Information processing method and apparatus for question-and-answer interface, device, medium, and program product

Abstract

Disclosed in embodiments of the present application are an information processing method and apparatus for a question-and-answer interface, a device, a medium, and a program product. The method comprises: displaying at least one first tag in a question-and-answer interface; receiving a target tag selected for question information; and outputting, in the question-and-answer interface, answer information corresponding to the question information. By using the embodiments of the present application, specific knowledge content in a knowledge base is indexed by means of tags, thereby improving the efficiency of knowledge question answering while improving the personalization of answers.

Description

Information processing methods, devices, equipment, media, and program products for question-and-answer interfaces

[0001] This application claims priority to Chinese Patent Application No. 2024119577739, filed on December 27, 2024, entitled “A knowledge question answering method, apparatus, device, medium and program product”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of computer technology, specifically to an information processing method for a question-and-answer interface, an information processing device for a question-and-answer interface, a computer device, a computer-readable storage medium, and a computer program product. Background Technology

[0003] Knowledge-based question answering refers to the process of answering user questions with accurate and concise natural language; it is a highly regarded and promising area within the field of Natural Language Processing (NLP).

[0004] Currently, existing knowledge-based question-answering solutions use the entire knowledge base as the information source for answering user questions. However, as the knowledge content in the knowledge base continues to increase, generating answers to user questions requires searching for specific information from the massive amount of knowledge in the knowledge base, which not only faces the problem of information overload but also reduces the efficiency of knowledge-based question answering. Summary of the Invention

[0005] This application provides an information processing method, apparatus, device, medium, and program product for a question-and-answer interface. By indexing specific knowledge content in a knowledge base using tags, it improves the personalization of answers while enhancing the efficiency of knowledge-based question-and-answering.

[0006] On one hand, embodiments of this application provide an information processing method for a question-and-answer interface, which is executed by a computer device and includes:

[0007] Display at least one first tag in the question-and-answer interface. The first tag is used to index at least one piece of knowledge content from the knowledge base.

[0008] Receive the target label selected for the problem information, where the target label is any one of at least one first label;

[0009] The question-and-answer interface outputs the answer information corresponding to the question information, which is generated based on the knowledge content indexed by the question information and the target tag.

[0010] On the other hand, embodiments of this application provide an information processing device for a question-and-answer interface, which is mounted in a computer device and includes:

[0011] The display unit is used to display at least one first label in the question-and-answer interface, and the first label is used to index at least one knowledge content from the knowledge base;

[0012] A processing unit is configured to receive a target label selected for problem information, wherein the target label is any one of at least one first label;

[0013] The processing unit is also used to output answer information corresponding to the question information in the question-and-answer interface. The answer information is generated based on the knowledge content indexed by the question information and the target tag.

[0014] On the other hand, embodiments of this application provide a computer device, the computer device comprising:

[0015] A processor, adapted to execute computer programs;

[0016] A computer-readable storage medium storing a computer program that, when executed by a processor, implements an information processing method such as the question-and-answer interface described above.

[0017] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed as described above for information processing of a question-and-answer interface.

[0018] On the other hand, embodiments of this application provide a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the aforementioned information processing method for a question-and-answer interface.

[0019] In this embodiment, at least one first tag is displayed in the question-and-answer interface, and each first tag can index at least one knowledge content in the knowledge base. The first tags are predefined by the user for the knowledge content in the knowledge base, such as defining first tag 1 and first tag 2 for knowledge content 1, and first tag 1 for knowledge content 2, etc. During the process of editing question information in the question-and-answer interface, users can customize the selection of target tags from at least one first tag for the edited question information. By allowing users to personalize the selection of target tags for answering questions, the generated answer information will be different when different users select different target tags for the same question, thus meeting the requirement of personalized answer information generation and improving user experience. In this way, after receiving the target tag and question information, the computer device can quickly filter the knowledge content indexed by the target tag from the knowledge base through tag indexing, and generate answer information based on the knowledge content indexed by the target tag and the question information. Compared with generating answer information based on the massive knowledge content in the knowledge base, on the one hand, it supports tag indexing to quickly locate specific knowledge content in the knowledge base as the information source of answer information, avoiding problems such as device failure caused by information overload. On the other hand, by generating answer information based solely on the knowledge content indexed by the target tags in the knowledge base, the speed and efficiency of answer generation are greatly improved, thereby enhancing the efficiency of knowledge-based question and answering and helping users improve their work efficiency and personal learning outcomes. Attached Figure Description

[0020] Figure 1a is a schematic diagram of the architecture of an information processing scenario provided by an exemplary embodiment of this application;

[0021] Figure 1b is a schematic diagram of the architecture of another information processing scenario provided by an exemplary embodiment of this application;

[0022] Figure 2 is a flowchart illustrating an information processing method for a question-and-answer interface provided in an exemplary embodiment of this application;

[0023] Figure 3a is a schematic diagram of knowledge content in a first tag index knowledge base provided by an exemplary embodiment of this application;

[0024] Figure 3b is a schematic diagram of a login knowledge question-and-answer application provided in an exemplary embodiment of this application;

[0025] Figure 3c is a schematic diagram of another login knowledge query application provided in an exemplary embodiment of this application;

[0026] Figure 3d is a schematic diagram of another login knowledge question-and-answer application provided by an exemplary embodiment of this application;

[0027] Figure 4a is a schematic diagram of a knowledge question-and-answer interface provided in an exemplary embodiment of this application;

[0028] Figure 4b is a schematic diagram of another knowledge question-and-answer interface provided in an exemplary embodiment of this application;

[0029] Figure 5a is a schematic diagram of a first label being directly displayed by default on a knowledge Q&A interface according to an exemplary embodiment of this application;

[0030] Figure 5b is a schematic diagram of another example of the present application where the first label is displayed directly on the knowledge question and answer interface by default;

[0031] Figure 6a is a schematic diagram of a first tag being displayed only when a tag activation operation is performed, according to an exemplary embodiment of this application;

[0032] Figure 6b is a schematic diagram illustrating another instance of the present application where the first label is displayed only when a label invocation operation is performed;

[0033] Figure 6c is a schematic diagram showing the first label only when a label invocation operation is performed, according to an exemplary embodiment of this application;

[0034] Figure 7 is a schematic diagram of selecting a first tag and deleting the selected first tag according to an exemplary embodiment of this application;

[0035] Figure 8a is a schematic diagram of a tag filtering method provided in an exemplary embodiment of this application;

[0036] Figure 8b is a schematic diagram of an exemplary embodiment of this application providing a method for building an inverted index for a first tag;

[0037] Figure 8c is a schematic diagram of the architecture of a knowledge base interaction system provided in an exemplary embodiment of this application;

[0038] Figure 9 is a schematic diagram of an exemplary embodiment of this application, which provides a method for generating answer information corresponding to question information based on target tags;

[0039] Figure 10 is a flowchart illustrating another information processing method for a question-and-answer interface provided in an exemplary embodiment of this application;

[0040] Figure 11a is a schematic diagram of an object setting a first tag for knowledge content in a knowledge base, provided by an exemplary embodiment of this application;

[0041] Figure 11b is a schematic diagram of an object selecting multiple information sources for problem information, provided in an exemplary embodiment of this application;

[0042] Figure 12 is a schematic diagram of an object setting priority for an information source according to an exemplary embodiment of this application;

[0043] Figure 13 is a schematic diagram of information source switching during a round of knowledge question answering provided by an exemplary embodiment of this application;

[0044] Figure 14 is a schematic diagram illustrating how to quickly locate knowledge content by triggering a target tag in a question message, according to an exemplary embodiment of this application.

[0045] Figure 15 is a schematic diagram of hiding or restoring the display of the question and answer area in a knowledge question and answer interface according to an exemplary embodiment of this application;

[0046] Figure 16 is a schematic diagram of an exemplary embodiment of this application, which illustrates how to quickly search for knowledge content indexed by a third tag using a search box in an information display area;

[0047] Figure 17 is a schematic diagram of a method for quickly locating knowledge content and segmented content based on an information source entry point, provided by an exemplary embodiment of this application;

[0048] Figure 18 is a schematic diagram of the overall flow of an information processing method for a question-and-answer interface provided in an exemplary embodiment of this application;

[0049] Figure 19 is a schematic diagram of the structure of an information processing device with a question-and-answer interface provided in an exemplary embodiment of this application;

[0050] Figure 20 is a schematic diagram of the structure of a computer device provided in an exemplary embodiment of this application. Detailed Implementation

[0051] This application provides an information processing method, specifically a method for implementing knowledge question answering by indexing specified knowledge content in a knowledge base using tags. The following is a brief introduction to the technical terms and related concepts involved in the information processing method provided in this application:

[0052] I. Knowledge Q&A.

[0053] Knowledge-based question answering, also known as intelligent question answering (QA), open-ended question answering, or interactive dialogue, belongs to the field of human-computer interaction. It encompasses both knowledge and questions. Knowledge refers to the collection of all retrievable materials and documents, while questions refer to the user's questions and the intelligent assistant's answers. Knowledge-based question answering is an advanced form of information retrieval system. It primarily involves receiving user questions through computer devices, generating corresponding answers, and then responding to the user's questions using accurate and concise natural language. With the rapid development and application of Artificial Intelligence (AI), knowledge-based question answering technology has become a highly anticipated and promising area within the field of Natural Language Processing (NLP).

[0054] In information processing scenarios, knowledge-based question-and-answer applications are commonly involved. These applications are characterized by interactive dialogue capabilities. In this embodiment, a smart assistant is used as an example. A smart assistant, or smart assistant application, refers to intelligent software deployed on a terminal that enables human-computer interaction with the user through voice, text, and images, providing rich functions such as information retrieval, life services, and learning guidance. A smart assistant can be deployed as an application on the terminal; an application is a computer program designed to perform one or more specific tasks. Classified by their operation method, applications can include, but are not limited to: clients that require downloading and installing a package, which is then deployed on the terminal to provide intelligent question-and-answer functionality; small programs that run as subroutines on the client without requiring a download; and web (World Wide Web) applications opened and run through a browser on the terminal; and so on. This application does not limit the way the intelligent assistant runs on the terminal. Taking the intelligent assistant as a client deployed and running on a PC (Personal Computer) as an example, that is, the intelligent assistant can be understood as a kind of PC-side intelligent workbench (such as a client with knowledge question-and-answer capabilities installed and running on a PC - a browser), which aims to use artificial intelligence technology to improve the efficiency of information retrieval, information browsing and information accumulation in the knowledge question-and-answer process.

[0055] In information processing scenarios, the process of implementing human-computer dialogue or knowledge-based question answering can include: a user inputs a question message into a smart assistant. After receiving the question message, the smart assistant sends it to a backend system. The backend system processes the question indicated by the message, obtaining an answer message that addresses the question. The backend system returns the answer message to the smart assistant, enabling it to output an accurate and concise natural language response to resolve the user's question. The question processing process mainly includes: question understanding, knowledge retrieval, and answer generation. Question understanding primarily involves using techniques such as question classification and keyword extraction to enable the computer to understand the semantics of the user-input question. Knowledge retrieval involves retrieving knowledge content matching the user's input from the smart assistant's knowledge base management system. Answer generation mainly includes answer extraction and verification, aiming to generate a corresponding answer to the question from the retrieved knowledge content.

[0056] II. Knowledge Base.

[0057] A knowledge base refers to a personal knowledge base within a smart assistant. In other words, a knowledge base can be understood as a collection of knowledge content created by the user on the smart assistant; the user adds knowledge content to this collection through operations such as collecting, uploading, or downloading to build their own personal knowledge base. The knowledge content in the knowledge base can include, but is not limited to, multimedia resources in various formats such as documents, files, images, web pages, audio, video, and animations. This application embodiment does not limit the quantity or format of the knowledge content in the knowledge base.

[0058] In this embodiment, the knowledge base management system supports the management of knowledge bases created by multiple users registered with the intelligent assistant. Management may include, but is not limited to, adding, deleting, or modifying knowledge content in the knowledge base, as well as querying or retrieving the knowledge base or its content. For example, in the process of knowledge question answering in an information processing scenario, knowledge retrieval is involved. The knowledge base management system can use the user's knowledge base as an information source (or information source, i.e., a reference for answer generation) for knowledge retrieval. In other words, when retrieving knowledge content that matches the question to be answered, the knowledge base management system can use the knowledge content in the user's knowledge base as the source of the answer to the corresponding question.

[0059] In practical applications, knowledge-based question-answering systems suffer from problems such as slow response efficiency, severe template-based approach, and poor question-answer quality. For example, when performing knowledge retrieval, the entire knowledge base is used as the information source. Retrieving relevant knowledge points from the massive amount of content in the knowledge base can lead to several issues. First, the relevance between the searched knowledge points and the question may decrease, thus reducing the quality of the question-answer. Second, as the amount of knowledge in the knowledge base increases, information overload may occur, resulting in slow response efficiency. Furthermore, given a similar knowledge base, when different users ask the same question, the computer retrieves the same or similar knowledge points using the same retrieval logic, leading to identical or similar answers and severe template-based responses.

[0060] To improve the quality and efficiency of question-and-answer systems, the information processing method for the question-and-answer interface provided in this application mainly introduces tags to each knowledge content in the knowledge base included in the knowledge base management system. This helps users manage knowledge content in a personalized way, while also making it easier for users to find and organize knowledge content. For example, users can directly ask and answer questions based on specific knowledge content under a certain tag, thus improving the personalization of knowledge question-and-answer. The information processing method for the question-and-answer interface provided in this application mainly includes: tag definition and tag indexing. The specific implementation process of tag definition and tag indexing in the information processing method of the question-and-answer interface is briefly introduced below:

[0061] (1) Tag definition refers to: users defining tags for different knowledge content in the knowledge base in a personalized way; that is, the embodiments of this application support users to customize the first tag for the knowledge content according to their own understanding of the knowledge content; the tags defined for different knowledge content can be the same or different. Among them, the tag can be understood as the information obtained by summarizing the knowledge content, such as the tags "new energy", "quantum theory", "autonomous driving" and "relativity".

[0062] (2) Tag indexing refers to the process of automatically indexing the knowledge content defined by the first tag selected by the user for the question information during the knowledge question-and-answer process. Specifically, the question-and-answer interface provided by the intelligent assistant displays at least one first tag, each of which is used to index at least one knowledge content from the user's personalized knowledge base. During the process of editing the question information in the question-and-answer interface, the user can select a target tag for the question information in a personalized way. The target tag is any one of the at least one first tag. In this way, the intelligent assistant can index the specific knowledge content defined by the target tag in the user's knowledge base management system based on the target tag selected by the user, thereby generating answer information corresponding to the question information based on the specific knowledge content and the question information, and outputting the answer information so that the user can view the answer information in a timely manner.

[0063] Practice has shown that the information processing method for the question-and-answer interface provided in this application has significant advantages in knowledge retrieval. The advantages of this application's embodiments are illustrated below by comparing the method of this application with existing mainstream question-and-answer scenarios for knowledge retrieval.

[0064] The existing mainstream question-and-answer methods for knowledge retrieval suffer from at least the following shortcomings: 1) Limited information sources: Some products only support collecting knowledge content, but when conducting knowledge-based question-and-answer sessions, they rely solely on information sources on the public internet, failing to fully utilize user-organized / collected knowledge content and thus failing to match information sources with user needs. 2) Limitations of knowledge retrieval (or information retrieval): Most products cannot enable flexible questioning based on knowledge bases, restricting users' ability to retrieve knowledge content and hindering efficient use of their personal knowledge bases. 3) Limited knowledge base management functions: Some products only support using the entire knowledge base as the information source for knowledge retrieval, limiting knowledge retrieval to simple keyword matching and lacking in-depth analysis and intelligent response capabilities.

[0065] However, the information processing method for the question-and-answer interface provided in this application has at least the following advantages: 1) Custom tags: It supports users to customize the first tag for knowledge content, which not only ensures that users can select the first tag corresponding to the knowledge content they want to refer to based on their memory when defining the tag in subsequent knowledge question-and-answer processes, thus helping users to generate personalized answers. Moreover, considering that different users have different understandings of the same knowledge content, allowing users to customize the first tag of knowledge content makes it easier for the knowledge content retrieved through the first tag in subsequent knowledge question-and-answer processes to be the content that users actually want to refer to, thereby ensuring that the answers generated based on the knowledge content meet the user's expectations and improving the user experience. 2) Improved information retrieval efficiency: In the knowledge question-and-answer process, by customizing target tags for question information, users can quickly and accurately find specific knowledge content indexed by the target tag in the knowledge base. Computer devices (or intelligent assistants, knowledge question-and-answer systems, knowledge base management systems) do not need to filter through a large amount of irrelevant knowledge content, which greatly saves time and effort and improves the efficiency and accuracy of information retrieval. 3) Enhance user experience: This application's embodiments introduce a question-asking function based on knowledge base tags and optimize the interaction, which not only enhances the interactivity between users and the knowledge base and improves the relevance and efficiency of information retrieval, but also simplifies the user's operation process, promotes the effective management and application of personal knowledge, and thus improves work efficiency and personal learning outcomes.

[0066] The knowledge-based question-and-answer system provided in this application embodiment serves as an automated question-and-answer solution for human-computer interaction. It can understand, parse, and answer user-submitted questions. This makes the information processing method for the question-and-answer interface provided in this application embodiment applicable to various interactive dialogue scenarios that require the use of a knowledge-based question-and-answer system for inquiry. Interactive dialogue scenarios may include, but are not limited to: 1) Customer support: The knowledge-based question-and-answer system can serve as a customer support tool to answer users' common questions, reducing the workload of customer service personnel and improving customer satisfaction. 2) Enterprise internal knowledge base: Enterprises can utilize the knowledge-based question-and-answer system to build internal knowledge bases, helping employees quickly find the information they need and improving work efficiency. 3) Virtual assistant: The knowledge-based question-and-answer system can serve as a virtual assistant for individuals or enterprises, providing functions such as daily task management, scheduling, and reminder services. 4) Online education: The knowledge-based question-and-answer system can be applied to the field of online education, providing students with personalized learning resources and real-time Q&A services. 5) E-commerce: The knowledge-based question-and-answer system can help users answer questions during the shopping process, provide shopping suggestions, and improve the shopping experience. 6) Financial services: The knowledge-based question-and-answer system can provide real-time consultation services to customers of financial institutions such as banks and insurance companies, answering questions about accounts, transactions, and products. 7) Medical Consultation: The knowledge-based Q&A system can provide patients with basic medical consultation services, answering questions about diseases, treatments, medications, etc. 8) Tourism Consultation: The knowledge-based Q&A system can provide tourists with real-time tourism information, answering questions about attractions, hotels, transportation, etc. 9) News and Information Retrieval: The knowledge-based Q&A system can help users quickly find the news and information they need, improving the efficiency of information retrieval.

[0067] It should be understood that the above description is merely an exemplary product performance and interactive dialogue scenario provided by the embodiments of this application, and does not limit the product performance and interactive dialogue scenario of the information processing method with question-and-answer interface provided by the embodiments of this application. The knowledge question-and-answer system provided by the embodiments of this application can provide efficient, accurate and convenient question-and-answer services in various interactive dialogue scenarios, demonstrating high value and practicality in various interactive dialogue scenarios, and helping to improve user experience and satisfaction.

[0068] For ease of explanation, a schematic diagram of an information processing scenario is given below with reference to Figure 1a. As shown in Figure 1a, the information processing scenario includes object 101, terminal 102, server 103 and server 104. In this embodiment of the application, the number and naming of object 101, terminal 102, server 103 and server 104 are not limited.

[0069] In this context, object 101 refers to the user holding terminal 102. Terminal 102 can be a terminal device with interactive dialogue capabilities; this terminal device runs on the aforementioned intelligent assistant (e.g., if the intelligent assistant is a PC-based intelligent question-and-answer platform, then the terminal device is a PC). Object 101 can interact with the intelligent assistant through terminal 102 to ask questions. Terminal devices can include, but are not limited to: smartphones (such as smartphones running the Android system, or smartphones running the Internetworking Operating System (IOS)), tablets, portable personal computers, mobile internet devices (MIDs), in-vehicle devices, head-mounted devices, intelligent chatbots, and aircraft, etc. This application embodiment does not limit the type of terminal device, which is stated herein.

[0070] Servers 103 and 104 are both servers corresponding to terminal 102, used to interact with terminal 102 to provide computing and application service support, specifically providing application services and technical support for the intelligent assistant running on terminal 102. For example, server 103 can be a knowledge question-and-answer system, mainly used to interact with terminal 102 to implement some interactive processes in the knowledge question-and-answer process; server 104 can be a knowledge base management system, used to store, manage, and retrieve users' personalized knowledge bases and the first tags of knowledge content. Servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. For example, server 103 is an independent physical server, where terminal 102, server 103, and server 104 can be directly or indirectly connected via wired or wireless communication; this application does not impose any limitations on this.

[0071] The information processing method for the question-and-answer interface provided in this application embodiment can be executed by a computer device, in which a smart assistant is deployed or running. The computer device can be a terminal or a server in the system shown in Figure 1a, or the computer device can include both a terminal and a server. In other words, the information processing method for the question-and-answer interface provided in this application embodiment can be executed by a terminal or a server, or jointly by a terminal and a server. The following describes the flow of the information processing method for the question-and-answer interface, taking as an example a computer device including terminal 102, server 103, and server 104, i.e., jointly executed by terminal 102, server 103, and server 104. The process is illustrated in the information processing scenario shown in Figure 1a.

[0072] 1) Object 101 is a custom first tag for the knowledge content in the knowledge base.

[0073] Specifically, object 101 can set a first tag for knowledge content. For example, if the knowledge content is a webpage about new energy vehicles and object 101 wants to set the first tag "new energy" for the webpage, then object 101 can upload the first tag "new energy" through the tag setting interface displayed on terminal 102. Terminal 102 sends the first tag "new energy" and the relevant information of the webpage (such as a unique identifier for the webpage) to the server 104 corresponding to the knowledge base management system. The server 104 then establishes an index relationship between the first tag "new energy" and the webpage and stores the index relationship between the first tag "new energy" and the webpage in the database. For example, if object 101 sets the first tag 1 for both knowledge content 1 and knowledge content 2, and sets the first tag 2 for knowledge content 3, then the knowledge content and the first tag can be stored in the database in the form of key-value pairs.

[0074] 2) Object 101 interacts with the intelligent assistant to achieve knowledge Q&A.

[0075] Specifically, when object 101 has interactive dialogue needs, it can open the question-and-answer interface provided by the intelligent assistant through terminal 102. This question-and-answer interface can be called a knowledge question-and-answer interface, which can be used for question-and-answer dialogue based on the knowledge accessed or searched by the intelligent assistant. In subsequent embodiments, the question-and-answer interface and the knowledge question-and-answer interface are not distinguished. At least one first tag can be displayed in the knowledge question-and-answer interface, and object 101 can select a target tag from the at least one first tag for the question-and-answer information to be answered. Terminal 102 sends the question information edited by object 101 and the selected target tag to the server 103 corresponding to the knowledge question-and-answer system. Server 103 analyzes the question information and sends the target tag to the server 104 corresponding to the knowledge base management system, so that server 104 can index at least one knowledge content in the knowledge base according to the target tag. Server 104 returns at least one knowledge content indexed by the target tag to server 103; server 103 determines at least one content segment for generating the answer based on the matching degree between the question information and the content segments included in the knowledge content, and generates answer information based on the content segment and the question information. Server 103 returns the answer information to terminal 102 so that terminal 102 can display the answer information in the knowledge Q&A interface through the smart assistant, so that object 101 can intuitively perceive the answer information corresponding to the question information.

[0076] Based on the above brief introduction to the information processing method and information processing scenario of the question-and-answer interface provided in the embodiments of this application, the following points should also be noted:

[0077] (1) The system architecture shown in Figure 1a mentioned above in the embodiments of this application is for the purpose of more clearly illustrating the technical methods of the embodiments of this application, and does not constitute a limitation on the technical methods provided in the embodiments of this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical methods provided in the embodiments of this application are also applicable to similar technical problems. That is to say, Figure 1a is only a schematic diagram of the architecture of an information processing scenario and is an exemplary schematic diagram; in actual applications, the number and distribution of computer devices included in the information processing scenario may change, and the embodiments of this application do not limit the schematic diagram of the architecture of the information processing scenario.

[0078] For example, Figure 1a illustrates a centralized system for both the question-answering system and the knowledge base management system. A centralized system is one where the system (such as a question-answering system or a knowledge base management system) is controlled by a central processing unit (which can be deployed on one or more computer devices). All tasks in the information processing scenario are uniformly processed and executed by this central processing unit, without the need for network connections or node configuration. However, in practical applications, the question-answering system and the knowledge base management system can also be distributed systems. A distributed system is one where multiple distributed computer devices are interconnected through a network. In a distributed system, computer devices can exchange information, and processing and control functions are distributed across various computer devices, with no master-slave relationship between the devices. As shown in Figure 1b, both the question-answering system and the knowledge base management system consist of multiple servers deployed on different servers, forming a distributed network. Alternatively, in practical applications, the question-answering system and the knowledge base management system can be deployed on the same server or in the same distributed network.

[0079] (2) The data collection and processing in this application embodiment should strictly comply with the requirements of relevant laws and regulations. The acquisition of personal information must be based on the knowledge or consent of the individual (or have a legal basis for information acquisition), and subsequent data use and processing should be carried out within the scope of laws and regulations and the authorization of the personal information subject. For example, when this application embodiment is applied to specific products or technologies, such as when submitting question information, the user's permission or consent is required, and the collection, use and processing of relevant data (such as question analysis, knowledge retrieval and answer generation of question information) must comply with the relevant laws, regulations and standards of the relevant country and region.

[0080] Figure 2 shows a flowchart illustrating an information processing method for a question-and-answer interface according to an exemplary embodiment of this application; the information processing method can be executed by a computer device, which can be terminal 102 in the system / scenario shown in Figure 1a. The information processing method may include, but is not limited to, steps S201-S203:

[0081] S201: Display at least one first tag in the question and answer interface.

[0082] A knowledge-based Q&A interface is a user interface (UI) capable of answering knowledge-related questions. This UI serves as the medium for interaction and information exchange between the operating system and the user, enabling the conversion between the internal form of information and a human-readable format. In other words, a knowledge-based Q&A interface is a service interface provided by an intelligent assistant running on a computer device; users can interact with this interface to answer knowledge-related questions.

[0083] In specific implementation, when an object has a query requirement, it can open a knowledge-based question-and-answer application on a computer device (such as the aforementioned browser deployed on a PC device with knowledge-based question-and-answer capabilities) and use its own object identifier (i.e., an identifier that uniquely identifies the object, such as a user ID, nickname, etc., if the object identifier is assigned to the object by the knowledge-based question-and-answer application when the object registers) to perform a login operation in the knowledge-based question-and-answer application. At this time, the computer device responds to the login operation for the object identifier in the knowledge-based question-and-answer application and displays the knowledge service interface of the knowledge-based question-and-answer application. The knowledge service interface includes a question-and-answer trigger component (or question-and-answer trigger options, question-and-answer trigger buttons, question-and-answer trigger controls, etc.) for entering the knowledge-based question-and-answer interface. Thus, when the object performs a trigger operation on the question-and-answer trigger component in the knowledge service interface, the knowledge-based question-and-answer interface is displayed. This knowledge-based question-and-answer interface can display at least one first tag defined in the object's personalized knowledge base, and each tag is used to index at least one knowledge content from the knowledge base. Therefore, this application embodiment requires objects to log in to the knowledge question and answer application using their own object identifiers. This enables the display of a first tag customized by the object in the knowledge question and answer interface, improving the correlation between the object and the tag. For example, a schematic diagram of a first tag indexing knowledge content in a knowledge base can be seen in Figure 3a; as shown in Figure 3a: the knowledge base includes knowledge content 1, knowledge content 2, and knowledge content 3. Knowledge content 1 is defined with first tag 1, first tag 2, and first tag 3; knowledge content 2 is defined with first tag 2; and knowledge content 3 is defined with first tag 4. Then, the first tags displayed in the knowledge question and answer interface include: first tag 1, first tag 2, first tag 3, and first tag 4; wherein, the knowledge content indexed by first tag 1 includes knowledge content 1, the knowledge content indexed by first tag 2 includes knowledge content 1 and knowledge content 2, the knowledge content indexed by first tag 3 includes knowledge content 1, and the knowledge content indexed by first tag 4 includes knowledge content 3.

[0084] The login operation of an object using its object identifier to log in to a knowledge-based Q&A application can include, but is not limited to, scanning login, password login, and link login. Specifically: 1) Scanning login refers to the process where a graphical code (such as a QR code) is displayed on the login interface provided by the knowledge-based Q&A application, and the object automatically logs in after scanning the graphical code using a terminal device (such as a smartphone or tablet). An exemplary diagram of scanning login can be seen in Figure 3b, where a graphical code 301 is displayed on the login interface. When the terminal successfully scans the graphical code 301 and confirms the login, it automatically logs in to the knowledge-based Q&A application using its object identifier. 2) Password login refers to the process where the object logs in using its object identifier by entering a password on the login interface provided by the knowledge-based Q&A application. This password can be a static password or a dynamic password. A static password is a fixed password pre-set by the object, while a dynamic password is a password (such as a verification code) dynamically issued by the knowledge-based Q&A application each time the object logs in. An exemplary diagram of password login can be seen in Figure 3c. 3) Linked login refers to the process of automatically logging into the knowledge access permission application using an object identifier that is logged into the computer device (such as the object identifier being logged into another application independent of the knowledge access permission application, or the object identifier being directly logged into the computer device). A schematic diagram of an exemplary linked login can be seen in Figure 3d, where a login link 302 is displayed in the login interface of the knowledge access permission application. When the login link 302 is triggered, the object identifier corresponding to the login link 302 is used to automatically log into the knowledge access permission application.

[0085] This application embodiment sets one or more question triggering components in the knowledge service interface, each question triggering component corresponds to a different knowledge Q&A interface, and each knowledge Q&A interface supports knowledge Q&A. The following, in conjunction with the accompanying drawings, provides two exemplary processes for displaying a knowledge Q&A interface through question-and-answer triggering components; wherein:

[0086] (1) As shown in Figure 4a, after logging into the knowledge question and answer application using the object identifier, a knowledge service interface 401 is displayed. This knowledge service interface 401 includes a question triggering component 402 corresponding to the knowledge base. When the object performs a triggering operation on the question triggering component 402, the computer device displays a knowledge question and answer interface 403 corresponding to the knowledge base. Considering that the knowledge question and answer interface 403 is displayed by triggering the question triggering component 402 corresponding to the knowledge base, the knowledge question and answer interface 403 may include a question and answer area 404 and an information display area 405. Wherein: 1) Question and answer area 404 is an area that supports interactive dialogue. This question and answer area 404 includes a message display sub-area 4041 and a dialogue sub-area 4042. The message display sub-area 4041 is used to display or present the question message and answer message generated by a round of knowledge question and answer. The question message can be understood as a message bubble (or dialogue bubble) that includes at least question information, such as the question message 40411 including the question information "Is the weather suitable for playing football today?". The question message provided in this application embodiment may also include a target tag selected for the question information, such as the target tag "#new energy" and the question information "electric vehicle quality..." in question message 40412. Similarly, the answer message is a message bubble that includes answer information, such as the answer message 40413 for question message 40411 including the answer information "The weather is sunny and suitable for playing football". 2) The information display area 405 is used to display relevant content from the information source. For example, if the information source is a knowledge base, the information display area 405 is used to display the knowledge content in the knowledge base. If the information source is the Internet, the information display area 405 may display relevant content from the Internet.

[0087] (2) As shown in Figure 4b, after logging into the knowledge Q&A application using the object identifier, the knowledge service interface 401 is displayed. This knowledge service interface 401 includes a question triggering component 406 corresponding to the knowledge Q&A application. When the object performs a triggering operation on the question triggering component 406, the computer device displays the knowledge Q&A interface 407 corresponding to the knowledge Q&A application. Since the knowledge Q&A interface 407 is displayed by triggering the question triggering component 406 corresponding to the knowledge Q&A application, it only includes a Q&A area 408. The Q&A area 408 also includes a message display sub-area and a dialogue sub-area, which can be seen in the relevant content of Figure 4a, and will not be described in detail here.

[0088] In summary, Figures 4a and 4b illustrate two triggering methods and interface styles for knowledge Q&A interfaces provided in this application embodiment. The information processing method for the Q&A interface provided in this application embodiment is applicable to each type of knowledge Q&A interface; for example, functions such as tag indexing and tag filtering can be implemented on both types of knowledge Q&A interfaces. For ease of explanation, the following description will take the knowledge Q&A interface displayed by triggering the Q&A triggering component corresponding to the knowledge base as an example to further illustrate this application embodiment, which is hereby explained.

[0089] Furthermore, when an individual has a query requirement, they can conduct a knowledge-based question and answer session in the question-and-answer area of ​​the knowledge-based question and answer interface. Specifically, while editing question information in the dialogue sub-area of ​​the question-and-answer area, the individual can select a target tag for the question. In this way, at least one knowledge item in the knowledge base indexed by that target tag can serve as the information source for the answer information corresponding to the question. That is, the scope of the information source is narrowed from the entire knowledge base to at least one knowledge item indexed by the target tag, effectively reducing the workload of knowledge retrieval and improving the matching between the information source and the question information, thereby improving the accuracy of the answer information to a certain extent.

[0090] Specifically, the process of an object selecting a target tag for question information in the knowledge question and answer interface may include: displaying at least one first tag in the knowledge question and answer interface; during the process of the object editing question information in the dialog sub-area of ​​the question and answer area, selecting a target tag for the question information from at least one first tag, where the number of target tags may be one or more; and displaying the selected target tag and question information together in the dialog sub-area as a question message to be sent.

[0091] The timing of the display of the first tag defined for knowledge content in the knowledge base in the knowledge Q&A interface includes: the first tag is displayed in the knowledge Q&A interface by default, or the first tag is displayed only after a tag-invocation operation is performed. In other words, the first tag can be displayed in the knowledge Q&A interface by default when it is displayed, or it can be displayed only after an object performs a tag-invocation operation. The following describes these two display timings with reference to the attached diagram:

[0092] 1) The first tag is displayed by default in the Q&A interface.

[0093] Specifically, after the knowledge Q&A interface is triggered and displayed, the first tag defined for the knowledge content in the knowledge base is displayed directly on the knowledge Q&A interface by default. As shown in Figure 5a, the first tag can be displayed in a specified position 501 in the dialog sub-area. Of course, the first tag can also be displayed in other display positions in the knowledge Q&A interface by default, without limitation. As shown in Figure 5b, the first tag can also be displayed in a floating window 502, which is displayed above the knowledge Q&A interface. On the one hand, the display position of the floating window 502 can be flexibly controlled by the object. For example, the object can adjust the display position of the floating window 502 by dragging it to meet the object's personalized display requirements. On the other hand, the floating window 502 can also be hidden or shown by the object itself. For example, the floating window 502 includes a hide option 5021. In response to the object's trigger operation on the hide option 5021, the computer device hides the floating window 502 on the knowledge Q&A interface and displays a prompt message 503. When the prompt message 503 is triggered, the display of the floating window 502 can be restored, which greatly facilitates the object's control over the display state of the floating window 502 and improves the object's experience.

[0094] 2) Based on the tag-invoking operation performed on the object, display at least one first tag in the knowledge Q&A interface.

[0095] Specifically, when an object is editing question information in a dialog sub-area of ​​the question-and-answer region (e.g., before editing, during, or after editing), if they want to select a target tag for the question information, they can perform a tag recall operation in the knowledge question-and-answer interface. At this time, the computer device responds to the tag recall operation in the knowledge question-and-answer interface by displaying a tag filtering window. This window displays at least one first tag defined in the knowledge base for the knowledge content. By recalling at least one first tag in the tag filtering window through the tag recall operation, the object can select an answer reference tag that matches the question information from at least one first tag, thereby improving the matching between the information source and the question information and increasing the accuracy of the answer information.

[0096] The tag activation operation performed in the knowledge Q&A interface can include any of the following:

[0097] a. Input operations for shortcut keys in the dialog sub-area. Shortcut keys can include, but are not limited to: specific characters entered via a virtual or physical keyboard (such as "#", "*", or "tag"), or a key on a computer device (such as double-clicking a volume key), etc. Taking the shortcut key "#" as an example, as shown in Figure 6a, when an object enters the character "#" in the dialog sub-area, the tag filter window 601 is automatically invoked, displaying at least one first tag. b. Triggering operations of the tag component. As shown in Figure 6b, assuming that the dialog sub-area of ​​the question-and-answer area in the knowledge question-and-answer interface displays a tag component 602; when an object wants to add a target tag, the object can actively perform a click operation on the tag component 602. At this time, the computer device responds to the click operation of the tag component 602, triggering the display of the tag filter window 601, and displaying at least one first tag in the tag filter window 601. c. Specified gesture operations. Gesture operations can include, but are not limited to: double-click operations (such as two consecutive clicks on the same position on the display plane using a finger, mouse, or stylus), sliding operations with a specified trajectory (such as a sliding operation with a specified trajectory shape of S), long-press operations, or knuckle operations (such as a click operation using a knuckle). As shown in Figure 6c, taking a sliding operation with a specified trajectory as an example; if an object performs a sliding operation with an S-shaped trajectory on the dialog sub-area (or knowledge Q&A interface), indicating that the object wants to activate the first tag, then the tag filtering window 601 is displayed, and at least one first tag is displayed in the tag filtering window 601.

[0098] It should be noted that the above are only three exemplary tag activation operations given in the embodiments of this application; in actual product design, developers can also set other feasible tag activation operations according to the object requirements. The specific implementation process of the tag activation operation is not limited in this embodiment of the application.

[0099] S202: Receive the target label selected for the problem information.

[0100] Based on step S201, after at least one first tag is displayed in the knowledge question and answer interface (e.g., displayed by activating the tag filter window or displayed by default in the knowledge question and answer interface), the object can select a tag from at least one first tag as the target tag for the question and answer information to be answered. When the computer device detects that the object has performed a selection operation on one or more first tags, it determines that the computer device has received the target tag selected by the object for the question information. As shown in Figure 7, first tags 701, 702, and 703 are displayed in the tag filter window. The object can select one or more first tags as the target tag according to its own needs, such as selecting first tag 701 as the target tag for the question information, or selecting first tags 701 and 702 as the target tags for the question information. At this time, the computer device receives the target tag selected for the question information and displays the selected target tag in the dialog sub-area so that the object can intuitively perceive the selected target tag.

[0101] This application embodiment also supports the deletion of target labels in the dialog sub-region by the object to meet the object's need to change the target label for the question information selection; continuing to refer to Figure 7, if the object wants to cancel the first label 701 as the target label, when the object triggers the first label 701 in the dialog sub-region (such as controlling the mouse to place the cursor on the first label 701, or performing a click operation on the first label), the cancellation option 7011 corresponding to the first label 701 is displayed. If the object triggers the cancellation option 7011, it indicates that the object wants to cancel the first label 701 as the target label for the question information, and the first label 701 is deleted in the dialog sub-region.

[0102] Furthermore, considering that the number of first tags defined for knowledge content in the knowledge base may be large, this application embodiment also provides a tag filtering function (or tag retrieval function) to facilitate quick selection of the desired target tag by the user. Tag filtering refers to filtering and displaying at least one second tag related to the input information entered by the user in the dialog sub-area in real time. This second tag belongs to at least one first tag. Through this tag filtering function, the user can flexibly and quickly locate the desired second tag from a large number of first tags, shortening the tag selection time and improving the user's question-and-answer experience.

[0103] Specifically, after an object performs a tag activation operation in the knowledge Q&A interface, such as entering # in the dialog sub-area to activate the tag filtering window, the object can continue to input information, such as in the dialog sub-area. At this time, the computer device receives the input information entered by the object in the knowledge Q&A interface, specifically the input information edited in the dialog sub-area. Furthermore, in the tag filtering window, at least one first tag is updated and displayed as at least one second tag related to the input information. The second tag being related to the input information can mean that the input information is contained within the second tag, such as the input information being "new energy" and the second tag being "new energy source"; or that the semantic features of the second tag are the same as or similar to the semantic features of the input information, such as the input information being "electric vehicle" and the second tag being "new energy vehicle". As shown in Figure 8a, when the object enters # in the dialog sub-area, a tag filtering window is output, which includes all the first tags defined for all knowledge content in the knowledge base. Then, the user can continue to edit the input information in the dialog sub-area. For example, if the input information is "new", the computer device receives this input information and performs tag filtering based on it to obtain at least one second tag related to the input information. For example, the second tags may include "news", "new energy", and "new energy vehicles...". The computer device displays at least one second tag in the tag filtering window in real time; this helps the user quickly define and find the specified second tag from a large number of first tags, improving the flexibility of tag selection. The user can continue to edit the input information. For example, if the input information is "new energy", the computer device will continue to perform tag filtering based on the received new input information to obtain at least one second tag related to the new input. At this time, the second tags may include "new energy" and "new energy vehicles...", until the user finds the second tag they want to use.

[0104] If at least one of the first tags does not contain a second tag related to the input information, the input information edited by the object can be used as part of the question information. In other words, if the object performs a tag invocation operation and the edited input information does not find a relevant second tag or the object does not select a second tag, then this input information is used as part of the question information, and the object can continue editing the question information. In this way, based on the relevance between the input information edited by the object and the first tag, the input information edited by the object can be flexibly handled (e.g., finding a second tag or using it as part of the question information), reducing the sense of separation between inputting question information and selecting a target tag during object editing, and improving the question-and-answer experience.

[0105] Figure 8a above describes the tag filtering function from the interface perspective. The following describes the backend logic of the computer device filtering tags based on the input information received. Specifically, during the process of setting or defining the first tag for knowledge content, the computer device performs word segmentation on the set first tag and establishes a multi-field and multi-dimensional inverted index for that first tag in the knowledge base interaction system corresponding to the knowledge question answering application. This aims to quickly retrieve or index the second tag related to the input information based on the input information edited by the object. The following explains the various concepts mentioned above, including:

[0106] 1) Word segmentation of the first tag involves dividing the first tag into multiple independent fields, such as words or phrases, according to segmentation rules, for subsequent tag filtering. For example, the segmentation rule can be to divide the first tag into strings; if the first tag is "new energy", then the keywords obtained from word segmentation of the first tag may include "new", "energy", "source", "new energy", and "energy". Another example is word segmentation based on semantic segmentation of the first tag; if the first tag is "new energy", the keyword obtained from word segmentation is "energy".

[0107] 2) An inverted index is an indexing method used to store the mapping of the storage location of a keyword within a set of first tags. It allows objects to quickly find the first tags containing the keyword (the first tag is then called the second tag) by editing the keyword (i.e., inputting information), greatly improving the efficiency of tag retrieval. Multi-field and multi-dimensional inverted indexes refer to the ability to create multiple inverted indexes for the same first tag based on different fields or dimensions. As shown in Figure 8b, inverted indexes are created according to fields, specifically by dividing the first tag into strings. For example, if the first tag "new energy" is segmented into the keywords "new" and "energy," the first tag "news" is segmented into the keyword "new," and the first tag "traditional energy" is segmented into the keyword "energy," then when creating an inverted index for the keyword "new," the first tags "new energy" and "news" can be retrieved based on the keyword "new." Similarly, when creating an inverted index for the keyword "energy," the first tags "new energy" and "traditional energy" can be retrieved based on the keyword "energy." Inverted indexes are built semantically. Specifically, the first tag is defined semantically. For example, if the first tag "new energy" corresponds to the keyword "energy," the first tag "news" corresponds to the keyword "information," and the first tag "traditional energy" corresponds to the keyword "energy," then when building an inverted index for the keyword "energy," the first tags that can be retrieved include "new energy" and "traditional energy." Similarly, when building an inverted index for the keyword "information," the first tags that can be retrieved include "news." In summary, building inverted indexes by field and by semantics are two dimensions for building inverted indexes. Of course, in practical applications, inverted indexes built by other dimensions can also be included, and this is not limited.

[0108] 3) The knowledge base interaction system is an organizational architecture based on multiple clusters and multiple indexes, capable of handling the storage and retrieval of user data at the terabyte (TB) level; for example, the knowledge base interaction system could be an ElasticSearch system. In other words, the tag retrieval scheme (i.e., the RAG (Retrieval-Augmented Generation) scheme) provided in this application embodiment can be implemented based on the ElasticSearch system, which is a distributed full-text search engine capable of processing massive amounts of data quickly and in real time. The inverted index mentioned above is built on the knowledge base interaction system; the system architecture diagram of the knowledge base interaction system is shown in Figure 8c. The knowledge base interaction system includes at least one index cluster and at least one tag storage shard; wherein, the index cluster stores addresses that are used or can be routed to sub-shards in the tag storage shard, specifically, the index cluster includes one or more index modules, and each index module stores addresses that can be routed to sub-shards in the tag storage shard. Subsegments are used to store the first tag of the knowledge content in the knowledge base (i.e., the knowledge base created or received by the object corresponding to the login knowledge question and answer application) corresponding to the object identifier (i.e., an identifier used to uniquely identify an object, such as a user ID or nickname). (This first tag may be defined by the object or automatically generated by the computer device.) For example, in the tag storage segment 1 shown in Figure 8c, subsegment 801 stores the object with the first tag "new energy" defined as the knowledge content, and subsegment 802 stores the object with the first tag "news" defined as the knowledge content, and so on.

[0109] Based on this, the computer device can route to different index modules (or indices) in different index clusters according to the object identifier of different objects, and then perform fragmented routing based on the input information to retrieve the second tag related to the input information. It is worth noting that if the object has not edited the input information, the computer device, when performing fragmented routing, directly routes to the sub-fraction in the tag storage fragment that stores all the first tags defined by the object, based on the object identifier, to retrieve all the first tags. Taking object editing input information as an example, the above routing process can include: after receiving the input information edited by the object in the knowledge question-and-answer interface, the computer device routes to the target index cluster in the knowledge base interaction system based on the object identifier. This target index cluster is at least one index cluster that stores the address of at least one reference sub-fraction, and the reference sub-fraction is a sub-fraction that stores the first tag of the knowledge content in the knowledge base corresponding to the object identifier. Then, the computer device obtains the first tag related to the input information based on the object's edited input information, the address of each reference sub-fraction, and the object identifier. The first tag retrieved at this time is used as the second tag to be displayed.

[0110] Therefore, on the one hand, tag filtering allows for the rapid location or retrieval of second tags related to the input information based on the keywords edited by the user, thus meeting the user's need for quick tag filtering while improving the flexibility of tag selection. On the other hand, the knowledge base interaction system consists of an index cluster and tag storage shards, ensuring dynamic allocation of the cluster based on the growth of business data. Specifically, as the user data for the knowledge question answering application grows, the system supports rapid expansion through scalable index clusters and tag storage shards, ensuring that the performance of data writing and retrieval for the knowledge base interaction system remains within a controllable range to cope with the rapid growth of business in the later stages.

[0111] S203: Output the answer information corresponding to the question information in the question-and-answer interface.

[0112] After receiving the target tag and edited question information selected by the user, the computer device can perform knowledge-based question answering based on the target tag and question information. Specifically, the terminal sends the target tag and question information to the knowledge-based question answering system, where the server performs the knowledge-based question answering based on the target tag and question information. The knowledge-based question answering process includes: tag indexing based on the target tag, and answer generation based on the indexed content segments, obtaining the answer information corresponding to the question information. Then, the computer device outputs the answer information corresponding to the question information in the knowledge-based question answering interface for the user to understand; specifically, the server in the knowledge-based question answering system returns the answer information to the terminal, so that the terminal can output an answer message in the knowledge-based question answering interface, which includes the answer information corresponding to the question information.

[0113] Figure 9 illustrates a process by which a computer device performs tag indexing and outputs answer information corresponding to the question information in a knowledge Q&A interface. As shown in Figure 9, a question message 901, edited and sent by an object, is displayed in the message display sub-area of ​​the Q&A area. This question message 901 contains question information and target tags. The computer device performs tag indexing based on the target tags, specifically by filtering one or more knowledge contents with defined target tags from the knowledge base, such as knowledge content 1 being a document, knowledge content 2 being an image, etc. Typically, to facilitate knowledge indexing, knowledge content is segmented. For example, if the knowledge content is in document format, the document is segmented to obtain multiple document segments; if the knowledge content is in audio format, the audio is segmented to obtain multiple audio segments. In this embodiment, each knowledge content includes multiple segmented contents, such as document segments of documents, audio segments of audio, etc.

[0114] Considering that the source of the answer information corresponding to the question information is the fragmented content in the knowledge content, in order to reduce the amount of computation and improve the accuracy of the answer information, this application embodiment also supports, after indexing one or more knowledge contents based on the target tag, calculating the matching degree between the question information and each fragmented content included in each knowledge content based on the content identifier of the knowledge content (such as a document ID used to uniquely identify a knowledge content), to obtain the matching degree result corresponding to each fragmented content included in each knowledge content. The matching degree result is used to characterize the reliability of the fragmented content as a reference for generating the answer information corresponding to the question information. The higher the reliability, the more likely the fragmented content should be recalled for the reference of answer generation.

[0115] In this way, the computer device can recall target content segments with matching scores greater than a matching score threshold (such as 80% or other reasonable values) from each knowledge content segment indexed based on the matching score result. The computer device then generates answer information corresponding to the question information based on the target content segments with matching scores greater than the matching score threshold. Specifically, this embodiment supports the introduction of an AI (Artificial Intelligence) model for answer information generation. The recalled content segments are assembled into input data for the AI ​​model, and this input data is fed into the AI ​​model so that the AI ​​model can generate answer information based on the question information and the input data. By introducing an AI model for automatic answer generation during the knowledge question-and-answer process, the accuracy and reliability of the answer are greatly improved not only by the powerful knowledge reserves of the AI ​​model, but also by the powerful language understanding and organization capabilities of the AI ​​model, ensuring the fluency and readability of the answer. The AI ​​model is a machine learning model (or large model) with information generation capabilities. This embodiment does not limit the specific model type of the AI ​​model; for example, the AI ​​model may be a mixed model, a large language model, a linear regression model, or a random forest model, etc. Finally, the answer information is output to the Q&A interface as an answer message.

[0116] In summary, on the one hand, the embodiments of this application support tag indexing for quickly locating specific knowledge content in the knowledge base as the information source for answer information, avoiding problems such as device malfunctions caused by information overload. On the other hand, it supports tag retrieval / tag filtering to help users quickly locate the desired target tags, improving the flexibility of target tag selection; furthermore, for the same question information, even if the knowledge content is the same, different target tags selected by the user will result in different generated answer information, meeting the user's requirement for personalized answer information generation and improving user experience. Moreover, since answer information is generated only based on the knowledge content indexed by the target tags in the knowledge base, the speed and efficiency of answer generation are greatly improved, thereby increasing the efficiency of knowledge-based question answering and helping users improve work efficiency and personal learning outcomes.

[0117] Figure 10 shows a flowchart illustrating an information processing method for a question-and-answer interface according to an exemplary embodiment of this application; the information processing method can be executed by a computer device, which can be terminal 102 in the system / scenario shown in Figure 1a. The information processing method may include, but is not limited to, steps S1001-S1004:

[0118] S1001: Receive the first tag set for the knowledge content in the knowledge base.

[0119] Considering that different objects have different understandings of the same knowledge content, the first tags that different objects assign to the same knowledge content will also be different; by allowing objects to set personalized first tags for knowledge content, it can be ensured that the index relationship between the first tag and the knowledge content is more in line with the object's requirements; in addition, the first tags of the knowledge content are all defined by the object, which also avoids blind selection during the tag selection process when the object is not familiar with the first tag.

[0120] This application embodiment supports setting tags for knowledge content at any time. Optionally, when importing knowledge content into the knowledge base, a first tag can be set for the knowledge content. Optionally, after the knowledge content has been imported into the knowledge base, the setting of the first tag for the knowledge content can be initiated actively; as shown in Figure 11a, in response to the triggering operation (such as right-click or double-click operation) of the object on the knowledge content 1101 in the knowledge base, the computer device outputs a tag editing window 1102. The object can set a new first tag in the tag editing window 1102, or re-edit the original first tag, etc., to set a first tag for the knowledge content 1101.

[0121] It should be noted that the first tag defined for knowledge content can be set actively by the object, or it can be automatically generated by a computer device after content parsing processing of the knowledge content. Content parsing processing includes extracting content data (such as text and images) from the knowledge content (such as web pages, PDF documents, or Word documents), and performing data cleaning, organization, and removal of irrelevant information on the extracted content data to extract keywords that summarize the main content of the knowledge content. These keywords are then used as the first tag of the knowledge content. Based on this, the first tag set by the object for the knowledge content can be obtained by directly re-editing the first tag generated by the computer device, such as modifying the automatically generated first tag in the tag editing window 1102 shown in Figure 11a, to overcome inaccuracies or other problems caused by the computer device generating the first tag.

[0122] S1002: Display at least one first tag in the question and answer interface.

[0123] S1003: Receive the target label selected for the problem information.

[0124] It should be noted that the specific implementation process shown in steps S1002-S1003 is the same as the specific implementation process shown in steps S201-S203 in the embodiment shown in Figure 2 above. Please refer to the relevant description of the specific implementation process shown in steps S201-S203, which will not be repeated here.

[0125] This application's embodiments support users in customizing information sources during the knowledge-based question-and-answer process. Customizing information sources means that users can independently select information sources according to their own needs for answer sourcing. Information sources can include the internet and at least one knowledge base; the knowledge base can be created by the user or shared by other users. For example, if a user creates knowledge base 1 in a knowledge-based question-and-answer application and receives knowledge base 2 shared by other users, then the information sources that the user can independently choose include: knowledge base 1, knowledge base 2, and the internet. By allowing users to choose to obtain answers from a wide range of information on the internet or focus on specific content in their personal knowledge base, this approach satisfies various answer generation requirements and enhances the user experience.

[0126] In specific implementation, it is assumed that the knowledge question-and-answer interface includes at least one information source component, and each information source component corresponds to one type of information source. Before an object selects a target tag in the dialog sub-area, it first performs the selection of an information source component. For example, if the object performs a selection operation on the first information source component, the computer device responds to the selection operation on the first information source component by displaying the first information source component as selected. The purpose of displaying the first information source component as selected is to indicate to the object that the information source corresponding to the first information source component has been selected as the source of the answer. This embodiment does not limit the specific form of the display state; for example, the transparency of the first information source component may be lower than that of other information source components. Thus, when the information source corresponding to the first information source component is a knowledge base, at least one first tag defined in the knowledge base corresponding to the selected first information source component can be displayed in the knowledge question-and-answer interface. Alternatively, the computer device may automatically display at least one first tag based on the selection operation of the first information source component, or the computer device may display at least one first tag based on the object's tag invocation operation.

[0127] It is worth noting that when selecting information source components, the number of selected information source components can be one or more. For example, if there are multiple knowledge bases, multiple knowledge bases can be selected simultaneously as the answer source for this knowledge question and answer, or one or more knowledge bases and the Internet can be selected simultaneously as the answer source for this knowledge question and answer. This method of generating answers based on multiple information sources not only helps the object integrate knowledge content across information sources, but also improves the breadth and accuracy of answer sources. For example, a schematic diagram of selecting multiple information sources can be seen in Figure 11b; as shown in Figure 11b, information source component 1103 and information source component 1104 are displayed in the knowledge question and answer interface. The information source corresponding to information source component 1103 is the Internet, and the information source corresponding to information source component 1104 is knowledge base 1. Optionally, when the information source component 1104 is triggered, a component candidate window 1105 is displayed. This window displays the information source components corresponding to each knowledge base in the object's total knowledge base. For example, the total knowledge base includes information source component 1104 corresponding to knowledge base 1, information source component 11051 corresponding to knowledge base 2, and information source component 11052 corresponding to knowledge base 3. The object can select one or more information source components in this component candidate window 1105 to use the knowledge base corresponding to each information source component as the information source.

[0128] Furthermore, when multiple information sources include knowledge bases, at least one first tag displayed in the knowledge question-and-answer interface includes: the first tag defined for the knowledge content in each selected knowledge base. As shown in Figure 11b, assuming information source component 1104 and information source component 11051 are selected, and the first tags defined in knowledge base 1 corresponding to information source component 1104 include first tag 1 and first tag 2, and the first tags defined in knowledge base 2 corresponding to information source component 11051 include first tag 1 and first tag 3, then the first tags displayed in the knowledge question-and-answer interface include: first tag 1, first tag 2, and first tag 3.

[0129] Furthermore, when multiple knowledge bases are selected as information sources, the computer device, after indexing based on the selected target tags (which may come from different knowledge bases) and recalling multiple knowledge contents defined by the target tags, supports the generation of answer information based on the fragmented content of the multiple knowledge contents according to a content selection strategy. The content selection strategy may include, but is not limited to: a) an indiscriminate selection strategy, which refers to generating answer information based on the recalled fragmented content of each of the recalled knowledge contents. For example, assuming the selected knowledge bases are Knowledge Base 1 and Knowledge Base 2, and knowledge content 1 in Knowledge Base 1 is indexed by the target tag, and knowledge content 2 in Knowledge Base 2 is indexed by the target tag, then when using the indiscriminate recall strategy, the recalled knowledge content includes knowledge content 1 and knowledge content 2. Thus, the computer device generates answer information according to the fragmented content of knowledge content 1 that matches the question information, and the fragmented content of knowledge content 2 that matches the question information.

[0130] b. Priority Selection Strategy: This strategy generates answer information based on the priority order of the information sources to which each piece of knowledge content belongs among the recalled knowledge content. The information sources can be knowledge bases or the internet. For example, suppose the selected knowledge bases are Knowledge Base 1 and Knowledge Base 2, and knowledge content 1 in Knowledge Base 1 is indexed by the target tag, while knowledge content 2 in Knowledge Base 2 is also indexed by the target tag. Furthermore, Knowledge Base 1 has a higher priority than Knowledge Base 2. Therefore, when using the priority selection strategy, the recalled knowledge content includes both knowledge content 1 and knowledge content 2. Since Knowledge Base 1, to which knowledge content 1 belongs, has a higher priority than Knowledge Base 2, when generating answer information, the fragments of knowledge content 1 that match the question information are used first. If answer information generation fails or the generation quality is poor, then the answer is generated simultaneously based on the fragments of knowledge content 1 and knowledge content 2 that match the question information. Therefore, this method of generating answer information based on information sources according to priority can, to some extent, improve the success rate and accuracy of answer information generation, avoid computer devices failing to answer in knowledge-based question-and-answer sessions, and enhance the question-and-answer experience for users, when the answer information generated based on knowledge content in the knowledge base is poor or fails.

[0131] The priority level of the information source can be preset by the developers of the knowledge question answering application or customized by the object when selecting the information source. Specifically, an exemplary process for the object to customize the priority level of the information source when selecting the information source may include: the object performing a priority setting operation on at least two selected target information source components, which are information source components selected by the object as references for answer generation, and when the number of selected target information source components is at least two, the first label is a label defined in the information source corresponding to the at least two target information source components. The computer device displays a priority identifier at an adjacent display position of each target information source component according to the object's priority setting operation for the at least two target information source components. This priority identifier is used to characterize the priority level of the knowledge content indexed by the target label in the information source corresponding to the target information source component as a reference when generating answer information. This application embodiment does not limit the form of the priority identifier. For example, if the priority identifier is in numerical form, the smaller the number, the higher the priority level; for example, the priority level of the number 1 is higher than the priority level of the number 2. For example: Suppose that the priority indicator (e.g., number 1) displayed at the adjacent display position of the target information source component corresponding to knowledge base 1 is greater than the priority indicator (number 2) displayed at the adjacent display position of the target information source component corresponding to knowledge base 2. Then, the priority level of knowledge content 1 indexed by the target tag in knowledge base 1 as a reference when generating answer information is determined to be greater than the priority level of knowledge content 2 indexed by the target tag in knowledge base 2 as a reference when generating answer information. Thus, when generating answer information, the computer device first refers to the fragmented content in knowledge content 1. If the generation of answer information fails or is unsatisfactory, it then refers to both the fragmented content in knowledge content 1 and the fragmented content in knowledge content 2 to generate answer information.

[0132] As shown in Figure 12, assuming that information source component 1201 corresponding to knowledge base 1 and information source component 1202 corresponding to knowledge base 2 are selected, it indicates that the object wants to select both knowledge base 1 and knowledge base 2 as information sources for generating answer information. In this case, if the object wants to set priority levels for knowledge base 1 and knowledge base 2, it can input a priority value of 1 in the input area 1203 of the display area occupied by information source component 1201 and a priority value of 2 in the input area 1204 of the display area occupied by information source component 1202, indicating that the priority level of knowledge base 1 is higher than that of knowledge base 2. Here, priority value 1 can serve as the priority identifier of information source component 1201, and similarly, priority value 2 serves as the priority identifier of information source component 1202. It should be understood that the priority setting operation performed by the object for at least two target information source components can be other operations besides the specific implementation process shown in Figure 12. This application embodiment does not limit the specific operation process of the priority setting operation.

[0133] It should be noted that a round of knowledge-based question-and-answer sessions can include at least one question-and-answer dialogue, and each dialogue includes a question message and an answer message corresponding to that question. To improve the flexibility of the source of answer information in different question-and-answer dialogues during a round of knowledge-based question-and-answer sessions, this application embodiment supports flexible switching of information sources between different dialogues during a round. In other words, the information source selected for different dialogues can be changed during a round of knowledge-based question-and-answer sessions, effectively avoiding the need to restart a new round when participants want to switch to another information source to continue the discussion. This improves the convenience of continuous question-and-answer dialogues in situations with frequent topic changes (such as different information sources for different topics). Furthermore, each dialogue in a round of knowledge-based question-and-answer sessions supports the aforementioned functions of selecting multiple information sources and setting priority levels for multiple information sources.

[0134] Specifically, suppose that during the first question-and-answer session in a knowledge-based Q&A round, the object selects the first information source component, meaning that the first information source component is selected during the first Q&A session. After the first Q&A session ends, if the object wants to switch information sources, it can perform an information switching operation. The computer device responds to this operation by changing the first information source component from selected to unselected. Simultaneously, the object's newly selected second information source component is changed from unselected to selected, allowing the object to continue editing the question information in the second Q&A session. The second information source component is different from the first; for example, the first information source component might be the internet-related information source component, while the second information source component might be the knowledge base-related information source component. The above-described source switching diagram can be seen in Figure 13. As shown in Figure 13, assuming the object selects information source component 1302 as the first information source component in the question information 1301 of the first question-and-answer dialogue, and the answer information 1303 corresponding to question information 1301 is displayed in the message display sub-area, if the object wants to switch information sources and continue asking questions, the object can select a new second information source component, such as information source component 1304. At this time, information source component 1302 is displayed as unselected, and information source component 1304 is displayed as selected. The object can continue to input question information in the second question-and-answer dialogue in the dialogue sub-area, realizing flexible switching of information sources for question-and-answer in one round of knowledge question-and-answer.

[0135] S1004: Output the answer information corresponding to the question information in the question-and-answer interface.

[0136] The answer information corresponding to the question information is displayed in the knowledge Q&A interface in the form of answer messages (such as message bubbles), specifically in the message display sub-area of ​​the knowledge Q&A interface.

[0137] To enhance the user experience, this application embodiment supports the introduction of a highlighted tag display function in the message bubbles (i.e., question-and-answer messages) of the question-and-answer area. A highlighted tag refers to displaying the target tag in the question message as a highlighted state, allowing the user to intuitively perceive the target tag. The highlighted tag display function means that the user can click on these highlighted tags to directly filter and display all the indications defined by that target tag in the knowledge base, thereby enabling quick location and in-depth exploration of knowledge content related to the answer information generated in this question-and-answer dialogue.

[0138] As mentioned earlier, the question-and-answer area in the knowledge-based Q&A interface includes a message display sub-area. This sub-area can be used to display the question and answer messages generated in one round of knowledge-based Q&A. When the computer device detects that a target tag included in a question message in the message display sub-area has been triggered, indicating that the user wants to quickly locate relevant knowledge content, it displays the content identifier of at least one knowledge content indexed by the target tag. This content identifier is used to uniquely identify the knowledge content, such as in card or ID form. If the user wants to view the knowledge content in detail, the user can perform a trigger operation on the target content identifier, which is any one of the content identifiers of at least one knowledge content. In this case, the computer device responds to the trigger operation on the target content identifier and displays the knowledge content corresponding to the target content identifier.

[0139] A schematic diagram of a highlighted label display can be seen in Figure 14. As shown in Figure 14, a question message 1401 is displayed in the question-and-answer area. This question message 1401 includes a highlighted target label 1402 and question information 1403. When the target label 1402 is triggered, the content identifier of at least one knowledge content indexed by the target label is displayed. For example, the content identifier of at least one knowledge content indexed by the target label is displayed in the information display area 1404 of the knowledge question-and-answer interface. Furthermore, when the question-and-answer area is closed, the content identifier of at least one knowledge content indexed by the target label is displayed in the enlarged information display area 1404, such as content identifier 14041 for knowledge content 1, content identifier 14042 for knowledge content 2, etc. When an object performs a trigger operation on the target content identifier, such as when the target content identifier is content identifier 14042, knowledge content 2 is displayed.

[0140] As mentioned earlier, the knowledge Q&A interface includes an information display area and a Q&A area. This Q&A area can be understood as a sidebar within the knowledge Q&A interface; the sidebar is a context-dependent Q&A style that can be expanded at any time to ask questions. In other words, this embodiment supports hiding or restoring the Q&A area within the knowledge Q&A interface to meet the user's browsing needs for different areas of the interface and improve the user experience. Specifically, if the computer device detects a hiding operation on the Q&A area within the knowledge Q&A interface, it hides the Q&A area and enlarges the information display area, such as to achieve full-screen magnification. After full-screen magnification, the display area of ​​the information display area is the sum of the display areas of the information display area and the Q&A area before full-screen magnification. In this case, the knowledge Q&A interface only includes the information display area and not the Q&A area.

[0141] The hiding operation for the question-and-answer area can include any of the following: the operation triggered by the target tag included in the question message, and the operation triggered by the hidden component in the question-and-answer area. The interface illustration process for hiding the question-and-answer area when the target tag in the question message is triggered is shown in Figure 14, and will not be elaborated here. The interface illustration process for hiding the question-and-answer area when the hidden component in the question-and-answer area is triggered is shown in Figure 15; as shown in Figure 15, the question-and-answer area includes a hidden component 1501; when the hidden component 1501 is triggered, the question-and-answer area is closed or hidden in the knowledge question-and-answer interface, and the information display area is enlarged. Furthermore, the closed or hidden question-and-answer area can be restored to the display; specifically, a question-and-answer display component 1502 is displayed in the knowledge question-and-answer interface, such as in the information display area. When an object triggers the question-and-answer display component 1502, it indicates that the object may have a need to continue asking questions or viewing historical dialogues. In response to the triggering operation of the question-and-answer display component, the computer device displays (i.e., restores) the question-and-answer area in the knowledge question-and-answer interface, and correspondingly reduces the display area of ​​the information display area. The content displayed in the message display sub-area and dialogue sub-area of ​​the restored question-and-answer area is the same as the content displayed in the message display sub-area and dialogue sub-area before the question-and-answer area was hidden, to facilitate the object continuing the current round of knowledge question-and-answer. Therefore, this embodiment supports personalized control of the display and hiding of the question-and-answer area according to the object's needs, improving the display flexibility of the question-and-answer area.

[0142] Furthermore, to facilitate the management and viewing of knowledge content indexed by the first tag in the knowledge base, this application embodiment provides a convenient content viewing function. For example, before selecting a target tag for question information during the knowledge Q&A process, the content viewing function allows previewing of the knowledge content indexed by each first tag, helping the user to better select the target tag. Specifically, the information display area in the knowledge Q&A interface includes a search box, as shown in search box 1601 in Figure 16. The user can input a third tag in the search box 1601. The computer device indexes the knowledge content indexed by the third tag based on the third tag entered in the search box 1601 and outputs the content identifier of the knowledge content indexed by the third tag. Specifically, the content identifier of the knowledge content defined by the third tag in the knowledge base is displayed in the information display area. The user can perform a trigger operation on the content identifier of the knowledge content, at which time the details of the knowledge content are displayed in the information display area, facilitating the user's preview of the knowledge content. The third tag entered in the search box belongs to at least one of the first tags.

[0143] Furthermore, this application embodiment also supports quickly locating reference segments within knowledge content based on answer information, helping users to deeply understand the relevant knowledge points of the answer information based on these reference segments, thereby improving the quality of knowledge-based question-and-answer sessions. Specifically, answer information can be understood as being composed of at least one sub-information, and the reference sources for different sub-information may be different segments within the same knowledge content, or different segments within different knowledge content. Based on this, this application embodiment supports displaying the information source entry for the target sub-information at an adjacent display position within the answer information. This information source entry can be represented as an icon or a number, etc., and the target sub-information is any one of the at least one sub-information that makes up the answer information. If a user wants to view the knowledge content and segments referenced by the target sub-information, the user can click on the information source entry. The computer device responds to the user's trigger operation on the information source entry by displaying the target knowledge content used as a reference for generating the target sub-information, such as displaying the target knowledge content in the information display area. Among them, it supports the annotation and display of the segmented content that serves as a reference for generating target sub-information in the target knowledge content, helping the object to intuitively perceive the source location of the target sub-information in the knowledge content, and avoiding information comparison and searching in the knowledge content.

[0144] A schematic diagram of a method for quickly locating knowledge content and segmented content based on information source entry points can be seen in Figure 17. As shown in Figure 17, an answer message is displayed in the message display sub-area. The answer information included in the answer message consists of sub-information 1701, sub-information 1702, and sub-information 1703. An information source entry point is displayed at the adjacent display position of each sub-message, such as information source entry point 1704 displayed at the adjacent display position of sub-information 1701. When an object performs a trigger operation on information source entry point 1704, the computer device displays the target knowledge content as a reference for generating the target sub-information in the information display area. For example, if the target knowledge content is knowledge content 1, the content identifier of knowledge content 1 is displayed in the information display area. When the content identifier of knowledge content 1 is triggered, the detailed content of knowledge content 1 is displayed, or the detailed content of knowledge content 1 is directly displayed in the information display area. When displaying the details of knowledge content 1 in the information display area, the segmented content within knowledge content 1 that serves as a reference for generating target sub-information is also annotated. For example, the annotation method involves darkening the background color of the segmented content to facilitate intuitive perception and quick location of the referenced segmented content within the knowledge content. It should be understood that the annotation method for segmented content can also be other than those shown in Figure 17, which is merely an example and does not limit the scope of this application's embodiments.

[0145] The foregoing mainly introduced the information processing method of the question-and-answer interface proposed in this application from the perspective of the interface. The following describes the overall backend process of the information processing method in conjunction with Figure 18. As shown in Figure 18, the information processing method is mainly implemented based on the knowledge base interaction system (such as the ElasticSearch system), which roughly includes tag filtering and tag index establishment, as well as tag index knowledge content. Among them: (1) Tag filtering and tag index establishment includes: the object sets a first tag for the knowledge content, and the computer device receives the first tag. On the one hand, the first tag is processed by word segmentation, etc. (the specific implementation process of word segmentation can be referred to the relevant content in the embodiment shown in Figure 2 above, which will not be repeated here), so as to establish a multi-field and multi-dimensional inverted index of the first tag in the knowledge base interaction system, so as to enable the tag filtering or tag retrieval to be quickly realized according to the input information edited by the object in the knowledge question and answer process, and accurately locate the second tag related to the input information. On the other hand, an index relationship between the first tag and the knowledge content will be established so as to generate answer information based on the first tag index to the corresponding knowledge content. (2) Tag indexing includes: In the actual knowledge question-and-answer process, after the computer device receives the target tag set for the question information, it performs tag indexing processing based on the target tag to index at least one knowledge content; then, based on the content identifier of the knowledge content and the question information, it recalls the segmented content that matches the question information, so that the computer device can generate answer information for the question information based on the segmented content. The tag indexing and the calculation of the matching between the question information and the segmented content can be found in the relevant content of the embodiment shown in Figure 2 above, and will not be elaborated here.

[0146] In summary, on the one hand, the embodiments of this application support the user to customize a first tag for knowledge content, thus personalizing the knowledge content and facilitating the user's understanding and management of the knowledge content in the knowledge base. On the other hand, when the user selects a target tag for question information, it supports precise and rapid location of the second tag that the user might choose through tag filtering, thereby improving the efficiency and flexibility of tag selection. Furthermore, by establishing a tag index between the first tag and the knowledge content, personalized answer information can be generated based on the knowledge content of the target tag index when generating answer information, improving user satisfaction with the answer information and reducing the search scope compared to searching the entire knowledge base, thereby improving the efficiency of knowledge question answering.

[0147] Figure 19 shows a schematic diagram of an information processing apparatus with a question-and-answer interface provided in an exemplary embodiment of this application; the information processing apparatus can be used to execute some or all of the steps in the method embodiments shown in Figures 2 and 10. Referring to Figure 19, the apparatus includes the following units:

[0148] Display unit 1901 is used to display at least one first label in the question and answer interface, each first label being used to index at least one knowledge content from the knowledge base;

[0149] Processing unit 1902 is configured to receive a target label selected for problem information, wherein the target label is any one of at least one first label;

[0150] The processing unit 1902 is also used to output answer information corresponding to the question information in the question-and-answer interface. The answer information is generated based on the knowledge content indexed by the question information and the target tag.

[0151] In one implementation, the display unit 1901, when displaying at least one first label in the question-and-answer interface, is specifically used for:

[0152] In response to a tag activation action in the Q&A interface, a tag filtering window is displayed; the tag activation action includes any of the following: input action for a shortcut key, trigger action for a tag component, and specified gesture action;

[0153] Display at least one first tag in the tag filtering window.

[0154] In one implementation, the processing unit 1902 is further configured to:

[0155] Receive input information edited in the question-and-answer interface;

[0156] In the tag filtering window, at least one first tag is updated to display as at least one second tag related to the input information; the second tag belongs to at least one first tag.

[0157] In one implementation, the method is applied to a knowledge question answering application, which corresponds to a knowledge base interaction system. The knowledge base interaction system includes at least one index cluster and at least one tag storage shard. The index cluster stores addresses that can be routed to sub-shards in the tag storage shard. A sub-shard is used to store the first tag of the knowledge content in the knowledge base corresponding to the object identifier of the logged-in knowledge question answering application.

[0158] In one implementation, the processing unit 1902 is further configured to:

[0159] Based on the object identifier, the system routes to the target index cluster in the knowledge base interaction system. The target index cluster stores the address that can be routed to at least one reference sub-segment. At least one reference sub-segment refers to the sub-segment that stores the first tag of the knowledge content in the knowledge base corresponding to the object identifier.

[0160] Based on the input information and the address of each reference sub-segment, obtain the first tag associated with the input information; the first tag associated with the input information is used as the second tag.

[0161] In one implementation, the question-and-answer interface includes at least two information source components, each corresponding to an information source, including: the Internet and at least one knowledge base; the processing unit 1902 is further used for:

[0162] In response to the selection operation of the first information source component, the first information source component is displayed as selected;

[0163] When the information source corresponding to the first information source component is a knowledge base, the step of displaying at least one first tag in the question and answer interface is triggered.

[0164] In one implementation, a round of knowledge question-and-answer includes at least one question-and-answer dialogue, each dialogue including a question message and an answer message. The question message includes question information, and the answer message includes answer information. During the first question-and-answer dialogue, the first information source component is selected. The processing unit 1902 is further configured to:

[0165] After the first question-and-answer dialogue ends, in response to the information source switching operation performed in the question-and-answer interface, the first information source component is displayed as unselected; and,

[0166] The selected second information source component is displayed as selected, and the question information in the second question-and-answer dialogue is edited in the question-and-answer interface; the second information source component is different from the first information source component.

[0167] In one implementation, the selected information source component is represented as a target information source component. When the number of selected target information source components is at least two, the first label is a label defined in the information sources corresponding to the at least two target information source components. The processing unit 1902 is further configured to:

[0168] Based on the priority setting operation for at least two target information source components, a priority identifier is displayed at an adjacent display position for each target information source component; the priority identifier is used to characterize the priority level of the knowledge content indexed by the target tag in the information source corresponding to the target information source component as a reference for generating answer information.

[0169] In one implementation, the question-and-answer interface includes a question-and-answer area, which in turn includes a message display sub-area. This sub-area displays the question and answer messages generated during a round of knowledge-based question-and-answer sessions. The processing unit 1902 is further configured to:

[0170] When the target tag included in the problem message in the message display sub-area is triggered, display the content identifier of at least one knowledge content of the target tag index;

[0171] In response to a trigger operation on a target content identifier, the knowledge content corresponding to the target content identifier is displayed; the target content identifier is any one of the content identifiers of at least one knowledge content.

[0172] In one implementation, the question-and-answer interface also includes an information display area, which is used to display knowledge content from the knowledge base. The processing unit 1902 is also used for:

[0173] Hide the question and answer area in the question and answer interface based on the hiding operation for the question and answer area; the hiding operation includes any of the following: the operation triggered by the target tag included in the question message, and the operation triggered by the hidden component in the question and answer area;

[0174] Enlarge the information display area.

[0175] In one implementation, the question-and-answer area further includes a dialogue sub-area, which is used to receive question information and target tags; the question-and-answer interface includes a question-and-answer display component, and the processing unit 1902 is further used for:

[0176] In response to a trigger action on the Q&A display component, the Q&A area is displayed in the Q&A interface; the content displayed in the message display sub-area and dialogue sub-area of ​​the Q&A area is the same as before the Q&A area was hidden.

[0177] In one implementation, the information display area includes a search box, and the processing unit 1902 is further used for:

[0178] Based on the third tag entered in the search box, the content identifier of the knowledge content defined by the third tag in the knowledge base is displayed in the information display area.

[0179] In one implementation, the answer information consists of at least one sub-information; the processing unit 1902 is further configured to:

[0180] The information source entry is displayed at a display position adjacent to the target sub-information, where the target sub-information is any one of at least one sub-information;

[0181] In response to a trigger operation on the information source entry point, the target knowledge content is displayed as a reference for generating target sub-information;

[0182] Within the target knowledge content, the fragmented content that serves as a reference for generating target sub-information is annotated and displayed.

[0183] In one implementation, the method is applied to a knowledge question answering application; the processing unit 1902 is also used for:

[0184] In response to a login operation targeting an object identifier in a knowledge-based question-and-answer application, the knowledge service interface is displayed; the knowledge service interface includes a question-and-answer triggering component.

[0185] When the question-and-answer trigger component is triggered, the question-and-answer interface is displayed.

[0186] In one implementation, the processing unit 1902 is further configured to:

[0187] Filter one or more knowledge contents with defined target tags from the knowledge base, with each knowledge content including multiple segments;

[0188] The matching degree is calculated between the question information and the content segments included in each knowledge content, and the matching degree result corresponding to each content segment included in each knowledge content is obtained. The matching degree result is used to characterize the reliability of the content segments as a reference for generating answer information corresponding to the question information.

[0189] Based on the target fragment content where the matching degree result is greater than the matching degree threshold, the answer information corresponding to the question information is generated.

[0190] According to one embodiment of this application, the various units in the information processing device shown in FIG19 can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This can achieve the same operation without affecting the technical effect of the embodiment of this application. The above-mentioned units are based on logical function division. In practical applications, the function of one unit can also be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, the information processing device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by multiple units working together. According to another embodiment of this application, the information processing device shown in FIG19 and the information processing method for implementing the question-and-answer interface of the embodiment of this application can be constructed by running a computer program (including program code) capable of executing the steps involved in the corresponding methods shown in FIG2 and FIG10 on a general-purpose computing device including processing elements and storage elements such as a central processing unit (CPU), random access storage medium (RAM), and read-only storage medium (ROM). Computer programs can be recorded on, for example, a computer-readable recording medium, loaded onto the aforementioned computing device via the computer-readable recording medium, and run therein.

[0191] Based on the same inventive concept, the principle and beneficial effects of the computer device provided in the embodiments of this application in solving the problem are similar to the principle and beneficial effects of the information processing method of the question-and-answer interface in the embodiments of this application in solving the problem. Please refer to the principle and beneficial effects of the implementation of the method. For the sake of brevity, they will not be repeated here.

[0192] Figure 20 shows a schematic diagram of a computer device provided in an exemplary embodiment of this application. Referring to Figure 20, the computer device includes a processor 2001, a communication interface 2002, and a computer-readable storage medium 2003. The processor 2001, communication interface 2002, and computer-readable storage medium 2003 can be connected via a bus or other means. The communication interface 2002 is used to receive and send data. The computer-readable storage medium 2003 can be stored in the memory of the computer device and is used to store computer programs. The processor 2001 is used to execute the computer programs stored in the computer-readable storage medium 2003. The processor 2001 (or CPU (Central Processing Unit)) is the computing and control core of the computer device, suitable for implementing one or more computer programs, specifically suitable for loading and executing one or more computer programs to achieve corresponding method flows or corresponding functions.

[0193] This application embodiment also provides a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the processing system of the computer device. Furthermore, one or more computer programs suitable for loading and execution by the processor 2001 are also stored in this storage space. It should be noted that the computer-readable storage medium here can be high-speed RAM memory or non-volatile memory, such as at least one disk storage device; optionally, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.

[0194] In one embodiment, a computer-readable storage medium stores one or more computer programs; the processor 2001 loads and executes one or more computer programs stored in the computer-readable storage medium to implement the corresponding steps in the above-described question-and-answer interface information processing method embodiment; in a specific implementation, one or more computer programs in the computer-readable storage medium are loaded and executed by the processor 2001 to implement the aforementioned question-and-answer interface information processing method.

[0195] Based on the same inventive concept, the principle and beneficial effects of the computer device provided in the embodiments of this application in solving the problem are similar to the principle and beneficial effects of the information processing method of the question-and-answer interface in the embodiments of this application in solving the problem. Please refer to the principle and beneficial effects of the implementation of the method. For the sake of brevity, they will not be repeated here.

[0196] This application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the information processing method of the above-mentioned question-and-answer interface.

[0197] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0198] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. A computer program product includes one or more computer programs. When a computer program is loaded and executed on a computer device, the computer program performs the processes or functions described above in the embodiments of this application. The computer device can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in or transmitted through a computer-readable storage medium. The computer program can be transmitted from one website, computer device, server, or data center to another website, computer device, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible to the computer device or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0199] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An information processing method for a question-and-answer interface, characterized in that, The method is performed by a computer device, and the method includes: The question-and-answer interface displays at least one first tag, which is used to index at least one knowledge content from the knowledge base; Receive a target label selected for the problem information, wherein the target label is at least one of the first labels; The answer information corresponding to the question information is output in the question-and-answer interface. The answer information is generated based on the question information and the knowledge content indexed by the target tag.

2. The method as described in claim 1, characterized in that, Displaying at least one first label in the question-and-answer interface includes: In response to a tag activation operation in the question-and-answer interface, a tag filtering window is displayed; the tag activation operation includes any of the following: input operation for a shortcut key, trigger operation for a tag component, and specified gesture operation; At least one first tag is displayed in the tag filtering window.

3. The method of claim 1 or 2, wherein, The method further includes: Receive input information edited in the question-and-answer interface; In the tag filtering window, at least one of the first tags is updated to be displayed as at least one second tag related to the input information; the second tag belongs to at least one of the first tags.

4. The method according to any one of claims 1 to 3, characterized in that, The method is applied to a knowledge question answering application, which corresponds to a knowledge base interaction system. The knowledge base interaction system includes at least one index cluster and at least one tag storage shard. The index cluster stores addresses for routing to sub-shards in the tag storage shard. One of the sub-shards stores a first tag of the knowledge content in the indexed knowledge base. The knowledge base is created or received by an object corresponding to the object identifier that logs into the knowledge question answering application.

5. The method according to any one of claims 1-4, characterized in that, After receiving the input information edited in the question-and-answer interface, the method further includes: Based on the object identifier, the system routes to the target index cluster in the knowledge base interaction system. The target index cluster stores addresses for routing to at least one reference sub-segment. The at least one reference sub-segment refers to a sub-segment that stores the first tag of the knowledge content in the knowledge base corresponding to the object identifier. Based on the input information and the address of each reference sub-segment, a first tag associated with the input information is obtained; the first tag associated with the input information is used as the second tag.

6. The method according to any one of claims 1-5, characterized in that, The question-and-answer interface includes at least two information source components, each corresponding to an information source, including: the Internet and at least one of the knowledge bases; before displaying at least one first tag in the question-and-answer interface, the process further includes: In response to the selection operation of the first information source component, the first information source component is displayed as selected; When the information source corresponding to the first information source component is the knowledge base, the step of displaying at least one first tag in the question-and-answer interface is triggered.

7. The method according to any one of claims 1-6, characterized in that, A round of knowledge-based question-and-answer sessions includes at least one question-and-answer dialogue, and each dialogue includes a question message and an answer message. The question message includes question information, and the answer message includes answer information. During the first question-and-answer dialogue, the first information source component is selected. The method further includes: After the first question-and-answer dialogue ends, in response to the information source switching operation performed in the question-and-answer interface, the first information source component is displayed as unselected. as well as, The selected second information source component is displayed as selected, and the question information in the second question-and-answer dialogue is edited in the question-and-answer interface; the second information source component is different from the first information source component.

8. The method according to any one of claims 1-7, characterized in that, The selected information source component is referred to as the target information source component. When the number of the selected target information source components is at least two, the first tag is the tag defined in the information source corresponding to each of the at least two target information source components. The method further includes: Based on the priority setting operation for at least two of the target information source components, a priority identifier is displayed at an adjacent display position for each of the target information source components; The priority identifier is used to characterize the priority level of the knowledge content indexed by the target tag in the information source corresponding to the target information source component, as a reference for generating answer information.

9. The method according to any one of claims 1-8, characterized in that, The question-and-answer interface includes a question-and-answer area, which in turn includes a message display sub-area. The message display sub-area is used to display the question and answer messages generated in one round of knowledge-based question-and-answer sessions. The method further includes: When the target tag included in the question message in the message display sub-area is triggered, the content identifier of each knowledge content in at least one of the knowledge contents in the target tag index is displayed; In response to a trigger operation on a target content identifier, the knowledge content corresponding to the target content identifier is displayed; the target content identifier is any one of the content identifiers of at least one of the knowledge content.

10. The method according to any one of claims 1-9, characterized in that, The question-and-answer interface also includes an information display area, which is used to display knowledge content from the knowledge base. The method further includes: According to the hiding operation for the question and answer area, the question and answer area is hidden in the question and answer interface; the hiding operation includes any one of the following: the operation triggered by the target tag included in the question message, or the operation triggered by the hidden component in the question and answer area; The information display area is enlarged.

11. The method according to any one of claims 1-10, characterized in that, The question-and-answer area further includes a dialogue sub-area, which is used to receive question information and target tags; the question-and-answer interface includes a question-and-answer display component, and the method further includes: In response to a trigger operation on the question-and-answer display component, the question-and-answer area is displayed in the question-and-answer interface; the content displayed in the message display sub-area and the dialogue sub-area of ​​the question-and-answer area is the same as the content displayed before the question-and-answer area was hidden.

12. The method according to any one of claims 1-11, characterized in that, The information display area includes a search box, and the method further includes: Based on the third tag entered in the search box, the content identifier of the knowledge content defined by the third tag in the knowledge base is displayed in the information display area.

13. The method according to any one of claims 1-12, characterized in that, The answer information consists of at least one sub-information; the method further includes: The information source entry is displayed at a display position adjacent to the target sub-information, wherein the target sub-information is any one of at least one of the sub-information; In response to a trigger operation on the information source entry point, target knowledge content is displayed as a reference for generating the target sub-information; In the target knowledge content, the segmented content that serves as a reference for generating the target sub-information is annotated and displayed.

14. The method according to any one of claims 1-13, characterized in that, The method is applied to knowledge-based question-and-answer applications; Before displaying at least one first tag in the question-and-answer interface, the method further includes: In response to a login operation targeting an object identifier in the knowledge Q&A application, a knowledge service interface is displayed; the knowledge service interface includes a Q&A triggering component. When the question-and-answer triggering component is triggered, the question-and-answer interface is displayed.

15. The method according to any one of claims 1-14, characterized in that, Before outputting the answer information corresponding to the question information in the question-and-answer interface, the method further includes: Filter one or more knowledge contents defined with the target tag from the knowledge base, each of the knowledge contents including multiple segments of content; A matching degree calculation is performed on the question information and each segment of content included in each knowledge content to obtain a matching degree result corresponding to each segment of content included in each knowledge content; the matching degree result is used to characterize the reliability of the segment content as a reference for generating answer information corresponding to the question information; Based on the target fragment content where the matching degree result is greater than the matching degree threshold, answer information corresponding to the question information is generated.

16. An information processing device with a question-and-answer interface, characterized in that, The information processing device is mounted in a computer device, and the information processing device includes: The display unit is used to display at least one first label in the question-and-answer interface, wherein the first label is used to index at least one knowledge content from the knowledge base; Processing unit, configured to receive a target label selected for problem information, wherein the target label is at least one of the first labels; The processing unit is further configured to output answer information corresponding to the question information in the question-and-answer interface, wherein the answer information is generated based on the question information and the knowledge content indexed by the target tag.

17. A computer device, characterized in that, include: A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the information processing method of the question-and-answer interface as described in any one of claims 1-15.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer application program, which, when executed, implements the information processing method of the question-and-answer interface as described in any one of claims 1-15.

19. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the information processing method of the question-and-answer interface as described in any one of claims 1-15.

Images