectional link documents by themselves, thereby improving the user's work efficiency.

[0059] On this basis, when determining the target document associated with document 202, directly find those documents with forward links and reverse links in the bidirectional link area 200A, and then filter out the target document. On the one hand, since these bidirectional link documents are highly correlated with document 202, recommendations based on these bidirectional link documents can achieve better results. On the other hand, the documents presented in the bidirectional link area 200A can be obtained through pre-processing. By directly obtaining the documents with forward links and reverse links therefrom, the process of traversing document 202 to obtain documents that have a citing and being cited relationship with it can be omitted, thereby improving the processing speed.

[0060] As an optional embodiment, keywords of document 202 may be extracted, 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 of document 202. Optionally, the keyword may be a term in the title of document 202. For example, if the title is "Prospects for the Development of Artificial Intelligence", the keyword may be "artificial intelligence". Optionally, the keyword may also be a term that appears frequently (for example, more than 10 times) in document 202, such as "natural language model", "large language model", etc. By extracting keywords to search for documents that match the keywords, and then determining the target document based on these documents, the target document is more closely associated with document 202, and a better recommendation effect is obtained.

[0061] In some embodiments, in order to make the recommended questions more personalized, when obtaining other documents in the above embodiments, documents that meet the requirements of the above embodiments can be obtained in the target database. The target database can be a private database of the enterprise where user 104 is located. In this way, the documents obtained from the database can reflect the characteristics or personality of the enterprise where user 104 is located, so that the recommended related questions can be more in line with the actual situation of the enterprise where user 104 is located, thereby improving the office efficiency of user 104.

[0062] Optionally, in order to improve the relevance of the generated questions to the document 202, when determining one or more target documents associated with the document 202, one or more first documents referenced by the document 202 and one or more second documents that reference the document 202 may be first obtained, and if the sum of the number of the first documents and the second documents is less than a preset number (e.g., 10), then one or more third documents associated with the keywords of the document 202 are obtained. The preset number is used to limit the total number of target documents to avoid insufficient number of questions generated due to a small total number of target documents, or too many questions generated due to a large number of target documents (there are also more impurities), thereby weakening the relevance between the questions and the document 202.

[0063] Accordingly, if the sum of the number of first documents and second documents is greater than or equal to a preset number (for example, 10), the one or more target documents associated with the document can 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 the preset number, the one or more target documents associated with the document can be determined based on the one or more first documents, the one or more second documents and the one or more third documents.

[0064] In some embodiments, when other documents referenced by document 202, other documents that reference document 202, or other documents associated with keywords of document 202 are obtained from the database, these documents can also be filtered to obtain the final first document, second document, and third document, so that the first document, second document, and third document meet some specific requirements.

[0065] Specifically, optionally, one or more first candidate documents referenced by document 202 may be first obtained from the target database, and then the one or more first documents may be screened from the one or more first candidate documents based on the user's reading authority, the number of clicks on the first candidate documents, and the number of words in the first candidate documents.

[0066] It is understandable that when other documents corresponding to the document links and titles contained in document 202 are not in the target database, in some embodiments, in order to ensure the personalization of the question, such documents will not be used as the first document and also need to be filtered out.

[0067] Among them, screening is performed based on the user's reading authority. It can be that user 104 does not have the reading authority of the first candidate document, and the first candidate document is filtered. Screening is performed based on the number of clicks on the first candidate document. It can be that the number of clicks on the first candidate document is small (for example, less than 10 times), which means that the popularity of the document is low and the content quality may be poor, and it also needs to be filtered out. Screening continues based on the number of words in the first candidate document. It can be that the number of words in the content of the first candidate document is small (for example, less than 10 words or characters), which means that the content quality of the document is poor and it also needs to be filtered out.

[0068] In this way, by screening candidate documents and then obtaining the target document, the effectiveness of the recommendation problem can be improved.

[0069] Similarly, to determine one or more second documents that reference document 202, one or more second candidate documents referenced by document 202 may be determined first, and then, based on the user's reading authority, the number of clicks on the second candidate document, and the number of words in the second candidate document, the one or more second documents may be obtained by screening the one or more second candidate documents. The specific implementation method is described in the previous embodiment, which will not be repeated here.

[0070] Similarly, to determine one or more third documents associated with the keywords of the document 202, one or more third candidate documents associated with the keywords of the document 202 may be determined first, and then the one or more third candidate documents are screened from the one or more third candidate documents according to the user's reading authority, the number of clicks on the third candidate documents, and the number of words in the third candidate documents. The specific implementation method is referred to in the above embodiment, which will not be described in detail here.

[0071] At this point, a certain number of first documents, second documents, and third documents can be screened and obtained.

[0072] Then, a target document may be determined based on these first documents, second documents, and third documents.

[0073] As mentioned above, when the sum of the number of the first document and the second document is greater than or equal to the preset number, the target document can be determined based on the first document and the second document. Specifically, if the sum of the number of the first document and the second document is equal to the preset number, the first document and the second document can be directly used as the target document. If the sum of the number of the first document and the second document is greater than the preset number, in some embodiments, the first document and the second document can be sorted, and then the target document can be screened based on the sorting result.

[0074] As an optional embodiment, considering that other documents referenced by document 202 are more relevant to document 202, the first document can be placed before the second document. If the number of first documents is equal to the preset number, the first document can be directly used as the target document, and the second documents can be filtered out. If the number of first documents is greater than the preset number, the first documents can be sorted according to the order of the time when they are referenced by document 202 (the earlier referenced documents are placed at the back, and the later referenced documents are placed at the front), and then the target documents are selected in order. If the number of first documents is less than the preset number, the documents are selected from the second document to complete the list. The method of selecting the second document is the same as the method of selecting the first document, which will not be repeated here.

[0075] As mentioned above, in some other embodiments, when the sum of the number of the first document and the second document is less than a preset number, the one or more target documents associated with the document 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 completed by selecting documents from the third document based on the difference obtained by subtracting the sum of the number of the first document and the second document from the preset number.

[0076] Optionally, the third documents may be sorted according to the degree of matching between the third documents and the document 202 , and then screened from high to low according to the degree of matching, and the documents with high matching degrees are supplemented into the target document.

[0077] In this way, a predetermined number of target documents are obtained.

[0078] It should be understood that the above embodiments are only exemplary. When comparing with the preset number, in addition to comparing with the preset 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 can also be used to compare with the preset number. When the number of the first document meets the requirement, it means that the obtained target document has a stronger relevance to the document 202 as a reference relationship, so that questions more relevant to the background information of the document 202 can be recommended; in other embodiments, the number of the second document can also be used to compare with the preset number. When the number of the second document meets the requirement, it means that the obtained target document has a stronger relevance to the document 202 as a reference relationship, so that questions more relevant to the further development information of the document 202 can be recommended. Further, it can also be understood that after the first document and the second document are screened, when determining the one or more target documents associated with the document based on the one or more first documents and / or the one or more second documents, according to different actual needs, it can be selected to determine the target document based on the first document or the second document, so that the recommended questions can be more relevant to the background information or more relevant to the further development information of the document 202. In addition, when determining multiple target documents, the quantity ratio of the first document and the second document may be allocated therefrom so that the recommendation effect is more related to the background information or to the further development information of the document 202 .

[0079] It should also be understood that, similarly, in determining the one or more target documents associated with the document based on the one or more first documents, the one or more second documents and / or the one or more third documents, the target documents can be screened from the first document, the second document and the third document according to the aforementioned embodiments, and a quantitative ratio can be allocated among the first document, the second document and the third document, so that the recommended questions are more relevant to a certain aspect or to a broader issue.

[0080] Next, one or more candidate questions may be generated based on the content of each target document.

[0081] As an optional embodiment, a pre-trained first model can be used to generate candidate questions based on the target document. The first model can be a machine learning model based on natural language processing, and can be trained based on a document as a training text. Optionally, the training text can be tagged with a question (the question tag can be a question extracted based on the content of the training text), and then the model can be supervised based on the training text with the question tag, thereby obtaining the pre-trained first model.

[0082] Therefore, optionally, each target document can be used as the input of the first model to output a certain number (for example, 3) of candidate questions.

[0083] In this way, some candidate questions are obtained. For example, when the number of target documents is 10, 30 candidate questions can be obtained.

[0084] In some embodiments, when inputting a target document, a prompt can also be provided to the first model as part of the model input data or as a constraint of the model to provide context or guide the model's predictions, so as to make the question clearer and more instructive, thereby helping the user understand the question.

[0085] Optionally, the prompt may be at least one of the following information:

[0086] Only generate questions directly related to the document content;

[0087] Use the title as key context to add to the question;

[0088] Questions should be specific and pointed. Avoid using vague pronouns such as "this" and "the". Instead, replace them with specific terms in the document.

[0089] Make sure the question contains contextual specificity when it is broad or general, and make sure the subject is fully and clearly stated.

[0090] By using the above information as prompts to constrain the model's predictions, we can get clearer and more guided questions.

[0091] As an optional embodiment, the prompt may also include outputting a prompt message of a symbol or icon associated with the question. For example, "Attach a symbol or icon that matches the theme of each question to enhance its expression effect." In this way, the model can output a symbol or icon that matches the theme of the question, which is then displayed together with the question in the future, enhancing the visual effect and improving the user experience.

[0092] In some embodiments, the candidate questions may be text in JSON (JavaScript Object Notation) format, so that when the questions are subsequently displayed, they may be rendered directly based on the text in JSON format, thereby improving processing efficiency.

[0093] After obtaining a plurality of candidate questions, one or more questions for recommendation to the user 104 may be determined based on the candidate questions generated from the target documents.

[0094] Optionally, the one or more questions may be obtained by screening from the one or more candidate questions according to the number of words in the one or more candidate questions.

[0095] Optionally, questions with more words (e.g., more than 18 words) or fewer words (e.g., fewer than 10 words) can be filtered out. Filtering out questions with more words can better display the questions when displaying them; filtering out questions with fewer words can avoid questions with less information and lower reference value due to fewer words.

[0096] In some embodiments, after filtering based on word count, if the number of remaining candidate questions is greater than the predetermined number of questions to be displayed (e.g., 10), the remaining candidate questions may be further filtered. For example, the remaining candidate questions may be sorted according to the priority of the target document that generates the candidate questions. For example, if the target document is the first document, its corresponding candidate questions are ranked first, followed by the candidate questions whose target document is the second document, and finally the candidate questions whose target document is the third document. Among them, the candidate questions whose target document is the third document may be further sorted according to the degree of match between the target document and the document 202. Then, one or more questions associated with the document are filtered out from the candidate questions in the order of arrangement.

[0097] In this way, some questions associated with the document 202 are obtained.

[0098] Then, when the user's operation of accessing the document 202 meets a predetermined condition (for example, the user 104 scrolls the document 202 to the last page), the terminal device 102 can determine one or more questions associated with the document 202. For example, one or more questions are determined from the questions generated in the previous embodiment. Then, the one or more questions are displayed in a preset area of ​​the document 202. In this way, when the user 104's operation of reading the document 202 meets a specific condition, the questions associated with the document 202 can be seen, so that the information related to the document 202 can be further explored based on the questions, which saves a lot of work that needs to be sorted and summarized by oneself, and greatly improves the work efficiency of the user 104.

[0099] Figure 2B Another schematic diagram of an exemplary page 200 according to an embodiment of the present disclosure is shown.

[0100] like Figure 2B As shown, in some embodiments, the operation of the user accessing the document 202 satisfies the predetermined condition, which may mean that the document 202 is scrolled to the end by the user 104. At this time, it means that the user 104 may have finished reading the document 202 and may continue with subsequent work, for example, looking up other materials related to the document 202. Therefore, in this case, relevant questions may be recommended to the user 104, and the recommendation of questions at this time is relatively less likely to affect the reading experience of the user 104.

[0101] It can be understood that, in addition to this embodiment, there can be many preset conditions. For example, when the user 104 is reading the document 202, he leaves the current page 200, and after a period of time, he continues to return to the page 200 to read the document 202, indicating that in the process of leaving the page 200, the user 104 may have consulted other materials. Therefore, the user's operation of accessing the document 202 meets the predetermined condition, which may mean that the time difference between the user 104 leaving the document 202 and returning to the document 202 exceeds the preset time. In this case, recommending relevant questions to the user 104 can make it easier for the user 104 to understand the relevant information and reduce the time for the user 104 to consult other materials as much as possible. For another example, the document 202 has multiple chapters, and relevant questions can be recommended to the user 104 at the end of each chapter. In this way, inserting relevant questions between chapters allows the user 104 to be promptly answered and improves the user experience. At this time, the user's operation of accessing the document 202 meets the predetermined condition, which may mean before the content of each chapter enters the visible area of ​​the page 200.

[0102] Optionally, the preset area may be at least one of the following areas:

[0103] an area adjacent to an editable area of ​​the document 202;

[0104] The neighboring area of ​​the like area of ​​the document 202;

[0105] an adjacent region of a bidirectionally linked region of document 202;

[0106] A newly added area within the bidirectional link area of ​​document 202 .

[0107] Among them, Figure 2B As shown, the editable area of ​​the document 202 may refer to the area where the document 202 is located. The user 104 may edit the document 202 in this area if he / she has the editing authority of the document 202. As an optional embodiment, the preset area for displaying the one or more questions may be an adjacent area of ​​the editable area of ​​the document 202, for example, located on the left or right side of the editable area of ​​the document 202, or, when the document 202 is scrolled to the end, located below and close to the editable area of ​​the document 202. In this way, the user 104 may view related questions from an adjacent area of ​​the editable area of ​​the document 202 while reading the document 202, which is more convenient to operate.

[0108] like Figure 2BAs shown, in some embodiments, when the document 202 is scrolled to the end, the page 200 may also display a like button 210, and the user 104 may like the document 202 by triggering the button 210. As an optional embodiment, the preset area for displaying the one or more questions may be an adjacent area to the area where the like button 210 of the document 202 is located (for example, above, below, left, or right of the like area). On the one hand, both likes and question exploration are operations other than reading the document 202, and setting the preset area in an adjacent area to the like area may facilitate user operations; on the other hand, since the like area is usually located at the end of the document, setting the preset area in an adjacent area to the like area allows the user 104 to view questions and likes after finishing reading the document 202, thereby ensuring the integrity of the reading experience.

[0109] As mentioned above, Figure 2B As shown, in some embodiments, the page 200 may also include a bidirectional link area 200A, which may be used to display bidirectional links (including forward links and reverse links). The user 104 may trigger these links to jump to the document page corresponding to the link, and may further read the document corresponding to the link if the user 104 has reading authority. As an optional embodiment, the preset area for displaying the one or more questions may be an adjacent area of ​​the bidirectional link area 200A of the document 202 (e.g., above, below, left, or right of the bidirectional link area 200A). In this way, by displaying the one or more questions in an adjacent position of the bidirectional link area 200A, the user 104 may view the bidirectional links and recommended questions at the same time, which is convenient for comparison and viewing, and is more in line with user habits.

[0110] In some embodiments, a new area may be added to the bidirectional link area 200A of the document 202 as the preset area for displaying the one or more questions, so that the bidirectional link area 200A may be used to set the preset area, thereby saving page space.

[0111] like Figure 2B As shown, as an optional embodiment, the bidirectional link area 200A may further include three tabs, wherein the first tab corresponds to the preset area and is used to display the one or more questions; the second tab corresponds to the forward link and is used to display one or more other documents referenced by the document; and the third tab corresponds to the reverse link and is used to display one or more other documents that reference the document.

[0112] In some embodiments, Figure 2BAs shown, a first label 208A corresponding to the first label page can be displayed at an associated position (e.g., top) of the bidirectional link area 200A, and the one or more questions can be displayed in the bidirectional link area 200A by triggering the label 208A. Optionally, the information of the label 208A can be, for example, "question and answer", thereby prompting the user 104 to ask and answer questions based on the questions recommended in the first label page, thereby obtaining corresponding answers, thereby improving work efficiency.

[0113] Alternatively, if Figure 2B As shown, a second label 208B corresponding to the second tab page and a third label 208C corresponding to the third tab page may also be displayed at an associated position of the bidirectional link region 200A (e.g., at the top of the region 200A, on one side of the first label 208A). Optionally, since the first tab page is currently displayed in the bidirectional link region 200A, the corresponding first label 208A may be highlighted to enhance the visual effect.

[0114] In some embodiments, the corresponding second and third tabs can be displayed by triggering the second label 208B and the third label 208C. For example, if the second label 208B is triggered (for example, clicking the second label 208B), the terminal device 102 can display the information of one or more other documents referenced by the document 202 in the two-way link area 200A, for example, the title and thumbnail content of the first document as the target document (for example, the highlighted content in the document, the fragment of the key content). For another example, if the third label 208C is triggered (for example, clicking the third label 208C), the terminal device 102 can display one or more other documents that reference the document 202 in the two-way link area 200A, for example, the title and thumbnail content of the second document as the target document (for example, the highlighted content in the document, the fragment of the key content). In this way, the user 104 can see the referenced or referenced document information corresponding to the document 202 for generating questions by switching labels, and can further view these documents.

[0115] It can be understood that if the document 202 does not reference or is referenced by other documents, the bidirectional link area 200A may not display the second label 208B and the third label 208C.

[0116] In some embodiments, the timing for triggering the question generation mechanism may also be when the first tab 208A enters the visible area of ​​the page 200. In this way, by generating the question before it is displayed, it is possible to avoid the waste of resources caused by early question generation but the user exiting the document midway. At the same time, it is possible to avoid the problem that when the document has a small number of pages and the question generation mechanism cannot be triggered at all if the nth page does not exist.

[0117] like Figure 2B As shown, in some embodiments, the one or more questions, for example, questions 204A to 204D, may be displayed in the first tab of the bidirectional link area 200A of the page 200. The bidirectional link area 200A is located at the end of the document 202. In this way, displaying the questions at the end of the document 202 can avoid the problems appearing too early and affecting the user 104 reading the document 202, which is more in line with the user's usage habits and improves the user experience.

[0118] In some embodiments, Figure 2B As shown, in page 200, symbols or icon questions 206A-206D associated with questions 204A-204D may also be displayed at associated positions (eg, in front) of questions 204A-204D, thereby enhancing the visual effect.

[0119] As an optional embodiment, in order to improve the user experience, questions 204A to 204D may be displayed at a position closest to the end of document 202. Figure 2B As shown, there is no other interface content (e.g., like button 210, comment area (not shown), etc.) between questions 204A-204D and the last paragraph of document 202. In this way, user 104 can find recommended questions earlier, thereby improving his work efficiency.

[0120] Optionally, the arrangement of questions 204A to 204D in page 200 may be different depending on the type of terminal device 102 .

[0121] As an optional embodiment, if the terminal device 102 is a personal computer (PC) or a tablet computer, the questions 204A to 204D may be arranged in an array, such as Figure 2B As the horizontal space of page 200 is relatively large, questions 204A to 204D can be arranged from left to right and from top to bottom in accordance with the length of the questions themselves, so that page 200 can be more compact and beautiful.

[0122] As another optional embodiment, Figure 3A As shown, if the terminal device 102 is a mobile phone, since the horizontal space of the page 300 is small at this time, the questions 302A to 302D can be arranged in order from top to bottom, so that the page 300 can be more beautiful.

[0123] In some embodiments, Figure 3A As shown, since the available space of page 300 is small, the label of the above embodiment may not be displayed, but prompt information 304 may be displayed to prompt user 104 that they can ask and answer questions based on questions 302A to 302D, so as to quickly obtain corresponding answers.

[0124] As an optional embodiment, if the question acquisition fails due to network or server reasons, the pages 200 and 300 may not display the questions 204A-204D, 302A-302D, nor the first label 208A, the second label 208B, the third label 208C, and the prompt information 304, so as to avoid affecting the aesthetics of the page due to displaying labels or prompt information when the question is not displayed. Optionally, the user 104 can refresh the pages 200 and 300 to obtain the question again. If the question can be obtained, it can be displayed normally according to the above embodiment.

[0125] Furthermore, in some embodiments, when user 104 triggers a question in page 200 or 300, a corresponding answer can be generated based on the question, so that user 104 can quickly understand relevant information by reading the answer, saving time for sorting and summarizing, and improving work efficiency.

[0126] In some embodiments, in response to a trigger instruction for a target question among the one or more questions, a target application may be called to generate a target answer corresponding to the target question.

[0127] As an optional embodiment, for example, the terminal device 102 is a personal computer or a tablet computer, and the page 200 is displayed by a web browser. The web browser may not be able to generate a target answer based on the target question. Therefore, the target application can be called to generate the target answer corresponding to the target question.

[0128] Figure 4 A schematic diagram of another exemplary page 400 according to an embodiment of the present disclosure is shown.

[0129] like Figure 4 As shown, in some embodiments, in response to a trigger instruction for a target question (e.g., question 204A) among the one or more questions, a target application (e.g., collaborative office software) may be called to jump from page 200 to page 400, which further includes a window for question and answer, and the target question may be sent in the window to generate an answer corresponding to the target question through the target application. In addition, the target question 402 and the answer 404 corresponding to the target question 402 may be displayed in page 400.

[0130] In some embodiments, the answer 404 may be generated based on the target question 402 using a pre-trained second model. Alternatively, the second model may be a large language model that is pre-trained based on a question-answering mechanism. As an optional embodiment, when the terminal device 102 calls the target application, the target question 402 may be sent to the server 106, and the second model deployed in the server 106 may generate the answer 404 and return it to the terminal device 102 for display.

[0131] Optionally, before jumping from page 200 to page 400, a prompt message may be displayed to prompt the user 104 that the user 104 currently needs to jump to another software. As another optional embodiment, when page 200 itself is a document page of the target application, the question and answer page 400 may be switched to the target application, and the second model module in the target application may be used to generate an answer 404 using the second model. Optionally, the second model module may send the 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 receives the answer 404 returned by the server 106 for display.

[0132] Figure 3B Another schematic diagram of an exemplary page 300 according to an embodiment of the present disclosure is shown.

[0133] like Figure 3B As shown, in some embodiments, if the terminal device 102 is a mobile phone, in response to a trigger instruction for a target question among the one or more questions (for example, question 302A), a first window 306 is displayed in the page 300, and the target question 3062 and the answer 3064 corresponding to the target question 3062 are displayed in the first window 306.

[0134] In some embodiments, the answer 3064 may be generated based on the target question 3062 using a pre-trained second model. Alternatively, the second model may be a large language model that is pre-trained based on a question-answering mechanism. As an optional embodiment, when the terminal device 102 opens the window 306, the target question 3062 may be sent to the server 106, and the answer 3064 may be generated by the second model deployed in the server 106 and returned to the terminal device 102 for display.

[0135] Alternatively, if Figure 3B As shown, window 306 can be displayed in half the screen of page 300, thereby presenting a visual effect of a window popping up from the bottom. After closing window 306 and returning to the document page, other operations can be continued, thereby improving the user experience.

[0136] From the above embodiments, it can be seen that the method for recommending questions for documents provided by the embodiments of the present disclosure can recommend and display questions generated based on documents related to the currently read document at the bottom of the document after the document is finished reading, eliminating the need for the user to summarize the questions themselves, thereby improving work efficiency. In some embodiments, after clicking on a question to view the details, the intelligently refined answer to the question can be displayed, eliminating the need to search and organize the answers, thereby further improving work efficiency.

[0137] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0138] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0139] Based on basically the same inventive concept, the embodiment of the present disclosure also provides a document information recommendation method.

[0140] Figure 5 FIG. 5 is a flow chart of an exemplary method 500 provided by an embodiment of the present disclosure. The method 500 may be Figure 1 The terminal device 102 can also be implemented by Figure 1 The method 500 can be implemented by the system 100, and the method 500 can be used to recommend document information. The method 500 can further include the following steps.

[0141] In step 502, in response to a user's operation of accessing a document satisfying a predetermined condition, one or more issues associated with the document are determined.

[0142] At step 504, the one or more questions are displayed in a preset area of ​​the document (e.g., Figure 2B Questions 204A to 204D, Figure 3A Questions 302A to 302D).

[0143] The one or more questions are generated based on the content of one or more target documents associated with the document.

[0144] The document information recommendation method provided by the present disclosure allows users to view questions related to the document in a preset area of ​​the document when the document reading operation meets specific conditions during the document reading process, so that users can further explore information related to the document based on the questions, thereby eliminating a lot of work that needs to be sorted and summarized, and greatly improving user work efficiency.

[0145] In some embodiments, the one or more target documents associated with the document include at least one of the following documents:

[0146] the document itself;

[0147] one or more other documents referenced by the document;

[0148] one or more other documents that reference the document;

[0149] Other documents recorded in the bidirectional link area of ​​the document;

[0150] One or more other documents associated with the keywords of the document.

[0151] Among them, other documents that have a reference or referenced relationship with the document have a high relevance to the content of the document. Generating questions based on these documents can better recommend questions related to the document. Other documents associated with the keywords of the document also have a high relevance to the document. Generating questions based on these documents can also better recommend questions related to the document. Generating questions based on the document itself can play a role in summarizing the essence or key content of the document for the user, and can also better recommend questions related to the document. When determining the target document associated with the document, the documents with forward links and reverse links can be directly found in the bidirectional link area, and then the target document can be screened out. On the one hand, since these bidirectional link documents have a strong relevance to the document, recommending based on these bidirectional link documents can achieve better results. On the other hand, the documents presented in the bidirectional link area can be obtained through pre-processing. By directly obtaining the documents with forward links and reverse links from them, the process of traversing the document to obtain the documents with reference and reference relationships can be omitted, thereby improving the processing speed. In addition, by extracting keywords to search for documents matching the keywords, and then determining the target document based on these documents, the target document is more closely associated with the document 202, thereby obtaining a better recommendation effect.

[0152] In some embodiments, the method 500 further includes:

[0153] determining one or more target documents associated with the document;

[0154] Based on the content of each of the target documents, generate one or more candidate questions respectively;

[0155] The one or more questions are determined based on the one or more candidate questions corresponding to each of the target documents.

[0156] In this way, candidate questions are generated according to the contents of one or more target documents associated with the document, and the one or more questions are screened out from the candidate questions, so that question recommendation can be better achieved.

[0157] In some embodiments, the method 500 further includes:

[0158] determining one or more first documents referenced by the document and one or more second documents referencing the document;

[0159] In response to determining that the number of the first documents and / or the second documents is greater than or equal to a preset number, determining the one or more target documents associated with the documents based on the one or more first documents and / or the one or more second documents; or,

[0160] In response to determining that the number of the first document and / or the second document is less than a preset number, determining one or more third documents associated with the keywords of the documents;

[0161] Based on the one or more first documents, the one or more second documents and / or the one or more third documents, one or more target documents associated with the document are determined.

[0162] In this way, documents that have a citing or cited relationship with the document are preferentially selected as target documents for generating questions, which can improve the relevance of the recommended question and the document and obtain better recommendation effects.

[0163] In some embodiments, the method 500 further includes:

[0164] determining one or more first candidate documents referenced by the document;

[0165] Filtering the one or more first candidate documents to obtain the one or more first documents according to the user's reading authority, the number of clicks on the first candidate document, and / or the number of words in the first candidate document;

[0166] and / or

[0167] Determining one or more second documents that reference the document includes:

[0168] determining one or more second candidate documents referenced by the document;

[0169] Filtering the one or more second candidate documents to obtain the one or more second documents according to the user's reading authority, the number of clicks on the second candidate document, and / or the number of words in the second candidate document;

[0170] and / or

[0171] Determining one or more third documents associated with the keyword of the document includes:

[0172] determining one or more third candidate documents associated with the keyword of the document;

[0173] The one or more third documents are obtained by screening from the one or more third candidate documents according to the user's reading authority, the number of clicks on the third candidate document and / or the number of words in the third candidate document.

[0174] In this way, by screening candidate documents and then obtaining the target document, the effectiveness of the recommendation problem can be improved.

[0175] In some embodiments, determining the one or more questions based on the one or more candidate questions corresponding to each of the target documents includes:

[0176] The one or more questions are obtained by screening from the one or more candidate questions according to the word count of the one or more candidate questions.

[0177] Optionally, questions with more words (e.g., more than 18 words) or fewer words (e.g., fewer than 10 words) can be filtered out. Filtering out questions with more words can better display the questions when displaying them; filtering out questions with fewer words can avoid questions with less information and lower reference value due to fewer words.

[0178] In some embodiments, displaying a document includes: on a first page (e.g., Figure 2A Page 200, Figure 3A The document is displayed in page 300 of FIG.

[0179] Displaying the one or more questions at the end of the document includes, in a first area of ​​the first page (e.g., Figure 2B The one or more questions are displayed in area 200A), the first area being located at the end of the document.

[0180] In this way, displaying the problem at the end of the document can avoid the problem appearing too early and affecting the user's reading of the document. It is also more in line with user habits and improves user experience.

[0181] In some embodiments, the preset area includes:

[0182] an area adjacent to an editable area of ​​the document;

[0183] An area adjacent to the like area of ​​the document;

[0184] An area adjacent to a bidirectionally linked area of ​​the document; or

[0185] A new area is added to the bidirectional link area of ​​the document.

[0186] The editable area of ​​the document may refer to the area where the document is located, and the user may edit the document in this area if the user has the editing authority of the document. As an optional embodiment, the preset area for displaying the one or more questions may be an adjacent area of ​​the editable area of ​​the document, for example, located on the left or right side 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 the adjacent area of ​​the editable area of ​​the document 202 while reading the document, which is more convenient to operate.

[0187] As an optional embodiment, the preset area for displaying the one or more questions may be an area adjacent to the area where the like button of the document is located (for example, above, below, left, or right of the like area). On the one hand, likes and question exploration are operations other than reading the document. Setting the preset area in an area adjacent to the like area can facilitate user operations. On the other hand, since the like area is usually located at the end of the document, setting the preset area in an area adjacent to the like area allows users to view questions and likes after finishing reading the document, thereby ensuring the integrity of the reading experience.

[0188] As an optional embodiment, the preset area for displaying the one or more questions may be an adjacent area of ​​the bidirectional link area of ​​the document (e.g., above, below, left, or right of the bidirectional link area). In this way, by displaying the one or more questions at adjacent positions of the bidirectional link area, the user can view the bidirectional link and the recommended questions at the same time, which is convenient for comparison and more in line with user habits.

[0189] Displaying the one or more questions in a newly added area within the bidirectional link area of ​​the document includes at least one of the following:

[0190] displaying the one or more questions in a first tab of the bidirectional link area;

[0191] Displaying one or more other documents referenced by the document in a second tab page of the bidirectional link area;

[0192] A third tab page in the bidirectional link area displays one or more other documents that reference the document.

[0193] In this way, a new tab is added in the bidirectional link area of ​​the document as the preset area for displaying the one or more questions, so that the bidirectional link area can be used to set the preset area, thereby saving page space.

[0194] In some embodiments, displaying the one or more questions in the first area of ​​the first page includes:

[0195] A first label (eg, Figure 2B The first tag 208A of the document, the second tags corresponding to one or more other documents referenced by the document (for example, Figure 2B The second tag 208B of the document and the third tags corresponding to one or more other documents that reference the document (e.g., Figure 2B A third label 208C) is provided, wherein the first label is highlighted.

[0196] Since the question is currently displayed, the corresponding first label is highlighted to enhance the visual effect.

[0197] In some embodiments, the method further comprises:

[0198] In response to a trigger instruction for the second tag, displaying one or more other documents referenced by the document in the first area; or

[0199] In response to a trigger instruction for the third tag, one or more other documents that reference the document are displayed in the first area.

[0200] In this way, the user can display the corresponding document information by triggering the second tag and the third tag, which is convenient for operation.

[0201] In some embodiments, the method further comprises:

[0202] In response to a trigger instruction for a target question among the one or more questions, a target application is called, and the target question (for example, Figure 4 402), so as to generate an answer corresponding to the target question through the target application (for example, Figure 4 404 answer); or

[0203] In response to a trigger instruction for a target question among the one or more questions, a first window (eg, Figure 3B306), displaying the target question (e.g., Figure 3B 3062) and the answer corresponding to the target question (e.g., Figure 3B The answer is 3064).

[0204] Displaying different pages on different types of devices can make the page layout more suitable for the device type and improve the visual effect. In addition, using the question-answering capabilities of the target application to generate answers to questions can further improve processing efficiency and save resources.

[0205] In some embodiments, displaying the one or more questions in a preset area of ​​the document further includes: displaying a symbol or icon (for example, Figure 2B symbols or icons 206A~206D) to enhance the visual effect.

[0206] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0207] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0208] Based on substantially the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present disclosure further provides a document information recommendation device. Figure 6 A schematic structural diagram of an exemplary device 600 provided in an embodiment of the present disclosure is shown.

[0209] refer to Figure 6 The document information recommendation device 600 may include:

[0210] The determination module 602 is configured to: determine one or more issues associated with the document in response to a user's operation of accessing the document satisfying a predetermined condition;

[0211] The display module 604 is configured to: display the one or more questions in a preset area of ​​the document;

[0212] The one or more questions are generated based on the content of one or more target documents associated with the document.

[0213] In some embodiments, the one or more target documents associated with the document include at least one of the following documents:

[0214] the document itself;

[0215] one or more other documents referenced by the document;

[0216] one or more other documents that reference the document;

[0217] Other documents recorded in the bidirectional link area of ​​the document;

[0218] One or more other documents associated with the keywords of the document.

[0219] In some embodiments, the determination module 602 is configured to:

[0220] determining one or more target documents associated with the document;

[0221] Based on the content of each of the target documents, generate one or more candidate questions respectively;

[0222] The one or more questions are determined based on the one or more candidate questions corresponding to each of the target documents.

[0223] In some embodiments, the determination module 602 is configured to:

[0224] determining one or more first documents referenced by the document and one or more second documents referencing the document;

[0225] In response to determining that the number of the first documents and / or the second documents is greater than or equal to a preset number, determining the one or more target documents associated with the documents based on the one or more first documents and / or the one or more second documents; or,

[0226] In response to determining that the number of the first document and / or the second document is less than a preset number, determining one or more third documents associated with the keywords of the documents;

[0227] Based on the one or more first documents, the one or more second documents and / or the one or more third documents, one or more target documents associated with the document are determined.

[0228] In some embodiments, the determination module 602 is configured to:

[0229] determining one or more first candidate documents referenced by the document;

[0230] The one or more first documents are obtained by screening from the one or more first candidate documents according to the user's reading authority, the number of clicks on the first candidate document and / or the number of words in the first candidate document.

[0231] In some embodiments, the determination module 602 is configured to:

[0232] determining one or more second candidate documents referenced by the document;

[0233] The one or more second documents are obtained by screening from the one or more second candidate documents according to the user's reading authority, the number of clicks on the second candidate document and / or the number of words in the second candidate document.

[0234] In some embodiments, the determination module 602 is configured to:

[0235] determining one or more third candidate documents associated with the keyword of the document;

[0236] The one or more third documents are obtained by screening from the one or more third candidate documents according to the user's reading authority, the number of clicks on the third candidate document and / or the number of words in the third candidate document.

[0237] In some embodiments, the determination module 602 is configured to: filter the one or more candidate questions to obtain the one or more questions according to the word count of the one or more candidate questions.

[0238] In some embodiments, the preset area includes:

[0239] an area adjacent to an editable area of ​​the document;

[0240] An area adjacent to the like area of ​​the document;

[0241] An area adjacent to a bidirectionally linked area of ​​the document; or

[0242] A new area is added to the bidirectional link area of ​​the document.

[0243] In some embodiments, the display module 604 is configured to: perform at least one of the following:

[0244] displaying the one or more questions in a first tab of the bidirectional link area;

[0245] Displaying one or more other documents referenced by the document in a second tab page of the bidirectional link area;

[0246] A third tab page in the bidirectional link area displays one or more other documents that reference the document.

[0247] In some embodiments, the display module 604 is configured to: in response to a trigger instruction for a target question among the one or more questions, call a target application, send the target question in a window of the target application, and generate an answer corresponding to the target question through the target application.

[0248] In some embodiments, the display module 604 is configured to: in response to a trigger instruction for a target question among the one or more questions, display a first window in the document page, and display the target question and an answer corresponding to the target question in the first window.

[0249] In some embodiments, the display module 604 is configured to display a symbol or icon associated with the question at a location associated with the question.

[0250] For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0251] The device of the above embodiment is used to implement the corresponding method 500 in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0252] Based on basically the same inventive concept, the embodiment of the present disclosure further provides a computer device for implementing the above method 500 . Figure 7 FIG. 7 is a schematic diagram showing the hardware structure of an exemplary computer device 700 provided in an embodiment of the present disclosure. The computer device 700 can be used to implement Figure 1 In some scenarios, the computer device 700 can also be used to implement Figure 1 Server 106 and database server 108.

[0253] like Figure 7 As shown, the computer device 700 may include: a processor 702, a memory 704, a network module 706, a peripheral interface 708 and a bus 710. The processor 702, the memory 704, the network module 706 and the peripheral interface 708 are connected to each other in communication within the computer device 700 through the bus 710.

[0254] 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. Processor 702 may be used to perform functions related to the technology described in this disclosure. In some embodiments, processor 702 may also include multiple processors integrated into a single logical component. For example, Figure 7 As shown, processor 702 may include a plurality of processors 702a, 702b, and 702c.

[0255] The memory 704 may be configured to store data (eg, instructions, computer code, etc.). Figure 7 As shown, the data stored in the memory 704 may include program instructions (e.g., program instructions for implementing the method 500 of the embodiment of the present disclosure) and data to be processed (e.g., the memory may store configuration files of other modules, etc.). The processor 702 may also access the program instructions and data stored in the memory 704, and execute the program instructions to operate on the data to be processed. The memory 704 may include a volatile storage device or a non-volatile storage device. In some embodiments, the memory 704 may include a random access memory (RAM), a read-only memory (ROM), an optical disk, a magnetic disk, a hard disk, a solid-state drive (SSD), a flash memory, a memory stick, etc.

[0256] The network interface 706 can be configured to provide the computer device 700 with communication with other external devices via a network. The network can be any wired or wireless network capable of transmitting and receiving data. For example, the network can be a wired network, a local wireless network (e.g., Bluetooth, WiFi, near field communication (NFC)), a cellular network, the Internet, or a combination thereof. It is understood that the type of network is not limited to the above specific examples.

[0257] The peripheral interface 708 can be configured to connect the computer device 700 to one or more peripheral devices to achieve information input and output. For example, the peripheral devices can include input devices such as a keyboard, a mouse, a touch pad, a touch screen, a microphone, and various sensors, and output devices such as a display, a speaker, a vibrator, and an indicator light.

[0258] The bus 710 may be configured to transmit information between various components of the computer device 700 (e.g., the processor 702, the memory 704, the network interface 706, and the peripheral interface 708), such as an internal bus (e.g., a processor-memory bus), an external bus (USB port, PCI-E bus), etc.

[0259] It should be noted that, although the architecture of the computer device 700 only shows the processor 702, the memory 704, the network interface 706, the peripheral interface 708 and the bus 710, in the specific implementation process, the architecture of the computer device 700 may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the architecture of the computer device 700 may also only include components necessary for implementing the embodiments of the present disclosure, and does not necessarily include all the components shown in the figure.

[0260] Based on basically the same inventive concept, corresponding to any of the above-mentioned embodiments, the present disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute method 500 described in any of the above embodiments.

[0261] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0262] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the method 500 described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0263] Based on the same inventive concept, corresponding to the method 500 in any of the above embodiments, the present disclosure further provides a computer program product, which includes a computer program. In some embodiments, the computer program is executable by one or more processors so that the processors execute the method 500. Corresponding to the execution subject corresponding to each step in each embodiment of the method 500, the processor that executes the corresponding step may belong to the corresponding execution subject.

[0264] The computer program product of the above embodiment is used to enable the processor to execute the method 500 described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0265] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of simplicity.

[0266] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present disclosure difficult to understand, the known power / ground connections to the integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure will be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it is apparent to those skilled in the art that the embodiments of the present disclosure can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0267] Although the present disclosure has been described in conjunction with specific embodiments of the present disclosure, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0268] The embodiments of the present disclosure are intended to cover 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 the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A document information recommendation method, comprising: In response to a user's operation of accessing a document satisfying a predetermined condition, determining one or more issues associated with the document; displaying the one or more questions in a predetermined area of ​​the document; The one or more questions are generated based on the content of one or more target documents associated with the document.

2. The method of claim 1, wherein: One or more target documents associated with the document include at least one of the following documents: the document itself; one or more other documents referenced by the document; one or more other documents that reference the document; Other documents recorded in the bidirectional link area of ​​the document; One or more other documents associated with the keywords of the document.

3. The method of claim 1, further comprising: determining one or more target documents associated with the document; Based on the content of each of the target documents, generate one or more candidate questions respectively; The one or more questions are determined based on the one or more candidate questions corresponding to each of the target documents.

4. The method of claim 1, further comprising: determining one or more first documents referenced by the document and one or more second documents referencing the document; In response to determining that the number of the first documents and / or the second documents is greater than or equal to a preset number, determining the one or more target documents associated with the documents based on the one or more first documents and / or the one or more second documents; or, In response to determining that the number of the first document and / or the second document is less than a preset number, determining one or more third documents associated with the keywords of the documents; Based on the one or more first documents, the one or more second documents and / or the one or more third documents, one or more target documents associated with the document are determined.

5. The method of claim 3, further comprising: determining one or more first candidate documents referenced by the document; Filtering the one or more first candidate documents to obtain the one or more first documents according to the user's reading authority, the number of clicks on the first candidate document, and / or the number of words in the first candidate document; and / or Determining one or more second documents that reference the document includes: determining one or more second candidate documents referenced by the document; Filtering the one or more second candidate documents to obtain the one or more second documents according to the user's reading authority, the number of clicks on the second candidate document, and / or the number of words in the second candidate document; and / or Determining one or more third documents associated with the keyword of the document includes: determining one or more third candidate documents associated with the keyword of the document; The one or more third documents are obtained by screening from the one or more third candidate documents according to the user's reading authority, the number of clicks on the third candidate document and / or the number of words in the third candidate document.

6. The method of claim 3, wherein: Determining the one or more questions based on the one or more candidate questions corresponding to each of the target documents includes: The one or more questions are obtained by screening from the one or more candidate questions according to the word count of the one or more candidate questions.

7. The method according to claim 1, wherein the preset area comprises: an area adjacent to an editable area of ​​the document; An area adjacent to the like area of ​​the document; an area adjacent to a bidirectionally linked area of ​​the document; or A new area is added to the bidirectional link area of ​​the document.

8. The method of claim 7, wherein: Displaying the one or more questions in a newly added area within the bidirectional link area of ​​the document includes at least one of the following: displaying the one or more questions in a first tab of the bidirectional link area; Displaying one or more other documents referenced by the document in a second tab page of the bidirectional link area; A third tab page in the bidirectional link area displays one or more other documents that reference the document.

9. The method of claim 1, further comprising: In response to a trigger instruction for a target question among the one or more questions, calling a target application, sending the target question in a window of the target application, so as to generate an answer corresponding to the target question through the target application; or In response to a trigger instruction for a target question among the one or more questions, a first window is displayed in the document page, and the target question and an answer corresponding to the target question are displayed in the first window.

10. The method of claim 1, wherein: Displaying the one or more questions in a preset area of ​​the document further comprises: At the associated position of the question, a symbol or icon associated with the question is displayed.

11. A document information recommendation device, comprising: A determination module, configured to: in response to a user's operation of accessing a document satisfying a predetermined condition, determine one or more issues associated with the document; A display module, configured to: display the one or more questions in a preset area of ​​the document; The one or more questions are generated based on the content of one or more target documents associated with the document.

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

13. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 10.

14. A computer program product, wherein: The method comprises computer program instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 10.

Images