Data processing method and device of knowledge base, electronic equipment, storage medium and program product

Abstract

The invention provides a data processing method and device of a knowledge base, electronic equipment, a storage medium and a program product. The method comprises the steps that a knowledge base interface is displayed, and the knowledge base interface comprises at least one knowledge base; in response to an account creation operation in the knowledge base interface, a newly created first knowledge base account is displayed, and the first knowledge base account has the permission of releasing the shared knowledge base on the knowledge base platform; in response to a permission setting operation for the first knowledge base, under the condition that the permission setting operation sets the first knowledge base as the shared knowledge base, the first knowledge base belonging to the first knowledge base account is published in the knowledge base platform, and the first knowledge base is used for being searched and used in the knowledge base platform. According to the application, the shared knowledge base can be constructed through the knowledge base account to improve the sharing efficiency of the knowledge information.

Description

Technical Field

[0001] The present application relates to computer technology, and in particular to a data processing method, apparatus, electronic device, storage medium and program product for a knowledge base. Background Art

[0002] In the digital age where the information entropy increase effect is becoming increasingly significant, the massive heterogeneous data shows an exponential growth trend, and users are faced with the dual dilemmas of information overload and lack of relevant knowledge. Especially in vertical fields with high professional barriers, the unstructured characteristics of information resources and the discreteness of knowledge service supply form a significant information potential difference. In related technologies, in order to enable the information circulation in vertical fields, information sharing, video lectures and other methods are often used to achieve information circulation. However, the information output method is not efficient, which affects the convenience of users to obtain information in specific fields.

[0003] In related technologies, there is no good information sharing method that can improve the knowledge dissemination efficiency. Summary of the Invention

[0004] Embodiments of the present application provide a data processing method, apparatus, electronic device, computer-readable storage medium and computer program product for a knowledge base, which can build a shared knowledge base through a knowledge base account to improve the sharing efficiency of the knowledge base.

[0005] The technical solution of the embodiments of the present application is implemented as follows:

[0006] Embodiments of the present application provide a data processing method for a knowledge base, the method comprising:

[0007] Display a knowledge base interface, wherein the knowledge base interface includes at least one knowledge base;

[0008] In response to an account creation operation in the knowledge base interface, display a newly created first knowledge base account, wherein the first knowledge base account has the permission to publish and share the knowledge base on the knowledge base platform;

[0009] In response to a permission setting operation for the first knowledge base, in the case where the first knowledge base is set as the shared knowledge base in the permission setting operation, publish the first knowledge base belonging to the first knowledge base account on the knowledge base platform, wherein the first knowledge base is used to be searched and used on the knowledge base platform.

[0010] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object;

[0011] The method further comprises:

[0012] In response to a first transfer trigger operation for the first knowledge base account, when both the first instant messaging account and the second instant messaging account authorize the transfer, change the at least one first knowledge base from the first knowledge base account belonging to the first object to the second knowledge base account belonging to the second object, where the first object is the object to which the first instant messaging account belongs, and the second knowledge base account and the second instant messaging account belong to the second object.

[0013] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object;

[0014] The method further includes:

[0015] In response to a closing operation for the first knowledge base account, convert the type of the at least one first knowledge base from the shared knowledge base to a private knowledge base belonging to the first object, where the first object is the object to which the first instant messaging account belongs.

[0016] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object;

[0017] The method further includes:

[0018] Mark the knowledge base account as the first knowledge base account belonging to the first object;

[0019] In response to a merge trigger operation for the first knowledge base account and the second knowledge base account belonging to the second object, when both the first instant messaging account and the second instant messaging account authorize the merge, merge the at least one first knowledge base with at least one fourth knowledge base created based on the second knowledge base account to obtain at least one fifth knowledge base, where the second knowledge base account and the second instant messaging account belong to the same object, and the at least one fifth knowledge base is shared by the first knowledge base account and the second knowledge base account.

[0020] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object;

[0021] The method further includes:

[0022] In response to a second transfer trigger operation for the first knowledge base account, when both the first instant messaging account and the second instant messaging account authorize the transfer, change the first knowledge base account from the knowledge base account belonging to the first object to the knowledge base account belonging to the second object, where the first object is the object to which the first instant messaging account belongs, and the second object is the object to which the second instant messaging account belongs.

[0023] An embodiment of the present application provides a method for processing data of a knowledge base. The method includes:

[0024] Display a knowledge base interface, where the knowledge base interface includes a search control and an interaction control;

[0025] In response to an input operation on the search control, display at least one third knowledge base, where the type of the at least one third knowledge base is a shared knowledge base set based on a pre-created knowledge base account, and the at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keywords;

[0026] In response to an input operation on the interaction control, display the input first information, and

[0027] Display second information for replying to the first information, where the second information is generated based on materials related to the first information searched from the third knowledge base.

[0028] An embodiment of the present application provides a data processing device for a knowledge base, including:

[0029] A display module for displaying a knowledge base interface, where the knowledge base interface includes at least one knowledge base;

[0030] The display module is further configured to display a newly created first knowledge base account in response to an account creation operation in the knowledge base interface, where the first knowledge base account has the permission to publish a shared knowledge base on the knowledge base platform;

[0031] The display module is further configured to, in response to a permission setting operation for the first knowledge base, publish the first knowledge base belonging to the first knowledge base account on the knowledge base platform when the first knowledge base is set as the shared knowledge base in the permission setting operation, where the first knowledge base is used to be searched and used in the knowledge base platform.

[0032] An embodiment of the present application provides a data processing device for a knowledge base, including:

[0033] A display module for displaying a knowledge base interface, where the knowledge base interface includes a search control and an interaction control;

[0034] The display module is further configured to display at least one third knowledge base in response to an input operation on the search control, wherein the type of the at least one third knowledge base is a shared knowledge base set based on a pre-created knowledge base account, and the at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keywords;

[0035] The display module is further configured to display the input first information and display second information for replying to the first information in response to an input operation on the interaction control, wherein the second information is generated based on materials related to the first information searched from the third knowledge base.

[0036] An embodiment of the present application provides an electronic device, which includes:

[0037] A memory for storing computer-executable instructions or computer programs;

[0038] A processor for implementing the data processing method of the knowledge base provided by the embodiment of the present application when executing the computer-executable instructions or computer programs stored in the memory.

[0039] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions or computer programs, which are used to implement the data processing method of the knowledge base provided by the embodiment of the present application when being executed by a processor.

[0040] An embodiment of the present application provides a computer program product including a computer program or computer-executable instructions, and when the computer program or computer-executable instructions are executed by a processor, the data processing method of the knowledge base provided by the embodiment of the present application is implemented.

[0041] The embodiments of the present application have the following beneficial effects:

[0042] Set a first knowledge base account with the permission to publish a shared knowledge base on the knowledge base platform, and publish the shared knowledge base belonging to the first knowledge base account on the knowledge base platform. Establish a new form of knowledge dissemination through the knowledge base account, which is convenient for information sharing and use. The knowledge base account is dedicated to the creation and publication of shared knowledge bases. Compared with creating and publishing through the account logged in to the knowledge base interface, the risk isolation of the creation and publication permissions of the knowledge base is realized, and the security of the data in the knowledge base is improved. When the created knowledge base is set as a shared knowledge base, the knowledge base is published. The shared knowledge base is available for searching and using in the knowledge base platform, effectively protecting the data privacy of the knowledge base, and sharing knowledge data in the form of a knowledge base can improve the data sharing efficiency. Description of the Drawings

[0043] Figure 1 It is a schematic diagram of the application mode of the data processing method of the knowledge base provided by the embodiment of the present application;

[0044] Figure 2 It is a schematic diagram of the structure of the electronic device provided by the embodiment of the present application;

[0045] Figure 3A It is a schematic diagram of the first process of the data processing method of the knowledge base provided by the embodiment of the present application;

[0046] Figure 3B It is a schematic diagram of the second process of the data processing method of the knowledge base provided by the embodiment of the present application;

[0047] Figure 3C It is a schematic diagram of the third process of the data processing method of the knowledge base provided by the embodiment of the present application;

[0048] Figure 4 It is a schematic diagram of the fourth process of the data processing method of the knowledge base provided by the embodiment of the present application;

[0049] Figure 5A It is a schematic diagram of the first interface of the knowledge base provided by the embodiment of the present application;

[0050] Figure 5B It is a schematic diagram of the second interface of the knowledge base provided by the embodiment of the present application;

[0051] Figure 5C It is a schematic diagram of the third interface of the knowledge base provided by the embodiment of the present application;

[0052] Figure 5D It is a schematic diagram of the fourth interface of the knowledge base provided by the embodiment of the present application;

[0053] Figure 5E It is a schematic diagram of the fifth interface of the knowledge base provided by the embodiment of the present application;

[0054] Figure 6A It is a schematic diagram of the sixth interface of the knowledge base provided by the embodiment of the present application;

[0055] Figure 6B It is a schematic diagram of the seventh interface of the knowledge base provided by the embodiment of the present application;

[0056] Figure 6C It is a schematic diagram of the eighth interface of the knowledge base provided by the embodiment of the present application;

[0057] Figure 6D It is a schematic diagram of the ninth interface of the knowledge base provided by the embodiment of the present application;

[0058] Figure 6EIt is a schematic diagram of the second information provided by an embodiment of the present application;

[0059] Figure 7A It is the tenth schematic diagram of the knowledge base interface provided by an embodiment of the present application;

[0060] Figure 7B It is the eleventh schematic diagram of the knowledge base interface provided by an embodiment of the present application.

[0061] It should be noted that the above "first" and "second" are only used to distinguish different solutions, and do not represent the distinction of the quality of the solutions or the priority in the implementation process. Detailed implementation manners

[0062] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.

[0063] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0064] In the following description, the terms "first / second / third" are only used to distinguish similar objects, and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when allowed, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0065] It should be noted that the relevant data collection and processing in the present application (for example: data in the private knowledge base) should strictly comply with the requirements of relevant laws and regulations during actual application, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing behaviors within the scope authorized by laws and regulations and the personal information subject.

[0066] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other relevant parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of the module or unit.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are for the purpose of describing embodiments of this application only and are not intended to limit this application.

[0068] Before further elaborating on the embodiments of this application, the nouns and terms involved in the embodiments of this application are described, and the nouns and terms involved in the embodiments of this application are subject to the following explanations.

[0069] 1) Knowledge base: It is a structured and shareable knowledge collection. The knowledge base stores and manages various types of knowledge such as information, experience, rules, and cases in an orderly manner so that users can quickly and accurately retrieve and use this knowledge. For example: In an enterprise, the knowledge base can contain product materials, technical documents, frequently asked questions, etc. to help employees better complete their work; in the field of education, the knowledge base can be a collection of teaching resources, academic literature, etc. to assist students in learning and teachers in teaching. The types of knowledge bases include private knowledge bases and shared knowledge bases. A private knowledge base is only viewable by the creator of the knowledge base and the users shared by the creator. A shared knowledge base is published on a knowledge base platform and can be accessed jointly by multiple users, the entire organization, or even external personnel.

[0070] 2) Knowledge base platform (also known as the knowledge base square): It is an information system used to create, store, manage, and share knowledge. The knowledge base platform provides users with functions such as uploading files, or collecting content during the retrieval and reading process, and publishing shared knowledge bases.

[0071] 3) Knowledge base account (abbreviated as knowledge number): An account created based on an instant messaging account in a knowledge base application, with the permission to publish shared knowledge bases on the knowledge base platform.

[0072] 4) Retrieval-Augmented Generation (RAG): It is a model that combines retrieval and generation technologies. Retrieval-Augmented Generation generates answers or content by referring to information from an external knowledge base, has strong interpretability and customization capabilities, and is applicable to multiple natural language processing tasks such as question-and-answer systems, document generation, and intelligent assistants. Retrieval-Augmented Generation combines a language model and information retrieval technology. When generating text or answering questions, relevant information is retrieved from a large collection of documents, and this retrieved information is used to guide the text generation process of the language model, thereby improving the quality and accuracy of predictions.

[0073] 5) Hierarchical Navigable Small Word (HNSW) algorithm: It is an approximate nearest neighbor search (ANN) method based on graph structure, which accelerates the search process through the locality principle and hierarchical structure, and is applicable to scenarios with high requirements for accuracy and search efficiency.

[0074] 6) Vector indexes: It is a data structure that stores and organizes the vectors generated by text embedding, used to quickly query similar vectors. The purpose of vector indexes is to improve the retrieval efficiency and can efficiently find other vectors similar to the query vector.

[0075] 7) Full-text indexes: It is an index type specifically used to optimize the retrieval of text data, especially suitable for query requirements for fields containing a large amount of text (such as article content, comments, blogs, etc.). It supports fast keyword matching queries, can find one or more words in the text, and return relevant results. Full-text indexes are often applied in search engines and text analysis systems.

[0076] In the digital age when the information entropy increase effect is becoming increasingly significant, the massive heterogeneous data shows an exponential growth trend, and users are faced with the dual dilemmas of information overload and lack of knowledge acquisition channels. Especially in vertical fields with high professional barriers (such as clinical medicine, microelectronics science and engineering, biotechnology, etc.), the unstructured characteristics of information resources and the discreteness of knowledge service supply form a significant information potential difference.

[0077] In related technologies, knowledge bases can help manage massive unstructured documents and data, enabling all knowledge to be queried and applied in natural language. However, knowledge bases can only be applied within a specific range, and the lack of information sharing hinders the knowledge exchange and dissemination within the industry. It is difficult for researchers and practitioners to quickly understand the latest research results and practical experiences, restricting the collision of innovative thinking and the emergence of new theories and new technologies.

[0078] The embodiments of this application provide a data processing method for a knowledge base, a data processing device for a knowledge base, an electronic device, a computer-readable storage medium, and a computer program product, which can improve the sharing efficiency of knowledge information by constructing a shared knowledge base through a knowledge base account.

[0079] The following describes the exemplary applications of the electronic device provided in the embodiments of the present application. The electronic device provided in the embodiments of the present application may implement a terminal device, such as various types of terminals including a laptop computer, a tablet computer, a desktop computer, a set-top box, a smart TV, a vehicle-mounted terminal, a virtual reality (VR) device, an augmented reality (AR) device, etc., or may also be implemented as a server. Below, the exemplary applications when the electronic device is implemented as a terminal device or a server will be described.

[0080] Referring to Figure 1 , Figure 1 is a schematic diagram of the application mode of the data processing method of the knowledge base provided in the embodiments of the present application; for example, Figure 1 involves a first terminal device 400, a server 200, a network 300, and a database 500. The first terminal device 400 is connected to the server 200 through the network 300. The network 300 may be a wide area network, a local area network, or a combination of the two.

[0081] An application program based on artificial intelligence is installed in the first terminal device 400. For example, it can be called a smart workbench, which is an efficiency tool integrating search, reading, and collaboration, and its functions cover knowledge acquisition, information processing, and content output. For example, specifically, it may include: knowledge base management, content generation, artificial intelligence (AI) question answering, multi-modal text creation, image generation, writing assistance, multi-language translation, automatic generation of mind maps, and intelligent arrangement of outlines, etc. The smart workbench can access various artificial intelligence models and support users to select.

[0082] The server 200 may be the background server of the application program, and the database 500 may be the database of the application program, storing a large amount of knowledge data, which will be explained based on the above examples.

[0083] In some embodiments, the user can log in to the application program based on artificial intelligence through an instant messaging account. In the case of logging in to the application program, the user creates a first knowledge base account through the knowledge base interface 101 displayed in the first terminal device 400. The knowledge base interface 101 is a tab page embedded in the knowledge base platform of the application program based on artificial intelligence. The user creates the first knowledge base account after reading and agreeing to the "Operation Specifications" and the "User Agreement". In response to the creation of the first knowledge base account, in the knowledge base interface 102, the already created knowledge base "LLM Papers" (Large Language Model Papers) is set as a shared knowledge base based on the first knowledge base account. The shared knowledge base is published to the knowledge base platform, and other users can search, browse, and use the content of the knowledge base "LLM Papers" through other terminal devices. Through the above method, the sharing channels of knowledge are enriched and the sharing efficiency is improved.

[0084] In some embodiments, the data processing method of the knowledge base of the embodiments of the present application can also be applied to the following application scenarios:

[0085] 1. Literature query: Technical personnel can create a knowledge base account based on the data processing method of the knowledge base of the embodiments of the present application, and publish and share the knowledge base based on the knowledge base account. Ordinary users can log in to the intelligent work platform including the knowledge base platform service based on their instant messaging accounts, and search for relevant literature materials in the knowledge base platform based on their instant messaging accounts for learning.

[0086] 2. Intelligent question-answering system: The first user can create a knowledge base account based on the data processing method of the knowledge base of the embodiments of the present application, and publish and share the knowledge base based on the knowledge base account. For example, share travel guides, photography tutorials, or knowledge in a specific field, such as medical-related knowledge, biotechnology, etc. The second user can log in to the intelligent work platform including the knowledge base platform service based on their instant messaging accounts, select at least one interested knowledge base in the knowledge base platform to ask questions, and the knowledge base platform generates answers based on the content of the knowledge base that the user is interested in to meet the user's needs.

[0087] 3. Knowledge base management: Users can create a knowledge base account based on the data processing method of the knowledge base of the embodiments of the present application, create and edit the knowledge base based on the knowledge base account. Based on the knowledge base account, the knowledge base can also be set as a shared knowledge base or a private knowledge base. The shared knowledge base can be browsed and used by users who use the knowledge base platform, and the private knowledge base of the knowledge base account is only for the current knowledge base account.

[0088] In some embodiments, the server 200 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, which are not limited in the embodiments of the present application.

[0089] The embodiments of the present application can be implemented through database technology. A database, in short, can be regarded as a place for storing electronic files in an electronic filing cabinet, and users can perform operations such as adding, querying, updating, and deleting data in the files. The so-called "database" is a data set stored together in a certain way, shared by multiple users, with as little redundancy as possible, and independent of application programs.

[0090] A database management system (DBMS) is a computer software system designed to manage databases and generally has basic functions such as storage, retrieval, security, backup, etc. Database management systems can be classified according to the database models they support, such as relational, XML (Extensible Markup Language); or according to the types of computers they support, such as server clusters, mobile phones; or according to the query languages they use, such as Structured Query Language (SQL), XQuery; or according to the key performance metrics, such as maximum scale, highest running speed; or other classification methods. Regardless of the classification method used, some DBMSs can cross categories. For example, they can support multiple query languages simultaneously.

[0091] Embodiments of this application can also be implemented through cloud technology. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool, be used on demand, and is flexible and convenient. Cloud computing technology will become an important support. The back-end services of the technical network system require a large amount of computing and storage resources, such as video websites, picture-based websites, and more portal websites. With the high development and application of the Internet industry, and the promotion of demands such as search services, social networks, mobile commerce, and open collaboration, in the future, each item may have its own hash code identification mark and needs to be transmitted to the back-end system for logical processing. Data at different levels will be processed separately, and various industry data requires a powerful system back-end support, which can only be achieved through cloud computing.

[0092] See Figure 2 , Figure 2 is a schematic structural diagram of an electronic device provided by an embodiment of this application. The electronic device can be Figure 1 the terminal device 400 shown in Figure 2 The terminal device 400 shown in the figure includes: at least one processor 410, a memory 450, at least one network interface 420, and a user interface 430. Each component in the terminal device 400 is coupled together through a bus system 440. It can be understood that the bus system 440 is used to realize the connection and communication between these components. In addition to including a data bus, the bus system 440 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clear illustration, in Figure 2 all kinds of buses are labeled as the bus system 440.

[0093] Processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0094] The user interface 430 includes one or more output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0095] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0096] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0097] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0098] The operating system 451 includes system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic businesses and process hardware-based tasks.

[0099] The network communication module 452 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 420. Exemplary network interfaces 420 include: Bluetooth, Wireless LAN (WiFi), and Universal Serial Bus (USB).

[0100] A presentation module 453 for enabling presentation of information (e.g., a user interface for operating a peripheral device and displaying content and information) via one or more output devices 431 associated with the user interface 430 (e.g., a display screen, a speaker, etc.).

[0101] An input processing module 454 for detecting and translating one or more user inputs or interactions from one of one or more input devices 432.

[0102] In some embodiments, the device provided by the embodiments of the present application can be implemented in software. Figure 2 A data processing device 455 of a knowledge base stored in the memory 450 is shown, which can be software in the form of a program and a plug-in, etc., including the following software modules: a display module 4551, a search module 4552. These modules are logical, so they can be combined arbitrarily or further split according to the implemented functions. In Figure 2 For the convenience of expression, all the above modules are shown at once, but it should not be considered that the data processing device 455 of the knowledge base excludes the embodiment that may only include the display module 4551. The functions of each module will be described below.

[0103] In some embodiments, the terminal device or the server can implement the data processing method of the knowledge base provided by the embodiments of the present application by running a computer program. For example, the computer-executable instructions can be commands at the microprogram level, machine instructions or software instructions. The computer program can be a native program or a software module in the operating system; it can be a local (Native) application (APPlication, APP), that is, a program that needs to be installed in the operating system to run, such as an intelligent workbench APP or an instant messaging APP; it can also be a small program that can be embedded in any APP, that is, a program that only needs to be downloaded to the browser environment to run. In short, the above computer-executable instructions can be instructions in any form, and the above computer program can be an application program, a module or a plug-in in any form.

[0104] The data processing method of the knowledge base provided by the embodiments of the present application will be described in combination with the exemplary applications and implementations of the terminal device provided by the embodiments of the present application.

[0105] Next, the data processing method of the knowledge base provided by the embodiments of the present application will be described. As before, the electronic device for implementing the data processing method of the knowledge base of the embodiments of the present application can be a terminal device, a server, or a combination of the two. Therefore, the execution subject of each step will not be repeated hereinafter.

[0106] It should be noted that in the example of data processing in the knowledge base described below, text data is taken as an example for illustration. Those skilled in the art can apply the data processing method of the knowledge base provided in the embodiments of the present application to the processing of other types of data according to the understanding of the following text, such as: pictures, videos, and audios.

[0107] See Figure 3A , Figure 3A is a schematic flowchart of the data processing method of the knowledge base provided in the embodiments of the present application, and will be described in conjunction with Figure 3A the steps shown. Figure 3A The execution subject of the step is Figure 1 the first terminal device 400 in

[0108] In step 301, display the knowledge base interface.

[0109] Here, the knowledge base interface includes at least one knowledge base.

[0110] Exemplarily, the knowledge base interface is an interface located in the intelligent workbench application. The knowledge base interface can be used to browse the related functions of the knowledge base, including the creation, editing, search, and use of the knowledge base. The intelligent workbench application is logged in based on an instant messaging account, and the instant messaging account is pre-created before using the intelligent workbench application. The knowledge base interface of the shared knowledge base automatically subscribed by the intelligent workbench is the knowledge base tab page of the intelligent workbench program, and at least one knowledge base is displayed in the form of a knowledge base list in the knowledge base tab page. The intelligent workbench program also includes a knowledge base square tab page, and the knowledge base square tab page is used to display the publicly shared knowledge bases.

[0111] Refer to 5A, Figure 5A is the first schematic diagram of the knowledge base interface provided in the embodiments of the present application. Refer to Figure 5A , Figure 5A is the first schematic diagram of the knowledge base interface provided in the embodiments of the present application; the knowledge base interface 501A is the knowledge base tab page in the intelligent workbench application, and the knowledge base interface 501A includes a knowledge number creation control 502A and a knowledge base list 503A. The knowledge base list includes shared knowledge bases and personal knowledge bases (private knowledge bases). The shared knowledge bases include those created by the first knowledge base account and those joined (subscribed) by the first knowledge base account.

[0112] In step 302, in response to an account creation operation in the knowledge base interface, display the newly created first knowledge base account.

[0113] Here, the first knowledge base account has the permission to publish and share knowledge bases on the knowledge base platform.

[0114] Exemplarily, in response to an account creation operation in the knowledge base interface, it is implemented as follows: for a triggering operation of the knowledge number creation control, display a knowledge number creation interface; in response to an account creation operation in the knowledge number creation interface, display the newly created first knowledge base account.

[0115] In some embodiments, step 302 can be implemented as follows: in response to a triggering operation of the knowledge number creation control in the knowledge base interface, display a knowledge number creation interface; in response to an account attribute setting operation in the knowledge number creation interface, display the first knowledge base account created based on the input account attributes (user avatar or user name).

[0116] Exemplarily, the triggering operation of the knowledge number creation control in the knowledge base interface can be any one of the following operations: a triggering operation set by the user; in the case of not having a knowledge base account, a triggering operation for the creation control of the shared knowledge base. The knowledge number creation interface is an interface for inputting information such as user name and user avatar to create a knowledge base account. Continuing to refer to Figure 5A , the user can input a user name and set a user avatar in the knowledge number creation control 502A. In the case where the user has selected to confirm "I have read and agreed to the 'Operation Specifications' and 'User Agreement'", in response to a triggering operation of the "Create" button in the knowledge number creation control 502A, create a knowledge base account based on the user's name, instant messaging account, and user avatar.

[0117] In some embodiments, step 302 can be implemented as follows:

[0118] In response to the created private knowledge base in the knowledge base interface meeting a preset public condition, display a prompt message for creating a knowledge base account, where the prompt message for creating a knowledge base account includes a knowledge number creation control; in response to a confirmation operation for the prompt message for creating a knowledge base account, display a knowledge number creation interface; in response to an account attribute setting operation in the knowledge number creation interface, display the first knowledge base account created based on the input account attributes (user avatar or user name).

[0119] Exemplarily, the principle of creating a knowledge base account has been explained above and will not be elaborated here. The preset public condition is a standard used to characterize that the content of the knowledge base can be made public. Referring to Figure 6A , Figure 6A is the sixth schematic diagram of the knowledge base interface provided by the embodiments of the present application. In the knowledge base interface 601A, the content of the prompt message 602A is "The knowledge base 'Travel Guide' has met the public condition. Do you want to publish it as a shared knowledge base?" to prompt the user that the knowledge base 'Travel Guide' during the creation process that has not been published to the knowledge base platform can be published to the knowledge base platform.

[0120] In some embodiments, the preset public conditions include at least one of the following:

[0121] Condition 1: The created private knowledge base is a private knowledge base in a specific field, and the number of questions for the specific field is greater than or equal to the question count threshold.

[0122] For example, the number of questions for the specific field can be obtained in the following way: Obtain the average value of the number of questions for the knowledge base in the specific field in the knowledge base platform within a preset time period. The question count threshold can be determined in the following way: Obtain the average value of the number of questions for the knowledge bases in all fields in the knowledge base platform, and multiply the average value of the number of questions for the knowledge bases in all fields by a preset calibration coefficient to obtain the question count threshold.

[0123] Condition 2: The number of title levels of the created private knowledge base is greater than or equal to the title level count threshold.

[0124] For example, the title level is the level in the document structure, which is used to organize the logical relationship and hierarchy of the content. If the number of title levels of the private knowledge base is greater than or equal to the title level count threshold, it means that the content in the private knowledge base has a certain logical relationship and scale, and can be published as a shared knowledge base. The title level count threshold can be set according to the actual application scenario, or the title level count threshold can be determined in the following way: Obtain the average value of the number of title levels of all shared knowledge bases in the knowledge base platform, and multiply the average value of the number of title levels by a preset calibration coefficient to obtain the title level count threshold.

[0125] For example, the number of title levels, tag coverage rate, and version iteration times are indicators used to evaluate the content integrity of the knowledge base. When at least one of the above indicators reaches the corresponding threshold, it means that the content of the private knowledge base is complete and can be used as a shared knowledge base. If the user wants to publish a public shared knowledge base, the user needs to apply for a knowledge base account, and a prompt message for creating a knowledge base account will be displayed.

[0126] Condition 3: The tag coverage rate of the created private knowledge base is greater than or equal to the coverage rate threshold.

[0127] For example, the tag coverage rate refers to the proportion of the number of data items with the tag in a knowledge base to the total number of data items. The coverage rate threshold can be set according to actual needs. Assume that 80% of the documents in the private knowledge base have been assigned tags, then it is determined that the private knowledge base can be converted into a shared knowledge base, and the user is prompted to create a knowledge base account. The tags of the document are used to describe the content or attributes of the document. For example, the title of a certain document is "Photography Appreciation", and the tags of "Photography Appreciation" include: the tag "Photography" indicating the field to which the document belongs, and the tag "Landscape Photography Tutorial" indicating the content of the document.

[0128] Condition 4: The version iteration count of the created private knowledge base is greater than or equal to the iteration count threshold.

[0129] Exemplarily, the version iteration count refers to the number of iterations performed during the knowledge base editing process, starting from the initial version and each time the software version is updated or improved. The iteration count reflects the number of updates the knowledge base has undergone from the first version to the current version. Assume that the version iteration count in the private knowledge base is greater than 50 times, then it is determined that the private knowledge base can be converted into a shared knowledge base, and the user is prompted to create a knowledge base account.

[0130] In the embodiments of the present application, according to the conditions satisfied by the private knowledge base, the user is prompted to create a knowledge base account to publish the shared knowledge base, which can improve the knowledge transfer efficiency. When the user creates an account and publishes the shared knowledge base, the knowledge resources on the platform will become more diverse.

[0131] In step 303, in response to a permission setting operation for the first knowledge base, when the permission setting operation sets the type of the first knowledge base to a shared knowledge base, the first knowledge base belonging to the first knowledge base account is published in the knowledge base platform.

[0132] Here, the first knowledge base is used to be searched and used in the knowledge base platform.

[0133] Exemplarily, the first knowledge base being searched and used in the knowledge base platform means that any knowledge base account and any instant messaging account logged in to the intelligent workbench can search for the first knowledge base and use it in functions such as AI Q&A and writing assistance. The prerequisite for using the first knowledge base in the knowledge base platform is that the first knowledge base is added to the shared knowledge base list, indicating that the instant messaging account or the knowledge base account has subscribed to the first knowledge base.

[0134] In the embodiments of the present application, granting the publishing permission of the shared knowledge base to the knowledge base account can encourage more users to actively create and publish knowledge bases, thereby increasing the knowledge resources on the knowledge base platform and making the content of the knowledge base platform more diverse. The shared knowledge base is used to be searched and used in the knowledge base platform, which can improve the data sharing efficiency.

[0135] In some embodiments, when the permission setting operation sets the type of the first knowledge base to a private knowledge base, a graphic code is displayed, where the graphic code carries the identifier of the first knowledge base; in response to a sharing operation for the graphic code, the graphic code is sent to a second instant messaging account, and when the graphic code is scanned by the second instant messaging account, the first knowledge base is added to the private knowledge base list of the second instant messaging account.

[0136] Exemplarily, the graphic code may be a bar code or a two-dimensional code, and both the private knowledge base and the shared knowledge base can be shared with other users through the graphic code. Refer to Figure 5B , Figure 5B is the second schematic diagram of the knowledge base interface provided by the embodiments of the present application; in the knowledge base interface 501B, the user creates a "travel guide" knowledge base and adds multiple documents of photographic appreciation and landscape photography to the "travel guide" knowledge base. Refer to Figure 5C , Figure 5C is the third schematic diagram of the knowledge base interface provided by the embodiments of the present application; a permission setting control 502C is displayed in the knowledge base interface 501C. When the knowledge base is published, different permissions can be set, including: Default: It can be shared through the two-dimensional code generated by the link, but cannot be discovered in the square (knowledge base platform). The default permission in the permission setting control 502C means that the knowledge base can be shared through the link two-dimensional code, but cannot be searched by other instant messaging accounts or knowledge base accounts in the knowledge base platform.

[0137] In the embodiments of the present application, sharing the private knowledge base through the graphic code enables the content of the private knowledge base to be spread to other users; sharing the private knowledge base through the graphic code only enables a specific group to view the content of the private knowledge base, maintaining the confidentiality of the content of the private knowledge base.

[0138] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; in the case where the type of the first knowledge base is set to a private knowledge base during the permission setting operation, the permission of the first knowledge base is set to be visible only to the first instant messaging account.

[0139] Exemplarily, the permission of the first knowledge base is set to be visible only to the first instant messaging account, that is, the first knowledge base will be displayed and used only when logging in to the intelligent work platform based on the first instant messaging account. Continue to refer to Figure 5C , "Converted to private, the knowledge base is only visible to oneself" indicates that the permission of the first knowledge base is set to be visible only to the first instant messaging account.

[0140] In the embodiments of the present application, setting a private knowledge base that can only be browsed when the first instant messaging account logs in to the intelligent work platform improves the confidentiality of information and is convenient for users to store private files.

[0141] In some embodiments, after step 302, a prompt message for creating a knowledge base in a specific field is displayed; in response to a trigger operation on the knowledge base creation control, a first knowledge base created based on the first knowledge base account and belonging to the specific field is displayed.

[0142] Here, the prompt message for creating a knowledge base in a specific field includes a knowledge base creation control.

[0143] Exemplarily, the specific field satisfies at least one of the following conditions:

[0144] Condition 1: The number of knowledge bases in the specific field is less than the knowledge base number threshold.

[0145] Exemplarily, the specific field can be determined according to the actual application scenario. Suppose the specific field is the biotechnology field, and the prompt message content is "Relevant knowledge is scarce. Do you want to create a knowledge base for the biotechnology field?" The above prompt message indicates that the number of knowledge bases in the specific field is less than the knowledge base number threshold, and then a prompt message is sent to the user to promote the user to build a relevant knowledge base.

[0146] Condition 2: The similarity between the features of the specific field and the features of the first instant messaging account corresponding to the first knowledge base account is greater than the first similarity threshold.

[0147] Exemplarily, the features of the first instant messaging account can be extracted through the account information of the first instant messaging account and the content of the created knowledge base to obtain the features that can represent the interest field of the first instant messaging account corresponding to the first knowledge base account. Suppose the similarity between the features of the specific field and the features of the interest field is greater than the first similarity threshold, which indicates that the user is interested in this field, and the user can be advised to build a knowledge base for this field. Refer to Figure 6B , Figure 6B FIG. 18 is the seventh schematic diagram of the knowledge base interface provided by the embodiment of the present application. The knowledge base interface 601B includes a prompt message 602B, and the content of the prompt message 602B is "Do you want to create a knowledge base for the photography field?" There is a large amount of photography-related content in the travel guide knowledge base created by the user, indicating that the user is interested in photography-related content, and then a prompt message is sent to promote the user to create a photography-related knowledge base.

[0148] In the embodiment of the present application, the user is prompted to build a knowledge base for a specific field through a prompt message. Prompting to build a knowledge base for a specific field can guide the user to comprehensively sort out and integrate the knowledge in this field, and enrich the knowledge reserve in the knowledge base platform.

[0149] In some embodiments, after displaying the first knowledge base created based on the first knowledge base account and belonging to the specific field, in response to a trigger operation for searching for materials for the first knowledge base, a prompt message for adding materials and at least one material are displayed, where at least one material is searched from the network or locally based on the name and tags of the first knowledge base, and the prompt message for adding materials is used to prompt that at least one material matches the first knowledge base; in response to a confirmation operation for the prompt message, at least one material is added to the first knowledge base.

[0150] Exemplarily, the prompt message includes a button for indicating confirmation of addition, and the confirmation operation may be a triggering operation on the button. Refer to Figure 6C , Figure 6C FIG. 8 is a schematic diagram of the knowledge base interface provided by an embodiment of the present application. Continuing with the above Figure 6B as an example, after the user confirms the creation of a knowledge base in the photography field, create Figure 6C the photography guide knowledge base in the knowledge base interface 601C. In the knowledge base interface 601C, display the materials obtained by searching the network or locally according to the name and tags of the first knowledge base. For example: documents such as Pet Photography Special Issue.doc, How to Choose a Camera for Beginners.doc, Photography Skills That Even Beginners Can Learn.doc in the search results 602C. The content of the prompt message 603C is "Do you want to add relevant documents?", which is used to prompt that at least one material matches the first knowledge base. At least one of the materials, Pet Photography Special Issue.doc and How to Choose a Camera for Beginners.doc, is displayed in a selected state. In response to the triggering operation on the option "Yes" in the prompt message 603C, add Pet Photography Special Issue.doc and How to Choose a Camera for Beginners.doc to the photography guide knowledge base.

[0151] In the embodiments of the present application, by automatically searching for materials related to the knowledge base, the construction efficiency of the knowledge base can be improved. By searching for materials, multiple different types of data sources can be integrated, including but not limited to web search engines, professional databases, academic literature databases, social media, etc. This enables the knowledge base to obtain more extensive and comprehensive materials.

[0152] In some embodiments, after displaying the first knowledge base created based on the first knowledge base account and belonging to a specific field, in response to a triggering operation for searching for materials of the first knowledge base, display a prompt message for adding materials and at least one material, where at least one material is searched from the network or the local space based on the characteristics of the first knowledge base account, and the similarity between the characteristics of at least one material and the characteristics of the first knowledge base account is less than a second similarity threshold; in response to the confirmation operation for the prompt message, add at least one material to the first knowledge base.

[0153] Exemplarily, the similarity between the characteristics of at least one material and the characteristics of the first knowledge base account is less than the second similarity threshold, indicating that the relevance of at least one material to the fields already involved in the first knowledge base account is not high. That is, the repetition rate of at least one material and the materials in the knowledge base already created by the first knowledge base account is not high. Then, at least one material can be added to the first knowledge base as the content of the newly created knowledge base.

[0154] In the embodiments of the present application, by obtaining materials whose similarity to the features of the first knowledge base account is less than the second similarity threshold, the duplication rate of materials in the knowledge base can be reduced. Reducing duplicate materials can reduce the storage space requirements of the knowledge base, avoid a large amount of redundant information in the knowledge base, and make the content in the knowledge base more refined and valuable. Each piece of material can contribute unique knowledge to the knowledge base, thereby improving the overall knowledge content and professionalism of the knowledge base.

[0155] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; when the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; in response to a permission switching operation for the first knowledge base, the type of the first knowledge base is switched from a shared knowledge base to a private knowledge base, where the private knowledge base is only searchable or usable by the following accounts: the first instant messaging account, and the second instant messaging account that scans the graphic code shared by the first instant messaging account.

[0156] Exemplarily, the permission switching operation refers to the user manually triggering the switching of the type of the first knowledge base, converting the type from a shared knowledge base to a private knowledge base, and the private knowledge base is only usable by the first instant messaging account or can be shared with the second instant messaging account based on the graphic code. The second instant messaging account can be an account with a corresponding second knowledge base account or an instant messaging account without a created second knowledge base account. If the second instant messaging account has a corresponding knowledge base account, when the second instant messaging account scans the graphic code and adds the first knowledge base to the private knowledge base, the second instant messaging account corresponding to the second knowledge base can also be given the permission to edit the first knowledge base.

[0157] Exemplarily, in terms of storage space, the difference between the shared knowledge base and the private knowledge base is that the space occupied by the private knowledge base is the personal cloud storage space owned by the first instant messaging account on the intelligent work platform, and the space occupied by the shared knowledge base is the public cloud storage space of the knowledge base platform. This is because, for the shared knowledge base, multiple knowledge base accounts or instant messaging accounts access the same knowledge base, and separate storage space is not allocated for each account, thus saving storage space; for the private knowledge base, since the private knowledge base is unique to the knowledge base account or instant messaging account, it occupies the storage space of the account.

[0158] When the type of the first knowledge base is switched from a shared knowledge base to a private knowledge base, the first knowledge base is stored in the personal cloud storage space owned by the first instant messaging account on the intelligent work platform; conversely, when the type of the first knowledge base is switched from a private knowledge base to a shared knowledge base, the space occupied by the first knowledge base in the personal cloud storage space is released, and the first knowledge base is stored in the public cloud storage space of the knowledge base platform.

[0159] In the embodiments of the present application, a function of switching the permission of the first knowledge base is provided, which can switch the type of the first knowledge base from a shared knowledge base to a private knowledge base, can improve the security of the content in the first knowledge base, protect user privacy, and the conversion of the shared knowledge base to a private knowledge base also makes the first knowledge base no longer occupy the shared storage space, saving the shared storage space.

[0160] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; when the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; in response to the first knowledge base meeting the first type switching condition, the type of the first knowledge base is switched from a shared knowledge base to a private knowledge base, where the private knowledge base is only available for search or use by the following accounts: the first instant messaging account, and the second instant messaging account that scans the graphic code shared by the first instant messaging account.

[0161] Exemplarily, when the first knowledge base meets the first type switching condition, the user can be prompted to convert the first knowledge base from a shared knowledge base to a private knowledge base. Refer to Figure 6D , Figure 6D is the ninth schematic diagram of the knowledge base interface provided by the embodiments of the present application. Assume that the travel guide knowledge base in the knowledge base interface 601D meets the first type switching condition, and the prompt message 602D "Not used for a long time. Do you want to add the travel guide as a personal knowledge base?" is displayed, indicating that the content in the travel guide knowledge base has not been browsed by users within the preset time period, and prompting the creator user that it can be converted into a private knowledge base.

[0162] In some embodiments, the first type switching condition includes at least one of the following:

[0163] Condition 1: The usage rate of the first knowledge base within a preset time period is lower than the usage rate threshold.

[0164] Exemplarily, the usage can be represented by the following: user editing behavior, user browsing behavior, storage space usage, and network traffic usage. The preset time period can be set according to the actual application scenario. Taking the user editing behavior in the above text as an example, the usage rate is the ratio of the following parameters within the preset time period: the number of user editing behaviors of the first knowledge base by users who have subscribed to the first knowledge base, and the number of editing behaviors of all knowledge bases by users who have subscribed to the first knowledge base. Taking the storage space usage as an example, the usage rate is the ratio between the storage space occupied by the first knowledge base and the upper limit of the storage space pre-allocated to the first knowledge base by the knowledge base platform. Taking the network traffic usage as an example, the usage rate is the ratio between the network traffic consumed by users using the first knowledge base and the preset network traffic.

[0165] Condition 2: The proportion of data with the exclusive identifier of the creator in the first knowledge base is greater than the first proportion threshold.

[0166] Exemplarily, the types of the exclusive identifier of the creator include but are not limited to: personal watermark, customized template, and personal information. For example: More than 60% of the data in the first knowledge base contains the personal watermark of the creator, and more than 50% of the exclusive labels strongly related to the creator's personal project appear in the knowledge base tag system.

[0167] Condition 3: The proportion of duplicate data in the first knowledge base is greater than the second proportion threshold.

[0168] Exemplarily, the proportion of duplicate data is the ratio between the duplicate data and all the data in the first knowledge base, and the second proportion threshold can be set according to the actual application scenario. Assuming that the proportion of duplicate data is greater than 30%, it is determined that the first knowledge base can be converted into a private knowledge base.

[0169] Condition 4: There is third-party authorized data in the first knowledge base and the authorization agreement prohibits conversion to private.

[0170] Exemplarily, the meaning that the authorization agreement prohibits conversion to private means that in an authorization agreement, it is clearly stipulated that the licensee shall not sublicense the obtained authorization rights and obligations to a third party. That is, the first user is the licensee, and the third-party authorized data is stipulated as not being able to be licensed to objects other than the first user. Then, the first knowledge base should be set as the private knowledge base of the first user and cannot be made public.

[0171] In the embodiments of the present application, by converting the first knowledge base from a shared knowledge base to a private knowledge base, the confidentiality of the content in the first knowledge base can be improved. Converting the shared knowledge base to a private knowledge base also makes the first knowledge base no longer occupy the shared storage space, saving the shared storage space.

[0172] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; when the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; in the case where at least one knowledge base includes a second knowledge base of the type of private knowledge base, in response to the second knowledge base meeting the second type switching condition, the type of the second knowledge base is switched from a private knowledge base to a shared knowledge base, or a prompt message for switching the type of the second knowledge base to a shared knowledge base is displayed, wherein the private knowledge base is only searchable or usable by the following accounts: the first instant messaging account, and a second instant messaging account that scans the QR code shared by the first instant messaging account.

[0173] Exemplarily, the second type switching condition indicates that the content of the private knowledge base meets the criteria for being made public as a shared knowledge base.

[0174] In some embodiments, the second type switching condition includes at least one of the following:

[0175] Condition 1: The number of second instant messaging accounts that initiate a collaboration request is greater than or equal to an account number threshold.

[0176] Exemplarily, the second instant messaging account initiates a collaboration request by scanning the QR code shared by the first instant messaging account. For example: There are more than 3 external users initiating access requests based on the QR code, and the request frequency is greater than or equal to once a week. For example, the user has shared the QR code with multiple users, resulting in the accumulation of collaboration requests.

[0177] Condition 2: The number of data belonging to the collaboration type in the second knowledge base is greater than or equal to a collaboration data volume threshold.

[0178] Exemplarily, the data of the collaboration type refers to data that requires multiple objects to collaborate on editing. For example: project plans, meeting minutes, etc. The collaboration data volume threshold can be set according to the actual application scenario. For example: More than 30% of the document types in the knowledge base belong to team project plans, etc.

[0179] Condition 3: The proportion of data with the exclusive identifier of the creator in the second knowledge base is less than a first proportion threshold.

[0180] Exemplarily, Condition 3 in the second type switching condition is the inverse of Condition 2 in the above-mentioned first type switching condition, and the principle is similar, so it will not be elaborated here one by one.

[0181] Condition 4: The number of title levels of the second knowledge base is greater than or equal to a title level number threshold.

[0182] Condition 5: The label coverage rate of the second knowledge base is greater than or equal to a coverage rate threshold.

[0183] Condition 6: The version iteration count of the second knowledge base is greater than or equal to the iteration count threshold.

[0184] Exemplarily, Conditions 4 to 6 in the second type switching condition are the same as Conditions 2 to 4 in the preset public condition described above, and will not be elaborated here one by one.

[0185] The number of title levels, the tag coverage rate, and the version iteration count are indicators used to evaluate the content integrity of the knowledge base. When at least one of the above indicators reaches the corresponding threshold, it means that the content of the private knowledge base is complete and can be used as a shared knowledge base.

[0186] In the embodiments of the present application, converting the private knowledge base into a shared knowledge base can save the cloud storage space in the user's personal account and provide the function of switching the knowledge base type, which can meet the diverse needs of different users and organizations at different stages.

[0187] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; at least one of the following processes is performed to allocate the editing permission of the knowledge base:

[0188] Method 1: In response to the second knowledge base account meeting the permission condition, set the permission of the second knowledge base account to be able to edit the first knowledge base, where the permission condition includes: when the second knowledge base account is added to the knowledge base account list of the first knowledge base, the number of knowledge base accounts in the knowledge base account list is less than the preset number, and the accounts included in the knowledge base account list of the first knowledge base are instant messaging accounts or knowledge base accounts using the first knowledge base.

[0189] Exemplarily, the number of knowledge base accounts in the knowledge base account list being less than the preset number indicates that the first preset number of knowledge base accounts added to the knowledge base account list can obtain the editing permission. For example: when the number of knowledge base accounts in the knowledge base account list is less than the preset number 4, the accounts added to the knowledge base account list can obtain the editing permission, that is, the first knowledge base account and 2 second knowledge base accounts can obtain the editing permission.

[0190] Method 2: In the case where the second knowledge base account is added to the knowledge base account list, in response to the permission setting operation based on the first knowledge base account, set the permission of the second knowledge base account to be able to edit the first knowledge base.

[0191] Exemplarily, the permission setting operation based on the first knowledge base account is set for the second knowledge base account, that is, it supports the user who creates the knowledge base to allocate the editing permission to other users by themselves.

[0192] Method 3: When the second instant messaging account scans the graphic code shared by the first instant messaging account, set the permission of the second knowledge base account to be able to edit the first knowledge base, where the second instant messaging account and the second knowledge base account belong to the same object.

[0193] Exemplarily, the graphic code shared by the first instant messaging account carries the identifier of the first knowledge base. When the second instant messaging account scans the code, the user who creates the knowledge base is supported to allocate the editing permission to other users by himself.

[0194] In the embodiments of the present application, by allocating the editing permission of the knowledge base in different ways, the management efficiency of the knowledge base and the sharing efficiency of the content in the knowledge base can be improved. Multiple accounts having the editing permission of the same knowledge base can improve the co-construction efficiency of the knowledge base, and reasonable allocation of editing permissions can ensure information synchronization among all parties. By setting multiple knowledge base accounts with editing permissions, it is supported that multiple administrators synchronously update the content of the knowledge base (such as uploading documents and adding generated abstracts), and achieve structured storage through tag classification, reducing version conflicts. If multiple knowledge base accounts belong to a team, the team members uniformly manage the knowledge base, and the team members can centralize scattered resources such as documents, web pages, and pictures into the shared knowledge base, ensuring that all members generate artificial intelligence question-and-answer results based on the same data source, and improving output consistency.

[0195] In some embodiments, the knowledge base interface includes a search control and an interaction control; refer to Figure 3B , Figure 3B is the second process schematic diagram of the data processing method of the knowledge base provided by the embodiments of the present application. It will be described in conjunction with Figure 3B the steps shown. Figure 3B The execution subject of the step is Figure 1 the first terminal device 400 in

[0196] In step 311, in response to an input operation on the search control, at least one third knowledge base is displayed.

[0197] Here, the type of at least one third knowledge base is a shared knowledge base, and at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keywords.

[0198] Exemplarily, refer to Figure 5D , Figure 5D is the fourth schematic diagram of the knowledge base interface provided by the embodiments of the present application; the knowledge base interface 501D is the interface of the knowledge base square. The knowledge base interface 501D includes a search control 502D. In response to an input operation on the search control 502D, multiple knowledge bases searched based on the input content are displayed.

[0199] In step 312, in response to an input operation on the interactive control, the first input information is displayed, and the second information for replying to the first information is displayed.

[0200] Here, the second information is generated based on the materials related to the first information retrieved from the third knowledge base.

[0201] For example, referring to Figure 5E , Figure 5E is the fifth schematic diagram of the knowledge base interface provided by the embodiments of the present application; the knowledge base interface 501E includes an interactive control 503E. Assume that the user selects a "medical aesthetics literature" knowledge base and enters the question "How to treat nose flushing (erythema) combined with enlarged pores?" The intelligent assistant generates an answer based on the content of the "medical aesthetics literature" knowledge base and the question entered by the user, and the answer is represented as the content in the second information 502E.

[0202] In the embodiments of the present application, question-and-answer processing is performed for a specific knowledge base, which facilitates users to quickly understand the content in the knowledge base and improves the knowledge acquisition efficiency. When users encounter problems in a specific field, they can directly obtain accurate answers from the corresponding specific knowledge base quickly. Compared with searching and filtering by themselves in a vast amount of Internet information, this method saves a lot of time and effort and can meet the knowledge needs more efficiently.

[0203] In some embodiments, before step 312, the second information is generated through the following processing:

[0204] Feature extraction processing is performed on the first information to obtain a query vector; for the query vector and each vector index of the third knowledge base, the first similarity between the query vector and the vector index is determined, where different vector indexes correspond to different materials; based on the target vector indexes with the first similarity greater than the third similarity threshold, the materials corresponding to the target vector indexes are extracted from the third knowledge base; the second information is generated based on the materials corresponding to the target vector indexes.

[0205] For example, in the embodiments of the present application, the multi-way recall method is adopted, and the first similarity between the query vector and the vector index can be determined in multiple ways, that is, the similarity is determined through different retrieval strategies to achieve multi-way recall. For example: by converting the text into a vector representation, by calculating the cosine value of the angle between vectors and other methods to determine the similarity, by semantic analysis, by edit distance and other methods to determine the similarity respectively, and sorting the similarities uniformly to determine the target vector indexes with the first similarity greater than the third similarity threshold.

[0206] In the embodiments of the present application, a language model and information retrieval technology are combined. Through the Retrieval-Augmented Generation (RAG) technology, when generating text or answering questions, relevant information is retrieved from a large collection of documents, and the retrieved information is used to guide the text generation process of the language model, thereby improving the quality and accuracy of predictions. Through vectorized storage and real-time retrieval, the general large model is enabled to have dynamic knowledge memory ability and improve the accuracy of question answering.

[0207] In some embodiments, generating the second information based on the material corresponding to the target vector index can be achieved in the following manner: performing feature extraction processing on the material corresponding to the target vector index to obtain material features; based on the query vector and the material features, calling a neural network model to perform text generation processing to obtain candidate information; splitting the candidate information into multiple parts; obtaining a second similarity between each part and each material feature, and determining the original content of the material corresponding to the target vector index for the part where the second similarity is greater than the fourth similarity threshold, where the type of the original content includes at least one of text or image; determining the position information of the original content in the file to which the material corresponding to the target vector index belongs; marking the original content in the candidate information according to the position information, and using the marked candidate information as the second information, where the original content is displayed in a manner different from other parts in the second information.

[0208] Exemplarily, the neural network model is a large language model (e.g., a Transformer model), and the candidate information is the answer result of the large language model. Splitting the candidate information into multiple parts can be achieved in the following manner: calling the large language model to determine the semantics of each sentence in the candidate information, and combining the sentences with a semantic similarity greater than the threshold according to the semantics of each sentence. Taking the file as a document as an example for illustration, the original content and the material corresponding to the target vector index are represented as text shards, then the position information is the position where the document shard is located in the document, and the position information is represented by the document name and the paragraph, or by the document name and the hierarchical title in the document. For example, the position information of the original content 1 is (the third part of "a certain document"), and the third part is the hierarchical title in a certain document.

[0209] In some embodiments, after step 312, at least part of the original content of the second target material is displayed in a manner different from other parts in the second information; in response to a trigger operation on the original content, the file to which the second target material belongs and the position of the second target material in the file are displayed.

[0210] Exemplarily, referring to Figure 6E , Figure 6E is a schematic diagram of the second information provided by the embodiments of the present application; Figure 6EThe second information 601E in it is text information, and the tail of the part of the original text in the second information 601E marks the name of the literature to which it belongs in bold. For example: It can shorten the erythema period and synergistically improve inflammation (in the combined treatment part of "Laser Beauty Guide").

[0211] In some embodiments, after the third knowledge base is published on the knowledge base platform, an index for each material in the knowledge base is constructed: each file in the third knowledge base is segmented to obtain a plurality of materials; each material is vectorized to obtain a vector representation of the material; the vector representation of the material is combined with the position of the material in the file to form a vector index of the material.

[0212] Exemplarily, taking text as an example, the materials in the knowledge base are document shards. For vector retrieval technology, vector retrieval mainly endows the knowledge base with the ability of semantic search. By embedding and vectorizing the user's query content (query), the vector of the query content is used to retrieve on the vector index of EleasticSearch based on the hierarchical navigable small world algorithm, and the relevant semantic document shards are recalled. The vectorization of materials can be achieved in the following way: based on the document shards, the embedding model bge-m3 is called to embed and vectorize the content of the document shards, convert it into a 1024-dimensional vector, and establish a vector index in the search service database based on the hierarchical navigable small world algorithm. The vector index is stored in the form of nodes of a graph structure.

[0213] In the embodiments of the present application, by establishing a vector index, the retrieval efficiency can be improved, and other vectors similar to the query vector can be found efficiently. The vector index optimizes the search path, reduces unnecessary calculations, and reduces the demand for computing resources.

[0214] In some embodiments, the attribute parameters of each shared knowledge base published by the first knowledge base account are determined, and the first evaluation index of the first knowledge base account for the knowledge base platform is determined based on the attribute parameters of each shared knowledge base. The attribute parameters include at least one of the following: the number of subscriptions of the shared knowledge base (the number of accounts added to the knowledge base account list of the shared knowledge base), the number of views of the shared knowledge base, the number of files in the shared knowledge base, the number of questions for the shared knowledge base, and the number of accounts asking questions for the shared knowledge base.

[0215] For example, the number of questions asked in the shared knowledge base refers to the number of times a user asks questions using the shared knowledge base through an instant messaging account or a knowledge base account. The number of accounts that ask questions about the shared knowledge base refers to the number of accounts that ask questions about the shared knowledge base. The first evaluation index can be determined in the following way: for a shared knowledge base, multiply the number of subscriptions, the number of files, the number of views, the number of accounts that ask questions, and the number of questions asked by their corresponding weight values respectively, and take the sum of the products as the second evaluation index. The second evaluation index represents the contribution degree of the shared knowledge base to the knowledge base platform. Add up the second evaluation indexes of all the shared knowledge bases created by a knowledge base account, which is the first evaluation index of the knowledge base account.

[0216] In some embodiments, a list of knowledge base accounts in multiple fields is displayed in the knowledge base interface. The list of knowledge base accounts includes multiple knowledge base accounts, and each knowledge base account in the list of knowledge base accounts is sorted in descending order according to the first evaluation index.

[0217] Reference Figure 7A , Figure 7A is the tenth schematic diagram of the knowledge base interface provided by the embodiments of the present application. The knowledge base interface 701A is the knowledge base square tab page in the intelligent workbench. When the user does not enter search content in the search control 702A, the knowledge base interface 701A defaults to display recommended knowledge bases in multiple fields, and a list of knowledge base accounts in each field. For example: the list of knowledge base accounts (total knowledge number ranking list) of all knowledge bases in the knowledge base platform includes accounts such as knowledge base account 1 and knowledge base account 2. The values in the list of knowledge base accounts are the first evaluation indexes corresponding to each account.

[0218] In some embodiments, the second evaluation index of the knowledge base can also be determined based on the following parameters of the knowledge base: problem-solving rate, average dialogue depth, negative feedback rate, knowledge coverage rate, content accuracy rate.

[0219] The problem-solving rate is the proportion of users who use the knowledge base and do not transfer to manual service after terminating the question. The average dialogue depth is the average value of the effective follow-up question times of users who use the Q&A function of the knowledge base in a single session. The negative feedback rate is the proportion of users who use the Q&A function of the knowledge base and actively mark "the answer is useless".

[0220] The knowledge coverage rate is the degree of completeness of the knowledge points in the target field covered by the knowledge base. The calculation formula is: knowledge coverage rate = (number of included knowledge points / total number of knowledge points in the field) × 100%. The total number of knowledge points in the field can be verified and obtained according to industry white papers or expert knowledge graphs.

[0221] The content accuracy rate is used to represent the matching accuracy between the knowledge base answer and the standard answer. The calculation formula is: (number of correct answers / total number of valid questions) × 100% = content accuracy rate. The total number of valid questions and the number of correct answers are determined through manual review or by comparison with reference data.

[0222] Exemplarily, the evaluation index of the knowledge base can be any one of the question-solving rate, average dialogue depth, negative feedback rate, knowledge coverage rate, and content accuracy rate, or the weighted sum result of multiple parameters. At least some of the above parameters can be set as the parameters for obtaining the evaluation index of the knowledge base according to the requirements of the actual application scenario.

[0223] In the embodiments of the present application, by quantifying the evaluation index, users using the knowledge base function can clearly understand the contribution degree of each knowledge base account. The knowledge base platform can recommend the knowledge bases edited by knowledge numbers with higher evaluation indexes to users according to the evaluation index. At the same time, by quantifying the evaluation index, it can promote the creators of the knowledge base to improve the quality of the knowledge base. For example, in order to obtain a higher evaluation index, the creator will pay more attention to the creation quality of the content. Prioritizing the recommendation of knowledge numbers with high evaluation indexes can help users quickly find those high-quality and reliable knowledge sources, saving users' time and energy and improving the efficiency of obtaining knowledge.

[0224] In some embodiments, the second evaluation index of the shared knowledge base for the knowledge base platform is determined based on the attribute parameters of the shared knowledge base. The attribute parameters include at least one of the following: the number of subscriptions of the shared knowledge base (the number of accounts added to the knowledge base account list of the shared knowledge base), the number of views of the shared knowledge base, the number of files in the shared knowledge base, the number of times the shared knowledge base is questioned, and the number of accounts that question the shared knowledge base.

[0225] Exemplarily, the determination process of the second evaluation index has been described above and will not be repeated here.

[0226] In some embodiments, a list of shared knowledge bases in multiple fields is displayed on the knowledge base interface. For each list of shared knowledge bases in a field, in the list of shared knowledge bases, each shared knowledge base is sorted in descending order according to the second evaluation index.

[0227] Reference Figure 7B , Figure 7BIt is the eleventh schematic diagram of the knowledge base interface provided by the embodiments of the present application. The knowledge base interface 701B is the knowledge base square tab page in the intelligent workbench, and multiple recommended knowledge bases in multiple fields are defaultly displayed in the knowledge base interface 701B. In the shared knowledge base list of each field, the knowledge bases are sorted in descending order according to the evaluation index. For example, the recommended knowledge base list 703B successively includes knowledge bases such as AI Knowledge Base (continuously updated), AI Selection Set, and AI Learning Knowledge Base. The sorting of the AI Knowledge Base (continuously updated), AI Selection Set, and AI Learning Knowledge Base is based on the evaluation index, and the evaluation index of the AI Knowledge Base is greater than that of the AI Selection Set.

[0228] In some embodiments, in response to an input operation on the search control in the knowledge base interface, multiple fourth knowledge bases are searched based on the content input by the input operation, sorted in descending order according to the evaluation index of each fourth knowledge base, and multiple fourth knowledge bases starting from the head of the descending sorted list are selected as the third knowledge bases recommended to the object. The multiple third knowledge bases are displayed, and the third knowledge bases are sorted in descending order according to the evaluation index.

[0229] Exemplarily, the third knowledge base is selected from multiple matching fourth knowledge bases, that is, in the case where the search content matches, the knowledge base with a higher evaluation index is preferentially returned.

[0230] In the embodiments of the present application, the evaluation index of the knowledge base is quantified. The evaluation index can characterize information such as the number of times the knowledge base is questioned. Recommending the knowledge base according to the evaluation index can improve the accuracy of the recommended knowledge base. The evaluation index quantifies the usage value of each knowledge base. When the user searches for the knowledge base, recommending according to the evaluation index can accurately locate the knowledge base that meets the specific needs of the user.

[0231] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; the ownership of the first knowledge base is transferred in the following manner: in response to a first transfer trigger operation on the first knowledge base account, when both the first instant messaging account and the second instant messaging account authorize the transfer, at least one first knowledge base is changed from the first knowledge base account belonging to the first object to the second knowledge base account belonging to the second object, where the first object is the object to which the first instant messaging account belongs, and the second knowledge base account and the second instant messaging account belong to the second object.

[0232] Exemplarily, through the above processing, cross-account operations of the shared knowledge base can be conveniently implemented, that is, the knowledge base is transferred to other knowledge base accounts in batches. The authorization of both the first instant messaging account and the second instant messaging account for the transfer means that the first instant messaging account confirms the transfer of at least one first knowledge base corresponding to the first knowledge base account, and the second instant messaging account agrees to receive the ownership of at least one first knowledge base corresponding to the first knowledge base account.

[0233] In the embodiments of the present application, through the overall sharing of the knowledge base across accounts, the sharing efficiency of the knowledge base can be improved, and the knowledge dissemination efficiency can be improved. Transferring the knowledge base through a dedicated knowledge base account, independent of the personal account system of instant messaging, in the case of the handover of the owner of the instant messaging account, the knowledge base can still be seamlessly handed over through the administrator permission to ensure business continuity.

[0234] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; the first knowledge base account is closed by the following method: in response to the closing operation for the first knowledge base account, convert the type of at least one first knowledge base from a shared knowledge base to a private knowledge base belonging to the first object, where the first object is the object to which the first instant messaging account belongs.

[0235] Exemplarily, when the first knowledge base account is closed, the shared knowledge base belonging to the first knowledge base account is transferred to the private knowledge base, the registration information of the first knowledge base account is cancelled, but the first instant messaging account to which the first knowledge base account belongs can still use the content in the private knowledge base, which is convenient for the user to retain private data.

[0236] In some embodiments, the knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; the knowledge bases corresponding to different knowledge base accounts are merged by the following method: mark the knowledge base account as the first knowledge base account belonging to the first object; in response to the merge trigger operation for the first knowledge base account and the second knowledge base account belonging to the second object, when both the first instant messaging account and the second instant messaging account authorize the merge, merge at least one first knowledge base with at least one fourth knowledge base created based on the second knowledge base account to obtain at least one fifth knowledge base, where the second knowledge base account and the second instant messaging account belong to the same object, and at least one fifth knowledge base is shared by the first knowledge base account and the second knowledge base account.

[0237] Exemplarily, the above processing merges the knowledge bases of two knowledge base accounts, and merging at least one first knowledge base with at least one fourth knowledge base created based on a second knowledge base account can be achieved in the following manner: removing duplicate content in at least one first knowledge base and at least one fourth knowledge base, and merging the remaining content into at least one fifth knowledge base.

[0238] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; the knowledge base account is transferred to another instant messaging account in the following manner: in response to a second transfer trigger operation for the first knowledge base account, when both the first instant messaging account and the second instant messaging account authorize the transfer, changing the first knowledge base account from a knowledge base account belonging to the first object to a knowledge base account belonging to the second object, where the first object is the object to which the first instant messaging account belongs, and the second object is the object to which the second instant messaging account belongs.

[0239] Exemplarily, the knowledge base account can be transferred, that is, transferred from one instant messaging account to another instant messaging account. After the transfer, the original instant messaging account of the knowledge base account no longer has the ownership of the knowledge base account. Before the transfer, the instant messaging account of the second object that accepts the transfer of the knowledge base account does not have a corresponding knowledge base account. When the first knowledge base account changes from a knowledge base account belonging to the first object to a knowledge base account belonging to the second object, all the knowledge bases belonging to the first knowledge base account also belong to the second instant messaging account.

[0240] In some embodiments, the embodiments of the present application further provide a method for processing data of a knowledge base. Refer to Figure 3C , Figure 3C is the second process schematic diagram of the method for processing data of the knowledge base provided by the embodiments of the present application. The steps shown in Figure 3C will be described. Figure 3C The execution subject of the step is Figure 1 the first terminal device 400 in

[0241] In step 321, a knowledge base interface is displayed.

[0242] Here, the knowledge base interface includes a search control and an interaction control.

[0243] Exemplarily, the principle of step 321 refers to step 301 above.

[0244] In step 322, in response to an input operation on the search control, at least one third knowledge base is displayed.

[0245] Here, the type of at least one third knowledge base is a shared knowledge base set up based on a pre-created knowledge base account, and at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keywords.

[0246] Exemplarily, the principle of step 322 refers to step 311 above.

[0247] In step 323, in response to an input operation on the interactive control, the input first information is displayed, and second information for replying to the first information is displayed.

[0248] Here, the second information is generated based on materials related to the first information searched from the third knowledge base.

[0249] Exemplarily, the principle of step 323 refers to step 312 above.

[0250] In the embodiments of the present application, a first knowledge base account with the permission to publish a shared knowledge base on the knowledge base platform is set up, and a shared knowledge base belonging to the first knowledge base account is published on the knowledge base platform based on the first knowledge base account. A new form of knowledge dissemination is established through the knowledge base account, facilitating the sharing and use of information. The knowledge base account is dedicated to the creation and publication of shared knowledge bases. Compared with creating and publishing through the account for logging in to the knowledge base interface, the risk isolation of the creation and publication permissions of the knowledge base is achieved, and the security of the data in the knowledge base is improved. The shared knowledge base is used to be searched and used in the knowledge base platform, which can improve the data sharing efficiency.

[0251] Next, an exemplary application of the data processing method of the knowledge base in the embodiments of the present application in an actual application scenario will be described.

[0252] In the digital age where the information entropy increase effect is becoming increasingly significant, massive heterogeneous data shows an exponential growth trend, and users are faced with the dual dilemmas of information overload and lack of relevant knowledge. Especially in vertical fields with high professional barriers (such as clinical medicine, biotechnology, etc.), the unstructured characteristics of information resources and the discreteness of knowledge service supply form a significant information potential difference.

[0253] The knowledge sharing of related technologies often realizes the circulation of information through ways such as information sharing and video lectures. The above information circulation methods are inefficient. Firstly, the information output method is inefficient. The sharer often combines information through specific topics to build a course system, and the course R & D and construction are extremely energy-consuming. Secondly, the information absorption and secondary application methods are inefficient. Learners need to integrate and absorb information through self-study and obtain guidance for practical life applications through reasoning and other methods.

[0254] In view of the above problems existing in the related art, in the embodiments of the present application, the knowledge base application program is logged in through an instant messaging account. When logged in, a knowledge base account can be applied for in the knowledge base application program. Based on the knowledge base account, a shared knowledge base can be published in the knowledge base square. An instant messaging account corresponds to a knowledge base account. If a user does not have a knowledge base account, the user can only publish a personal knowledge base. A knowledge base account can publish multiple knowledge bases. As the owner of the knowledge base account, the user filters information in a specific field and constructs a knowledge base in the specific field. For a publicly available knowledge base, when an ordinary user inputs question text, the answer required by the user can be extracted from the publicly available knowledge base through the reasoning ability of the large language model and the Retrieval-Augmented Generation (RAG) technology.

[0255] Reference Figure 4 , Figure 4 is the fourth process schematic diagram of the data processing method of the knowledge base provided by the embodiments of the present application; it will be described in combination with Figure 4 the steps shown. Figure 4 The execution subject of the step is Figure 1 the first terminal device 400 in

[0256] In step 401, a knowledge base account is created in the knowledge base interface.

[0257] For example, a knowledge base account is an account (abbreviated as knowledge number) used to publish a publicly available knowledge base. A knowledge base account can create multiple knowledge bases. The types of knowledge bases include private and shared knowledge bases. A shared knowledge base is a knowledge base that can be searched after being published in the knowledge base square; a private knowledge base (personal knowledge base) can only be browsed by an individual or shared with specific users through a QR code link by an individual. Reference Figure 5A , Figure 5A is the first schematic diagram of the knowledge base interface provided by the embodiments of the present application; the knowledge base interface 501A includes a knowledge number creation control 502A. The user can input the user name and set the user avatar in the knowledge number creation control 502A. When the user has selected to confirm "I have read and agreed to the 'Operation Specifications' and 'User Agreement'", in response to the triggering operation on the "Create" button in the knowledge number creation control 502A, a knowledge base account is created based on the user's name, instant messaging account, and user avatar.

[0258] In step 402, a knowledge base is created.

[0259] Exemplarily, creating a private knowledge base can be performed without applying for a knowledge base account. In the embodiments of the present application, the creation of a shared knowledge base is taken as an example for illustration. When there is a knowledge base account, a shared knowledge base can be created. The user creates a knowledge base on a specific topic according to the fields of the collected documents, and stores different documents around the topic into the knowledge base. Refer to Figure 5B , Figure 5B is the second schematic diagram of the knowledge base interface provided by the embodiments of the present application; in the knowledge base interface 501B, the user creates a "travel guide" knowledge base and adds multiple documents of photography appreciation and landscape photography to the "travel guide" knowledge base.

[0260] In step 403, the created knowledge base is published to the knowledge base platform based on the knowledge base account.

[0261] Exemplarily, whether the creation of the knowledge base is completed can be judged by the user. Or, when the content of the knowledge base meets the preset conditions, corresponding prompt information is displayed in the knowledge base interface to remind the user to publish the created shared knowledge base.

[0262] Refer to Figure 5C , Figure 5C is the third schematic diagram of the knowledge base interface provided by the embodiments of the present application; a permission setting control 502C is displayed in the knowledge base interface 501C. When the knowledge base is published, different permissions can be set, including: Default: Can be shared through a link or QR code, but cannot be discovered in the square (knowledge base platform). Published to the square: Can be discovered in the square, joining does not require confirmation, and no longer occupies personal capacity. Converted to private: The knowledge base is only visible to oneself (when logged in with the instant messaging account of the creator himself).

[0263] A shared knowledge base can be shared by multiple member users. When the permission of "members can view the file content" is set in the main settings of the knowledge base account, multiple member users can view the article content in the knowledge base.

[0264] In step 404, search for the knowledge base in the knowledge base platform.

[0265] Exemplarily, users who log in to the knowledge base platform based on the instant messaging account and users of the instant messaging account holding the knowledge base account can both search for the knowledge base through the knowledge base platform. Refer to Figure 5D , Figure 5D is the fourth schematic diagram of the knowledge base interface provided by the embodiments of the present application; the knowledge base interface 501D is the interface of the knowledge base square. The knowledge base interface 501D includes a search control 502D. In response to an input operation on the search control 502D, multiple knowledge bases searched based on the input content are displayed.

[0266] In some embodiments, before step 404, an index of the documents in each knowledge base in the knowledge base platform is constructed, where retrieval processing can be performed based on the index and the question input by the user to obtain the content required by the user. In some embodiments, the retrieval enhancement generation solution of the knowledge base is mainly implemented based on the search service (Eleastic Search) and is divided into two parts: index building and retrieval. To cope with the storage of large-scale user data, the embodiments of the present application design an extensible index management solution to facilitate subsequent expansion. At the same time, to improve the recall rate, the embodiments of the present application establish two indexing methods: embedding vectors and text retrieval. For the recalled data, to further improve the relevance of sharding, the embodiments of the present application perform re-ranking and screening through a re-rank model. Finally, in the original text index, the embodiments of the present application calculate the similarity of the original text through the re-rank model and index the content answered by the large language model (LLM). The core objective of the re-rank model is to perform a secondary sorting on the preliminary retrieval results to ensure that the most relevant documents are ranked at the top. This is particularly important in the retrieval enhancement generation process because although retrieval enhancement generation can retrieve a large number of documents, not all documents are closely related to the query question. The re-rank model reorders to preferentially display documents more relevant to the question, thereby improving the overall performance.

[0267] The construction of the index includes a vector index and a text index (inverted index). For the vector index, the embodiments of the present application adopt a multilingual embedding model bge-m3 fine-tuned based on business data corpus to perform embedding vectorization on the document shard content and convert it into a 1024-dimensional vector (the document is divided into multiple document shards, and the document shards are converted into embedding vectors). A vector index is established in the search service database based on the hierarchical navigable small world algorithm. To balance the large-scale vector search speed, int8 quantization is adopted. An int8 string represents an integer with 8-bit binary numbers.

[0268] To further improve the recall rate, the embodiments of the present application also establish a text-based inverted index. By performing word segmentation on the document shards, a multi-field and multi-dimensional inverted index is established in the search service database. Specifically, indexes are established for the title, content, tags, pinyin of the title, etc. The inverted index originates from the need to find records according to the values of attributes in practical applications. Each item in this index table includes an attribute value and the addresses of the records with this attribute value. Since it is not the record that determines the attribute value, but the attribute value that determines the position of the record, it is called an inverted index. The inverted index is a reverse mapping. The text inverted index is a mapping from words to documents, that is, for each word, the information of all documents containing this word is recorded.

[0269] In some embodiments, to handle the storage and retrieval of large-scale TB-level data, based on an organizational structure of multiple clusters and multiple indexes, clusters are dynamically allocated according to the growth of business data, routed to different indexes according to the user identifier (uid), and then the routing of shards is performed through the user identifier. Ensure that the performance of writing and retrieval is within a controllable range to cope with the high-speed growth in the later stage of the business. Sharding is to divide a large-scale data set into multiple smaller and relatively independent parts, and each part is called a shard.

[0270] The routing of the user identifier to different indexes can be achieved in the following way: When the system receives a large amount of user data, to improve the query efficiency of the data, the data will be mapped to different indexes according to the user identifier. The specific approach is usually to convert the user identifier into an index key through a certain hash function or rule, and then find the corresponding index according to this index key.

[0271] For example, assume there is a database that uses the hash function hash(uid) % N (where N is the number of indexes) to determine which index the data of the user knowledge base account (user uid) should be stored in. If there are 10 indexes (N = 10) and the result obtained after the hash calculation of the user identifier is 3, then the knowledge base data under this knowledge base account will be routed to the 3rd index. The advantage of doing this is that the user data can be evenly distributed among different indexes, avoiding excessive load on a certain index.

[0272] The routing of shards through the user identifier can be achieved in the following way: Determine which shard the data should be stored in according to the user knowledge base account. This process is similar to index routing and also maps the user identifier to a specific shard through a certain rule or algorithm.

[0273] For example: The hash function can be used again to map the user knowledge base account to different shard nodes. Each shard node is responsible for storing a part of the knowledge base data under the user knowledge base account, which can achieve distributed storage of the data, improve the concurrent processing ability and fault tolerance of the system. When querying a certain piece of data, the system can quickly locate the shard where the knowledge base data under the user knowledge base account is located according to the knowledge base account, and then perform the query operation in the corresponding shard.

[0274] In step 405, question-answering processing is performed based on the retrieved knowledge base.

[0275] Exemplarily, the user determines the topic of interest. In response to an input operation on the search control for the knowledge base square tab page, the user's input topic of interest is displayed in the search control, and multiple knowledge bases searched based on the topic of interest are displayed in the knowledge base square tab page. The user selects at least one of the knowledge bases. In response to an input operation of a question for the selected at least one knowledge base, an answer generated based on the selected at least one knowledge base and the input question is displayed.

[0276] Reference Figure 5E , Figure 5E is the fifth schematic diagram of the knowledge base interface provided by the embodiment of the present application; the knowledge base interface 501E includes an interaction control 503E. Assume that the user selects a "medical aesthetics literature" knowledge base and inputs the question "How to treat the combination of nose flushing (erythema) and enlarged pores?". The intelligent assistant generates an answer based on the content of the "medical aesthetics literature" knowledge base and the question input by the user, and the answer is characterized as the content in the second information 502E.

[0277] In the embodiment of the present application, the retrieval process based on the knowledge base is implemented based on vector retrieval and text retrieval.

[0278] For vector retrieval, vector retrieval mainly endows the knowledge base with the ability of semantic search. By embedding and vectorizing the user's query content (query), the vector of the query content is used to retrieve based on the hierarchical navigable small world algorithm on the vector index of EleasticSearch, and relevant semantic document shards are recalled. For example: based on the question text input by the user, the question text is converted into a query vector, and retrieved based on the hierarchical navigable small world algorithm to obtain the embedded vector index of the document shards with a similarity greater than the threshold to the query vector, and the corresponding document shards are extracted from the knowledge base based on the vector index.

[0279] For text retrieval, text retrieval is mainly used to supplement the shard recall pool and further improve the recall rate. In the embodiment of the present application, the query content input by the user is segmented. Different fields adopt different processing and search strategies. For example, for the search of tags, complete matching is selected, and for the title, pinyin search is also used at the same time. Through the integration of multiple strategies, text retrieval based on BM25 for document shards is performed to further improve the recall rate.

[0280] For the recall of multi-way sharding, it is necessary to perform the final relevance calculation and scoring on the shard content to obtain the final re-ranked sequence. The re-rank model in this embodiment of the application is a multilingual re-rank model bge-reranker-v2-m3 fine-tuned based on business corpus. Multi-Route Retrieval refers to a technology in an information retrieval system that, in order to improve the comprehensiveness and accuracy of retrieval, obtains information through multiple different retrieval paths or different retrieval strategies. The core idea of multi-way recall is that a single retrieval path may miss some important information or not cover all possibly relevant content. Therefore, multiple retrieval methods need to be used in parallel or serially to improve the final recall rate and accuracy.

[0281] Taking the re-rank strategy in the text search scenario as an example for illustration, in the text search scenario, for the shards recalled based on semantic vectors, the requirement for document relevance is higher, so the re-rank strategy will be more strict. For the shards in text search, as long as there is a hit, it needs to be displayed. Therefore, in the text search scenario, the re-rank strategy can include: re-rank scoring and filtering for the content retrieved by vector search, and directly displaying the shards retrieved by text search.

[0282] In the question-and-answer scenario, the goal is to give the most relevant shard content within the context of the large language model as much as possible. Therefore, in this scenario, the strategy designed in this embodiment of the application is multi-way recall, unified re-rank, and finally select multiple (TopN) shards with the top rankings according to the question-and-answer scenario.

[0283] When displaying the answer, at the same time, display a marker near each document shard. In response to the marker or the document shard being clicked, based on the coordinate information and original text link associated with the document shard, display the original text corresponding to the document shard and the coordinate position of the document shard in the original text. The advantage of such display is that each document shard is well-founded, avoiding providing users with incorrect answers formed by the large model hallucination.

[0284] The data processing method of the knowledge base provided in this embodiment of the application solves the problem of low knowledge flow efficiency in the knowledge sharing solution of the related technology, and has the following effects:

[0285] (1) It improves the knowledge output efficiency of knowledge sharers. Knowledge sharers do not have to build and develop a logically rigorous and professional teaching system. They only need to select high-quality content based on professional knowledge, and the large language model understands, organizes, and re-produces knowledge according to user questions. (2) It improves the knowledge acquisition efficiency of ordinary users: In the past, users needed to first understand the content under the course system, and then integrate and apply the knowledge to guide their actual lives. Now, they only need to ask questions, skip the complex processes of knowledge understanding, absorption, and output, and directly solve their doubts through the knowledge base constructed by professionals.

[0286] Next, the exemplary structure of the software module for the data processing device 455 of the knowledge base provided in the embodiments of the present application will be further described. In some embodiments, as Figure 2 shown, the software module in the data processing device 455 of the knowledge base stored in the memory 450 may include: a display module 4551, configured to display a knowledge base interface, where the knowledge base interface includes at least one knowledge base; the display module 4551 is further configured to, in response to an account creation operation in the knowledge base interface, display a newly created first knowledge base account, where the first knowledge base account has the permission to publish and share the knowledge base on the knowledge base platform; the display module 4551 is further configured to, in response to a permission setting operation for the first knowledge base, publish the first knowledge base belonging to the first knowledge base account on the knowledge base platform when the first knowledge base is set as the shared knowledge base in the permission setting operation, where the first knowledge base is used to be searched and used on the knowledge base platform.

[0287] In some embodiments, the display module 4551 is configured to, in response to a trigger operation on the knowledge number creation control in the knowledge base interface, display a knowledge number creation interface; and in response to an account attribute setting operation in the knowledge number creation interface, display the first knowledge base account created based on the input account attributes.

[0288] In some embodiments, the display module 4551 is configured to, in response to the created private knowledge base in the knowledge base interface meeting a preset public condition, display a prompt message for creating a knowledge base account, where the prompt message for creating a knowledge base account includes a knowledge number creation control; in response to a confirmation operation on the prompt message for creating a knowledge base account, display a knowledge number creation interface; and in response to an account attribute setting operation in the knowledge number creation interface, display the first knowledge base account created based on the input account attributes.

[0289] In some embodiments, the preset public condition includes at least one of the following:

[0290] the created private knowledge base is a private knowledge base in a specific field, and the number of questions for the specific field is greater than or equal to a question number threshold; the number of title levels of the created private knowledge base is greater than or equal to a title level number threshold; the label coverage rate of the created private knowledge base is greater than or equal to a coverage rate threshold; the number of version iterations of the created private knowledge base is greater than or equal to an iteration number threshold.

[0291] In some embodiments, the display module 4551 is configured to display a graphical code when the permission setting operation sets the type of the first knowledge base to a private knowledge base, where the graphical code carries an identifier of the first knowledge base; in response to a sharing operation on the graphical code, send the graphical code to a second instant messaging account, and when the graphical code is scanned by the second instant messaging account, the first knowledge base is added to the private knowledge base list of the second instant messaging account.

[0292] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; the display module 4551 is configured to set the permission of the first knowledge base to be visible only to the first instant messaging account when the permission setting operation sets the type of the first knowledge base to a private knowledge base.

[0293] In some embodiments, the display module 4551 is configured to display a prompt message for creating a knowledge base in a specific field after displaying the newly created first knowledge base account in response to an account creation operation in the knowledge base interface, where the prompt message for creating a knowledge base in a specific field includes a knowledge base creation control, and the specific field satisfies at least one of the following conditions: the number of knowledge bases in the specific field is less than a knowledge base number threshold; the similarity between the characteristics of the specific field and the characteristics of the first instant messaging account corresponding to the first knowledge base account is greater than a first similarity threshold; in response to a trigger operation on the knowledge base creation control, display a first knowledge base created based on the first knowledge base account and belonging to the specific field.

[0294] In some embodiments, the display module 4551 is configured to display a prompt message for adding materials and at least one material after displaying the first knowledge base created based on the first knowledge base account and belonging to the specific field, where the at least one material is obtained by searching based on the name and tags of the first knowledge base, and the prompt message for adding materials is used to prompt that the at least one material matches the first knowledge base; in response to a confirmation operation on the prompt message, add the at least one material to the first knowledge base.

[0295] In some embodiments, a display module 4551 is configured to, after displaying a first knowledge base that is created based on the first knowledge base account and belongs to the specific domain, display a prompt message for adding materials and at least one material, where the at least one material is obtained by searching based on the characteristics of the first knowledge base account, and the similarity between the characteristics of the at least one material and the characteristics of the first knowledge base account is less than a second similarity threshold; in response to a confirmation operation for the prompt message, add the at least one material to the first knowledge base.

[0296] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; when the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; a display module 4551 is configured to, in response to a permission switching operation for the first knowledge base, switch the type of the first knowledge base from the shared knowledge base to a private knowledge base, where the private knowledge base is only searchable or usable by the following accounts:

[0297] The first instant messaging account, and a second instant messaging account that scans a graphical code shared by the first instant messaging account.

[0298] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; when the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; a display module 4551 is configured to, in response to the first knowledge base meeting a first type switching condition, switch the type of the first knowledge base from the shared knowledge base to a private knowledge base, where the private knowledge base is only searchable or usable by the following accounts:

[0299] The first instant messaging account, and a second instant messaging account that scans a graphical code shared by the first instant messaging account.

[0300] In some embodiments, the first type switching condition includes at least one of the following:

[0301] The usage rate of the first knowledge base within a preset time period is lower than a usage rate threshold; the proportion of data with the exclusive identifier of the creator in the first knowledge base is greater than a first proportion threshold; the proportion of duplicate data in the first knowledge base is greater than a second proportion threshold; there is third-party authorized data in the first knowledge base and the authorization agreement prohibits conversion to private.

[0302] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; when the first knowledge base is searched for and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; a display module 4551 is configured to, when the at least one knowledge base includes a second knowledge base of the type of a private knowledge base, in response to the second knowledge base satisfying a second type switching condition, switch the type of the second knowledge base from the private knowledge base to the shared knowledge base, or display a prompt message for switching the type of the second knowledge base to the shared knowledge base, where the private knowledge base is only searchable or usable by the following accounts:

[0303] the first instant messaging account and a second instant messaging account that scans a graphic code shared by the first instant messaging account.

[0304] In some embodiments, the second type switching condition includes at least one of the following:

[0305] the number of second instant messaging accounts that initiate a collaboration request is greater than or equal to an account number threshold, where the second instant messaging account initiates the collaboration request by scanning a graphic code shared by the first instant messaging account; the number of data of the collaboration type in the second knowledge base is greater than or equal to a collaboration data volume threshold; the proportion of data with an exclusive identifier of the creator in the second knowledge base is less than a first proportion threshold; the number of title levels of the second knowledge base is greater than or equal to a title level number threshold; the label coverage rate of the second knowledge base is greater than or equal to a coverage rate threshold; the number of version iterations of the second knowledge base is greater than or equal to an iteration number threshold.

[0306] In some embodiments, the knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; the display module 4551 is configured to perform at least one of the following processes:

[0307] In response to the second knowledge base account meeting the permission conditions, set the permission of the second knowledge base account to be able to edit the first knowledge base, where the permission conditions include: when the second knowledge base account is added to the knowledge base account list of the first knowledge base, the number of knowledge base accounts in the knowledge base account list is less than a preset number, and the accounts included in the knowledge base account list of the first knowledge base are the accounts using the first knowledge base; in the case where the second knowledge base account is added to the knowledge base account list, in response to the permission setting operation based on the first knowledge base account, set the permission of the second knowledge base account to be able to edit the first knowledge base; in the case where the second instant messaging account scans the graphic code shared by the first instant messaging account, set the permission of the second knowledge base account to be able to edit the first knowledge base, where the second instant messaging account and the second knowledge base account belong to the same object.

[0308] In some embodiments, the knowledge base interface includes a search control and an interaction control; a search module 4552, configured to display at least one third knowledge base in response to an input operation on the search control, where the type of the at least one third knowledge base is the shared knowledge base, and the at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keyword; in response to an input operation on the interaction control, display the input first information and display second information for replying to the first information, where the second information is generated based on the materials related to the first information searched from the third knowledge base.

[0309] In some embodiments, the search module 4552 is configured to, before displaying the second information for replying to the first information, perform feature extraction processing on the first information to obtain a query vector; for the query vector and each vector index of the third knowledge base, determine a first similarity between the query vector and the vector index, where different vector indexes correspond to different materials; based on the target vector index with the first similarity greater than a third similarity threshold, extract the material corresponding to the target vector index from the third knowledge base; generate the second information based on the material corresponding to the target vector index.

[0310] In some embodiments, the search module 4552 is configured to perform feature extraction processing on the materials corresponding to the target vector index to obtain material features; based on the query vector and the material features, call a neural network model to perform text generation processing to obtain candidate information; split the candidate information into multiple parts; obtain a second similarity between each of the parts and each of the material features, and determine the part with the second similarity greater than the fourth similarity threshold as the original content of the material corresponding to the target vector index, where the type of the original content includes at least one of text or image; determine the position information of the original content in the file to which the material corresponding to the target vector index belongs; mark the original content in the candidate information according to the position information, and use the marked candidate information as the second information, where the original content is displayed in a manner different from other parts in the second information.

[0311] In some embodiments, after the search module 4552 displays the second information for replying to the first information, at least part of the original content of the second target material is displayed in the second information in a manner different from other parts; in response to a trigger operation on the original content, the file to which the second target material belongs and the position of the second target material in the file are displayed.

[0312] In some embodiments, after the third knowledge base is published on the knowledge base platform, the search module 4552 is configured to perform segmentation processing on each file in the third knowledge base to obtain a plurality of materials; perform vectorization processing on each of the materials to obtain a vector representation of the material; combine the vector representation of the material with the position of the material in the file to form a vector index of the material.

[0313] The software module in the data processing device 455 of the knowledge base stored in the memory 450 may further include:

[0314] The display module 4551 is configured to display a knowledge base interface, where the knowledge base interface includes a search control and an interaction control; the display module 4551 is further configured to, in response to an input operation on the search control, display at least one third knowledge base, where the type of the at least one third knowledge base is a shared knowledge base set based on a pre-created knowledge base account, and the at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keyword; the display module 4551 is further configured to, in response to an input operation on the interaction control, display the input first information and display the second information for replying to the first information, where the second information is generated based on materials related to the first information searched from the third knowledge base.

[0315] An embodiment of the present application provides a computer program product, which includes a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer program or computer-executable instructions from the computer-readable storage medium, and the processor executes the computer program or computer-executable instructions, so that the electronic device executes the data processing method of the knowledge base in the above embodiments of the present application.

[0316] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, where computer-executable instructions or a computer program are stored. When the computer-executable instructions or the computer program are executed by a processor, the processor will be caused to execute the data processing method of the knowledge base provided by the embodiment of the present application. For example, as Figure 3A the data processing method of the knowledge base shown.

[0317] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM; or may be various devices including one or any combination of the above memories.

[0318] In some embodiments, the computer-executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including being deployed as an independent program or being deployed as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0319] As an example, the computer-executable instructions may or may not correspond to a file in a file system, and may be stored as part of a file that stores other programs or data. For example, stored in one or more scripts in a HyperText Markup Language (HTML) document, stored in a single file dedicated to the program under discussion, or stored in multiple cooperating files (for example, files that store one or more modules, subroutines, or code portions).

[0320] As an example, the computer-executable instructions may be deployed to execute on one electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed at multiple locations and interconnected by a communication network.

[0321] In summary, by setting up a first knowledge base account with the permission to publish and share the knowledge base on the knowledge base platform in the embodiments of the present application, and publishing the shared knowledge base belonging to the first knowledge base account on the knowledge base platform based on the first knowledge base account, a new form of knowledge dissemination is established through the knowledge base account, facilitating the sharing and use of information. Endowing the knowledge base account with the publishing permission for the shared knowledge base can encourage more users to actively create and publish knowledge bases, thereby increasing the knowledge resources on the knowledge base platform and making the content of the knowledge base platform more rich and diverse. The shared knowledge base is used to be searched and used on the knowledge base platform, which can improve the sharing efficiency of data. The quick sharing of the shared knowledge base is realized through the knowledge number, improving the data processing efficiency of the knowledge base. The knowledge base account is dedicated to the creation and publication of the shared knowledge base. Compared with creating and publishing through the account logged in to the knowledge base interface, the risk isolation of the creation and publication permissions of the knowledge base is achieved, and the security of the data in the knowledge base is improved.

[0322] As mentioned above, the foregoing are only embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are all included in the protection scope of the present application.

Claims

1. A method for processing data of a knowledge base, characterized in that, The method includes: Displaying a knowledge base interface, where the knowledge base interface includes at least one knowledge base; In response to an account creation operation in the knowledge base interface, displaying a newly created first knowledge base account, where the first knowledge base account has the permission to publish and share the knowledge base on the knowledge base platform; In response to a permission setting operation for the first knowledge base, when the permission setting operation sets the type of the first knowledge base to the shared knowledge base, publishing the first knowledge base belonging to the first knowledge base account in the knowledge base platform, where the first knowledge base is used to be searched and used in the knowledge base platform.

2. The method according to claim 1, wherein The step of, in response to an account creation operation in the knowledge base interface, displaying a newly created first knowledge base account includes: In response to a triggering operation on a knowledge number creation control in the knowledge base interface, displaying a knowledge number creation interface; In response to an account attribute setting operation in the knowledge number creation interface, displaying the first knowledge base account created based on the input account attributes.

3. The method according to claim 1, wherein The step of, in response to an account creation operation in the knowledge base interface, displaying a newly created first knowledge base account includes: In response to the fact that the created private knowledge base in the knowledge base interface meets a preset public condition, displaying a prompt message for creating a knowledge base account, where the prompt message for creating a knowledge base account includes a knowledge number creation control; In response to a confirmation operation on the prompt message for creating a knowledge base account, displaying a knowledge number creation interface; In response to an account attribute setting operation in the knowledge number creation interface, displaying the first knowledge base account created based on the input account attributes.

4. The method according to claim 3, wherein The preset public condition includes at least one of the following: The created private knowledge base is a private knowledge base in a specific field, and the number of questions for the specific field is greater than or equal to a question count threshold; The number of title levels of the created private knowledge base is greater than or equal to a title level threshold; The tag coverage rate of the created private knowledge base is greater than or equal to a coverage rate threshold; The number of version iterations of the created private knowledge base is greater than or equal to an iteration count threshold.

5. The method according to claim 1, wherein The method further includes: When the permission setting operation sets the type of the first knowledge base to a private knowledge base, displaying a graphic code, where the graphic code carries an identifier of the first knowledge base; In response to a sharing operation on the graphic code, sending the graphic code to a second instant messaging account, where when the graphic code is scanned by the second instant messaging account, the first knowledge base is added to the private knowledge base list of the second instant messaging account.

6. The method according to claim 1, wherein The knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; The method further includes: When the permission setting operation sets the type of the first knowledge base to a private knowledge base, setting the permission of the first knowledge base to be visible only to the first instant messaging account.

7. The method according to claim 1, characterized in that After the step of, in response to an account creation operation in the knowledge base interface, displaying a newly created first knowledge base account, the method includes: Display a prompt message for creating a knowledge base in a specific domain, where the prompt message for creating a knowledge base in the specific domain includes a knowledge base creation control, and the specific domain satisfies at least one of the following conditions: the number of knowledge bases in the specific domain is less than a knowledge base quantity threshold; the similarity between the features of the specific domain and the features of the first instant messaging account corresponding to the first knowledge base account is greater than a first similarity threshold; In response to a trigger operation on the knowledge base creation control, display a first knowledge base created based on the first knowledge base account and belonging to the specific domain.

8. The method according to claim 7, wherein After displaying the first knowledge base created based on the first knowledge base account and belonging to the specific domain, the method further includes: Display a prompt message for adding materials and at least one material, where the at least one material is obtained by searching based on the name and tags of the first knowledge base, and the prompt message for adding materials is used to prompt that the at least one material matches the first knowledge base; In response to a confirmation operation on the prompt message, add the at least one material to the first knowledge base.

9. The method according to claim 7, wherein After displaying the first knowledge base created based on the first knowledge base account and belonging to the specific domain, the method further includes: Display a prompt message for adding materials and at least one material, where the at least one material is obtained by searching based on the features of the first knowledge base account, and the similarity between the features of the at least one material and the features of the first knowledge base account is less than a second similarity threshold; In response to a confirmation operation on the prompt message, add the at least one material to the first knowledge base.

10. The method according to claim 1, characterized in that The knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; When the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; The method further includes: In response to a permission switching operation on the first knowledge base, switch the type of the first knowledge base from the shared knowledge base to a private knowledge base, where the private knowledge base is only available for searching or using by the following accounts: The first instant messaging account, a second instant messaging account that scans the QR code shared by the first instant messaging account.

11. The method according to claim 1, wherein The knowledge base interface is logged in based on a first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; When the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; The method further includes: In response to the first knowledge base meeting a first type switching condition, switch the type of the first knowledge base from the shared knowledge base to a private knowledge base, where the private knowledge base is only available for searching or using by the following accounts: The first instant messaging account, a second instant messaging account that scans the QR code shared by the first instant messaging account.

12. The method according to claim 11, wherein The first type switching condition includes at least one of the following: The usage rate of the first knowledge base within a preset time period is lower than the usage rate threshold; The proportion of data with the exclusive identifier of the creator in the first knowledge base is greater than the first proportion threshold; The proportion of duplicate data in the first knowledge base is greater than the second proportion threshold; There is third-party authorized data in the first knowledge base and the authorization agreement prohibits conversion to private.

13. The method according to claim 1, wherein The knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; when the first knowledge base is searched and used in the knowledge base platform, the type of the first knowledge base is a shared knowledge base; In the case where the at least one knowledge base includes a second knowledge base of the type of private knowledge base, the method further includes: In response to the second knowledge base satisfying the second type switching condition, switching the type of the second knowledge base from the private knowledge base to the shared knowledge base, or displaying a prompt message for switching the type of the second knowledge base to the shared knowledge base, wherein the private knowledge base is only for the following accounts to search or use: The first instant messaging account, and the second instant messaging account that scans the graphic code shared by the first instant messaging account.

14. The method according to claim 13, wherein The second type switching condition includes at least one of the following: The number of second instant messaging accounts that initiate a collaboration request is greater than or equal to the account number threshold, wherein the second instant messaging account initiates the collaboration request by scanning the graphic code shared by the first instant messaging account; The number of data belonging to the collaboration type in the second knowledge base is greater than or equal to the collaboration data volume threshold; The proportion of data with the exclusive identifier of the creator in the second knowledge base is less than the first proportion threshold; The number of title levels of the second knowledge base is greater than or equal to the title level number threshold; The label coverage rate of the second knowledge base is greater than or equal to the coverage rate threshold; The number of version iterations of the second knowledge base is greater than or equal to the iteration number threshold.

15. The method according to claim 1, characterized in that, The knowledge base interface is logged in based on the first instant messaging account, and the first knowledge base account and the first instant messaging account belong to the same object; The method further includes: Performing at least one of the following processes: In response to the second knowledge base account satisfying the permission condition, setting the permission of the second knowledge base account to be able to edit the first knowledge base, wherein the permission condition includes: when the second knowledge base account is added to the knowledge base account list of the first knowledge base, the number of knowledge base accounts in the knowledge base account list is less than the preset number, and the knowledge base accounts included in the knowledge base account list of the first knowledge base are accounts that use the first knowledge base; In the case where the second knowledge base account is added to the knowledge base account list, in response to the permission setting operation based on the first knowledge base account, setting the permission of the second knowledge base account to be able to edit the first knowledge base; In the case where the second instant messaging account scans the graphic code shared by the first instant messaging account, set the permission of the second knowledge base account to be able to edit the first knowledge base, where the second instant messaging account and the second knowledge base account belong to the same object.

16. The method according to any one of claims 1 to 15, characterized in that The knowledge base interface includes a search control and an interaction control; The method further includes: In response to an input operation on the search control, display at least one third knowledge base, where the type of the at least one third knowledge base is the shared knowledge base, and the at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keyword; In response to an input operation on the interaction control, display the input first information and display second information for replying to the first information, where the second information is generated based on materials related to the first information searched from the third knowledge base.

17. The method according to claim 16, wherein Before displaying the second information for replying to the first information, the method further includes: Perform feature extraction processing on the first information to obtain a query vector; For the query vector and each vector index of the third knowledge base, determine a first similarity between the query vector and the vector index, where different vector indexes correspond to different materials; Based on the target vector index where the first similarity is greater than a third similarity threshold, extract the material corresponding to the target vector index from the third knowledge base; Generate the second information based on the material corresponding to the target vector index.

18. The method according to claim 17, characterized in that The generating the second information based on the material corresponding to the target vector index includes: Perform feature extraction processing on the material corresponding to the target vector index to obtain a material feature; Based on the query vector and the material feature, call a neural network model to perform text generation processing to obtain a candidate information; Split the candidate information into multiple parts; Obtain a second similarity between each part and each material feature, and determine the part where the second similarity is greater than a fourth similarity threshold as the original content of the material corresponding to the target vector index, where the type of the original content includes at least one of text or image; Determine the position information of the original content in the file to which the material corresponding to the target vector index belongs; Mark the original content in the candidate information according to the position information, and use the marked candidate information as the second information, where the original content is displayed in a manner different from other parts in the second information.

19. The method according to claim 18, wherein After displaying the second information for replying to the first information, the method further includes: Display at least part of the original content of the second target material in a manner different from other parts in the second information; In response to a trigger operation on the original content, display the file to which the second target material belongs and the position of the second target material in the file.

20. The method according to claim 17, wherein After the third knowledge base is published on the knowledge base platform, the method further includes: Performing a splitting process on each file in the third knowledge base to obtain a plurality of materials; Performing a vectorization process on each of the materials to obtain a vector representation of the material; Combining the vector representation of the material with the position of the material in the file to form a vector index of the material.

21. A data processing method for a knowledge base, characterized in that, The method includes: Displaying a knowledge base interface, where the knowledge base interface includes a search control and an interaction control; In response to an input operation on the search control, displaying at least one third knowledge base, where the type of the at least one third knowledge base is a shared knowledge base set based on a pre-created knowledge base account, and the at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keyword; In response to an input operation on the interaction control, displaying the input first information, and Displaying second information for replying to the first information, where the second information is generated based on materials related to the first information searched from the third knowledge base.

22. A data processing device for a knowledge base, characterized in that The apparatus includes: A display module for displaying a knowledge base interface, where the knowledge base interface includes at least one knowledge base; The display module is further configured to, in response to an account creation operation in the knowledge base interface, display a newly created first knowledge base account, where the first knowledge base account has the permission to publish a shared knowledge base on the knowledge base platform; The display module is further configured to, in response to a permission setting operation on the first knowledge base, when the first knowledge base is set as the shared knowledge base in the permission setting operation, publish the first knowledge base belonging to the first knowledge base account on the knowledge base platform, where the first knowledge base is used to be searched and used in the knowledge base platform.

23. A data processing device for a knowledge base, characterized in that, The apparatus includes: A display module for displaying a knowledge base interface, where the knowledge base interface includes a search control and an interaction control; The display module is further configured to, in response to an input operation on the search control, display at least one third knowledge base, where the type of the at least one third knowledge base is a shared knowledge base set based on a pre-created knowledge base account, and the at least one third knowledge base is obtained by searching in the knowledge base platform based on the input keyword; The display module is further configured to, in response to an input operation on the interaction control, display the input first information and display second information for replying to the first information, where the second information is generated based on materials related to the first information searched from the third knowledge base.

24. An electronic device, characterized in that, The electronic device includes: A memory for storing computer-executable instructions or a computer program; A processor for implementing the data processing method of the knowledge base according to any one of claims 1 to 21 when executing the computer-executable instructions or the computer program stored in the memory.

25. A computer-readable storage medium stores computer-executable instructions or a computer program, characterized in that, The computer-executable instructions or the computer program, when executed by the processor, implement the data processing method of the knowledge base according to any one of claims 1 to 21.

Images