Method and device for processing document based on large model, equipment and medium

Abstract

The invention provides a method, device and equipment for processing a document based on a large model and a medium, and relates to the technical field of artificial intelligence, in particular to the technical fields of machine learning, deep learning, large models and the like. The method comprises the following steps: in response to a detected first browsing operation of a user on a target document, identifying a keyword item in the target document; determining related content of the keyword item, wherein the related content at least comprises context information of the keyword item in the target document; calling a large model to generate entry explanations for the keyword items based on related contents; and displaying the entry explanation in response to detecting a first interaction operation of the user on the keyword item and in response to determining that the large model has completed the generation of the entry explanation.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to technical fields such as machine learning, deep learning and big models, and specifically to a method for processing documents based on big models, an apparatus for processing documents based on big models, an electronic device, a computer-readable storage medium and a computer program product. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include natural language processing technology, computer vision technology, speech recognition technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] In an enterprise knowledge base environment, users often need to understand and apply professional terms or technical vocabulary, which often involves a tedious and time-consuming query process, especially in documents with a large amount of information. In an enterprise knowledge base environment, users often need to understand and apply professional terms or technical vocabulary, which often involves a tedious and time-consuming query process, especially in documents with a large amount of information.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides a method for processing documents based on a large model, an apparatus for processing documents based on a large model, an electronic device, a computer-readable storage medium, and a computer program product.

[0006] According to one aspect of the present disclosure, a method for processing documents based on a large model is provided. The method includes: in response to detecting a first browsing operation of a user on a target document, identifying a keyword entry in the target document; determining relevant content of the keyword entry, the relevant content at least including context information of the keyword entry in the target document; calling the large model to generate a term explanation for the keyword entry based on the relevant content; and in response to detecting a first interactive operation of the user on the keyword entry, and in response to determining that the large model has completed the generation of the term explanation, displaying the term explanation.

[0007] According to another aspect of the present disclosure, a device for processing documents based on a large model is provided. The device includes: a first recognition unit, configured to identify a keyword entry in a target document in response to detecting a first browsing operation of a user on the target document; a first determination unit, configured to determine the relevant content of the keyword entry, the relevant content at least including context information of the keyword entry in the target document; a first calling unit, configured to call the large model to generate a term explanation for the keyword entry based on the relevant content; and a first display unit, configured to display the term explanation in response to detecting a first interactive operation of the user on the keyword entry and in response to determining that the large model has completed the generation of the term explanation.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above method.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the above method.

[0010] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the above method when executed by a processor.

[0011] According to one or more embodiments of the present disclosure, the present disclosure generates term explanations of key words based on contextual content by calling a large model, so that users can be provided with instant and accurate term explanation content while browsing documents, thereby optimizing users' reading experience and work efficiency.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0014] Figure 1 A schematic diagram showing an exemplary system in which the various methods described herein may be implemented according to an embodiment of the present disclosure;

[0015] Figure 2 A flowchart of a method for processing documents based on a large model according to an embodiment of the present disclosure is shown;

[0016] Figure 3 A flowchart of a method for processing documents based on a large model according to an embodiment of the present disclosure is shown;

[0017] Figure 4 A flowchart of a method for processing documents based on a large model according to an embodiment of the present disclosure is shown;

[0018] Figure 5 A flow chart showing the interaction between a user, a knowledge base service, and a card content service according to an embodiment of the present disclosure;

[0019] Figure 6 A structural block diagram of an apparatus for processing documents based on a large model according to an embodiment of the present disclosure is shown; and

[0020] Figure 7 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

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

[0022] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0023] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0024] In the related art, if a user needs to understand certain terms in a document when reading it, the user is usually required to go through a tedious and time-consuming query process, especially in documents with a large amount of information, which results in low efficiency in user understanding and application.

[0025] To solve the above problems, the present invention generates term explanations of key words based on contextual content by calling a large model, so that users can be provided with instant and accurate term explanation content while browsing documents, thereby optimizing users' reading experience and work efficiency.

[0026] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0028] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable execution of the methods of the present disclosure.

[0029] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0030] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0031] The user can use client devices 101, 102, 103, 104, 105 and / or 106 to perform human-computer interaction. The client device can provide an interface that enables the user of the client device to interact with the client device. The client device can also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0032] Client devices 101, 102, 103, 104, 105 and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. Client devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0033] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0034] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0035] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0036] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and / or 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and / or 106.

[0037] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0038] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0039] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0040] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0041] According to one aspect of the present disclosure, a method for processing documents based on a large model is provided. Figure 2 As shown, the method includes: step S201, in response to detecting a user's first browsing operation on the target document, identifying a keyword entry in the target document; step S202, determining relevant content of the keyword entry, the relevant content at least including context information of the keyword entry in the target document; step S203, calling the big model to generate a term explanation for the keyword entry based on the relevant content; and step S204, in response to detecting a user's first interactive operation on the keyword entry and in response to determining that the big model has completed the generation of the term explanation, displaying the term explanation.

[0042] Therefore, by calling the large model to generate term explanations for key words based on contextual content, users can be provided with instant and accurate term explanation content while browsing documents, thereby optimizing their reading experience and work efficiency.

[0043] The method disclosed in the present invention can be used for document display in a knowledge base environment, and can be widely used in enterprise knowledge management systems, enterprise internal education platforms, technical document readers, etc., and is particularly suitable for environments that require efficient understanding and application of professional knowledge. In addition, the method disclosed in the present invention can be used in browser plug-ins, web page pipelines, applications, or other scenarios, which are not limited here.

[0044] The target document may be any document in the knowledge base. The user's first browsing operation on the target document may trigger any operation of the user to read the page of the target document.

[0045] In step S201, semantic analysis may be performed on the target document to obtain keyword entries.

[0046] Keyword entries can be predefined in a variety of ways. In an exemplary embodiment, the user's interaction history with the document in the knowledge base can be recorded, and the entry selected by the user is used as the keyword entry. In addition, multiple keyword entries can also be predefined by entity recognition, relationship extraction, synonym resolution or other methods, which are not limited here.

[0047] In step S202, the relevant content of the keyword is determined, and the relevant content at least includes the context information of the keyword in the target document.

[0048] In some embodiments, context information may include the content of the paragraph where the keyword entry is located. Other words in the paragraph where the keyword entry appears may provide the explanation, background or purpose of the keyword entry. Context information may also include adjacent sentences or paragraphs. The adjacent sentences or paragraphs of the keyword entry may contain definitions, examples or detailed descriptions directly related to it.

[0049] By determining the context information of the key words, it is helpful to better understand the meaning of the key words in the current context, so that more accurate interpretation of the terms can be generated later and ambiguity can be avoided.

[0050] According to some embodiments, step S202, determining relevant content of the keyword entry may include: using the search enhancement generation system to search in the knowledge base based on context information to obtain search results, and the relevant content includes the search results.

[0051] Therefore, by searching the knowledge base based on context information, the scope of content covered by the term explanation can be expanded, significantly improving the relevance and accuracy of the term explanation.

[0052] Retrieval-Augmented Generation (RAG) is a technology that combines information retrieval and generative models. In this way, data related to these key terms can be extracted from the knowledge base to provide more comprehensive and contextual explanations or information for the subsequent large model. In addition, by maintaining the knowledge base in real time, the retrieval-augmented generation system can retrieve timely and accurate search results related to the key terms, ensuring that the large model can generate instant and accurate term explanations.

[0053] In step S203, the large model is called to generate term explanations for key words based on relevant content.

[0054] The large model (or deep learning large model) described in the present disclosure may be a large language model. The deep learning large model has end-to-end characteristics and can directly generate reply data based on the user's input data without the help of functional components or other inputs outside the deep learning large model. In other words, the deep learning large model itself has a generation function. A large language model generally refers to a deep learning large model with billions or even hundreds of billions of parameters, which are usually trained on large-scale text data or data of other modalities. Large language models can be used for various natural language processing tasks, such as text generation, language translation, and question-answering systems.

[0055] The deep learning large model can, for example, adopt an N-layer Transformer network structure with an encoder (Encoder) and a decoder (Decoder), or a unified pre-trained language model (Unified pre-trained LanguageModel, UniLM) network structure. It is understandable that the deep learning large model can also be other neural network models based on the Transformer network structure, which is not limited here. The input and output of the deep learning large model are both composed of identifiers (token). Each identifier can correspond to a single word, character, word, or special symbol. The deep learning large model can be trained using pre-training tasks and generation tasks to have the above-mentioned generation function.

[0056] In step S204, in response to detecting a first interactive operation of the user on a key word entry and in response to determining that the large model has completed the generation of the term explanation, the term explanation is displayed.

[0057] According to some embodiments, the method for processing documents based on the large model may also include: after identifying the keyword entry, highlighting the keyword entry. The first interactive operation may include moving the cursor above the keyword entry, and the entry explanation may be displayed in the form of a card. By highlighting the keyword entry, the user can more intuitively know which entries have corresponding entry explanations. By moving the cursor above the keyword to trigger the display of the entry explanation, the user can more directly and conveniently obtain the corresponding entry explanation, reducing the operating cost. By presenting the entry explanation in the form of a card, it is convenient for the user to browse the target document and the entry explanation at the same time, further improving the user experience.

[0058] It should be noted that identifying the keyword, determining the relevant content of the keyword, and calling the big model are triggered after the user's first browsing operation is detected. Compared with triggering the above steps after detecting the user's first interactive operation on the keyword, it can effectively reduce the user's waiting time and improve the user experience.

[0059] In some embodiments, the large model can be asynchronously called to generate an entry explanation based on the relevant content. This approach can ensure that the system provides fast response while supporting concurrent processing of multiple users browsing multiple target documents, and can maintain the accuracy and real-time nature of the explanation content, thereby improving the user experience.

[0060] According to some embodiments, preset explanations corresponding to key words may be pre-stored in the entry database. These preset explanations may be cross-document and context-independent. The preset explanations may be generated using a large model, or may be manually edited, or may be generated by other means, which are not limited here.

[0061] like Figure 3 As shown, the method for processing documents based on the big model may also include: step S304, after identifying the keyword entry, obtaining a preset explanation from the entry database; and step S305, in response to detecting the user's first interactive operation on the keyword entry and in response to determining that the big model has not yet completed the generation of the entry explanation, displaying the preset explanation. It can be understood that Figure 3 The operations and effects of steps S301 to S303 and S306 in the above description can be referred to. Figure 2 The description of steps S201 to S204 in the process will not be repeated here.

[0062] Therefore, by pre-storing the preset explanations in the entry database and displaying the preset explanations when the large model has not yet completed the generation of the entry explanations, users can get immediate responses and avoid waiting too long. This method improves the smoothness of the user experience, and the preset explanations can also provide reliable information as backup content in emergency situations.

[0063] In some embodiments, the term explanation can be updated after the large model is generated to make the content more accurate and dynamic. In step S306, in response to detecting the user's first interactive operation on the key term and in response to determining that the large model has completed the generation of the term explanation, the term explanation can be used to replace the preset explanation and displayed.

[0064] According to some embodiments, the method for processing documents based on the large model may further include: after identifying the key words, determining the user interaction history. The user interaction history may include the words that the user has clicked, selected and / or viewed. Step S203 (step S303), calling the large model to generate a word interpretation library for the key words based on the relevant content may include: calling the large model to generate a word interpretation based on the relevant content and the user interaction history.

[0065] Therefore, by using the big model to analyze the user interaction history, the content of the entry explanation can be dynamically adjusted. The background big model generates personalized explanations based on these behavior models, making the entry content more in line with user needs. This not only improves the user experience, but also ensures that the content provided by the system remains highly relevant and real-time in different scenarios.

[0066] In some embodiments, the user's behavior patterns, preference information and other content can also be obtained, and the large model can be called to generate entry explanations based on relevant content, user interaction history, user behavior patterns and / or user preference information to further enhance the user experience.

[0067] According to some embodiments, Figure 3 As shown, the method for processing documents based on the big model may also include: step S307, in response to detecting the user's first interactive operation on the keyword entry, after the big model completes the generation of the entry explanation, the entry explanation is stored in the entry database and associated with the user.

[0068] Therefore, by associating and storing the explanations of the terms that users interact with, the system can identify the content that users are interested in, and provide customized explanations of the terms in subsequent interactions to achieve personalized recommendations. Storing the explanations of the terms that users actually interact with can save storage space in the term database and reduce the redundant accumulation of unnecessary large model call data. When the user browses the target document again, the system can quickly retrieve the previously generated term explanations from the term database, thereby improving the response speed and user experience, reducing the repeated calls of large models, and optimizing resource scheduling. At the same time, for key terms that have not generated interactions, the system can regenerate explanations as needed to maintain a certain degree of flexibility.

[0069] In some embodiments, for the same keyword entry, the entry database may store preset explanations that are not related to documents or users, and may store the entry explanation of the keyword entry at a specific position in a specific document (for example, generated by the large model after detecting the user's browsing operation), and may also store the entry explanation associated with a specific user (for example, generated by the large model based on the user interaction history or other user-related information after detecting the user's browsing operation). When a browsing operation on a target document including the keyword entry is subsequently detected, it may be determined whether to use these explanations in the entry database and which explanation to use for display according to the scenario.

[0070] According to some embodiments, Figure 3 As shown, the method for processing documents based on a large model may also include: step S308, in response to detecting a second browsing operation of the user on the target document, identifying key words in the target document; step S309, in response to determining that the generation time of the term explanation is less than a preset time, obtaining the term explanation associated with the user from the term database; and step S310, in response to detecting a second interactive operation of the user on the key words, displaying the term explanation.

[0071] After the term explanation has been stored and associated with the user, if the generation time of the term explanation is short, indicating that it is still timely, the generated explanation can be directly called during subsequent browsing, reducing the repeated calls of large models and the consumption of computing resources, thereby improving the overall performance and concurrent processing capabilities of the system.

[0072] In some embodiments, in response to determining that the generation time of the term explanation is not less than a preset time, the relevant content of the key term can be re-determined, and the large model can be re-called to generate an updated term explanation, thereby ensuring the timeliness and accuracy of the term explanation.

[0073] In other words, the system can dynamically adjust the way explanations are obtained based on multiple browsing and interactions of users. If the generation time of the stored entry explanation is long, the large model can be re-called to generate a more timely explanation; otherwise, the personalized explanations stored in the database are used first, flexibly responding to different situations and ensuring the consistency and real-time nature of the user experience.

[0074] In some embodiments, the second browsing operation may be similar to the first browsing operation, and the second interaction operation may be similar to the first interaction operation, which will not be described in detail herein.

[0075] According to some embodiments, Figure 4As shown, the method for processing documents based on the big model may include: step S407, in response to detecting a third interaction operation of multiple users on the same other terms other than the key terms in the target document, determining the other terms as key terms; and step S408, calling the big model to generate term explanations for the other terms, and storing the term explanations as preset explanations corresponding to the other terms in the term database. It can be understood that Figure 4 The operations and effects of steps S401 to S406 in the above description can be referred to. Figure 3 The description of steps S301 to S306 in the process will not be repeated here.

[0076] Thus, by detecting the interactive operations of multiple users on the same other terms in the document, the system can dynamically identify potential important terms and determine them as key terms. This method enables the system to automatically mine the content that users are interested in, and improves the accuracy and dynamics of key terms on the basis of manually predefined terms. This method can also continuously expand the term database, improve the coverage of term explanations, meet users' needs for different terms, and enhance the interpretation ability of documents.

[0077] In some embodiments, the third interactive operation may be a selection operation on other terms. A large number of user-selected contents may be considered as terms that the user is interested in, so determining them as key terms and generating corresponding preset explanations can improve the user experience.

[0078] In some embodiments, the front end for displaying documents may use a framework that supports dynamic content change and display, so that when the term recognition strategy or the term explanation content changes dynamically, it can be adjusted and changed in real time.

[0079] Figure 5A flowchart of the interaction between a user, a knowledge base service, and a card content service according to an embodiment of the present disclosure is shown. The knowledge base service 504 can provide a browsing service for a target document for a user 502. The card content service 506 can provide card content (term explanation). At 506, the user's document browsing operation 508 can trigger the knowledge base service 504 to call the keyword term identification and keyword term highlighting 510, and send the document's identification id, document version, and document content to the card content service 506. The card content service 506 can further call the keyword term acquisition interface 512, and return the identified keyword term identification id, term position, and preset explanation to 510. 510 can further send the document's identification id, document version, term identification id, term position, preset explanation, term context, and user identification id to the term update interface 514, and the term update interface 514 can further perform retrieval and call the large model to generate the term explanation. After the user triggers the interactive operation 516 on the keyword entry, the card query interface 518 may be called, and the card query interface 518 returns the card information (the term explanation or the preset explanation) for display.

[0080] According to another aspect of the present disclosure, a device for processing documents based on a large model is provided. Figure 6 As shown, the device 600 for processing documents based on the big model includes: a first identification unit 610, configured to identify a keyword entry in the target document in response to detecting a first browsing operation of the user on the target document; a first determination unit 620, configured to determine the relevant content of the keyword entry, the relevant content at least including the context information of the keyword entry in the target document; a first calling unit 630, configured to call the big model to generate a term explanation for the keyword entry based on the relevant content; and a first display unit 640, configured to display the term explanation in response to detecting a first interactive operation of the user on the keyword entry and in response to determining that the big model has completed the generation of the term explanation. It can be understood that the operations and effects of units 610-640 in the device 600 can be referred to respectively. Figure 2 Steps S201 to S204 in the above are not described in detail here.

[0081] According to some embodiments, the first determining unit may be configured to use the search enhancement generation system to search in the knowledge base based on the context information to obtain a search result. The relevant content may include the search result.

[0082] According to some embodiments, the apparatus for processing documents based on a large model may further include: a fourth display unit configured to highlight the keyword entry. The first interactive operation may include moving a cursor over the keyword entry, and displaying the entry explanation in the form of a card.

[0083] According to some embodiments, preset explanations corresponding to the key words are pre-stored in the entry database. The apparatus for processing documents based on the big model may also include: a first acquisition unit, configured to acquire the preset explanation from the entry database after identifying the key words; and a second display unit, configured to display the preset explanation in response to detecting a first interactive operation of the user on the key words and in response to determining that the big model has not yet completed the generation of the explanation of the entry.

[0084] According to some embodiments, the apparatus for processing documents based on the big model may further include: a second determining unit configured to determine a user interaction history, wherein the user interaction history includes entries clicked, selected and / or viewed by the user. The calling unit may be configured to call the big model to generate an entry interpretation based on relevant content and the user interaction history.

[0085] According to some embodiments, the device for processing documents based on the big model may also include: a term interpretation storage unit, which is configured to store the term interpretation in the term database in response to detecting a first interactive operation of the user on the keyword term after the big model completes the generation of the term interpretation.

[0086] According to some embodiments, the device for processing documents based on the large model may also include: a second identification unit, configured to identify key words in the target document in response to detecting a second browsing operation of the user on the target document; a second acquisition unit, configured to acquire the term explanation from the term database in response to determining that the generation time of the term explanation is less than a preset time; and a third display unit, configured to display the term explanation in response to detecting a second interactive operation of the user on the key words.

[0087] According to some embodiments, the device for processing documents based on the big model may also include: a third determination unit, configured to determine other terms as keyword terms in response to detecting a third interaction operation of multiple users on the same other terms other than the keyword terms in the target document; and a second calling unit, configured to call the big model to generate term interpretations for other terms, and store the term interpretations as preset interpretations corresponding to the other terms in the term database.

[0088] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0089] According to an embodiment of the present disclosure, an electronic device, a readable storage medium and a computer program product are also provided.

[0090] refer to Figure 7, a block diagram of an electronic device 700 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0091] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0092] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 can be any type of device that can input information to the electronic device 700. The input unit 706 can receive input digital or character information and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 707 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 708 can include but is not limited to a disk, an optical disk. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0093] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods, processes, and / or processes described above. For example, in some embodiments, these methods, processes, and / or processes may be implemented as computer software programs, which are tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the methods, processes, and / or processes described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform these methods, processes, and / or processes in any other appropriate manner (e.g., by means of firmware).

[0094] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0096] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0097] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0098] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0099] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0100] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0101] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A method for processing documents based on a large model, comprising: In response to detecting a first browsing operation of a user on a target document, identifying a keyword term in the target document; Determine relevant content of the keyword entry, the relevant content at least including context information of the keyword entry in the target document; Calling the big model to generate a term explanation for the key word based on the relevant content; as well as In response to detecting a first interactive operation of the user on the keyword term, and in response to determining that the large model has completed the generation of the term explanation, the term explanation is displayed.

2. The method according to claim 1, wherein: The entry database pre-stores a preset explanation corresponding to the key word entry, and the method further includes: After identifying the key word, obtaining the preset explanation from the word database; and In response to detecting a first interactive operation of the user on the keyword entry, and in response to determining that the large model has not yet completed the generation of the interpretation of the entry, the preset interpretation is displayed.

3. The method according to claim 2, further comprising: determining a user interaction history, the user interaction history including terms that the user has clicked, swiped, and / or viewed, The calling of the large model to generate an entry explanation for the key word entry based on the relevant content includes: The large model is called to generate the term explanation based on the relevant content and the user interaction history.

4. The method according to claim 3, further comprising: In response to detecting a first interactive operation of the user on the keyword entry, after the large model completes generating the interpretation of the entry, the interpretation of the entry is stored in the entry database and associated with the user.

5. The method according to claim 4, further comprising: In response to detecting a second browsing operation of the user on the target document, identifying the keyword term in the target document; In response to determining that the generation time of the term explanation is less than a preset time, acquiring the term explanation associated with the user from the term database; as well as In response to detecting a second interaction operation of the user on the keyword entry, the keyword explanation is displayed.

6. The method according to claim 2, further comprising: In response to detecting a third interaction operation of multiple users on the same other term other than the keyword term in the target document, determining the other term as a keyword term; as well as The large model is called to generate term explanations for the other terms, and the term explanations are stored in the term database as preset explanations corresponding to the other terms.

7. The method according to any one of claims 1 to 6, wherein: The relevant contents for determining the key words include: A search enhancement generation system is used to search in a knowledge base based on the context information to obtain a search result, and the related content includes the search result.

8. The method according to any one of claims 1 to 6, further comprising: The keyword item is highlighted. The first interactive operation includes moving the cursor above the keyword entry, and the entry explanation is displayed in the form of a card.

9. A device for processing documents based on a large model, comprising: A first recognition unit is configured to recognize a keyword entry in the target document in response to detecting a first browsing operation of the user on the target document; A first determining unit is configured to determine relevant content of the keyword entry, wherein the relevant content at least includes context information of the keyword entry in the target document; A first calling unit is configured to call the big model to generate a term explanation for the key word based on the relevant content; as well as The first display unit is configured to display the term explanation in response to detecting a first interactive operation of the user on the key term and in response to determining that the large model has completed the generation of the term explanation.

10. The device according to claim 9, wherein: The entry database pre-stores a preset explanation corresponding to the key word entry, and the device further includes: A first acquisition unit is configured to acquire the preset explanation from the term database after identifying the key term; and The second display unit is configured to display the preset explanation in response to detecting a first interactive operation of the user on the keyword entry and in response to determining that the large model has not yet completed the generation of the explanation of the entry.

11. The apparatus according to claim 10, further comprising: A second determining unit is configured to determine a user interaction history, wherein the user interaction history includes entries clicked, selected and / or viewed by the user, Wherein, the calling unit is configured to call the large model to generate the term explanation based on the relevant content and the user interaction history.

12. The apparatus according to claim 11, further comprising: The term explanation storage unit is configured to, in response to detecting a first interactive operation of the user on the key term, store the term explanation in the term database after the large model completes the generation of the term explanation.

13. The apparatus according to claim 12, further comprising: A second recognition unit is configured to recognize the keyword entry in the target document in response to detecting a second browsing operation of the user on the target document; A second acquisition unit is configured to acquire the term explanation from the term database in response to determining that the generation time of the term explanation is less than a preset time; as well as The third display unit is configured to display the term explanation in response to detecting a second interaction operation of the user on the key term.

14. The apparatus according to claim 10, further comprising: a third determining unit, configured to, in response to detecting a third interaction operation of multiple users on the same other word other than the keyword word in the target document, determine the other word as a keyword word; as well as The second calling unit is configured to call the large model to generate term explanations for the other terms, and store the term explanations as preset explanations corresponding to the other terms in the term database.

15. The device according to any one of claims 9 to 14, wherein: The first determination unit is configured to use a search enhancement generation system to search in a knowledge base based on the context information to obtain a search result, and the related content includes the search result.

16. The apparatus according to any one of claims 9 to 14, further comprising: The fourth display unit is configured to highlight the keyword item. The first interactive operation includes moving the cursor above the keyword entry, and the entry explanation is displayed in the form of a card.

17. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

19. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images