Content extraction method and apparatus, and electronic device and storage medium

Abstract

The present application relates to the field of Internet technology, and particularly relates to a content extraction method and apparatus, and an electronic device and a storage medium. The method comprises: in response to an uploading operation triggered on the basis of an information interaction interface, presenting a document selection interface, wherein the document selection interface includes at least one document; in response to a selection operation regarding a first document among the at least one document, presenting the first document in the information interaction interface, and presenting processing information of the first document in a state region corresponding to the first document; and after content extraction of the first document has been completed, canceling the display of the state region, and presenting, in the information interaction interface, a document abstract obtained by means of performing content extraction on the first document. By means of the present application, abstract extraction can be automatically performed on an uploaded document, so as to provide summary content of the document, and thus improving the information presentation efficiency and improving the reading efficiency.

Description

Content extraction method, device, electronic device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on September 27, 2023, with application number 2023112828820 and application name “A content extraction method, device, electronic device and storage medium”. The entire contents of the application are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of Internet technology, in particular to the field of artificial intelligence technology, and provides a content extraction method, device, electronic device and storage medium. Background Art

[0003] With the popularization of computer technology and the rapid rise of the Internet, the way people obtain and send information has become more convenient, the network resources on the Internet have grown at an unprecedented rate, and a large amount of information has appeared in front of people in the form of documents.

[0004] Specifically, online resources such as news reports, scientific papers, legal documents, novels, financial reports, and textbooks are a vast source of text data. This, coupled with emerging self-media platforms, has further complicated the presentation of text information. While the rapid development of informatization has brought convenience, the information explosion has also posed challenges. Users struggle to grasp the key points from this vast amount of information. Therefore, extracting the key content from various documents is both urgent and crucial.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a content extraction method, device, electronic device and storage medium, which help to select documents and generate document summaries, thereby facilitating the provision of summary content of the document, thereby improving information presentation efficiency and reading efficiency.

[0007] An embodiment of the present application provides a content extraction method, including:

[0008] In response to an upload operation triggered based on the information interaction interface, presenting a document selection interface, wherein the document selection interface includes at least one document;

[0009] In response to a selection operation on a first document among the at least one document, presenting the first document in the information interaction interface and presenting processing information of the first document in a status area corresponding to the first document, the processing information indicating a current processing stage and a corresponding processing status during content extraction of the first document;

[0010] After the content extraction of the first document is completed, the display of the status area is canceled, and a document summary obtained by extracting the content of the first document is presented in the information interaction interface.

[0011] Another content extraction method provided in an embodiment of the present application includes:

[0012] extracting text information from a first document after receiving a document processing request for the first document; the first document being uploaded by a client in response to a selection operation of the first document from at least one document in a document selection interface, the document selection interface being presented by the client in response to the upload operation triggered by the information interaction interface;

[0013] Slicing the extracted text information to obtain at least one text slice;

[0014] Extracting a summary of each text slice in the at least one text slice to obtain a slice summary corresponding to each of the at least one text slice;

[0015] The obtained slice summary is summarized to obtain a document summary corresponding to the first document, and the document summary is fed back to the client so that the client presents the document summary obtained by content extraction of the first document in the information interaction interface.

[0016] An embodiment of the present application provides a content extraction device, comprising:

[0017] A first response unit, configured to present a document selection interface in response to an upload operation triggered based on the information interaction interface, wherein the document selection interface includes at least one document;

[0018] a second response unit, configured to, in response to a selection operation on a first document among the at least one document, present the first document in the information interaction interface and present processing information of the first document in a status area corresponding to the first document, the processing information indicating a current processing stage and a corresponding processing status during content extraction of the first document;

[0019] After the content extraction of the first document is completed, the display of the status area is canceled, and a document summary obtained by extracting the content of the first document is presented in the information interaction interface. Another content extraction device provided by an embodiment of the present application includes:

[0020] an information extraction unit configured to extract text information from a first document upon receiving a document processing request for the first document; the first document being uploaded by a client in response to a selection operation of the first document from at least one document in a document selection interface, the document selection interface being presented by the client in response to the upload operation triggered by the information interaction interface;

[0021] a slicing processing unit, configured to slice the extracted text information to obtain at least one text slice; and extract a summary of each text slice in the at least one text slice to obtain a slice summary corresponding to each of the at least one text slice;

[0022] A summarizing unit is used to summarize the obtained slice summary to obtain a document summary corresponding to the first document, and feed the document summary back to the client so that the client presents the document summary obtained by content extraction of the first document in the information interaction interface.

[0023] An embodiment of the present application provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of any one of the above-mentioned content extraction methods.

[0024] An embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to perform the steps of any one of the above-mentioned content extraction methods.

[0025] An embodiment of the present application provides a computer program product, which includes a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the steps of any one of the above-mentioned content extraction methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0027] FIG1 is a schematic diagram of an application scenario in an embodiment of the present application;

[0028] FIG2 is a flowchart of an implementation of a content extraction method provided in an embodiment of the present application;

[0029] FIG3A is a schematic diagram of a function discovery interface and a document summary interface in an embodiment of the present application;

[0030] FIG3B is a schematic diagram of another function discovery interface and document summary interface in an embodiment of the present application;

[0031] FIG4 is a schematic diagram of a document summary viewing process of an example document in an embodiment of the present application;

[0032] FIG5 is a schematic diagram of a document summary interface and a document selection interface in an embodiment of the present application;

[0033] FIG6 is a schematic diagram of a document selection interface in an embodiment of the present application;

[0034] FIG7A is a schematic diagram of a state area in an embodiment of the present application;

[0035] FIG7B is a schematic diagram of another state area in an embodiment of the present application;

[0036] FIG8A is a schematic diagram of a default message and status area in an embodiment of the present application;

[0037] FIG8B is a schematic diagram of another default message and status area in an embodiment of the present application;

[0038] FIG9A is a schematic diagram of a state area in an expanded state according to an embodiment of the present application;

[0039] FIG9B is a schematic diagram of a state area in another expanded state according to an embodiment of the present application;

[0040] FIG10A is a schematic diagram of countdown information in an embodiment of the present application;

[0041] FIG10B is a schematic diagram of another type of countdown information in an embodiment of the present application;

[0042] FIG11 is a schematic diagram of another countdown information in an embodiment of the present application;

[0043] FIG12A is a schematic diagram of an upload failure prompt message according to an embodiment of the present application;

[0044] FIG12B is a schematic diagram of another upload failure prompt message in an embodiment of the present application;

[0045] FIG13A is a schematic diagram of a process for handling stage abnormalities in an embodiment of the present application;

[0046] FIG13B is a schematic diagram of another processing stage abnormality in an embodiment of the present application;

[0047] FIG14 is a schematic diagram of a processing result in an embodiment of the present application;

[0048] FIG15 is a schematic diagram of another processing result in an embodiment of the present application;

[0049] FIG16 is a schematic diagram of a first document summary in an embodiment of the present application;

[0050] FIG17A is a schematic diagram of a second document summary in an embodiment of the present application;

[0051] FIG17B is a schematic diagram of a third document summary according to an embodiment of the present application;

[0052] FIG17C is a schematic diagram of a fourth document summary according to an embodiment of the present application;

[0053] FIG18A is a schematic diagram of a summary switching control in an embodiment of the present application;

[0054] FIG18B is a schematic diagram of another summary switching control in an embodiment of the present application;

[0055] FIG19A is a schematic diagram of a question-and-answer scenario for a document summary in an embodiment of the present application;

[0056] FIG19B is a schematic diagram of another question-and-answer scenario for document summaries in an embodiment of the present application;

[0057] FIG20 is a schematic diagram of a modification scenario for a document summary in an embodiment of the present application;

[0058] FIG21 is a schematic diagram of a presentation style of a question and answer message in an embodiment of the present application;

[0059] FIG22 is a schematic diagram of a presentation method of multiple first documents and document summaries in an embodiment of the present application;

[0060] FIG23 is a schematic diagram of another presentation method of multiple first documents and document summaries in an embodiment of the present application;

[0061] FIG24 is a schematic diagram of another method for presenting multiple first documents and document summaries in an embodiment of the present application;

[0062] FIG25A is a schematic diagram of a stop prompt message in an embodiment of the present application;

[0063] FIG25B is a schematic diagram of another stop prompt message in an embodiment of the present application;

[0064] FIG26A is a schematic diagram of an exit prompt message in an embodiment of the present application;

[0065] FIG26B is a schematic diagram of another exit prompt message in an embodiment of the present application;

[0066] FIG27 is a schematic diagram of a second function control in an embodiment of the present application;

[0067] FIG28A is a schematic diagram of a landing page of a shared party in an embodiment of the present application;

[0068] FIG28B is a schematic diagram of another landing page of a shared party in an embodiment of the present application;

[0069] FIG29 is a schematic diagram of a historical record in an embodiment of the present application;

[0070] FIG30 is a flowchart of another content extraction method according to an embodiment of the present application;

[0071] FIG31 is a schematic diagram of a single-document rough summary extraction process in an embodiment of the present application;

[0072] FIG32 is a schematic diagram of a multi-document summary extraction process in an embodiment of the present application;

[0073] FIG33 is a schematic diagram of a feature matching process in an embodiment of the present application;

[0074] FIG34 is a schematic diagram of a document content parsing and question-answering scheduling process in an embodiment of the present application;

[0075] FIG35 is a schematic diagram of the composition structure of a content extraction device according to an embodiment of the present application;

[0076] FIG36 is a schematic diagram of the composition structure of a content extraction device according to an embodiment of the present application;

[0077] FIG37 is a schematic diagram of a hardware structure of an electronic device to which an embodiment of the present application is applied;

[0078] FIG38 is a schematic diagram of the hardware structure of another electronic device to which an embodiment of the present application is applied. DETAILED DESCRIPTION

[0079] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of the technical solutions of this application, but not all of them. Based on the embodiments described in this application document, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the technical solutions of this application.

[0080] The following is an introduction to some concepts involved in the embodiments of this application.

[0081] Document summaries and slice summaries: A document summary summarizes the overall content of a document, while a slice summary summarizes each text slice contained in the document. Summarization here refers to extracting content through generalization. For example, summarization is abstract extraction. A document summary summarizes the overall content of a document, while a document can be divided into at least one text slice. A slice summary summarizes the content contained in the corresponding text slice.

[0082] Text slicing and content slicing: Text slicing is mainly used in the summary extraction process, which refers to slicing the text information contained in the parsed document; while content slicing is mainly used in multi-round question-answering scenarios, which refers to splitting the document into finer granularity according to the preset slicing granularity (such as paragraph granularity, sentence granularity, etc.), which is used for subsequent feature matching with questions.

[0083] Processing stage (also called processing node): refers to the process of document content extraction divided into multiple steps. Each step can be understood as a processing stage. Each step in the process of document content extraction will correspond to a processing status, indicating whether the step is being processed, completed, not yet processed, or failed.

[0084] In an embodiment of the present application, content extraction can be performed on the first document based on natural language processing technology and machine learning technology to generate a document summary corresponding to the first document. This process can be implemented based on artificial intelligence automatic content generation (AI-Generated Content, AIGC) technology. It can be applied in a variety of scenarios, such as extracting summaries of text documents (which may contain graphics), audio documents, video documents, etc. Moreover, on this basis, multiple rounds of question and answer can be performed in combination with document summaries. When inputting multiple rounds of questions and answers, the system will perform similarity matching between the object's questions and the text features of the document parsing results, find the content in the document that is most relevant to the object's questions, and then summarize it through the model to output the answers.

[0085] Specifically, when generating document summaries or multi-round question-answering answers based on AIGC, a large language model (LLM) can be used. LLM is an artificial intelligence model designed to understand and generate human language. They are trained on large amounts of text data and can perform a wide range of tasks, including text summarization, translation, sentiment analysis, and more. LLMs are characterized by their large scale and contain billions of parameters, which help them learn complex patterns in language data. These models are usually based on deep learning architectures such as transformers, which helps them achieve impressive performance on various NLP tasks.

[0086] The following is a brief introduction to the design of the embodiment of the present application:

[0087] With the popularization of computer technology and the rapid rise of the Internet, the way people obtain and send information has become more convenient, the network resources on the Internet have grown at an unprecedented rate, and a large amount of information has appeared in front of people in the form of documents.

[0088] Specifically, online resources such as news reports, scientific papers, legal documents, novels, financial reports, and textbooks are a vast source of text data. Coupled with emerging self-media platforms, the presentation of text information has become even more complex. While the rapid development of informatization has brought convenience, the information explosion has also brought challenges. It is difficult for users to timely grasp the key points from this vast amount of information. Therefore, extracting the main content of various documents is particularly urgent and important.

[0089] In summary, how to extract the content of documents and provide users with convenient document summary content to improve the reading efficiency of documents is an urgent problem to be solved.

[0090] In view of this, the embodiments of the present application provide a content extraction method, device, electronic device and storage medium. Since the present application supports the object to upload the first document that needs to be extracted through the information interaction interface according to its own needs, and then automatically extract the content of the first document, after the processing of the content extraction of the first document is completed, the document summary obtained after the content extraction of the first document can be directly presented to the object on the information interaction interface. The object can directly read the document summary information to quickly understand the content of the first document, thereby improving the efficiency of information presentation and reading efficiency. In addition, the process of extracting the content of the first document involves multiple processing stages, and the execution of these processing stages will consume a certain amount of time. In order to reduce the object's sense of waiting, manage the object's expectations, and avoid the object from being lost during the summary generation process, the present application sets a status area in the information interaction interface for displaying the progress related to the processing stage. Specifically, in the process of extracting the content of the first document, the current processing stage and the corresponding processing status corresponding to the first document are directly presented to the object through the status area to enhance the object's experience.

[0091] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application can be combined with each other if there is no conflict.

[0092] As shown in Figure 1, which is a schematic diagram of an application scenario in an embodiment of the present application, the application scenario diagram includes two terminal devices 110 and a server 120.

[0093] In the embodiment of the present application, the terminal device 110 includes but is not limited to mobile phones, tablet computers, laptop computers, desktop computers, e-book readers, intelligent voice interaction devices, smart home appliances, car terminals and other devices; a content extraction-related client can be installed on the terminal device, which can be software (such as a browser, instant messaging software, etc.), or a web page, applet, etc. The server 120 is a background server corresponding to the software or web page, applet, etc., or a server specifically used for content extraction, which is not specifically limited in this application. The server 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and basic cloud computing services such as big data and artificial intelligence platforms.

[0094] It should be noted that the content extraction method in each embodiment of the present application can be executed by an electronic device, which can be a terminal device 110 or a server 120. That is, the method can be executed independently by the terminal device 110 or the server 120, or can be executed jointly by the terminal device 110 and the server 120. For example, when executed jointly by the terminal device 110 and the server 120, a content extraction-related client can be installed on the terminal device 110. The object can trigger an upload operation based on the information interaction interface of the client. In response to the upload operation, the client presents a document selection interface to the object, supporting the object to select a document from the document selection interface for upload. Specifically, in response to the object's selection operation on a first document from at least one document in the document selection interface, the client presents the first document in the information interaction interface and sends a document processing request for the first document to the server 120 via the terminal device 110. Then, the server 120 extracts content from the first document, generates a corresponding document summary, and feeds it back to the client. The client presents the document summary to the object in the information interaction interface via the terminal device 120.

[0095] In addition, the server 120 is also used to provide real-time feedback on the processing information of the first document to the client, so that the client can present the processing information in the status area corresponding to the first document through the terminal device 110; and the server 120 is also used to provide real-time feedback on the estimated completion time corresponding to the key processing stage to the client, so that the client can present the countdown information of the estimated completion time corresponding to the key processing stage in the status area through the terminal device 110 when the current processing stage of the first document is the key processing stage.

[0096] In an optional implementation, the terminal device 110 and the server 120 may communicate via a communication network.

[0097] In an optional implementation, the communication network is a wired network or a wireless network.

[0098] It should be noted that what is shown in FIG1 is only an example. In fact, the number of terminal devices and servers is not limited and is not specifically limited in the embodiments of the present application.

[0099] In an embodiment of the present application, when there are multiple servers, the multiple servers can be combined into a blockchain, and the servers are nodes on the blockchain; such as the content extraction method in an embodiment of the present application, the document-related data involved can be saved on the blockchain, for example, the document content of the first document, the generated slice summary, the document summary, the summarized document summary, the estimated completion time of the key processing stage corresponding to the first document, the answer messages of multiple rounds of questions and answers, etc.

[0100] In addition, the embodiments of the present application can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving and other scenarios.

[0101] The following describes the content extraction method provided by the exemplary embodiment of the present application in combination with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present application, and the implementation of the present application is not limited in this respect.

[0102] Refer to FIG. 2 , which is a flowchart of an implementation method of a content extraction method provided in an embodiment of the present application. Taking the client as the execution subject as an example, the specific implementation process of the method is as follows S21 to S23:

[0103] S21: In response to an upload operation triggered based on the information interaction interface, presenting a document selection interface, where the document selection interface includes at least one document.

[0104] In the embodiment of the present application, uploading of different types of documents can be supported, such as documents in WORD, PDF, EXCEL, PPT and other formats.

[0105] In addition, it supports uploading documents of various contents. Generally speaking, the content contained in the documents can be in various data formats, such as text documents (which can contain images and text), audio documents, video documents, etc. From a more detailed content classification point of view, it can be public account articles, research reports, news reports, resumes, product analysis reports, English articles, legal documents, financial reports, papers, textbooks, novels, etc. This article does not make specific restrictions.

[0106] In an embodiment of the present application, a subject can trigger an upload operation on the information interaction interface and then select the first document for content extraction from the document selection interface. Specifically, a subject can upload only one document at a time, and then extract a summary for only that document. Alternatively, a subject can upload multiple documents at once. In such a case, a summary can be extracted for each document separately, or a summary can be extracted for all documents together. This will be explained in detail below and will not be repeated here.

[0107] It should be noted that the information interaction interface in the embodiments of the present application can be any interactive interface that supports conversational functionality. In general, the information interaction interface can be any conversational interface in the client (such as a chat interface), or it can be a functional interface that supports conversational functionality and is specifically used for document summarization, which can be called a document summary interface.

[0108] In addition, the client in the embodiments of the present application includes but is not limited to: mini-programs, APPs, web pages, etc.

[0109] The following mainly takes the information interaction interface as a document summary interface as an example. Of course, the information interaction interface can also be other conversation interfaces, which will not be described one by one here.

[0110] Optionally, the document summary function in the embodiment of the present application can be only a function in the client. In addition, the client can also support other functions, such as AI painting, AI copywriting generation, AI outline generation, etc. Based on this, the information interaction interface can be opened by the object based on the first interface in the client. An optional implementation method is as follows:

[0111] Prior to S21, the client presents an information interaction interface in response to a document summary operation triggered by a first function control in the first interface. The information interaction interface includes a default message and a document upload control. The default message is used to present an example document summary function, which generates a document summary by extracting content from a document. The first interface can be referred to as a function discovery interface, for example.

[0112] The information interaction interface presented in this case can be understood as a functional interface that supports conversation functions and is specifically used for document summarization, that is, a document summary interface.

[0113] On this basis, the specific implementation of S21 is: the client presents a document selection interface in response to an upload operation triggered by a document upload control in the information interaction interface.

[0114] Refer to FIG3A , which is a schematic diagram of a function discovery interface and a document summary interface in an embodiment of the present application. The function discovery interface includes multiple first function controls, such as a document summary, a public account article summary, a friend circle copy, an application A recommendation copy, a short video script, a travel plan, etc. The subject can click on the document summary shown in S31 to trigger the document summary operation, presenting the document summary interface shown in FIG3A .

[0115] Among them, the document summary interface also presents a default message in the form of a message, as shown in message box S32, prompting the object to upload the document, extract the core content of the document, and generate a document summary. For example, S32 contains a text prompt message "I can help you summarize the documents in application B. After uploading the document, I can help you quickly summarize the core content."

[0116] In addition, a document upload control is displayed at the bottom of the document summary interface (it can also be set at other locations), namely "Import B application document" as shown in Figure 3A. The object can click on the control to enter the document selection interface.

[0117] As shown in FIG3B , it is a schematic diagram of another function discovery interface and document summary interface in an embodiment of the present application. The function discovery interface includes multiple first function controls such as: document summary, cyberpunk style, travel plan, acrostic poem, PPT outline, fitness plan, etc. The subject can click the document summary shown in S32 to trigger the document summary operation, presenting the document summary interface shown in FIG3B .

[0118] As in FIG3A , a default message is displayed in the document summary interface, as shown in message box S34. Furthermore, a document upload control, namely, "Import PDF Document" as shown in FIG3B , is displayed at the bottom of the document summary interface (which may also be located elsewhere). The subject can click on this control to enter the document selection interface.

[0119] It should be noted that the triggering actions listed above for the controls can be clicks, long presses, double clicks, and other actions. The same applies to the following, and this article does not make specific restrictions.

[0120] In the above embodiment, the object can enter the information interaction interface through the function discovery interface, and can also enter other AI function-related interfaces through the function discovery interface. The document upload control is directly presented on the information interaction interface, which facilitates the object to directly upload documents by operating the document upload control, reducing the complexity of the object operation, saving operation time, and thereby improving the convenience of interaction.

[0121] Of course, the above-mentioned method of entering the information interaction interface is only one embodiment supported by this application. In addition, the object can also enter the information interaction interface through other methods, such as the object directly opening the chat window with the AI ​​summary robot in the client (which can be used as an information interaction interface), etc. This article does not make specific limitations.

[0122] Optionally, the default message in the information interaction interface includes at least one example document; in an embodiment of the present application, when content is not extracted from the first document, the example document is in an interactive state, and the interactive state means that a selection operation can be performed on any example document with an interactive state on the current information interaction interface.

[0123] Therefore, before S21, the object may also view the document summary of the sample document to further understand the document summarization function supported by the client. An optional implementation is as follows:

[0124] In response to a selection operation on any one of the at least one example document, the client presents a document summary corresponding to the any one example document.

[0125] Refer to Figure 4, which is a schematic diagram of the document summary viewing process for an example document in an embodiment of the present application. The example document, as shown in Document Summary Interface 1 and Document Summary Interface 2 in Figure 4, is in an interactive state. After a subject selects Example Document 1 in Document Summary Interface 1, the example document and its document summary are presented in the Document Summary Interface, as shown in Document Summary Interface 2 in Figure 4. Specifically, the document summary is presented in the form of a message.

[0126] In the above embodiment, the sample document is presented to the object based on the default message. The object can understand the document summary function more directly and quickly based on the sample document, and is convenient for performing operations related to the document summary, thereby improving the convenience of interaction.

[0127] In addition, in addition to understanding the document summary function based on the sample document, the object can also upload the first document based on the document upload control in the information interaction interface.

[0128] Refer to Figure 5, which is a schematic diagram of a document summary interface and a document selection interface in an embodiment of the present application. At the bottom of the document summary interface shown in Figure 5, a document upload control, namely, "Import B Application Document" as shown in Figure 5, is displayed. The user can click (or long press, double-click, or other actions) this control to enter the document selection interface shown in Figure 5.

[0129] The document upload control shown in FIG5 takes the example of importing local documents of the client (ie, application B). There are three documents presented in the document selection interface shown in FIG5 , namely, Article 1, Article 2, and Article 3.

[0130] Among them, these three articles are all related to the object "Xiao A" currently logged in by the B application, such as Article 1 uploaded by Xiao A to the B application on May 4, 2023, and Articles 2 and 3 sent by Xiao B to Xiao A on April 30, 2023.

[0131] The subject A may select at least one of the three articles as the first document to extract content from the first document.

[0132] As shown in Figure 6, it is a schematic diagram of a document selection interface in an embodiment of the present application. Document selection interface 1 shows that subject A has selected "Article 1" as the first document, meaning that only a summary needs to be extracted for the first document. Document selection interface 2 shows that subject A has selected "Article 1," "Article 2," and "Article 3" as first documents, meaning that summaries need to be extracted for three first documents.

[0133] It should be noted that the document upload controls shown in Figures 3A, 4, and 5 above are based on the example of importing local client documents or PDF types. In addition, it can also be used to import documents from other applications, or to import other types of documents, document links, etc. In summary, the first document in the embodiment of the present application can be any type of document uploaded through any channel, and will not be described one by one here.

[0134] In addition, it should be noted that the document uploading methods listed above are only simple examples. The document upload control may not be set in the information interaction interface in this application. For example, the object can directly send the first document to the dialogue window of the information interaction interface in the form of a message; or, the object can also call up the document selection interface based on voice commands in the information interaction interface, and then select the first document for upload, etc. Any method of uploading the first document based on the information interaction interface is applicable to the embodiments of this application and will not be described one by one here.

[0135] S22: In response to a selection operation on a first document among at least one document, the first document is presented in the information interaction interface, and processing information of the first document is presented in a status area corresponding to the first document, where the processing information indicates a current processing stage and a corresponding processing status in the process of content extraction for the first document.

[0136] In an embodiment of the present application, step S22 may select one or more first documents, present one or more first documents, and present processing information of the corresponding first documents in a status area corresponding to each first document.

[0137] In the embodiment of the present application, the process of extracting content from the first document can be divided into multiple steps, each step can be regarded as a processing stage, and thus, the process of extracting content from the first document includes multiple processing stages.

[0138] For example, the processing stages in the content extraction process may include: uploading documents, extracting content information, processing image content, processing text content, extracting core ideas, and organizing and merging summaries.

[0139] Among them, uploading a document means uploading all the contents contained in the document (including one or more contents such as text, pictures, videos, etc.); extracting content information refers to extracting specific information of one or more contents such as text, pictures, videos, etc. contained in the document; processing picture content can be understood as extracting text information in the picture (such as using optical character recognition (OCR) technology to identify picture content); processing text content is, for example, slicing the extracted text information to obtain at least one text slice, etc.; extracting the core idea can be understood as performing summary extraction on each text slice to obtain the slice summary corresponding to each text slice, etc.; arranging and merging summaries can be understood as extracting the content of each slice summary obtained again to obtain the document summary corresponding to the first document, etc. For details, please refer to the relevant instructions on the server side, and the repetitions will not be repeated.

[0140] In general, the above processing stages can be divided into two categories. One is document uploading, which corresponds to the "upload document" processing stage; the other is document summarization, which corresponds to the above-mentioned "extract content information, process image content, process text content, extract core ideas, and organize and merge summaries" processing stages.

[0141] It should be noted that the several processing stages listed above are just simple examples. In addition, other processing stages may also be included, such as processing video content, processing voice content, etc., which are not specifically limited in this article.

[0142] The processing status corresponding to each processing stage may be processing, completed, not yet processed, processing failed, etc. The processing status may further indicate the processing progress, etc., which is not specifically limited in this article.

[0143] In summary, you first need to upload the document. After the document is uploaded, you can extract the content information contained in the document. If the extracted content information includes picture content, then process the picture content. Furthermore, if the extracted content information includes text content, then process the text content, and then extract the core ideas of the processed content information. Finally, organize and merge these extracted core ideas to generate a document summary.

[0144] In an embodiment of the present application, taking into account that the execution of these processing stages will consume a certain amount of time, in order to reduce the object's sense of waiting, manage the object's expectations, and avoid the loss of the object during the summary generation process, the present application sets up a status area in the information interaction interface for displaying the progress related to the processing stage. Specifically, in the process of content extraction of the first document, the current processing stage and the corresponding processing status corresponding to the first document are directly displayed to the object through the status area to enhance the object's experience.

[0145] The status area may be presented at a relevant position of the first document, such as any position near the first document, such as below the first document message box, or above, left, or right, etc., which is not specifically limited herein.

[0146] Refer to FIG. 7A , which is a schematic diagram of a status area in an embodiment of the present application. S71 in FIG. 7A illustrates a status area in an embodiment of the present application. For example, taking the 22.5 MB PDF file "Great CCC" as the first document, at the current moment, the current processing stage corresponding to the first document is "Uploading Document," and the upload progress (i.e., processing status) is 75%. The processing information "Uploading Document 75%" can be displayed in the status area shown in S71.

[0147] Refer to FIG. 7B , which is a schematic diagram of another status area in an embodiment of the present application. S73 in FIG. 7B illustrates a status area in an embodiment of the present application. Similar to S71 in FIG. 7A , the status area shown in S73 may display the processing information "Document Uploading 90%," indicating that the current processing stage is uploading the document, and the corresponding processing status is 90% uploaded.

[0148] During this process, if the object does not want to extract the content of the document, he or she can cancel it at any time. For example, when the object is uploading the first document, the document upload control is updated from the style shown in Figures 3B, 4, and 5 to the style shown in S72 or S74, which prompts the object "Uploading, click to cancel". The object clicks the control shown in S72 or S74 to cancel the uploading of the first document.

[0149] Optionally, after the first document is uploaded, at least one example document is updated to a non-interactive state. The non-interactive state may indicate that the area displaying the document is inoperable. This ensures that the example document cannot be manipulated while the first document is being processed.

[0150] Refer to Figure 8A, which is a schematic diagram of a default message and status area in an embodiment of the present application. The processing information "Processing text content" in the status area S82 shown in Figure 8A indicates that the current processing stage is processing text content and the processing status is processing. In other words, the current processing stage is the post-upload processing process. In this case, the sample document needs to be updated to a non-interactive state, as shown in the default message S81 in Figure 8A, indicating a non-interactive state.

[0151] Refer to Figure 8B, which is a schematic diagram of another default message and status area in an embodiment of the present application. Among them, the processing information "Processing image content" in the status area S85 shown in Figure 8B has the same meaning as S81 in Figure 8A, and the default message S84 also indicates a non-interactive state.

[0152] During this process, if the object does not want to extract the content of the document, he or she can cancel it at any time. For example, when the object is uploading the first document, the document upload control is updated from the style shown in Figures 3B, 4, and 5 to the style shown in S83 or S86, which prompts the object "Summarizing, click to cancel". The object clicks the control shown in S83 or S86 to cancel the uploading of the first document.

[0153] In the above embodiment, the processing progress of the first document is immediately presented to the object through the status area, effectively managing the object's expectations and making it easier for the object to intuitively understand the progress. In this way, the embodiment of the present application can immediately present the processing progress of the first document.

[0154] Optionally, initially, the status area is collapsed to facilitate the subject to promptly understand the current processing stage.

[0155] In addition, if the subject wants to know more about the processing stage in a timely manner, the status area can be switched to the expanded state. An optional implementation is as follows:

[0156] In response to the expansion operation triggered on the status area, the client switches the status area to an expanded form; in the expanded form of the status area, various processing stages in the process of content extraction of the first document and the processing status of each processing stage are presented.

[0157] In order to facilitate the subject to further quickly understand the respective processing status of each processing stage, different display styles can also be used to distinguish the processing stages of different processing states to present different sensory effects to the subject.

[0158] Specifically, different display styles may be different colors, different text styles, additional different icons, patterns, etc., which are not specifically limited herein.

[0159] For example, when there is a processing stage where processing fails, such processing stage is displayed in red font to serve as a warning; or, the processing stage being processed is displayed in bold font to serve as emphasis; and so on.

[0160] In an embodiment of the present application, the status area can be divided into a collapsed form and an expanded form. In the collapsed form, the status area only needs to present the current processing stage of the first document and the processing status corresponding to the current processing stage, which can ensure that the object is aware of the current processing status of the first document in a timely manner.

[0161] In the expanded form, the status area can present the various processing stages involved in the process of content extraction of the first document, as well as the processing status corresponding to each of these processing stages, to ensure that the object has a clear understanding of the complete processing flow corresponding to the first document, such as which processing stage(s) have been completed, which are being processed, which are not yet completed, etc.

[0162] 9A is a schematic diagram of a state area in an expanded configuration according to an embodiment of the present invention. As shown in section S91 of FIG9A , in the expanded configuration, various processing stages are displayed, and different text styles are used to represent the different processing states corresponding to these processing stages.

[0163] Among them, uploading documents and extracting content information are in the completed state, processing image content is in the processing state, and processing text content, extracting core ideas, and organizing and merging summaries are in the unprocessed state.

[0164] In addition, the object can control the state of the status area to be collapsed or expanded through the control shown in S910.

[0165] 9B is a schematic diagram of the state area in another expanded configuration according to an embodiment of the present invention. As shown in section S92 of FIG9B , in the expanded configuration, various processing stages are displayed, and different text styles are used to represent the different processing states corresponding to these processing stages.

[0166] Among them, uploading documents, extracting content information and processing image content are in the completed state, processing text content is in the processing state, and extracting core ideas and organizing and merging summaries are in the unprocessed state.

[0167] In the above embodiment, the status area is supported to have at least two forms, namely, an expanded form and a collapsed form. In addition to facilitating the subject to intuitively understand the current processing progress of the first document, it can also support the subject to timely understand other processes required for content extraction of the first document, so as to reduce the subject's sense of waiting and avoid the subject from being lost during the summary generation process.

[0168] Optionally, regardless of whether the status area is in a collapsed state or an expanded state, if the current processing stage of the first document is a critical processing stage, countdown information of the estimated completion time corresponding to the critical processing stage is presented in the status area.

[0169] The key processing stage is at least one of the following: a preset processing stage and a processing stage whose estimated completion time exceeds a preset time threshold.

[0170] That is, the key nodes in the embodiments of the present application may be one or more pre-set processing stages. Generally, based on the importance or complexity of each processing stage, some more important and more complex processing stages may be prioritized as key processing stages.

[0171] Alternatively, a time threshold (i.e., a preset time threshold) is set in advance. After the server estimates the estimated completion time corresponding to each processing stage for the first document, these estimated completion times are compared with the preset time threshold respectively, and the processing stage whose estimated completion time exceeds the preset time threshold is regarded as the key processing stage.

[0172] The preset time threshold can be flexibly set based on actual needs, the model used for content extraction (e.g., the semantic understanding model (LLM)), the ratio of the estimated completion time between the various processing stages, and is not specifically limited in this document. For example, if the estimated completion time for most processing stages is 1-2 seconds, while some processing stages are estimated to take more than ten seconds, the preset time threshold can be set to 10 seconds, and so on.

[0173] Alternatively, the key processing stage may be determined by combining the above two methods.

[0174] Specifically, based on the above step-by-step progress display, in order to enhance the user experience of the object, reduce the object's sense of waiting, and let the object know the time required for processing in a timely manner, a countdown can also be displayed at some key processing stages.

[0175] Figure 10A shows a schematic diagram of a countdown timer in an embodiment of the present application. The current processing stage shown in status area S101 in Figure 10A is "Extracting Core Ideas," and the processing status is not "Processing." The corresponding estimated completion time countdown is 12 seconds. Over time, this countdown timer changes, such as decreasing to 11 seconds, 10 seconds, 9 seconds, and so on.

[0176] FIG10B is a schematic diagram of another type of countdown information in an embodiment of the present application. The current processing stage displayed in the status area S102 of FIG10B is "Collating and Merging Summary," and the processing status is not "Processing." The corresponding estimated completion time countdown information is 11 seconds. Over time, this countdown information also changes, such as decreasing to 10 seconds, 9 seconds, 8 seconds, and so on.

[0177] It should be noted that the countdown information listed in FIG. 10A or FIG. 10B is displayed in the collapsed state area. In addition, the countdown information of the key processing stage can also be displayed in the expanded state area.

[0178] As shown in Figure 11, it is a schematic diagram of another countdown information in an embodiment of the present application. Figure 11 shows the completed processing stages: uploading a document, extracting content information, processing image information, processing text information, and extracting core ideas. The processing stage currently being processed is: collating and merging summaries. This processing stage is a key processing stage and can further display countdown information, such as the 11s shown in Figure 11. As time passes, the countdown information can gradually decrease to 10s, 9s, 8s, etc.

[0179] In the above embodiment, the duration can be calculated in advance for some more complex, important or time-consuming links, and a countdown can be displayed to ensure that the object is aware of the current processing progress and the remaining processing time of the first document in a timely manner, so that the progress of the processing process can be notified in a timely manner to reduce the object's sense of waiting.

[0180] It should be noted that, although no abnormality occurs in the content extraction process listed in FIG. 9A , FIG. 9B , FIG. 10A , FIG. 10B or FIG. 11 , in actual application, processing failure may occur at some processing stage(s).

[0181] Optionally, in the event that the first document upload fails (i.e., the processing stage of uploading the document fails), a re-upload control may be presented, and the object may re-trigger the upload operation based on the re-upload control. The client re-uploads the first document in response to the re-upload operation triggered based on the re-upload control.

[0182] Specifically, an upload failure prompt message can also be presented. The upload failure prompt message can be in the form of a control, a pop-up window, etc., or it can be directly presented in the status area (that is, the processing information corresponding to the upload document processing stage in the event of processing failure, which can also be called upload failure prompt message), or a combination of two or more of the above situations, etc. This article does not make specific limitations. When the upload failure prompt message is in the form of a control, it is the re-upload control in the embodiment of the present application. The object can trigger the operation of re-uploading the document based on the re-upload control.

[0183] As shown in Figure 12A, it is a schematic diagram of an upload failure prompt message in an embodiment of the present application. If the first document fails to upload, the status area, as shown in S121, prompts the subject "Upload Failed". In addition, a "Re-upload" control is further presented below the status area, as shown in S122. S121 and S122 can be regarded as a form of upload failure prompt message in an embodiment of the present application. The subject can click the re-upload control shown in S122 to re-upload the first document.

[0184] It should be noted that the presentation method of the upload prompt information listed in Figure 12A is just a simple example. In addition, it can also be in other forms, such as a pop-up window. In addition, it can also further prompt the reason for the upload failure. As shown in Figure 12B, it is a schematic diagram of another upload failure prompt information in an embodiment of the present application. In particular, Figure 12B uses the control as an example to list two types of upload failure prompt information. For example, it can only prompt the object "Document upload failed", or it can prompt the reason for the upload failure, such as "Document too large, please upload a document smaller than 10M", etc.

[0185] In addition to the exceptions listed above regarding the upload document node, other nodes may also have exceptions. For example, if the image content processing node fails, the processing information indicating the failure can be directly displayed in the status area.

[0186] As shown in Figure 13A, it is a schematic diagram of a processing stage exception in an embodiment of the present application. The status area of ​​Figure 13A is in a collapsed state, wherein the processing information shown in S131 indicates that the processing status of the node processing the image content is: processing failed. In this case, a re-summarization control can be displayed below the status area, as shown in S132, and the subject can click on the control to re-extract the content of the first document.

[0187] As shown in Figure 13B, it is a schematic diagram of another processing stage exception in an embodiment of the present application. The status area of ​​Figure 13B is in an expanded form, wherein the processing status corresponding to the node "Processing Image Content" in the status area shown in S133 is: Processing Image Failed. After this step fails, the subsequent summary step cannot be continued. In this case, a re-summarization control can also be presented below the status area, as shown in S134. The subject can click on the control to re-extract the content of the first document.

[0188] It should be noted that FIG. 13A or FIG. 13B is an example of the processing stage of processing the image content. When an exception occurs in other processing stages, the same processing method is used, and the repeated parts are not repeated here.

[0189] In the above embodiment, when the upload object fails or other nodes handle abnormalities, the support object can quickly re-upload the document through the re-upload control, and re-extract the content of the first document through the re-summarize control, thereby facilitating the re-selection of the document to generate a summary in the event of a selection abnormality, thereby improving the operational convenience of selecting documents.

[0190] Optionally, in the expanded status area, after presenting the various processing stages in the process of content extraction for the first document and the respective processing status of each processing stage, the subject can also view the specific processing status of these processing stages.

[0191] For the target processing stages in the target processing state in each processing stage, in response to a selection operation on any target processing stage, a processing result of any target processing stage is presented.

[0192] The target processing status may be any specified processing status, such as completed, processing, or processing failure.

[0193] Typically, a target wants to view the processing results corresponding to a completed processing stage, or the failure reasons corresponding to a failed processing stage. Therefore, one optional implementation is: the target processing status includes at least one of completed and failed; when the processing status of any target processing stage is failed, the processing result includes at least one of the failure reason and document adjustment suggestions.

[0194] In the embodiment of the present application, the above processing results can be presented in a floating layer, a pop-up window, a new page, a certain area in the current page, etc., which is not specifically limited herein. The following is a simple example using a floating layer as an example.

[0195] Refer to Figure 14, which is a schematic diagram of a processing result in an embodiment of the present application. For example, the currently completed processing stages include uploading a document, extracting content information, and processing image content. Selecting the target processing stage "Process image content" will display the image content processing results corresponding to the first document. This processing result is the text information extracted from each image.

[0196] Refer to Figure 15, which is a schematic diagram of another processing result in an embodiment of the present application. For example, if the current processing stage that failed is processing image content, the object selects the target processing stage "Process image content" to view the image content processing results corresponding to the first document. The processing results are the text information successfully extracted from the image and the image that failed to be processed. In addition, the failure reason and document adjustment suggestions can be further presented, such as "The image is too large, it is recommended to adjust it to within 20M" in Figure 15, etc.

[0197] It should be noted that the several processing result presentation methods listed above are just simple examples. In addition, other processing result presentation methods are also applicable to the embodiments of this application and will not be described in detail here.

[0198] In the above embodiment, the processing results can be directly viewed based on the processing stage shown in the status area, which facilitates the rapid presentation of the relevant processing process and results of the document.

[0199] S23: After the content extraction of the first document is completed, the display of the status area is canceled, and a document summary obtained by extracting the content of the first document is presented in the information interaction interface.

[0200] Specifically, this application supports outputting document summaries in various forms, including but not limited to: text, pictures (flowcharts, mind maps, etc.), tables, etc.

[0201] In the embodiment of the present application, when processing (i.e., content extraction) of the first document is completed, the content extraction is complete, and a document summary for the first document is obtained. The document summary is generated by summarizing the overall content of the first document. By reading the document summary, the subject can quickly understand the main content (also called summarized content) of the first document.

[0202] In summary, the solution of the embodiment of the present application can provide an interactive solution for generating a summary corresponding to a document, which is convenient for selecting a document and generating a summary of the document, thereby facilitating the provision of a summary of the document content, thereby improving information presentation efficiency and reading efficiency.

[0203] In addition, considering that the processing of the first document has been completed, that is, all processing stages have been completed, there is no need to display the processing information in the status area, and the display of the status area can be cancelled.

[0204] In embodiments of the present application, when presenting a document summary in an information interaction interface, any method may be used, such as presenting the document summary in the form of a message. Specifically, a new message box may be directly generated in the information interaction interface, and the generated document summary may be fully presented in the message box. Alternatively, to enhance the subject's experience, the document summary corresponding to the first document may be streamed out in the form of messages in the information interaction interface, giving the subject the impression that these document summaries are being output gradually.

[0205] Furthermore, after the content of the first document is extracted, at least one example document may be updated to an interactive state. It should be noted that, when outputting a document summary in a streaming manner, the at least one example document may be updated to an interactive state before or during output of the document summary; or the at least one example document may be updated to an interactive state after the document summary is fully output.

[0206] Taking the streaming output method listed above as an example, as shown in Figure 16, it is a schematic diagram of the first document summary in the embodiment of the present application. As shown in the document summary interface 3 and the document summary interface 4 in Figure 16, the document summary shown in the message box S161 in the document summary interface 3 has not been fully output, and the document summary shown in the message box S163 in the document summary interface 4 represents the result of the complete output. In the case that the document summary has not been fully output, the aforementioned "summarizing, click to cancel" is updated to "stop generating" shown in S162, and the object can randomly click the control shown in S162 to pause the output of the document summary.

[0207] In addition, after the document summary is completely output, the sample document can be updated from the non-interactive state shown in the document summary interface 3 to the interactive state shown in the document summary interface 4.

[0208] FIG17A is a schematic diagram of the second document summary in an embodiment of the present application. FIG17A shows an example of a document summary interface when a document summary is being output. Similar to document summary interface 3 in FIG16 , the document summary in the message box has not yet been fully output, and the subject can randomly click "Stop Generating" to pause the output of the document summary.

[0209] FIG17B is a schematic diagram of a third document summary according to an embodiment of the present application. FIG17B shows an example of a document summary interface in which a complete document summary is output. Similar to document summary interface 4 in FIG16 , the document summary in the message box has been completely output. A re-summarize control can be displayed below the message box. The subject can click on the control to re-extract the content of the first document.

[0210] If the document summary is long and exceeds one screen, it can be scrolled, and the "Import New PDF Document" button at the bottom will be in a floating state. As shown in Figure 17C, which is a schematic diagram of the fourth document summary in an embodiment of the present application, a scroll bar can be displayed on the right side of the document summary interface, that is, S171. The subject can slide the screen up and down by pulling the scroll bar to view the complete document summary.

[0211] In the embodiment of the present application, the document summary can be presented in the form of a message. The present application also supports the object generating different document summaries for the same document multiple times. An optional implementation is as follows:

[0212] A re-summarize control for the first document is presented at a first relevant position of the document summary; then, the object can click the re-summarize control, and the client re-extracts content of the first document in response to the triggering operation on the re-summarize control, and after the re-content extraction is completed, a new document summary is presented at the original message corresponding to the document summary.

[0213] The first relevant position may be any position near the document summary, such as below the document summary message box, or above, to the left, or to the right, etc., which is not specifically limited herein.

[0214] Specifically, when outputting a complete document summary, a re-summarization control may be presented at the first relevant position of the document summary. Still taking FIG. 16 as an example, S164 in the document summary interface 4 shown in FIG. 16 is an example of a re-summarization control in an embodiment of the present application. The subject may click on the control to repeat the above-mentioned content extraction process. Specifically, the content extraction process in the embodiment of the present application includes multiple processing stages. When re-extracting the content of the first document, only some of the nodes in the multiple processing stages may be re-executed, or all of the nodes in the multiple processing stages may be re-executed. Among them, when re-executing some of the nodes in the multiple processing stages, it is mainly necessary to repeat at least the last processing stage, and it is also possible to repeat several processing stages before the last processing stage.

[0215] Optionally, considering that this application supports extracting summaries of the same document multiple times, in this case, the object can also switch to view the document summaries generated several times.

[0216] An optional implementation is as follows:

[0217] A summary switch control is presented at a second relevant position of the document summary; the object can switch the document summary for viewing based on the summary switch control, and the client switches and displays multiple document summary lines corresponding to the first document in the original message in response to the switching operation triggered by the summary switch control.

[0218] Specifically, when the multiple document summaries corresponding to the first document are summarized multiple times based on the above method, the document summaries generated each time can be displayed in the same message box and switched through the summary switching control.

[0219] The second relevant position can be any position near the document summary, such as below the document summary message box, or above, to the left, or to the right, etc., and is not specifically limited herein. The second relevant position can be the same as, or similar to, or different from the first relevant position.

[0220] First, it should be noted that during the re-content extraction process for the first document, the status area can be presented in any of the ways listed in the embodiments of this application, and the status area can be removed after the content extraction is complete. The newly generated document summary can be presented as a new message, or it can be updated based on the original message presented when the document summary was previously generated, and so on.

[0221] Taking the update based on the original message as an example, as shown in Figure 18A, it is a schematic diagram of a summary switching control in an embodiment of the present application. In the case of re-summarizing the summary, the newly generated document summary can still be displayed in the message box shown in S181, which is generated when the summary is first performed on the first document. In the case of generating a new document summary, the summary switching control can be presented at the positions shown in S182 and S183. The summary switching control shown in S182 in Figure 18A is used to view the document summary generated last time for the currently displayed article summary, and the summary switching control shown in S183 is used to view the document summary generated next time for the currently displayed article summary.

[0222] When the message box shown in S181 presents the latest generated document summary, the summary switching control shown in S183 is in a non-interactive state, which means that the currently displayed article summary is the latest generated one and S183 cannot be operated.

[0223] As shown in Figure 18B, which is a schematic diagram of another summary switching control in an embodiment of the present application, the summary switching control can be presented at the position shown in S186, and the object can view the document summary generated last / next time of the currently displayed article summary, where 2 / 2 means that a total of 2 document summaries were generated for the first document, and the currently presented one is the document summary generated for the second time.

[0224] In the above embodiment, the object is supported to extract content from the first document multiple times, and quickly obtain a new document summary through the re-summarization control until a more satisfactory summary is obtained, and the object is supported to switch to view the document summary generated each time.

[0225] This application also supports the subject to provide feedback on the quality of the generated document summary. An optional implementation is as follows:

[0226] A feedback control for evaluating the summary quality of the document summary is presented at a third relevant position of the document summary; and the client presents a corresponding evaluation result in response to an evaluation operation triggered by the feedback control.

[0227] For example, positive feedback and negative feedback can be generated by giving likes and dislikes, respectively. Alternatively, subjects can rate the document summary or provide feedback by lighting up different numbers of stars, etc., which is not specifically limited in this document. In addition, when multiple document summaries are generated for the same first document, subjects are supported to evaluate each document summary separately.

[0228] Still taking Figure 18A as an example, S184 in Figure 18A is an example of a positive feedback control in an embodiment of the present application. If the object is relatively satisfied with the generated document summary, the object can give a positive evaluation by clicking a like, and the evaluation results can be presented in the form of the current number of likes or successful likes; S185 is an example of a negative feedback control in an embodiment of the present application. If the object is dissatisfied with the generated document summary, the object can give a negative evaluation by clicking a dislike, and the evaluation results can be presented in the form of the current number of dislikes or successful dislikes.

[0229] It should be noted that the feedback controls listed in FIG. 18A are merely examples. In addition, other types of feedback controls are also applicable to the embodiments of the present application and will not be described in detail here.

[0230] In the above embodiment, the subjects are supported to evaluate the generated document summary, and the content extraction model can be fine-tuned based on the subject feedback to improve the accuracy of the generated document summary.

[0231] It should be noted that the content extraction method in the embodiments of this application, based on the content summarization capability, supports the encapsulation of different upper-layer applications in different industries. After fine-tuning the model and encapsulating the upper-layer product applications for different file scenarios in different industries, more product forms can be derived. Specific application scenarios include but are not limited to some or all of the following:

[0232] Financial report assistant: extract financial report summaries; paper assistant: extract academic papers; textbook assistant: extract textbook summaries; novel assistant: extract novel summaries and novel character relationships, etc.

[0233] In summary, the content extraction method in the embodiment of the present application supports the extraction of summaries of various documents, and the extracted summaries are not limited to paragraph-style texts, but can also be in the form of pictures, tables, or other forms, which are not specifically limited in this article.

[0234] Furthermore, the content extraction method in the embodiments of the present application also supports multiple rounds of question-and-answer sessions based on the generated document summary. The generation of the document summary can be considered the first round of dialogue / question-and-answer sessions. The subject can then begin the second round of dialogue, answering subsequent questions based on the document content, or repeatedly revising the document summary.

[0235] An optional implementation is: in addition to presenting the document summary obtained by content extraction from the first document in the information interaction interface, an input box may also be presented; the subject may input questions or modification instructions regarding the document summary based on the input box.

[0236] The input box may be presented in any area of ​​the information interaction interface, such as at the bottom of the information interaction interface.

[0237] Specifically, when a document upload control previously existed in an information interaction interface specifically used for document summarization (i.e., a document summary interface), an input box can be presented in the position of the original document upload control, as shown in S191 in Figure 19A, and the original document upload control can be collapsed into a small icon and presented in other locations, as shown in S192 in Figure 19A.

[0238] In addition, considering that the information interaction interface in the embodiment of the present application only needs to support the conversation function, it can be any conversation interface. Therefore, in addition to asking questions about the document content in the above-mentioned manner, questions can also be asked about non-document content (i.e., ordinary questions and answers based on AI).

[0239] Correspondingly, the input box may also be an input box that already exists in the conversation interface. The subject may input a first question regarding the document content or a second question regarding non-document content based on the input box.

[0240] The timing of the input box's presentation is not specifically limited herein. For example, the input box may be presented simultaneously with the presentation of the document summary in the information interaction interface, or after the subject triggers a preset action (such as a target gesture or voice command) in the information interaction interface. After the input box is presented, the subject may enter the first question, second question, modification instructions, etc. through text, voice, or other means, which is not specifically limited herein.

[0241] The following first introduces the question-and-answer scenario related to the first question:

[0242] Optionally, in response to the first question about the document summary input in the input box, the client presents an answer message corresponding to the first question; wherein the answer message is any one of the following:

[0243] A message generated based on the first question and content related to the first question in the first document, a message generated based on search results related to the first question, and a predetermined expression indicating that the answer cannot be given.

[0244] In summary, when the object inputs the first question, if the document content of the first document can answer the question, an answer message is generated directly based on the relevant content in the first document; if the document content of the first document has relevant parts but cannot answer the question, a search plug-in can be started to generate an answer message based on the search results; if the document content of the first document does not have relevant parts, a predetermined statement is returned to indicate that it cannot be answered.

[0245] Refer to FIG19A , which is a schematic diagram of a question-and-answer scenario for a document summary in an embodiment of the present application. An input box S191 is displayed at the bottom of the information interaction interface, and the subject can enter a first question based on the input box. For example, if the subject enters the first question "How to make dish D" as shown in S193, and there is content related to "How to make dish D" in the first document, and an answer message can be generated directly based on the relevant content in the first document, then the answer message shown in S194 can be presented.

[0246] It should be noted that the first question and the answer message in the embodiment of the present application can both be presented in the form of messages.

[0247] In addition, the object may also upload a new first document based on the document upload control shown in S192 to extract content from the new first document.

[0248] Furthermore, the above can be recorded as the second round of dialogue. On this basis, the subject can continue to ask questions, and then conduct the third round, or even the fourth round, or the fifth round of dialogue...

[0249] Refer to FIG19B , which is a schematic diagram of another question-and-answer scenario for a document summary in an embodiment of the present application. Based on FIG19A , the subject inputs the first question shown in S195, "How should the soy sauce be added?" In this case, the first question before the first question shown in S195 (i.e., S193) and the answer message (i.e., S194) can be combined to rewrite the context of the first question S195 at this time. For example, if the rewritten question is "How should the soy sauce be added during the preparation of dish D?", if the first document contains relevant content for the question "How should the soy sauce be added during the preparation of dish D?", the answer message shown in S196 can be directly generated based on the relevant content in the first document.

[0250] The following describes the modification scenario:

[0251] Optionally, in response to a modification instruction for the document summary input based on the input box, the client presents a modified document summary corresponding to the modification instruction.

[0252] The modification instruction may be directed to the content, word count, person, etc. of the document summary, such as adjusting the length from 300 words to 200 words, or adjusting the first person to the third person, etc. Furthermore, the modified document summary corresponding to the modification instruction in this application may be presented in the original message box corresponding to the document summary previously generated for the first document, or in a new message box, without specific limitation herein.

[0253] Referring to FIG. 20 , which is a schematic diagram illustrating a document summary modification scenario according to an embodiment of the present application, the subject inputs a modification instruction as shown in S201 to reduce the word count of the currently generated document summary to under 100 words. The generated modified document summary can then be presented in a new message box, as shown in S202 .

[0254] It should be noted that the several processes of question-answering or modification based on document summaries listed in Figures 19A, 19B or 20 are just simple examples. In addition, other implementation processes of the same functions are also applicable to the embodiments of this application, and this article does not make specific limitations.

[0255] In the above embodiment, after the summary is output, this application supports further questions based on the content of the summary. The model will further produce answer content, support the object to repeatedly modify the summary or ask questions about the content in the summary, which can enhance interactivity and facilitate the object to more quickly review the first document and obtain effective information.

[0256] The above example uses questions and answers about document content. If the information interaction interface also includes a second question input for non-document content, an optional implementation of the question and answer message is as follows:

[0257] A first message style is used to present a first question and an answer message corresponding to the first question; and a second message style is used to present a second question and an answer message corresponding to the second question.

[0258] That is, different message styles are used to distinguish between general Q&A (non-document content Q&A) scenarios and document Q&A scenarios. Specifically, different message styles can include different message fonts (such as different color fonts, different font sizes, etc.), different message boxes (such as different message bubbles), etc., which are not specifically limited in this article.

[0259] Refer to Figure 21, which is a schematic diagram of the presentation style of a question and answer message in an embodiment of the present application. Clearly, S211 in Figure 21 is a second question unrelated to the document content, S212 is the answer message corresponding to this question, and S211 and S212 are message boxes in dashed lines. S213 in Figure 21 is a first question related to the document content, S214 is the answer message corresponding to this question, and S213 and S214 are message boxes in solid lines. Message boxes with different lines represent different message styles.

[0260] Before the client uses different message styles to make the above distinction, it also needs to use certain logic to distinguish which questions in the object input belong to the first question and which belong to the second question.

[0261] In an embodiment of the present application, the first question and the second question are distinguished based on at least one of the following methods: predetermined character recognition, key information recognition, and intention recognition.

[0262] For example, when distinguishing by predetermined characters, the object of prompting needs to enter the predetermined characters in the question when asking questions about the content of the document. Then, when distinguishing the questions, if the predetermined characters (such as " / ") are recognized in the question, it can be used as the first question; if they are not recognized, it can be used as the second question.

[0263] Another example is identifying key information (keywords, keywords, etc.) of the question, such as setting the keyword "this document", etc. If the keyword is identified in the question, it can be used as the first question, and if it is not identified, it can be used as the second question.

[0264] Alternatively, the question is subjected to intent recognition to identify the intent of the question and analyze whether the intent is relevant to the previous first document. If so, the question can be used as the first question; if not, the question can be used as the second question.

[0265] In addition, the above-mentioned methods can also be combined, such as distinguishing problems through predetermined characters or keyword recognition, combined with intent recognition, etc.

[0266] It should be noted that the above process of distinguishing questions can also be performed by the server, that is, the client sends the question to the server, and the server uses the above logic to distinguish and feeds back the distinction result to the client.

[0267] In the above embodiment, when the subject asks questions about both document content and non-document content, the message style is used to effectively distinguish between questions and answer messages, which can ensure that the subject clearly understands which answer messages correspond to which questions, and clarifies the current questioning scenario, thereby enhancing the subject's experience.

[0268] It should be noted that the above examples are all based on the example of an object uploading a first document, extracting a summary of the first document, and performing questions and answers, modifications, etc. on the document summary of the first document. In addition, the object can also upload multiple first documents, extract summaries of multiple documents, and perform questions and answers, modifications, etc. on the document summaries of multiple documents.

[0269] In the case where the object uploads multiple first documents at one time, summary extraction may be performed on the multiple first documents to generate a document summary corresponding to each first document, or to generate a document summary corresponding to the multiple first documents as a whole.

[0270] That is, when there are multiple first documents, each of them can be presented in the information interaction interface, and the processing information of each first document can be presented in the status area corresponding to each first document. The specific presentation method is the same as the presentation method of the status area corresponding to a single first document listed above, including collapsed and expanded forms, etc., which are not specifically limited in this article. Similarly, after the content of each first document is extracted, the display of the status area corresponding to the first document can be cancelled.

[0271] Specifically, the multiple first documents can be processed in parallel to ensure the efficiency of abstract extraction and reduce the waiting time of the object. When presenting the document abstract, there are two presentation methods, including but not limited to the following:

[0272] Presentation method 1: presenting each first document and the document summary corresponding to each first document in the information interaction interface respectively, wherein each first document and the document summary corresponding to the first document form a group of messages.

[0273] This method means that every time a first document is processed, the document summary corresponding to the first document can be presented in the information interaction interface.

[0274] It should be noted that the first document in the embodiment of the present application can be a variety of presentation styles such as an actual document, a document icon, a document name, a document link, etc., and this article does not make specific limitations.

[0275] In the embodiment of the present application, when each first document and the document summary corresponding to the first document are presented through a group of messages, the group of messages essentially includes at least one message, that is, it can be one message or multiple messages. Therefore, there are actually multiple corresponding display styles, including but not limited to some or all of the following:

[0276] Display style 1: In one message, a partition block displays each first document and its document summary.

[0277] Display style 2: Display multiple messages, each message displays a first document and its document summary.

[0278] Display style 3: Display multiple messages. These messages are divided into two categories. The first category is that each message displays a first document, and the second category is that each message displays a document summary.

[0279] Display style 4: Display a message including the document name of each first document and the document summary of each first document displayed in segments, wherein the document name and document summary of the same first document may be displayed in the same segment.

[0280] It should be noted that the several display styles listed above are just simple examples. The method of presenting each first document and its corresponding document summary through at least one message is applicable to the embodiments of this application and will not be described in detail here.

[0281] The following uses the above display style 3 as an example for explanation.

[0282] Refer to Figure 22, which is a schematic diagram of a method for presenting multiple first documents and document summaries in an embodiment of the present application. If a subject uploads two first documents simultaneously, namely "Amazing CCC1" and "Amazing CCC2," these two first documents can be processed in parallel to ensure that the document summaries corresponding to each first document are presented synchronously as much as possible.

[0283] Specifically, when presenting the document summary corresponding to each first document, each first document and its document summary are grouped together as a message, presenting an interface as shown on the left side of FIG22 . For each first document, a re-summary control, feedback control, etc. may also be presented at the relevant location. The specific implementation method is the same as that of the above embodiment, and the repeated parts are not repeated here.

[0284] In addition, this application also supports the subject to choose whether to summarize the document summaries of multiple first documents. An optional implementation is as follows:

[0285] In addition to presenting each first document and the document summary corresponding to each first document in the information interaction interface, summary prompt information is further presented.

[0286] Among them, the summary prompt information is used to prompt whether to summarize the document summaries corresponding to each first document. The presentation time of the summary prompt information is not specifically limited in this article. For example, the summary prompt information can be presented at the same time as the document summary is presented in the information interaction interface. Alternatively, the summary prompt information is presented after the object triggers a preset operation (such as a target gesture, voice command, etc.) in the information interaction interface.

[0287] In the embodiments of the present application, the aggregation process includes at least one of the following: merging document summaries, determining commonalities among document summaries, or determining differences among document summaries. Based on this, the corresponding aggregation prompt information can also take various forms, such as only prompting the subject to determine commonalities among multiple document summaries; only prompting the subject to determine differences among multiple document summaries; or asking the subject whether to determine commonalities among multiple document summaries or determine differences among multiple document summaries; or directly asking the subject whether to aggregate multiple document summaries, etc.

[0288] Furthermore, when the object triggers the summary process, the client presents the summarized document summary corresponding to the summary process, which is generated based on the document summary corresponding to each first document, in response to the summary process triggered by the summary prompt information.

[0289] Still taking Figure 22 as an example, the S221 part in Figure 22 is an example of a summary prompt information in an embodiment of the present application. The summary prompt information includes the text "Do you want to summarize the above summary in the following way?", as well as the controls "Merge" and "Compare". Among them, the merge control supports determining the common points of multiple document summaries, and the compare control supports determining the differences between multiple document summaries. If the object is selected to merge, the summarized document summary shown in S222 can be presented. The summarized document summary is obtained after determining the common points in the document summaries corresponding to the two first documents generated previously. Similarly, if the object is selected to compare, the differences in the document summaries corresponding to the two first documents generated previously are determined to generate a summarized document summary.

[0290] Refer to FIG23, which is a schematic diagram of another presentation method for multiple first documents and document summaries in an embodiment of the present application. Unlike FIG22, the summary prompt information in FIG23 is in another style. As shown in S231, the summary prompt information includes the text "Do you want to summarize the above summaries?" and the controls "Yes" and "No". That is, there is no need to ask the subject whether to merge or compare multiple document summaries. Instead, the subject is directly asked whether to summarize. If the subject chooses yes, the summarized document summary shown in S232 can be presented, which not only determines the differences in the document summaries corresponding to the two previously generated first documents, but also determines the common points, and generates a summarized document summary.

[0291] It should be noted that the summary prompt information listed in Figure 22 or Figure 23 above is just a simple example. Other styles of summary prompt information are also applicable to the embodiments of the present application and will not be described in detail here.

[0292] In addition, if the subject uploads three or more first documents at the same time, the subject can also select the document summaries that he wants to summarize. If the subject does not make a selection, the document summaries of multiple first documents uploaded by the subject at the same time will be summarized by default.

[0293] Presentation method 2: presenting each first document and the summarized document summary separately in the information interaction interface, wherein the summarized document summary is obtained by respectively extracting the document summary corresponding to each first document and summarizing multiple document summaries.

[0294] Specifically, a group of messages is presented in the information interaction interface, where the group of messages includes a plurality of first documents and summarized document summaries.

[0295] Specifically, the first presentation method refers to presenting a separate summary of each first document, and asking the subject whether to summarize the summaries of multiple documents through the method of Figure 22 or Figure 23.

[0296] Different from the above-mentioned presentation method 1, the presentation method 2 does not ask or present a separate summary of each first document, but directly presents the summary of multiple documents.

[0297] In an embodiment of the present application, when a group of messages is used to present multiple first documents and summarized document summaries, the group of messages essentially includes at least one message, which can be a single message or multiple messages. Specifically, multiple first documents and summarized document summaries can be presented in a single message. Alternatively, the presentation can be performed using multiple messages, where these messages are divided into two categories: the first category has each message displaying a single first document, and the second category has only one message displaying the summarized document summary; and so on.

[0298] It should be noted that the several display styles listed above are just simple examples. The method of presenting each first document and the summarized document summary through at least one message is applicable to the embodiments of this application and will not be described in detail here.

[0299] See Figure 24, which is a schematic diagram of another method for presenting multiple first documents and document summaries in an embodiment of the present application. If a subject simultaneously uploads two first documents, "Amazing CCC1" and "Amazing CCC2," the document summaries corresponding to each first document may no longer be presented separately. Instead, the aggregated document summary may be presented directly, as shown in S241 of Figure 24.

[0300] It should be noted that, in the embodiment of the present application, the above-mentioned processing methods for the status area and document summary, etc., when extracting content from a single first document, are also applicable to the content extraction of multiple document summaries, and the repeated parts will not be repeated.

[0301] The above implementation supports simultaneous summary extraction for multiple documents, and allows users to choose whether to merge multiple document summaries based on their needs, facilitating timely understanding of multiple documents. Furthermore, if multiple documents are related, merging or comparing multiple document summaries allows users to more easily understand the connections between multiple documents and the specific focus of each document, further improving document reading efficiency.

[0302] In addition, it should be noted that during the processing of the first document, if the subject wants to pause the content extraction or leave the current information interaction interface, the content extraction process can be interrupted.

[0303] An optional implementation is as follows: in response to a processing stop operation on a first document, the client presents a stop prompt message and a corresponding re-summarize control in an information interaction interface; the object can re-trigger the content extraction process for the first document based on the re-summarize control, and the client re-extracts content from the first document in response to the triggering operation on the re-summarize control, and after the re-content extraction is completed, presents a document summary obtained by extracting content from the first document in the information interaction interface.

[0304] In addition, it should be noted that in the process of re-extracting the content of the first document, a status area can also be presented, in which the current processing stage and the corresponding processing status are presented. The object can also expand the status area to view a more specific processing process, and can also view the processing results corresponding to the processing stage under the target processing status, etc. This article will not repeat them.

[0305] Refer to FIG25A, which is a schematic diagram of a stop prompt message in an embodiment of the present application. As shown in S251 in FIG25A, the stop prompt message indicates that the generation of the document summary of the first document is stopped. The presentation of the stop prompt message can be triggered by the following methods:

[0306] As shown in S162 of FIG. 16 , if the document summary has not yet been fully output, the aforementioned "Summarizing, click to cancel" message is updated to "Stop generating" as shown in S162. The subject can click the control shown in S162 to pause the output of the document summary, and the stop prompt message shown in S251 will be displayed. Alternatively, during the summarizing process before outputting the document summary, the message "Summarizing, click to cancel" as shown in S83 or S86 may be displayed. The subject can also click the control shown in S83 or S86 to pause the generation of the document summary, and the stop prompt message shown in S251 will be displayed; and so on.

[0307] 25A, refer to FIG25B, which is a schematic diagram of another stop prompt message in an embodiment of the present application. As shown in S252 in FIG25B, the stop prompt message indicates stopping the generation of the document summary of the first document.

[0308] When a stop prompt message is presented, a re-summary control may be further presented. The presentation time of the re-summary control is not specifically limited in this article. For example, the re-summary control may be presented at the same time as the stop prompt message is presented in the information interaction interface. Alternatively, the re-summary control may be presented after the object triggers a preset operation (such as a target gesture, voice command, etc.) in the information interaction interface.

[0309] As shown in S252 in Figure 25A or S254 in Figure 25B, which are examples of the re-summarization control listed in the embodiments of the present application, the object can click the re-summarization control to re-trigger the content extraction process for the first document. The client responds to the triggering operation of the re-summarization control and re-extracts the content of the first document. After the re-content extraction is completed, the document summary obtained by extracting the content of the first document is presented in the information interaction interface.

[0310] In the above embodiment, the object is supported to stop at any time during the document summary generation process, or to quickly re-extract the document summary through the re-summarization control, thereby providing the object with higher operational flexibility.

[0311] In addition, during the processing of the first document, if the subject wants to leave the current information interaction interface, a second confirmation reminder can be provided to the subject to reduce the possibility of the subject exiting the current content extraction due to an erroneous operation. An optional implementation is as follows:

[0312] During the processing of the first document, the client responds to an exit operation on the information interaction interface by presenting an exit prompt message, wherein the exit prompt message is used to remind the object that the first document is currently being processed and to ask the object whether to confirm the exit.

[0313] If the object confirms the exit based on the exit prompt information, then exit the information interaction interface; if the object cancels the exit based on the exit prompt information, the content extraction process for the first document can continue.

[0314] Refer to Figure 26A, which is a schematic diagram of an exit prompt message in an embodiment of the present application, wherein the exit prompt message includes the text "Are you sure you want to leave? The task is in progress, leaving the current page will terminate the task", as well as the controls "Cancel" and "Confirm to Leave". If the object clicks Confirm to Leave, it can exit the current information interaction interface. If the object clicks Cancel, it can continue to extract content from the first document.

[0315] In addition, if the subject directly clicks the “×” in the upper right corner of the pop-up window shown in FIG. 26A , it can also be considered that the subject cancels this exit and continues to perform content extraction on the first document.

[0316] Refer to Figure 26B, which is a schematic diagram of another exit prompt message in an embodiment of the present application, wherein the exit prompt message includes the text "Are you sure you want to leave? The task is in progress. Leaving the current page will terminate the current task", as well as the controls "Leave" and "Continue Task". If the object clicks Leave, it can exit the current information interaction interface. If the object clicks Continue Task, it can continue to extract content from the first document.

[0317] In the above embodiment, the object is supported to exit at any time during the document summary generation process, and a secondary confirmation prompt is provided to prevent the object from terminating the summary extraction process by mistake.

[0318] It should be noted that after the document summary is normally generated, in addition to supporting the object to conduct multiple rounds of questions and answers based on the document summary, this application also supports the object to share and forward the generated document summary.

[0319] An optional implementation is as follows:

[0320] The client presents at least one second function control corresponding to the document summary of the first document; these second function controls are all operation controls for the document summary, and the object can share or forward the document summary based on the second function control. Then, in response to the sharing operation triggered by the at least one second function control, the client sends the document summary and the first document to the object to be shared. Here, the object to be shared is, for example, a user account.

[0321] Specifically, the document summary can be shared in the form of a link, a mini-program, a picture, etc. For example, a personal computer (PC) supports sharing in the form of a link, a mobile terminal supports sharing in the form of a mini-program, etc. This article does not make specific restrictions.

[0322] Among them, the above-mentioned second function control can be presented after the object performs the target action, as shown in Figure 27, which is a schematic diagram of a second function control in an embodiment of the present application. Taking the target action as a long press as an example, if the object long presses the document summary message box (also known as a bubble), the four second function controls shown in S271 can be presented, namely: copy, excerpt copy, multiple selection, and forward. The object can click forward and select the object to be shared, and then the client responds to the sharing operation triggered by the forwarding control and sends the document summary and the first document to the object to be shared.

[0323] In addition, the above-mentioned second function control can also be presented at the same time as the document summary is presented. Taking Figure 18B as an example, S187 is a copy control in an embodiment of the present application, and S188 is a forwarding control in an embodiment of the present application. Both of these belong to the second function control corresponding to the document summary of the first document. The object can click forward and select the object to be shared to be forwarded, and then the client responds to the sharing operation triggered by the forwarding control and sends the document summary and the first document to the object to be shared.

[0324] It should be noted that the several second function controls listed above are just simple examples. Any operation control related to the document summary can be used as a second function control, and this article will not go into details one by one.

[0325] It should also be noted that the above is a process of sharing the current message. In addition, the object can also select one or more messages from the current interface to share.

[0326] Specifically, when the object selects one or more messages by himself, the object can select a message to share directly, or after selecting a message and presenting a multi-select control, the object can select multiple messages through the multi-select control to share; or, the object can click a sharing control in the upper right corner of the current interface (or other location), click the sharing control and select multiple messages to share, and so on.

[0327] Through the above method or other selection methods, the subject can choose to share multiple messages. In addition to sharing the first document and the document summary, the subject can also further share the first document, multiple rounds of questions and answers related to the first document, or share other messages.

[0328] In the above embodiment, the object may share and forward the document summary generated for the first document so as to discuss and communicate with other objects.

[0329] Optionally, if the object is the shared party, if it receives a link / applet shared by other objects for the shared document, it can click on the link / applet, and then present the shared document and the document summary corresponding to the shared document, as well as a new dialogue entry; the object can use the new dialogue entry to create a new information interaction interface, and the client responds to the trigger operation for the new dialogue entry by presenting a default message and a document upload control in the information interaction interface, wherein the default message is used to present an example document summary function, and the document summary function represents generating a document summary by extracting content from the document. The object can upload a new document for content extraction based on the document upload control, wherein the process of uploading a new document and extracting content from the new document can be referred to the above embodiment, and the repeated parts will not be repeated.

[0330] Refer to Figure 28A, which is a schematic diagram of a landing page for a shared party in an embodiment of the present application. As shown in S281 of Figure 28A, the shared document is shown, S282 is the document summary of the shared document, and S283 is a new dialogue entry in an embodiment of the present application. The subject can click on this new dialogue entry to enter the interface shown on the right side of Figure 28A, where S284 is the default message and S285 is the document upload control. The subject can use the document upload control shown in S285 to upload a new document for content extraction.

[0331] Refer to Figure 28B, which is a schematic diagram of another landing page for the shared party in an embodiment of the present application. As shown in Figure 28B, S286 is the shared document, S287 is the document summary of the shared document, S288 is the summary switch control of the document summary, and S289 is a new dialogue entry in an embodiment of the present application. In particular, if the sharing party generates multiple summaries for the shared document, the summary switch control shown in S288 can also be presented to switch to the previous summary or the next summary, etc.

[0332] In the above implementation, the supporting objects can share and forward the document summary, so that other objects can quickly understand the document content and increase the discussion between objects.

[0333] The content extraction method in the embodiment of the present application also supports the subject to view the historical records related to the document content extraction. An optional implementation is as follows:

[0334] In response to the viewing operation on the historical records of the target object, the client presents the various historical documents corresponding to the target object for which the document summary has been currently generated; when viewing various historical documents, the object can view the corresponding document summary for any historical document, and the client presents the document summary corresponding to any historical document in response to the viewing operation on any historical document among the various historical documents.

[0335] The target object may refer to the account currently logged in by the client.

[0336] Specifically, the target object can be returned to the history record interface from the information interaction interface, or the history record interface can be directly opened, etc., in which the history record interface displays the various historical documents corresponding to the target object for which the document summary has been generated, as well as the corresponding content extraction time.

[0337] As shown in Figure 29, it is a schematic diagram of a historical record in an embodiment of the present application. The historical record interface displays various historical documents for which the target object "Xiao A" has currently generated document summaries, such as the amazing CCC1, amazing CCC2, amazing CCC3, etc. in Figure 29, as well as the content extraction time corresponding to each document. The target object can select one from them, such as the target object selects "Amazing CCC3", and then the information interaction interface shown on the right side of Figure 29 is presented to view the document summary corresponding to the document. In addition, the object can also click to start a new conversation to enter the information interaction interface containing a default message and document upload control, and so on.

[0338] In the above implementation, the object is supported to view the historical records and to understand the document summaries of each generated historical document in a timely and convenient manner.

[0339] It should be noted that during the process of extracting content from the first document, or after the content extraction is completed, or in the sharing state, the first document shown in the information interaction interface can be clicked to download the first document.

[0340] In addition, it should be noted that the above is a brief introduction to the content extraction method in the embodiment of the present application mainly from the client side. The following further describes the content extraction method in the embodiment of the present application from the server side:

[0341] 30 is a flowchart of another content extraction method according to an embodiment of the present application. Taking a server as an example, the specific implementation process of the method is as follows S301 to S303:

[0342] S301: After receiving a document processing request for a first document, the server extracts text information from the first document.

[0343] The first document is uploaded by the client in response to a selection operation on the first document among at least one document in the document selection interface, and the document selection interface is presented by the client in response to an upload operation triggered based on the information interaction interface.

[0344] In summary, the content extraction method in this application supports uploading single / multiple documents. Taking a single document as an example, it is necessary to slice the document content and perform content extraction on each slice content to determine the summary of the entire document. In order to achieve this function, it is first necessary to parse the document, extract all the text information in the document, then slice and segment it, and perform content extraction on each slice to obtain a slice summary, and finally perform content extraction on the multiple slice summaries as a whole again to obtain the document summary corresponding to the full text. Multiple documents can be summarized on the basis of obtaining the document summaries of each individual document.

[0345] In an embodiment of the present application, the object may select at least one first document based on the document selection interface in the client and upload it to the server. The document processing request may be sent to the server by the client in response to the object's upload operation for the first document.

[0346] After receiving the document processing request for the first document, the server first needs to parse the document and extract all text information (also called text information) in the document. Specifically, document parsing refers to parsing the document content to obtain the text in the document, including text, text extracted from images (which can be obtained through OCR), subtitles and text in videos, and text converted from the spoken words in videos (which can be obtained through Automatic Speech Recognition (ASR)). Then, each type of text is organized in spatial order, and then the following operations S302 to S303 can be performed:

[0347] S302: The server slices the extracted text information to obtain at least one text slice; and extracts a summary of each text slice in the at least one text slice to obtain a slice summary corresponding to each of the at least one text slice.

[0348] When slicing a document, the slicing granularity can be paragraphs, or a fixed text length L can be set. The value of L is a positive integer, which can be determined according to actual needs.

[0349] For example, if a fixed text length L=3000 is set, then in the embodiment of the present application, document slicing refers to dividing the text obtained in the document parsing link into text segments with a length not exceeding L (L=3000) tokens, also known as text slicing.

[0350] The specific segmentation method is: starting from the start token, take L tokens at a time. If a complete sentence is segmented, find the last punctuation mark such as a period, question mark, or exclamation mark and segment it, or find the first punctuation mark such as a period, question mark, or exclamation mark and segment it.

[0351] That is, the length of each text slice obtained in the end is not necessarily L. It is only sliced ​​with reference to the length L. In order to ensure the integrity of the sentence as much as possible and not affect the semantics of the sentence, when there is a need to split the complete sentence, it is possible to consider combining punctuation marks to generate text slices with a length close to L.

[0352] Based on the above slicing method, the original semantics of the sentence can be kept as unaffected as possible, thereby improving the accuracy of subsequent content extraction.

[0353] In this application, when at least one text slice is obtained, each of the above-obtained text slices can be respectively extracted by content extraction to obtain the main content of each text slice (i.e., the slice summary). An optional implementation method is as follows:

[0354] At least one text slice is input into the content extraction model respectively. For each text slice, the content extraction model is used to extract a slice summary corresponding to the text slice according to a preconfigured first summary instruction; wherein the first summary instruction is used to specify the number of words and summary format of the slice summary.

[0355] The content extraction model in this article can be used to extract summaries from text content (here, text slices). This can also be understood as summarizing the content of a text slice, extracting the main content as a slice summary. Therefore, the target text processing model can be any text processing model with summary extraction capabilities. For example, the content extraction model is a text processing model such as LLM.

[0356] For example, when using the above model to extract summaries from text slices, the extraction method is to add a first summary instruction in the prompt message, requesting the content extraction model to extract a content summary, and specifying the word count and summary format of the slice summary. The summary format may be, for example, "Summarize the text slice as concisely and clearly as possible, no more than XXXX words, and covering the important information of the text slice." The content extraction model will extract a summary for each text slice according to this instruction and return the corresponding slice summary for each text slice.

[0357] In the above embodiment, by pre-configuring the first summary instruction, the large model can be used to output a slice summary that meets the relevant requirements of the summary instruction, which is convenient for subsequent summary aggregation.

[0358] S303: The server summarizes the obtained slice summaries to obtain a document summary corresponding to the first document, and feeds the document summary back to the client, so that the client presents the document summary obtained by extracting content from the first document in an information interaction interface. Here, summarizing the obtained slice summaries means summarizing the content of the multiple slice summaries as a whole.

[0359] In summary, the embodiment of the present application can improve the accuracy of the document summary by first determining the slice summary of each slice and then summarizing the content of multiple slice summaries as a whole.

[0360] Specifically, after obtaining the slice summary of each text slice, all the obtained slice summaries can be aggregated and summarized using the content extraction model to obtain the overall summary corresponding to the first document, which is also referred to as the document summary in this article. An optional implementation method is as follows:

[0361] Each slice summary is input into the content extraction model respectively, and the content extraction model is used to summarize each slice summary according to the pre-configured second summary instruction to generate a document summary; wherein the second summary instruction is used to specify the word count and summary format of the document summary.

[0362] Among them, the content extraction model in this article can also be used to summarize (i.e., extract content) text content (content after the slice summary is summarized), and can be any text processing model with a summary function.

[0363] For example, when using the above model to extract content from the slice summaries of each text slice, the content extraction method adds a second summary instruction to the prompt information, requesting the main model (i.e., the content extraction model) to summarize the content. The second instruction also specifies the word count and summary format of the document summary, such as "Summarize the above content in no more than 300 words, including the main idea of ​​the article and listing 3-5 important information from the article." The main model will then summarize the content of the slice summaries according to this instruction and return the document summary corresponding to the first document as a whole.

[0364] In the above embodiment, by pre-configuring the second summary instruction, the large model can be used to output a document summary that meets the relevant requirements of the summary instruction, thereby effectively summarizing the overall content of the first document.

[0365] It should be noted that the main model in the embodiment of the present application can be used to extract the main content and theme of the text, summarize the text, etc., and belongs to a natural language processing model. Specifically, it can be any text processing model with the above functions, such as LLM or other models, which is not specifically limited in this article.

[0366] Furthermore, the present application takes into account that each text slice of an article is generally long, and a large language model of more than 6B is required for slice summarization. Therefore, in the embodiment of the present application, a large LLaMA 13B model is specially trained for summary extraction.

[0367] Optionally, when there are multiple first documents, in addition to summarizing the document summaries corresponding to each first document based on the above method, it is also necessary to summarize the respective topics of each first document; based on the respective topics of each first document, the document summaries corresponding to each first document are summarized, and then the summarized document summaries can be obtained and fed back to the client, so that the client presents the summarized document summaries in the form of messages in the information interaction interface, as shown in Figure 22, Figure 23 or Figure 24.

[0368] In summary, this application also supports the object to upload multiple documents at a time, summarize the contents of multiple documents separately, and aggregate the contents of the documents. The following is a detailed description of the content extraction process of multiple documents:

[0369] To achieve this capability, this application needs to be able to interpret and summarize each document from multiple perspectives, and then aggregate the information from these perspectives for summary and / or comparison. The specific implementation details are as follows:

[0370] First, we parse multiple documents. Similar to the single document parsing process listed above, we parse each document's content to obtain the text within it, including text, text extracted from images, subtitles and text from videos, and text converted from audio in videos. We then organize each type of text in spatial order. The resulting text information corresponding to the first document is recorded as:

[0371] The above T corresponds to a first document, and the parsed text information corresponding to each first document can be recorded as a T, including the extracted texts (text1, text2),..., the texts recognized by the image (OCR1, OCR2),..., and the texts recognized by the speech (ASR1)...

[0372] After parsing each first document and extracting the text information corresponding to each text, each document can be summarized and summarized, and the long document can be organized into a rough summary of M words (e.g., M = 500). In other words, the document summary corresponding to each first document (which can be understood as a rough summary) is extracted. Where M is a positive integer, and the value of M can be flexibly set according to actual needs, such as 500, 300, 200, etc., and is not specifically limited in this article.

[0373] After parsing the first document, the process of extracting a rough summary of the document can be summarized as follows: document segmentation, slice summary extraction, summary aggregation and content integration.

[0374] The process of document slicing, slicing summary extraction and summarizing can be referred to in the above embodiment, which is briefly described below in conjunction with Figure 31.

[0375] Refer to Figure 31, which is a schematic diagram of a single-document rough summary extraction process in an embodiment of the present application. As shown in Figure 31, after slicing the parsed document based on L to obtain n slices of text, the large language model (LLM) can be used to extract slice summaries for each of these n slices of text to obtain n slice summaries. Subsequently, all the slice summaries are aggregated and summarized using the large language model (LLM) to obtain an integrated document summary, i.e., the rough document summary corresponding to the entire article.

[0376] In addition, in the summary step, it is also necessary to summarize the aspects of the theme of this article so that in the subsequent content integration step, the document summaries of multiple single documents can be summarized to obtain the summarized document summaries corresponding to the multiple documents as a whole.

[0377] In the present embodiment, content integration refers to combining the results obtained from the summary step and expanding the description based on the themes summarized in the summary step to achieve multi-document aggregation. To achieve this capability, it is necessary to be able to interpret and summarize each article from multiple perspectives and then aggregate the information from these perspectives.

[0378] Refer to Figure 32, which is a schematic diagram of a multi-document summary extraction process in an embodiment of the present application. For example, rough article summaries are extracted for each of the multiple parsed documents. As shown in Figure 32, the rough summary corresponding to parsed document 1 is integration result 1, the rough summary corresponding to parsed document 2 is integration result 3, and so on. The rough summary corresponding to parsed document n is integration result n. Each integration result is obtained by interpreting and summarizing the document from multiple perspectives, as shown in Figure 32 using m aspects as an example.

[0379] After the rough summary of each document is extracted, the n integration results can be summarized according to the themes integrated in the rough classification, specifically divided into merging and comparison, to generate similarities and differences (i.e., distinguishing points) in various aspects.

[0380] In the above implementation, the object can upload a document (any format) through the front-end support, call various parsing services after uploading to parse the document, and then slice it through intelligent slicing. Summarize the slice content for each slice, and then the model summarizes the slice summaries into an overall article summary for output. After experimental analysis, the content extraction method in the embodiment of the application has achieved significant results in terms of the correctness, completeness, simplicity, intuitiveness and coherence of the generated document summary.

[0381] In addition, it should be noted that the above is a simple description of the process of extracting summaries from a single document or multiple documents. In combination with the above, it can be seen that the process of extracting summaries for each document includes multiple processing stages, such as uploading documents, extracting content information, processing image content, processing text content, extracting core ideas, and collating and merging summaries listed above. The processing status corresponding to these processing stages also needs to be fed back to the client in a timely manner, and presented to the object by the client through the status area. An optional implementation method is as follows:

[0382] The processing information of the first document is fed back to the client in real time, so that the client presents the processing information in the status area (collapsed form) corresponding to the first document, such as S71 in Figure 7A, etc.; or, the various processing stages when content extraction is performed on the first document and the respective processing status of the various processing stages are presented in the status area (expanded form), such as S91 in Figure 9A, etc.

[0383] The processing information indicates the current processing stage and the corresponding processing status when extracting content from the first document. For details, please refer to the above embodiment, and the repeated parts will not be repeated.

[0384] In addition, when the subsequent object views the processing results corresponding to the target processing stage through the client, the client can also send a corresponding request to the server, and the server will feed back the processing results to the client and present them to the object, as shown in Figure 14 or Figure 15, etc.

[0385] In addition, the server can also estimate the estimated completion time corresponding to each processing stage for the first document. The time can be specifically predicted based on the amount of content data to be processed, the complexity of the content, the model performance required to process the content, etc., and then provide real-time feedback to the client on the estimated completion time corresponding to the key processing stage, so that when the current processing stage of the first document is the key processing stage, the client will present the countdown information of the estimated completion time corresponding to the key processing stage in the status area, as shown in S101 in Figure 10A, S102 in Figure 10B, Figure 11, etc.

[0386] The present application also supports the object asking questions about the document summary, as shown in Figures 19A and 19B, etc. The object can enter a first question about the document summary corresponding to the first document on the client side, and then the client sends the first question to the server. After the server obtains the first question entered by the object for the document summary, it rewrites the first question in combination with the second question entered before the first question and the corresponding answer message to obtain a modified first question; then, the server extracts the first feature information corresponding to the modified first question, and obtains the second feature information corresponding to each content slice in the first document; finally, by matching the first feature information with each second feature information respectively, and generating an answer message corresponding to the first question according to the matching results.

[0387] It should be noted that the second feature information corresponding to each content slice in the first document may be pre-stored on the server side. Each content slice is obtained by dividing the first document based on a preset slice granularity. The preset slice granularity can be flexibly set according to actual needs. For example, the preset slice granularity can be a paragraph or a sentence, etc., which is not specifically limited in this document.

[0388] In summary, whether it is a single-document or multi-document scenario, this application supports answering subsequent questions based on the content of the document starting from the second round of dialogue.

[0389] To achieve this capability, on the one hand, the question needs to be rewritten in context, and on the other hand, the document needs to be split into more fine-grained paragraphs or even sentence-level segments.

[0390] The following uses the preset slice granularity as an example to illustrate the relevant process of the above question and answer:

[0391] First, the question is rewritten in one or more rounds based on the context and the previous answer, maintaining the original meaning of the question and answer content, and finally the rewritten question is obtained; for example, if the subject asks "How to make scrambled eggs with tomatoes" for the first time, and asks "How do you put soy sauce in this dish" for the second time (this question and answer), then in the process of this question and answer, you first need to combine the question and answer information of the previous (i.e. the first) question and answer, and rewrite the second question, such as "How do you put soy sauce when making scrambled eggs with tomatoes".

[0392] After obtaining the modified question (ie, the modified first question), feature extraction is performed on the rewritten question to obtain first feature information.

[0393] Furthermore, it is also necessary to perform feature extraction on the first document to be queried, such as extracting features from the document content at the sentence level, and modeling the correlation between sentences to obtain and store the second feature information corresponding to each sentence (content slice).

[0394] Then, combining the first and second feature information, the document content is searched to find documents relevant to the question. Specifically, this step can calculate the similarity between the first feature information and each piece of second feature information. For example, similarity can be represented by the distance between vectors. Sentences corresponding to second feature information with a similarity above a certain threshold are considered documents relevant to the question.

[0395] Refer to Figure 33, which is a schematic diagram of a feature matching process in an embodiment of the present application. For the parsed document, it can be split into multiple content fragments at the sentence granularity, such as sentence 1, sentence 2, ..., sentence n in Figure 33, and the second feature information corresponding to each sentence can be extracted by encoding (Encoder), that is, for each sentence in the document, the sentence-level embedding vector embedding is extracted, such as embedding 1, embedding 2, ..., embedding n in Figure 33. These embeddings can be stored on the server side and can be directly queried when performing questions and answers later.

[0396] In addition, after the question is contextually rewritten, the first feature information corresponding to the rewritten question can be extracted through encoding (Encoder), that is, the sentence-level embedding is extracted for the question raised in the conversation, such as embedding a in Figure 33.

[0397] Then, question retrieval is performed. Based on the feature-extracted embedding, the document embeddings are searched for similar content. Specifically, embedding a is matched with embedding 1, embedding 2, ..., embedding n, and the distance between the vectors is calculated. The closer the distance between the two vectors, the higher the corresponding similarity. Then, the sentences corresponding to the second feature information with a similarity higher than a certain threshold are regarded as document content related to the question.

[0398] In actual application scenarios, retrieval is divided into the following three situations:

[0399] a. The article contains relevant parts that can answer the question: answer directly based on the relevant content.

[0400] b. If the article content contains relevant sections but doesn't answer the question: Launch the search plugin to return search results. Specifically, when matching question features with document features, if the question content is mentioned in the document but there is no clear answer, the search plugin can also be used to search based on clues mentioned in the document.

[0401] c. If the article does not contain relevant information, the original statement will be returned, indicating that the answer cannot be given.

[0402] Finally, in case a, the main model (i.e., the content extraction model) can be used to generate an answer message corresponding to the first question based on the relevant question and the relevant content of the retrieved document. In case b, the main model can be used to summarize the search results and question, as well as the relevant content of the retrieved document, to generate an answer message to provide the answer.

[0403] It should also be noted that during feature extraction, the document's structural information, including page numbers, chapters, and other information, is retained. This allows subsequent searches to narrow down the scope of the content slices to be found based on page numbers, chapters, and other information. Searches are not conducted within the entire document, but rather within the content slices contained within the page numbers, chapters, and other information related to the first question. For example, if the question specifies a specific page and / or chapter, a round of content slice screening will be performed based on the chapter, page number, and other information in the question to narrow down the scope of the content slices that will be subsequently matched for feature matching.

[0404] Refer to Figure 34, which is a schematic diagram of a document content parsing and question-answering scheduling process in an embodiment of the present application. This process involves the business-side front-end page, engineering services, parsing services (crawler / OCR), algorithm preprocessing, and main model processing (also understood as model services).

[0405] Among them, the business-side front-end page is mainly used to realize interaction with the object. For example, in the first round of dialogue, the object uploads a PDF (i.e., the first document); then, the engineering service performs intent recognition, classification analysis, and other processing on the PDF uploaded by the object; then, the PDF is parsed through the parsing service, specifically including extracting text from the PDF, performing OCR recognition on images, and web crawling, etc., to exclude information irrelevant to the subject, pop-ups / advertisements / comments, etc., and dividing the chapter content in the PDF into paragraphs; then, the PDF is text-sliced ​​based on algorithm preprocessing. Referring to the above embodiment, taking L=3k (i.e., 3000) as an example, it is necessary to parse whether the content token is greater than 3k. If so, based on the specific implementation method in the above embodiment, the text information contained in the parsed document is text-sliced, otherwise the main model processing related steps are executed.

[0406] After obtaining at least one text slice based on algorithm preprocessing, the main model is used to generate summaries of each slice, which are then summarized to generate a document summary corresponding to the first document body and returned to the business side front end for content display. The specific implementation method can be found in the above embodiment, and the repeated parts will not be repeated.

[0407] During the main model processing, the number of abstracts extracted will vary depending on the number of text slices obtained in the previous step. This is because the process also needs to determine whether the number of abstracts is greater than 1. If so, the abstracts of each slice (such as Slice Abstract 1, Slice Abstract 2, and Slice Abstract N in Figure 34) are further aggregated based on the main model to obtain the document abstract corresponding to the first document. Otherwise, the document abstract corresponding to the first document is directly extracted based on the main model.

[0408] Based on the main model, the content of the first document is extracted to obtain a document summary, and the summary content is sent to the engineering service cache. The summary content, session ID, and file ID are combined with the previously cached parsed source content to bind. In addition, the content can be displayed through the business side front-end page, showing the document summary of the first document, such as S161 and S163 in Figure 16. The specific implementation method can be referred to the above embodiment, and the repeated parts will not be repeated.

[0409] In a multi-round dialogue scenario, the subject can upload a new document, ask questions about the document summary of the first document, etc. When the subject extracts the first document, the question is rewritten in combination with the context, and the rewritten question is semantically parsed and keyword extracted. Then, based on the above results, the search object and quantity are circled. For example, after keyword extraction of the rewritten question, the description related to the chapter page number is determined, and the object to be retrieved (referring to the content slice) and the corresponding quantity can be circled based on this. Then, the keyword search history is combined with the stored content, which refers to the previously stored content slice of the first document and the corresponding second feature information, and the matching result of the first feature information corresponding to the rewritten question, to retrieve the document history source content (i.e., the content related to the question in the first document). Finally, the keyword fragment is entered in the main model, and the model is required to give a reply in combination with the context main information. After obtaining the answer message corresponding to the question using the main model, it is returned to the business side front-end page for content display, as shown in Figures 19A and 19B. The specific implementation method can be found in the above embodiment, and the repeated parts will not be repeated.

[0410] In summary, this application supports multi-round question-answering by storing text features of document parsing results. When a subject enters a multi-round question, the system will perform a similarity match between the subject's question and the text features of the document parsing results, find the most relevant content in the document, and then summarize it through the model and output the answer. This approach can achieve multi-round question-answering and performs well.

[0411] Optionally, in S301, if the server receives multiple document processing requests within a certain period of time, the server may schedule the document processing requests in the following manner to extract content from multiple documents and generate corresponding document summaries:

[0412] Based on the respective receiving times of the multiple document processing requests received, the document processing requests whose receiving time differences are within a preset time range are processed in parallel to extract the content of the corresponding documents and generate corresponding document summaries.

[0413] The preset time range can be flexibly set according to actual needs, such as 1 minute, 30 seconds, 10 seconds, etc., and is not specifically limited in this article.

[0414] Compared with related technologies that often encounter problems such as insufficient resources and long object queuing times, the request scheduling method proposed in this application greatly improves model resource utilization. By accessing questions with similar time to the same model service, the concurrency of the model can be increased; and it ensures that newly arrived questions always access available model resources when there are available model resources, avoiding poor experience caused by blocking objects when questions access resources being inferred.

[0415] Optionally, the process of extracting the summary of each slice in S302 can also be implemented through multi-model parallelism, that is, abstract extraction is performed on at least one text slice in parallel to obtain a slice summary corresponding to each of the at least one text slice.

[0416] During the content extraction process for the first document, the application first slices the parsed document's text using an algorithm, dividing it into multiple text slices of a limited number of words. The model service is then called in parallel to summarize the information and generate a summary of the multiple summarized slices. The summary of the multiple summarized slices is then aggregated, and the model service is called again to generate a final content summary, which is then fed back to the target. This approach can shorten the time required to generate the content summary.

[0417] In addition, it should be noted that this application also supports solving input audit and output audit without affecting performance, ensuring output security.

[0418] Specifically, the document content, extracted summary content, the first question entered by the subject, modification instructions, etc. will be subject to real-time security review. Once sensitive and / or harmful information appears, the current conversation can be withdrawn or terminated to prevent the subject from maliciously guiding the model to generate sensitive and harmful information.

[0419] Based on the same inventive concept, the present application also provides a content extraction device. As shown in FIG35 , it is a schematic diagram of the structure of the content extraction device 3500, which may include:

[0420] The first responding unit 3501 is configured to present a document selection interface in response to an upload operation triggered by the information interaction interface, where the document selection interface includes at least one document;

[0421] A second response unit 3502 is configured to, in response to a selection operation on a first document among the at least one document, present the first document in the information interaction interface and present processing information of the first document in a status area corresponding to the first document, the processing information indicating a current processing stage and corresponding processing status of content extraction from the first document;

[0422] After the content extraction of the first document is completed, the display of the status area is cancelled, and a document summary obtained by extracting the content of the first document is presented in the information interaction interface.

[0423] Optionally, when the status area is in the collapsed state, the second response unit 3502 is further configured to:

[0424] In response to an expansion operation triggered on the status area, switching the status area to an expanded state;

[0425] In the expanded status area, various processing stages of content extraction for the first document and the processing status of each processing stage are presented.

[0426] Optionally, the second responding unit 3502 is further configured to:

[0427] If the current processing stage of the first document is a critical processing stage, countdown information of the estimated completion time corresponding to the critical processing stage is presented in the status area;

[0428] The key processing stage is at least one of the following: a processing stage whose estimated completion time exceeds a preset time threshold, and a preset processing stage.

[0429] Optionally, the second responding unit 3502 is further configured to:

[0430] In the expanded status area, the various processing stages when content extraction is performed on the first document, as well as the processing status of each processing stage, are presented. Then, for the target processing stage in the target processing state among the processing stages, in response to a selection operation on any target processing stage, the processing result of any target processing stage is presented.

[0431] Optionally, the target processing status includes at least one of completed and processing failed;

[0432] When the processing status of any target processing stage is processing failure, the processing result includes at least one of the failure reason and document adjustment suggestion.

[0433] Optionally, when there are multiple first documents, the second responding unit 3502 is specifically configured to:

[0434] Presenting each first document and the document summary corresponding to each first document in the information interaction interface, wherein each first document and the document summary corresponding to the first document form a group of conversation messages; or

[0435] In the information interaction interface, each first document and an aggregated document summary are presented separately, wherein the aggregated document summary is obtained by extracting the document summaries corresponding to each first document and aggregating multiple document summaries. A group of conversation messages includes multiple first documents and the aggregated document summaries.

[0436] Optionally, the second responding unit 3502 is further configured to:

[0437] Presenting summary prompt information, the summary prompt information is used to prompt whether to summarize the document summaries corresponding to the respective first documents; wherein, the summarization processing includes at least one of the following: determining the common points of the respective document summaries, determining the differences of the respective document summaries;

[0438] In response to the summary process triggered by the summary prompt information, a summarized document summary corresponding to the summary process and generated based on the document summary corresponding to each of the first documents is presented.

[0439] Optionally, the first responding unit 3501 is further configured to:

[0440] Before responding to an upload operation triggered by the information interaction interface, in response to a document summary operation triggered by a first function control in the function discovery interface, an information interaction interface is presented; the information interaction interface includes a default session message and a document upload control, wherein the default session message is used to present an example document summary function, which generates a document summary by extracting content from a document;

[0441] The first response unit 3501 is specifically configured to:

[0442] In response to an upload operation triggered by a document upload control in the information interaction interface, a document selection interface is presented.

[0443] Optionally, the default session message includes at least one sample document; the first responding unit 3501 is further configured to:

[0444] Before responding to the upload operation triggered based on the information interaction interface, in response to a selection operation on any one of the at least one example document, presenting a document summary corresponding to any one of the example documents;

[0445] The second response unit 3502 is further configured to:

[0446] During the processing after the first document is uploaded, at least one example document is updated to a non-interactive state; and after the content of the first document is extracted, at least one example document is updated to an interactive state.

[0447] Optionally, the document summary is presented in the form of a conversation message. The second response unit 3502 is further configured to:

[0448] presenting a re-summarize control for the first document at a first relevant location in the document summary;

[0449] In response to a triggering operation on the re-summarization control, content extraction is performed on the first document again, and after the re-content extraction is completed, a new document summary is presented at the original conversation message corresponding to the document summary.

[0450] Optionally, the second responding unit 3502 is further configured to:

[0451] presenting a summary toggle control at a second relevant location in the document summary;

[0452] In response to a switching operation triggered by the summary switching control, multiple document summary lines corresponding to the first document in the original conversation message are switched and displayed.

[0453] Optionally, the second responding unit 3502 is further configured to:

[0454] Presenting, at a third relevant position of the document summary, a feedback control for evaluating the summary quality of the document summary;

[0455] In response to the evaluation operation triggered based on the feedback control, the corresponding evaluation result is presented.

[0456] Optionally, the device further comprises:

[0457] The third responding unit 3503 is configured to, in response to a processing stop operation on the first document during the processing of the first document, present a stop prompt message and a corresponding resummarization control in the information interaction interface;

[0458] In response to a triggering operation on the re-summarization control, content extraction is performed on the first document again, and after the re-content extraction is completed, a document summary obtained by extracting the content of the first document is presented in the information interaction interface.

[0459] Optionally, the device further comprises:

[0460] The fourth response unit 3504 is used to present an exit prompt message in response to an exit operation on the information interaction interface during the processing of the first document. The exit prompt message is used to prompt the object that the first document is currently being processed and to ask the object whether to confirm the exit.

[0461] Optionally, if the first document upload fails, the apparatus further includes:

[0462] The fifth response unit 3505 is configured to present a re-upload control in the information interaction interface;

[0463] In response to a re-upload operation triggered by the re-upload control, the first document is re-uploaded.

[0464] Optionally, the second responding unit 3502 is further configured to:

[0465] Present an input box in the information interaction interface;

[0466] In response to a first question regarding the document summary input based on the input box, presenting an answer message corresponding to the first question;

[0467] The answer message is any of the following:

[0468] A predetermined expression indicating that an answer is unanswerable is generated based on the first question and content related to the first question in the first document and based on search results related to the first question.

[0469] Optionally, the information interaction interface further includes a second question for non-document content input, and the second response unit 3502 is specifically configured to:

[0470] Using a first message format, presenting a first question and an answer message corresponding to the first question; and using a second message format, presenting a second question and an answer message corresponding to the second question;

[0471] The first question and the second question are distinguished based on at least one of the following methods: predetermined character recognition, key information recognition, and intention recognition.

[0472] Optionally, the second responding unit 3502 is further configured to:

[0473] Present an input box in the information interaction interface;

[0474] In response to a modification instruction for the document summary input based on the input box, a modified document summary corresponding to the modification instruction is presented.

[0475] Optionally, the device further comprises:

[0476] A first sharing unit 3506, configured to present at least one second function control corresponding to the document summary of the first document;

[0477] In response to a sharing operation triggered by at least one second function control, the document summary and the first document are sent to a to-be-shared object.

[0478] Optionally, the device further comprises:

[0479] The second sharing unit 3507 is used to present the shared document and the document summary corresponding to the shared document, as well as a new conversation entry;

[0480] In response to the triggering operation for the new dialogue entry, a default conversation message and a document upload control are presented in the information interaction interface, wherein the default conversation message is used to present the sample document summary function, and the document summary function means generating a document summary by extracting content from the document.

[0481] Optionally, the device further comprises:

[0482] A history viewing unit 3508 is configured to present, in response to a viewing operation on the history records of a target object, each historical document corresponding to the target object for which a document summary has been currently generated;

[0483] In response to a viewing operation on any one of the historical documents, a document summary corresponding to the any one of the historical documents is presented.

[0484] Based on the same inventive concept, the present embodiment also provides another content extraction device. As shown in FIG36 , it is a schematic structural diagram of a content extraction device 3600 , which may include:

[0485] An information extraction unit 3601 is configured to extract text information from a first document upon receiving a document processing request for the first document; the first document is uploaded by the client in response to a selection operation of the first document from at least one document in a document selection interface, the document selection interface being presented by the client in response to the upload operation triggered by the information interaction interface;

[0486] The slicing processing unit 3602 is configured to slice the extracted text information to obtain at least one text slice; extract a summary of each of the at least one text slice to obtain a slice summary corresponding to each of the at least one text slice;

[0487] The summarizing unit 3603 is used to summarize the obtained slice summary, obtain the document summary corresponding to the first document, and feed back the document summary to the client so that the client can present the document summary obtained by content extraction of the first document in the information interaction interface.

[0488] Optionally, the slice processing unit 3602 is specifically configured to:

[0489] Inputting at least one text slice into the content extraction model respectively, and for each text slice, extracting a slice summary corresponding to the text slice using the content extraction model according to a pre-configured first summary instruction; the first summary instruction is used to specify the word count and summary format of the slice summary;

[0490] The summarizing unit 3603 is specifically used for:

[0491] Each slice summary is input into the content extraction model respectively, and the content extraction model is used to summarize the slice summary according to the pre-configured second summary instruction to generate a document summary; the second summary instruction is used to specify the word count and summary format of the document summary.

[0492] Optionally, the device further comprises:

[0493] Node processing unit 3604 is configured to provide real-time feedback of processing information of the first document to the client, so that the client displays the processing information in a status area corresponding to the first document, wherein the processing information indicates the current processing stage and corresponding processing status of content extraction from the first document;

[0494] The estimated completion time corresponding to the key processing stage is fed back to the client in real time, so that when the current processing stage of the first document is the key processing stage, the client presents the countdown information of the estimated completion time corresponding to the key processing stage in the status area.

[0495] Optionally, when there are multiple first documents, the slicing processing unit 3602 is further configured to:

[0496] Summarize the respective topics of each first document;

[0497] The summarizing unit 3603 is further configured to:

[0498] Based on the respective topics of the first documents, the document summaries corresponding to the first documents are summarized, and the summarized document summaries are obtained and fed back to the client, so that the client presents the summarized document summaries in the form of conversation messages in the information interaction interface.

[0499] Optionally, the device further comprises:

[0500] Question and answer unit 3605, configured to obtain a first question input by the subject regarding the document summary;

[0501] Rewrite the first question based on the question input before the first question and the corresponding answer message to obtain a modified first question;

[0502] Extracting first feature information corresponding to the modified first question, and obtaining second feature information corresponding to each content slice in the first document, where each content slice is obtained by dividing the first document based on a preset slice granularity;

[0503] The first characteristic information is matched with each piece of second characteristic information respectively, and an answer message corresponding to the first question is generated according to the matching results.

[0504] Optionally, the slice processing unit 3602 is specifically configured to perform summary extraction on at least one text slice in parallel to obtain a slice summary corresponding to each of the at least one text slice.

[0505] For the convenience of description, the above parts are divided into modules (or units) according to their functions and described separately. Of course, when implementing this application, the functions of each module (or unit) can be implemented in the same or multiple software or hardware.

[0506] After introducing the content extraction method and apparatus according to an exemplary embodiment of the present application, an electronic device according to another exemplary embodiment of the present application will be introduced next.

[0507] Those skilled in the art will appreciate that various aspects of the present application can be implemented as systems, methods, or program products. Therefore, various aspects of the present application can be specifically implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation that combines hardware and software aspects, which may be collectively referred to herein as a "circuit," "module," or "system."

[0508] Based on the same inventive concept as the above-mentioned method embodiment, an electronic device is also provided in an embodiment of the present application. In one embodiment, the electronic device may be a server, such as server 120 shown in FIG1 . In this embodiment, the structure of the electronic device may be as shown in FIG37 , including a memory 3701, a communication module 3703, and one or more processors 3702.

[0509] Memory 3701 is used to store computer programs executed by processor 3702. Memory 3701 may mainly include a program storage area and a data storage area. The program storage area may store an operating system and programs required for running instant messaging functions, while the data storage area may store various instant messaging messages and operating instruction sets.

[0510] Memory 3701 may be a volatile memory, such as random-access memory (RAM); a non-volatile memory, such as read-only memory, flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); or any other medium capable of carrying or storing a desired computer program in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 3701 may be a combination of the aforementioned memories.

[0511] The processor 3702 may include one or more central processing units (CPUs) or digital processing units, etc. The processor 3702 is configured to implement the above-mentioned content extraction method when calling the computer program stored in the memory 3701 .

[0512] The communication module 3703 is used to communicate with terminal devices and other servers.

[0513] The specific connection medium between the memory 3701, communication module 3703, and processor 3702 is not limited in the embodiments of the present application. In Figure 37, the embodiment of the present application shows that the memory 3701 and the processor 3702 are connected via a bus 3704. Bus 3704 is depicted as a bold line in Figure 37. The connection methods between other components are merely schematic and are not intended to be limiting. Bus 3704 can be divided into an address bus, a data bus, a control bus, etc. For ease of description, Figure 37 only uses a single bold line, but does not represent a single bus or a single type of bus.

[0514] The memory 3701 stores a computer storage medium, which stores computer executable instructions for implementing the content extraction method of the embodiment of the present application. The processor 3702 is used to execute the above content extraction method, as shown in Figure 30.

[0515] In another embodiment, the electronic device may also be other electronic devices, such as the terminal device 110 shown in FIG1 . In this embodiment, the structure of the electronic device may be as shown in FIG38 , including: a communication component 3810, a memory 3820, a display unit 3830, a camera 3840, a sensor 3850, an audio circuit 3860, a Bluetooth module 3870, a processor 3880, and other components.

[0516] The communication component 3810 is used to communicate with the server. In some embodiments, it may include a wireless fidelity (WiFi) module. The WiFi module is a short-range wireless transmission technology that allows electronic devices to help users send and receive information.

[0517] The memory 3820 can be used to store software programs and data. The processor 3880 executes various functions and data processing of the terminal device 110 by running the software programs or data stored in the memory 3820. The memory 3820 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The memory 3820 stores the operating system that enables the terminal device 110 to run. In the present application, the memory 3820 can store the operating system and various application programs, and may also store the computer program that executes the content extraction method of the embodiment of the present application.

[0518] The display unit 3830 can also be used to display information input by the user or information provided to the user, as well as a graphical user interface (GUI) of various menus of the terminal device 110. Specifically, the display unit 3830 may include a display screen 3832 disposed on the front of the terminal device 110. The display screen 3832 may be configured in the form of a liquid crystal display, a light-emitting diode, etc. The display unit 3830 can be used to display the information interaction interface, document selection interface, etc. in the embodiments of the present application.

[0519] The display unit 3830 can also be used to receive input digital or character information and generate signal input related to the user settings and function control of the terminal device 110. Specifically, the display unit 3830 may include a touch screen 3831 arranged on the front of the terminal device 110, which can collect user touch operations on or near it, such as clicking a button, dragging a scroll box, etc.

[0520] The touch screen 3831 can be covered on the display screen 3832, or the touch screen 3831 and the display screen 3832 can be integrated to realize the input and output functions of the terminal device 110. The integrated display screen can be simply called a touch screen. In this application, the display unit 3830 can display applications and corresponding operation steps.

[0521] Camera 3840 can be used to capture still images, and users can publish images captured by camera 3840 through an application. Camera 3840 can be one or more. The object is projected onto the photosensitive element through the lens to generate an optical image.

[0522] The terminal device may further include at least one sensor 3850, such as an acceleration sensor 3851, a distance sensor 3852, a fingerprint sensor 3853, and a temperature sensor 3854. The terminal device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, a light sensor, and a motion sensor.

[0523] The audio circuit 3860, speaker 3861, and microphone 3862 provide an audio interface between the user and the terminal device 110. The audio circuit 3860 can convert the received audio data into an electrical signal and transmit it to the speaker 3861, which converts it into a sound signal for output. The terminal device 110 may also be equipped with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 3862 converts the collected sound signal into an electrical signal, which is received by the audio circuit 3860 and converted into audio data. The audio data is then output to the communication component 3810 for transmission to, for example, another terminal device 110, or the audio data is output to the memory 3820 for further processing.

[0524] The Bluetooth module 3870 is used to exchange information with other Bluetooth devices having a Bluetooth module through the Bluetooth protocol. For example, the terminal device can establish a Bluetooth connection with a wearable electronic device (such as a smart watch) that also has a Bluetooth module through the Bluetooth module 3870 to exchange data.

[0525] Processor 3880 is the control center of the terminal device. It uses various interfaces and lines to connect various parts of the entire terminal. It executes various functions of the terminal device and processes data by running or executing software programs stored in memory 3820 and calling data stored in memory 3820.

[0526] In some possible implementations, various aspects of the content extraction method provided in the present application can also be implemented in the form of a program product, which includes a computer program. When the program product is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the content extraction method according to various exemplary embodiments of the present application described above in this specification. For example, the electronic device can execute the steps shown in Figure 2 or Figure 30.

[0527] Furthermore, although the operations of the method of the present application are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all illustrated operations must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0528] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain a computer-usable computer program.

Claims

1. A content extraction method, executed in a client, comprising: In response to an upload operation triggered based on the information interaction interface, presenting a document selection interface, wherein the document selection interface includes at least one document; In response to a selection operation on a first document among the at least one document, presenting the first document in the information interaction interface, and presenting processing information of the first document in a status area corresponding to the first document, the processing information indicating a current processing stage and a corresponding processing status in a process of extracting content from the first document; After the content extraction of the first document is completed, the display of the status area is cancelled, and a document summary obtained by extracting the content of the first document is presented in the information interaction interface.

2. The method of claim 1, further comprising: In response to an expansion operation triggered on the status area, switching the status area from a collapsed state to an expanded state; In the status area of ​​the expanded form, various processing stages in the process of extracting content from the first document and the processing status of each processing stage are presented.

3. The method according to claim 1 or 2, further comprising: If it is determined that the current processing stage of the first document is a critical processing stage, then in the status area, countdown information of an estimated completion time corresponding to the critical processing stage is presented; Among them, the key processing stage is at least one of the following: a processing stage whose estimated completion time exceeds a preset time threshold, and a preset processing stage.

4. The method according to claim 2, wherein after presenting, in the status area of ​​the expanded form, each processing stage in the process of extracting content from the first document and the processing status of each processing stage, the method further comprises: For the target processing stages in the target processing state among the various processing stages, in response to a selection operation on any target processing stage, a processing result of the selected target processing stage is presented.

5. The method according to claim 4, wherein the target processing status comprises at least one of completed and processing failed; in, When the processing status of any one of the target processing stages is processing failure, the processing result includes at least one of a failure reason and a document adjustment suggestion.

6. The method according to any one of claims 1 to 5, wherein when there are multiple first documents, presenting the first documents in the information interaction interface, and presenting a document summary obtained by extracting content from the first documents, comprises: presenting each first document and a document summary corresponding to each first document in the information interaction interface, wherein each first document and the corresponding document summary form a group of messages; or In the information interaction interface, each first document and an aggregated document summary are presented separately, wherein the aggregated document summary is a group of messages obtained by aggregating multiple document summaries after extracting the document summaries corresponding to each of the first documents respectively, and the group of messages includes multiple first documents and the aggregated document summary.

7. The method according to claim 6, wherein each first document and a document summary corresponding to each first document are presented in the information interaction interface, and further comprising: Presenting summary prompt information, wherein the summary prompt information is used to prompt whether to perform summary processing on the document summaries corresponding to the respective first documents; wherein the summary processing includes at least one of the following: determining the common points of the respective document summaries, determining the differences of the respective document summaries; In response to the summary process triggered by the summary prompt information, a summarized document summary corresponding to the summary process and generated based on the document summaries corresponding to each of the first documents is presented.

8. The method according to any one of claims 1 to 5, before responding to the upload operation triggered by the information interaction interface, further comprising: In response to a document summary operation triggered by a first functional control in the first interface, presenting the information interaction interface; The information interaction interface includes a default message and a document upload control, wherein the default message is used to present an example document summary function, and the document summary function represents generating a document summary by extracting content from a document; The presenting of a document selection interface in response to an upload operation triggered by the information interaction interface includes: In response to an upload operation triggered by a document upload control in the information interaction interface, the document selection interface is presented.

9. The method of claim 8, wherein the default message comprises at least one example document; Before responding to the upload operation triggered by the information interaction interface, the method further includes: In response to a selection operation on any one of the at least one example document, presenting a document summary corresponding to the any one example document; The method further comprises: During the process of extracting the content after the first document is uploaded, the at least one example document is updated to a non-interactive state; and after the content extraction of the first document is completed, the at least one example document is updated to an interactive state.

10. The method according to any one of claims 1 to 5, further comprising: During the process of extracting the content of the first document, in response to a processing stop operation on the first document, presenting a stop prompt message and a corresponding re-summarization control in the information interaction interface; In response to a triggering operation on the re-summarization control, content extraction is performed on the first document again, and after the content extraction is completed again, a document summary obtained by extracting content from the first document is presented in the information interaction interface.

11. The method according to any one of claims 1 to 5, wherein presenting, in the information interaction interface, a document summary obtained by extracting content from the first document, further comprises: Presenting an input box in the information interaction interface; In response to a first question for the document summary input based on the input box, presenting an answer message corresponding to the first question; The answer message is any one of the following: a message generated based on the first question and the content in the first document related to the first question, a message generated based on the search results related to the first question, and a message indicating a predetermined expression that cannot be answered.

12. The method according to claim 11, wherein the information interaction interface further comprises a second question for non-document content input, and the presenting of an answer message corresponding to the first question comprises: Using a first message format, presenting the first question and an answer message corresponding to the first question; And, using a second message format to present the second question and an answer message corresponding to the second question; The first question and the second question are distinguished based on at least one of the following methods: predetermined character recognition, key information recognition, and intent recognition.

13. The method according to any one of claims 1 to 5, wherein presenting, in the information interaction interface, a document summary obtained by extracting content from the first document, further comprises: Presenting an input box in the information interaction interface; In response to a modification instruction for the document summary input based on the input box, a modified document summary corresponding to the modification instruction is presented.

14. The method according to any one of claims 1 to 5, further comprising: Presenting at least one second function control corresponding to the document summary of the first document; In response to a sharing operation triggered by the at least one second functional control, the document summary and the first document are sent to a to-be-shared object.

15. The method according to any one of claims 1 to 5, further comprising: Presenting a shared document and a document summary corresponding to the shared document, as well as a new conversation entry; In response to a trigger operation for the new dialogue entry, a default message and a document upload control are presented in the information interaction interface, wherein the default message is used to provide an example document summary function to the object, and the document summary function represents generating a document summary by extracting content from the document.

16. The method according to any one of claims 1 to 5, further comprising: In response to a viewing operation on the historical records of a target object, presenting each historical document of which the document summary has been currently generated and corresponds to the target object; In response to a viewing operation on any one of the historical documents, a document summary corresponding to the any one of the historical documents is presented.

17. A content extraction method, executed in a server, comprising: After receiving a document processing request for a first document, extracting text information from the first document; the first document is uploaded by the client in response to a selection operation of the first document in at least one document in a document selection interface, and the document selection interface is presented by the client in response to an upload operation triggered based on an information interaction interface; Slicing the extracted text information to obtain at least one text slice; Extracting a summary of each text slice in the at least one text slice respectively to obtain a slice summary corresponding to each of the at least one text slice; The obtained slice summaries are summarized to obtain a document summary corresponding to the first document, and the document summary is fed back to the client so that the client presents the document summary obtained by extracting content from the first document in the information interaction interface.

18. The method of claim 17, further comprising: Feedback the processing information of the first document to the client in real time, so that the client presents the processing information in a status area corresponding to the first document, wherein the processing information indicates a current processing stage and a corresponding processing status in the process of extracting content from the first document; The estimated completion time corresponding to the key processing stage is fed back to the client in real time, so that when the current processing stage of the first document is the key processing stage, the client presents the countdown information of the estimated completion time corresponding to the key processing stage in the status area.

19. The method according to claim 17, when there are multiple first documents, the method further comprises: Summarize the respective topics of each first document; Based on the respective topics of the first documents, the document summaries corresponding to the first documents are summarized, and the summarized document summaries are obtained and fed back to the client, so that the client presents the summarized document summaries in the form of messages in the information interaction interface.

20. The method according to any one of claims 17 to 19, further comprising: Obtaining a first question input by the subject regarding the document summary; Based on other questions input before the first question and corresponding answer messages, rewrite the first question to obtain a modified first question; Extracting first feature information corresponding to the modified first question, and obtaining second feature information corresponding to each content slice in the first document, wherein each content slice is obtained by dividing the first document based on a preset slice granularity; The first characteristic information is matched with each piece of second characteristic information respectively, and an answer message corresponding to the first question is generated according to the matching result.

21. A content extraction device, comprising: A first response unit, configured to present a document selection interface in response to an upload operation triggered based on the information interaction interface, wherein the document selection interface includes at least one document; a second response unit, configured to, in response to a selection operation on a first document among the at least one document, present the first document in the information interaction interface, and present processing information of the first document in a status area corresponding to the first document, wherein the processing information indicates a current processing stage and a corresponding processing status in a process of extracting content from the first document; After the content extraction of the first document is completed, the display of the status area is cancelled, and a document summary obtained by extracting the content of the first document is presented in the information interaction interface.

22. A content extraction device, comprising: an information extraction unit, configured to extract text information from a first document after receiving a document processing request for the first document; the first document is uploaded by a client in response to a selection operation of a first document from at least one document in a document selection interface, the document selection interface being presented by the client in response to an upload operation triggered based on an information interaction interface; A slice processing unit, configured to slice the extracted text information to obtain at least one text slice; extract a summary of each text slice in the at least one text slice to obtain a slice summary corresponding to each of the at least one text slice; A summarizing unit is used to summarize the obtained slice summary to obtain a document summary corresponding to the first document, and to The summary is fed back to the client, so that the client presents the document summary obtained by extracting the content of the first document in the information interaction interface.

23. An electronic device comprising a processor and a memory, wherein: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of any one of the methods of claims 1 to 20.

24. A computer-readable storage medium comprising a computer program, wherein when the computer program is run on an electronic device, the computer program is used to cause the electronic device to execute the steps of the method according to any one of claims 1 to 20.

25. A computer program product, comprising a computer program, wherein the computer program is stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of any method described in claims 1 to 20.

Images