Dialogue processing methods, apparatus, devices, readable storage media, and program products

Abstract

This application relates to a dialogue processing method, apparatus, device, readable storage medium, and program product, belonging to the field of information processing technology. This application can effectively improve dialogue processing efficiency. The method includes: determining a topic card for a user account; the topic card is obtained by summarizing topics based on existing dialogue content between the agent and the user account; in response to a dialogue initiation operation for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface; the dialogue content input area is used for the user account to input first dialogue content for the topic card; based on the first dialogue content input by the user account in the dialogue content input area, a second dialogue content is displayed on the dialogue interface, showing the agent's reply based on the existing dialogue content corresponding to the topic card and the first dialogue content; the first and second dialogue contents are used to update the topic card.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to a dialogue processing method, apparatus, device, readable storage medium, and program product. Background Technology

[0002] With the rapid development of internet and artificial intelligence technologies, intelligent agent dialogue applications have emerged. Their interaction patterns have gradually evolved from single-turn question-and-answer to long-term, cross-topic, and coherent interactive modes. As dialogue needs and application scenarios become increasingly complex, users are placing higher demands on the overall interactive experience of intelligent agent dialogue applications.

[0003] In current technology, the dialogue content between the agent and the user is linearly accumulated. When the user wants to continue to ask questions about previous topics, they need to search through the long dialogue stream or re-lay out the background, which results in a technical problem of low dialogue processing efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a dialogue processing method, apparatus, device, readable storage medium, and program product to address the aforementioned technical problems.

[0005] Firstly, this application provides a dialogue processing method, including:

[0006] The topic cards for the user account are determined; the topic cards are obtained by summarizing the topics based on the existing dialogue content between the agent and the user account.

[0007] In response to a dialogue initiation operation for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface; the dialogue content input area is used by the user account to input the first dialogue content for the topic card.

[0008] Based on the first dialogue content for the topic card entered by the user account in the dialogue content input area, the second dialogue content replied by the agent based on the existing dialogue content corresponding to the topic card and the first dialogue content is displayed on the dialogue interface; the first dialogue content and the second dialogue content are used to update the topic card.

[0009] In one embodiment, the dialogue initiation operation includes a dialogue initiation operation triggered in the dialogue interface or a dialogue initiation operation triggered in the details interface of the topic card.

[0010] In one embodiment, the step of displaying a dialogue content input area for the topic card in the dialogue interface in response to a dialogue initiation operation for the topic card includes: displaying the dialogue interface; displaying a referable topic card in response to a card referencing operation triggered in the dialogue interface; and displaying a dialogue content input area for the topic card in the dialogue interface in response to a dialogue initiation operation triggered for the referable topic card.

[0011] In one embodiment, the dialogue interface provides a card reference entry; the step of displaying referenceable topic cards in response to a card reference operation triggered on the dialogue interface includes: displaying referenceable topic cards in response to an operation triggered on the card reference entry.

[0012] In one embodiment, after displaying the dialogue interface, the method further includes: displaying the dialogue content between the agent and the user account in the dialogue interface; the topic of the dialogue content may or may not be related to the topic card.

[0013] In one embodiment, the step of displaying a dialogue content input area for the topic card in the dialogue interface in response to a dialogue initiation operation for the topic card includes: displaying a topic interface for the user account; the topic interface displaying topic cards for the user account; displaying a details interface for the topic card in response to a card selection operation triggered on the topic interface; and displaying a dialogue interface and a dialogue content input area for the topic card in the dialogue interface in response to a dialogue initiation operation triggered on the details interface.

[0014] In one embodiment, the details interface displays a dialogue entry point; the step of displaying the dialogue interface and displaying a dialogue content input area for the topic card in response to a dialogue initiation operation triggered on the details interface includes: displaying the dialogue interface and displaying a dialogue content input area for the topic card in response to an operation triggered on the dialogue entry point of the details interface.

[0015] In one embodiment, the method further includes: displaying the first dialogue content in the dialogue interface in the form of target content based on the first dialogue content entered by the user account for the topic card in the dialogue content input area; the target content form is used to present that the first dialogue content is dialogue content entered by the user account for the topic card.

[0016] In one embodiment, after the first dialogue content for the topic card is entered in the dialogue content input area based on the user account, and the second dialogue content is displayed on the dialogue interface based on the existing dialogue content corresponding to the topic card and the first dialogue content, the method further includes: if the topics of the first dialogue content and the second dialogue content are related to the topic card, then the updated topic card is obtained.

[0017] Secondly, this application also provides a dialogue processing apparatus, comprising:

[0018] The card determination module is used to determine the topic cards of a user account; the topic cards are obtained by summarizing topics based on the existing dialogue content between the agent and the user account.

[0019] The dialogue initiation module is used to respond to a dialogue initiation operation for the topic card and display a dialogue content input area for the topic card in the dialogue interface; the dialogue content input area is used by the user account to input the first dialogue content for the topic card.

[0020] The content display module is used to display, on the dialogue interface, the second dialogue content replied by the agent based on the existing dialogue content corresponding to the topic card and the first dialogue content, according to the first dialogue content entered by the user account in the dialogue content input area; the first dialogue content and the second dialogue content are used to update the topic card.

[0021] Thirdly, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method.

[0022] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method.

[0023] Fifthly, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method.

[0024] The aforementioned dialogue processing method, apparatus, device, readable storage medium, and program product determine a topic card for a user account; the topic card is obtained by summarizing topics based on existing dialogue content between the agent and the user account; in response to a dialogue initiation operation for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface; the dialogue content input area is used for the user account to input first dialogue content for the topic card; based on the first dialogue content for the topic card entered by the user account in the dialogue content input area, a second dialogue content is displayed on the dialogue interface in which the agent responds based on the existing dialogue content corresponding to the topic card and the first dialogue content; the first and second dialogue contents are used to update the topic card. This method can obtain a topic card for a user account by summarizing topics based on existing dialogue content between the agent and the user account. Therefore, in response to a dialogue initiation operation by the user account for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface for the user account to input first dialogue content for the topic card, and then, based on the first dialogue content, the second dialogue content is displayed on the dialogue interface in which the agent responds based on the existing dialogue content corresponding to the topic card and the first dialogue content. This allows users to easily and efficiently initiate conversations about a topic card without having to manually search through previous conversations or repeatedly lay out the background, significantly reducing the cost of interaction and effectively improving the efficiency of conversation processing. At the same time, topic cards can be dynamically updated as the agent and user account communicate, enabling the long-term accumulation and reuse of conversation topics, continuously optimizing the long-term dialogue interaction experience of the agent, and improving the intelligence level and ease of use of human-computer dialogue. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is an application environment diagram of the dialogue processing method in one embodiment;

[0027] Figure 2 This is a flowchart illustrating a dialogue processing method in one embodiment;

[0028] Figure 3 This is a schematic diagram of the topic interface in one embodiment;

[0029] Figure 4 This is a schematic diagram of the details interface in one embodiment;

[0030] Figure 5This is a schematic diagram of a dialog interface in one embodiment;

[0031] Figure 6 This is a schematic diagram of the dialog interface in another embodiment;

[0032] Figure 7 This is a schematic diagram of the dialog interface in yet another embodiment;

[0033] Figure 8 This is a structural block diagram of a dialogue processing device in one embodiment;

[0034] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] Various intelligent agent dialogue applications (or applications with intelligent agent dialogue functionality) can provide users with an intelligent human-computer interaction platform. For example, applications can be equipped with intelligent agent interaction capabilities to provide users with interactive services such as intelligent question answering and multi-turn dialogue. Users can then use these applications for daily consultations, business communication, and other operations. Intelligent agent dialogue applications can be those that primarily use AI intelligent agent dialogue interaction to provide users with continuous human-computer conversation services. Applications with intelligent agent dialogue functionality can integrate AI intelligent agent dialogue interaction capabilities into their existing business functions, enabling them to engage in intelligent question answering and multi-turn dialogue with human-computer users. The intelligent agent can be an AI interactive entity built based on an AI model, possessing independent semantic understanding, autonomous response, and conversation memory capabilities, capable of engaging in multi-turn dialogues, topic summarization, and contextual semantic association with users. Intelligent agent dialogue applications (also applicable to applications with intelligent agent dialogue functionality, hereinafter referred to as applications) can run on a terminal. Users can create user accounts within these applications and, based on these user accounts, interact with the intelligent agent through the intelligent agent dialogue application running on the terminal. The application can be a parent application running on the terminal's operating system, a child application running within the parent application (such as a mini-program), or a web-based application.

[0037] With the rapid development of internet and artificial intelligence technologies, the interaction patterns of intelligent agent dialogue applications have gradually evolved from traditional single-turn question-and-answer to a mode of long-term, coherent, and continuous interaction across topics. As dialogue needs and application scenarios become increasingly complex, users are placing higher demands on the overall interactive experience of intelligent agent dialogue applications.

[0038] Currently, dialogues between agents and users are mostly presented in a linear, cumulative manner. When users want to continue asking questions about past topics, they need to manually search through the lengthy dialogue stream or re-establish the context of the previous conversation. Furthermore, users often have to choose between interrupting the current conversation and abandoning further questions about past topics. For example, if a user is discussing topic A and needs to ask a follow-up question about topic B, they usually have to either interrupt the current discussion on topic A or completely re-establish the context of topic B before continuing the conversation. This results in cumbersome dialogue operations and low dialogue processing efficiency.

[0039] To address this, this application provides a dialogue processing method. This method can summarize topics based on existing dialogue content between the agent and the user account to obtain topic cards for the user account. In response to a user account's initiation of a dialogue based on a topic card, a dialogue content input area for the topic card is displayed on the dialogue interface for the user account to input first dialogue content. Then, based on the first dialogue content, a second dialogue content is displayed on the dialogue interface, showing the agent's response based on the existing dialogue content corresponding to the topic card and the first dialogue content. This allows users to conveniently and efficiently initiate dialogues based on topic cards without manually searching through previous dialogues or repeatedly providing background information, significantly reducing interaction costs and effectively improving dialogue processing efficiency. Simultaneously, topic cards can be dynamically updated as the dialogue between the agent and the user account progresses, achieving long-term accumulation and reuse of conversation topics, continuously optimizing the long-term dialogue interaction experience of the agent, and improving the intelligence level and ease of use of human-computer dialogue.

[0040] Before describing the embodiments of this application, it should be noted that the term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is met. It will be understood that the timing of subsequent actions performed in response to an event or condition is not necessarily strongly correlated with the time when the event occurs or the condition is met. For example, in some cases, subsequent actions may be performed immediately upon the occurrence of the event or the fulfillment of the condition; while in other cases, subsequent actions may be performed some time after the occurrence of the event or the fulfillment of the condition. "Triggering operation" refers to an action performed by a user on a visual interface through clicking, dragging, swiping, or other interactive methods, which can be used to initiate or activate functions such as data generation, display, analysis, and publishing. The terms "first," "second," etc., used in the embodiments of this application can be used to describe various objects, but these objects are not limited by these terms. These terms are only used to distinguish between the first object and the second object. The terms "comprising" and "having," and any variations thereof, used in the embodiments of this application, are intended to cover non-exclusive inclusion. The term "multiple" used in the embodiments of this application refers to two or more. The term "and / or" used in the embodiments of this application refers to one of the solutions, or any combination of multiple solutions.

[0041] The dialogue processing method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown is as follows: The terminal communicates with the server via a network. The terminal can run applications, which can be a parent application running on the terminal's operating system, a sub-application running within the parent application (such as a mini-program), or a web-based application. The application can have functions including, but not limited to, AI-powered intelligent agent dialogue interaction. The server can provide services related to AI-powered intelligent agent dialogue interaction for the terminal's applications. A data storage system can store the data that the server needs to process. The data storage system can be integrated on the server or located on the cloud or other network servers. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart TVs, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0042] In one exemplary embodiment, such as Figure 2 As shown, a dialogue processing method is provided, which is applied to... Figure 1 Taking a terminal as an example, the method may include the following steps:

[0043] Step S201: Determine the topic cards for the user account. The topic cards are obtained by summarizing the topics based on the existing dialogue content between the agent and the user account.

[0044] The user account can be an identity identifier that a user registers and creates in an intelligent agent dialogue application running on the terminal. It can serve as an operational medium for users to interact with intelligent agents. The terminal can associate all existing dialogue content, topic cards, and interaction records of the user through the user account.

[0045] The topic card is a structured content unit that can be independently presented and reactivated, generated from existing dialogue content between the agent and the user account. This unit is created by using topic summarization algorithms (such as text clustering and keyword extraction algorithms like TF-IDF and K-means clustering) to extract and summarize topics from the existing dialogue content. It can be used to restore the complete topic context for the agent. The complete topic context can be considered as all the background information constituting the topic, including all existing dialogue content under that topic, information obtained by summarizing existing dialogue content, and structured data. The structured data can be data that the agent generates and outputs during existing dialogue interactions with the user account, according to preset formats, standardized fields, or a unified structure. This data is directly identifiable, quickly accessible, and structured, and can be directly used as part of the topic context for the agent to quickly read and reuse in subsequent responses. As an example, in the existing dialogue on the topic of "Weekend Trip Planning," the agent can provide users with structured data including: Scenic spot structured information: {Scenic spot name: XX Mountain, Type: Natural landscape, Driving distance: 1.5 hours, Ticket price: 50 yuan / person, Opening hours: 8:00-18:00}; Itinerary structured arrangement: {Date: Saturday, Morning: XX Mountain visit, Afternoon: XX Lake leisure, Transportation: Self-driving, Precautions: Bring sun protection products}; Core information extracted structured data: {Core needs: Weekend self-driving short trip, Preference: Natural landscape, Budget: Under 200 yuan / person}. This structured data, together with the natural dialogue text and topic summary information under this topic, constitutes the complete topic context for the agent to directly access when responding to user follow-up questions on this topic, without needing to re-parse the natural dialogue text, further improving dialogue processing efficiency.

[0046] Each topic card corresponds to an independent topic. Topic cards visually display the main information of the topic, allowing users to quickly locate the topic they need. Topic cards can include various components, such as a title (e.g., "10 Pieces of Mountaineering Gear for Beginners"), a subtitle (or summary, such as "Clothing System, Footwear, and Core Gear Recommendations"), a cover image, and complete topic context. Topic cards can be displayed with a title, subtitle, and cover image.

[0047] The topic cards are generated by summarizing existing conversations between the agent and the user account. The agent can be deployed on a server or a terminal. During the conversation between the agent and the user account, the agent can comprehensively determine whether a topic card can be generated based on multiple factors, including existing conversation content (including historical and ongoing conversations), the agent's output characteristics, the user's active collection behavior, and the stability of the conversation topic. For example, when the agent's output contains summable structured data (such as lists, grouping schemes, tables, etc.), the agent can automatically generate a topic card, including a title, subtitle / tag, cover image, structured main content, and complete topic context.

[0048] In this step, the terminal can first identify the currently logged-in user account and obtain all the topic cards for that user account. These topic cards can be generated by an agent deployed on the terminal or server, based on its existing dialogue content with the user account. The agent can generate topic cards in real-time or asynchronously based on its existing dialogue content with the user account. For example, if a user, using their own user account, has engaged in two dialogues with the agent in the terminal's application—one about "weekend travel planning" and the other about "office software operation consultation"—the agent can generate two topic cards, "weekend travel planning" and "office software operation consultation," respectively, by summarizing the topics of the existing dialogue content and associating them with the user account. The user can then quickly locate the corresponding topic in subsequent conversations using these two topic cards.

[0049] In step S202, in response to the dialogue initiation operation for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface. The dialogue content input area is used by the user account to enter the first dialogue content for the topic card.

[0050] The dialogue initiation operation can be an operation performed by the user in the terminal's application for a topic card to start a dialogue corresponding to that topic. As an example, the operation form can include, but is not limited to, interactive operations that can be recognized by the terminal, such as clicking the topic card, long-pressing the topic card, and double-clicking the topic card.

[0051] The dialogue interface can be a visual interface displayed to the user after the terminal runs the application, used for human-computer dialogue interaction, and can serve as a carrier for the user to conduct dialogue operations with the intelligent agent.

[0052] In this step, the terminal can respond to the user's dialogue initiation operation for a topic card by displaying a dialogue content input area for that topic card on the dialogue interface. This dialogue content input area can be a visual input control displayed on the dialogue interface for the user to input dialogue content. It can be presented as an input box and can support the user to input dialogue content via the terminal's keyboard, voice input, or other methods. After responding to the user's dialogue initiation operation for a topic card, the dialogue content input area displayed on the dialogue interface for that topic card can be bound to that topic card at least once, and used to input dialogue content related to the topic card's corresponding theme. That is, this dialogue content input area can be used by the user account to input the first dialogue content for the topic card. This first dialogue content can be the dialogue content entered in the dialogue content input area displayed on the terminal, specifically for the topic card bound to that dialogue content input area (such as follow-up questions, supplementary explanations, new inquiries, etc.). The terminal can receive the first dialogue content and use it to trigger the intelligent agent's response operation.

[0053] As an example, the terminal detects a user's initiation of a dialogue for a topic card. In response to this dialogue initiation, the terminal displays a dialogue input area for that topic card on the dialogue interface. This dialogue input area can have an identifier for that topic card (such as displaying "Additional question for 'Weekend travel planning'"), which can be used to prompt the user to enter the first dialogue content for the topic card (such as "Recommend a few scenic spots suitable for weekend road trips"). The terminal can also associate this dialogue input area with the user's account and the topic card to prepare for subsequent agent responses and topic card updates.

[0054] Step S203: Based on the first dialogue content for the topic card entered by the user account in the dialogue content input area, display the second dialogue content in the dialogue interface, which is the agent's reply based on the existing dialogue content corresponding to the topic card and the first dialogue content. The first and second dialogue contents are used to update the topic card.

[0055] The second dialogue content can be the response content of the intelligent agent after the terminal sends the first dialogue content input by the user, combined with the complete topic context under the topic card (which may include existing dialogue content, information obtained by summarizing existing dialogue content, structured data, etc.), to the intelligent agent; the response content can be generated by the intelligent agent based on the complete topic context under the topic card and the first dialogue content, to ensure the coherence and relevance of the dialogue, and is displayed to the user by the terminal on the dialogue interface.

[0056] As an example, the first dialogue content for a topic card can be submitted to the terminal by the user through a confirmation action triggered by the terminal (such as clicking the "send" button). After receiving the first dialogue content submitted by the user's account, the terminal can retrieve existing dialogue content and other information corresponding to the topic card, and send it to the agent along with the first dialogue content, instructing the agent to generate response content (i.e., the second dialogue content). After receiving the second dialogue content returned by the agent, such as "Recommended XX Mountain and XX Lake, 1-2 hours drive from the city, suitable for weekend road trips, with complete supporting facilities," the terminal can display the second dialogue content on the dialogue interface. The second dialogue content can be displayed below the first dialogue content, forming a coherent dialogue for the user to view.

[0057] In this step, the first and second dialogue contents are used to update the topic card. Specifically, after obtaining the first dialogue content input by the user's account and the second dialogue content generated by the agent's response, the terminal can incorporate the newly added first and second dialogue contents into the existing dialogue content associated with the corresponding topic card. Specifically, the terminal can synchronously adjust and iterate at least one of the topic card's title, subtitle, cover image, and structured data, enabling the topic card to adapt to the complete context of the current topic's evolution in real time, achieving dynamic updates and content iteration. Thus, the topic card can continuously supplement new dialogue content as the user and agent continue interacting on the same topic, without needing to create new topic cards. This continuously accumulates the complete dialogue of the topic, ensuring the integrity and continuity of the topic context. It also facilitates subsequent interactions on the same topic without needing to re-establish the background; users can directly interact based on the updated topic card.

[0058] The dialogue processing method in this embodiment determines a topic card for a user account. The topic card is obtained by summarizing existing dialogue content between the agent and the user account. In response to a dialogue initiation operation for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface. The dialogue content input area is used by the user account to input first dialogue content for the topic card. Based on the first dialogue content entered by the user account in the dialogue content input area, a second dialogue content is displayed on the dialogue interface, showing the agent's response based on the existing dialogue content corresponding to the topic card and the first dialogue content. The first and second dialogue contents are used to update the topic card. This method can obtain a topic card for the user account by summarizing existing dialogue content between the agent and the user account. Therefore, in response to a dialogue initiation operation by the user account for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface for the user account to input first dialogue content for the topic card. Then, based on the first dialogue content, the second dialogue content is displayed on the dialogue interface, showing the agent's response based on the existing dialogue content corresponding to the topic card and the first dialogue content. This allows users to easily and efficiently initiate conversations about a topic card without having to manually search through previous conversations or repeatedly lay out the background, significantly reducing the cost of interaction and effectively improving the efficiency of conversation processing. At the same time, topic cards can be dynamically updated as the agent and user account communicate, enabling the long-term accumulation and reuse of conversation topics, continuously optimizing the long-term dialogue interaction experience of the agent, and improving the intelligence level and ease of use of human-computer dialogue.

[0059] In one exemplary embodiment, the above method may further include the following steps:

[0060] Based on the first dialogue content for the topic card entered by the user account in the dialogue content input area, the first dialogue content is displayed in the dialogue interface in the form of target content.

[0061] In this embodiment, the target content format is used to present the first dialogue content as dialogue content entered by the user account in response to the topic card. As an example, this target content format can be used to display the referenced topic card (the aforementioned topic card that triggered the dialogue initiation operation) in a reference style, for example, by setting a vertical line mark on one side (to visually distinguish it from other content on the dialogue interface), along with a thumbnail of the topic card (which can be the cover image of the topic card), while appropriately weakening the display brightness of the referenced topic card, so that users can clearly identify the topic source corresponding to the current dialogue content without interfering with the current input and dialogue display. Specifically, when a user enters the first dialogue content (such as "What items do I need to prepare for driving to XX scenic spot?") in the dialogue content input box displayed on the terminal using the currently logged-in user account and submits it, the terminal receives the first dialogue content and displays it in the form of target content. For example, a referenced topic card is displayed above the first dialogue content. A vertical line can be set on the left side of the referenced topic card as a reference mark, and the cover image of the topic card is displayed in the middle. The overall display brightness is lower than that of the current dialogue content and the dialogue content input box, forming a visual hierarchy, allowing the user to intuitively know that the currently entered dialogue content is for the referenced topic card, without affecting the current operation.

[0062] In an exemplary embodiment, after the user enters the first dialogue content for the topic card in the dialogue content input area according to the user account in step S203, and the second dialogue content is displayed on the dialogue interface in which the agent replies according to the existing dialogue content corresponding to the topic card and the first dialogue content, the method of this application may further include the following steps:

[0063] If the topics of the first and second dialogues are related to the topic card, then obtain the updated topic card.

[0064] In this embodiment, the intelligent agent can identify and determine the association between the first and second dialogue contents generated in the current round of interaction after obtaining the first and second dialogue contents. Specifically, if the intelligent agent determines that the topics of the first and second dialogue contents are related to a topic card (e.g., having contextual relevance, topic continuity, etc.), it can determine that the newly added dialogue content in this round belongs to the same topic corresponding to that topic card. In this case, the intelligent agent can incorporate the first and second dialogue contents of this round into the existing dialogue content corresponding to that topic card, and can adjust at least some of the content in the topic card to generate an updated topic card. The terminal can obtain the updated topic card from the intelligent agent. The updated topic card can completely contain the continued dialogue content of this round, retaining the complete contextual logic of the topic. Subsequent users can continue to initiate a new round of dialogue interaction based on the updated topic card without creating a new topic card, effectively ensuring the continuity and integrity of dialogues on the same topic.

[0065] In one exemplary embodiment, the dialogue initiation operation includes a dialogue initiation operation triggered in the dialogue interface or a dialogue initiation operation triggered in the details interface of the topic card.

[0066] In this embodiment, the dialogue initiation operation can include two scenarios, corresponding to two dialogue initiation methods: proactive initiation and reference-based initiation. Specifically, the dialogue initiation operation includes one triggered in the dialogue interface and another triggered in the details interface of a topic card. These two scenarios correspond to reference-based initiation and proactive initiation, respectively.

[0067] Specifically, in the proactive initiation mode, users can access the details interface of a topic card based on their currently logged-in user account. This details interface displays the details of the topic card, including its title, structured data, and other information. Users can initiate a conversation by clicking buttons such as "Chat" or "Start a Conversation" in the details interface. At this time, the terminal can display a conversation input area for the topic card in the conversation interface. Users do not need to redo the background; they can directly input the first conversation content to continue the interaction. In other words, users can proactively initiate conversations about topic cards in the details interface, and the conversation can inherit the topic context of the topic card to achieve a coherent continuation of the topic.

[0068] Specifically, in the reference-based initiation, users can initiate conversations by referencing a specified topic card in the dialogue interface based on their currently logged-in user account. For example, a user can select a topic card to reference in the dialogue interface (corresponding to the dialogue initiation operation). The dialogue input area for that topic card is displayed in the dialogue interface. The terminal can inject the topic context of that topic card into the current dialogue. Thus, the user does not need to redo the background and can directly input the first dialogue content to achieve continued interaction. That is, a user can initiate a dialogue for that topic card by referencing it in the dialogue interface, and the dialogue can inherit the topic context of that topic card to achieve coherent continuation of the topic.

[0069] In this embodiment, both dialogue initiation operations allow users to clearly understand the source of the topic in the current dialogue, while ensuring the coherence of the dialogue and the integrity of the context.

[0070] In an exemplary embodiment, step S202, in response to a dialogue initiation operation for a topic card, displays a dialogue content input area for the topic card in the dialogue interface, which may include:

[0071] Display the dialogue interface; in response to a card referencing operation triggered in the dialogue interface, display the referable topic cards; in response to a dialogue initiation operation triggered on a referable topic card, display the dialogue content input area for the topic card in the dialogue interface.

[0072] In this embodiment, the card referencing operation can be an interactive operation performed by the user in the terminal's dialogue interface to invoke a referable topic card. Here, a referable topic card refers to a topic card of the user account that can be referenced in the dialogue interface. In some embodiments, it may include all topic cards of the user account. This referable topic card can be used to select the topic card to initiate the dialogue.

[0073] In this embodiment, the terminal can display a dialogue interface to the user. The user can trigger a card referencing operation within the dialogue interface. In response to this operation, the terminal can aggregate and display all referable topic cards under the user's account for browsing and selection. The user can select a topic card from the displayed referable topic cards to initiate a dialogue (e.g., by clicking a topic card). In response, the terminal displays a dialogue input area for that topic card within the dialogue interface, allowing the user to input initial dialogue content for that topic card. This enables dialogue based on referenced topic cards within the dialogue interface, eliminating the need for the user to manually repeat the topic background and improving the convenience and efficiency of dialogue interaction.

[0074] In one exemplary embodiment, the dialog interface provides a card reference entry; the above-described response to a card reference operation triggered in the dialog interface, displaying referenceable topic cards, may include:

[0075] In response to an action triggered by a card reference entry, display the referenceable topic cards.

[0076] In this embodiment, the card reference entry can be a visual interactive entry set in the dialogue interface. It can be located in an auxiliary position of the dialogue input area (such as an input box) or a functional area of ​​the dialogue interface. It can be any form of interactive control, such as the "reference card" button attached to the dialogue input area or the @mention interactive entry. It can be used to allow users to trigger the card reference operation and then select the topic card that can be referenced.

[0077] Specifically, the terminal displays a dialogue interface, which can have a preset card reference entry point. This entry point can be a "Quote Card" button attached to the input box, or any interactive control that can trigger a reference function, such as @mention. Users can trigger the card reference entry point by clicking the "Quote Card" button or using any interactive operation such as @mention. In response to this trigger, the terminal can display all or some of the topic cards under the user's account as available topic cards in the dialogue interface, allowing the user to select any one to initiate further dialogue. This embodiment's solution, based on the card reference entry point, allows for quick retrieval of referenceable topic cards, enabling rapid referencing of topic cards within the topic interface.

[0078] In one exemplary embodiment, after displaying the dialog interface in the above embodiments, the following steps may be included:

[0079] The dialogue interface displays the ongoing conversation between the agent and the user account. The topics of the conversation may or may not be related to the topic cards.

[0080] The dialogue between the agent and the user account can include one or more rounds of dialogue during the real-time interaction between the user account and the agent in the dialogue interface, and can include dialogue content input by the user and dialogue content replied by the agent.

[0081] Specifically, the relevance of the dialogue content to the topic card can be defined as follows: the topic of the ongoing dialogue between the agent and the user account has a certain degree of similarity to the topic of the topic card that triggered the dialogue. For example, a similarity threshold can be used to measure the similarity of the topics. If the similarity is greater than or equal to a certain threshold, it can be determined that the topics of the two are similar and the dialogue content is related to the topic card; if it is less than a certain threshold, the dialogue content is not related to the topic card. Conversely, the irrelevance of the dialogue content to the topic card can be defined as follows: the topic of the ongoing dialogue between the agent and the user account is not related to the topic of the topic card that triggered the dialogue.

[0082] Therefore, in this embodiment, the terminal can display a dialogue interface where the user is having a conversation with the agent. The user can trigger a card referencing operation within the dialogue interface, and the terminal displays referable topic cards. In response to the user's dialogue initiation operation triggered by the referable topic card, the terminal displays a dialogue content input area for the topic card within the dialogue interface. The topic of this topic card may or may not be related to the topic of the ongoing conversation between the agent and the user's account. The terminal can inject the topic context of the referenced topic card into the current dialogue, while the ongoing conversation between the agent and the user's account is not used as the context for this round of dialogue, thus avoiding topic contamination. This solution is applicable to scenarios where a user is having a conversation within the dialogue interface and temporarily wants to supplement their inquiry about a historical topic card without interrupting the ongoing conversation. The user can initiate a conversation about a topic card by referencing it within the dialogue interface, injecting the topic context of the referenced topic card without switching the current dialogue flow.

[0083] In an exemplary embodiment, step S202, in response to a dialogue initiation operation for a topic card, displays a dialogue content input area for the topic card in the dialogue interface, which may include:

[0084] The topic interface displays the user's account; the topic interface displays topic cards with the user's account; in response to a card selection operation triggered on the topic interface, the details interface of the topic card is displayed; in response to a dialogue initiation operation triggered on the details interface, the dialogue interface is displayed, and the dialogue content input area for the topic card is displayed on the dialogue interface.

[0085] The topic interface for a user account can be an interface provided by the terminal for displaying various topic cards under the user account. The topic interface can display various topic cards under the user account in a waterfall layout. The display format of topic cards can include cover, title and summary.

[0086] The card selection operation can be a user's interaction with any topic card displayed in the topic interface, such as clicking, long-pressing, or selecting. It can be used to select a topic card to bring up the corresponding details interface.

[0087] In this embodiment, the terminal can display the topic interface for the currently logged-in user account. The topic interface displays various topic cards under the user account in a waterfall layout. The user can select a topic card within the topic interface, and the terminal will then display the details interface for that topic card. The user can further initiate a conversation within the details interface of that topic card. In response to this conversation initiation, the terminal will display a conversation interface and a conversation input area for the topic card, allowing the user to input initial conversation content for that topic card.

[0088] In one exemplary embodiment, the details interface displays a dialogue entry point; the aforementioned response to a dialogue initiation operation triggered on the details interface, displaying the dialogue interface and a dialogue content input area for the topic card on the dialogue interface, may include:

[0089] In response to an action triggered by a dialogue entry in the details screen, the dialogue interface is displayed, along with a dialogue input area for the topic card.

[0090] The dialogue entry point can be a visual interactive control set in the details interface of the topic card on the terminal. It can serve as the operation entry point for users to initiate a dialogue for the corresponding topic card in the details interface. It can be triggered by users through clicking or other means, and can be used to quickly jump to the dialogue interface and bring up the dialogue content input area of ​​the corresponding topic card.

[0091] In this embodiment, the terminal can display a details interface for the topic card, and show a dialogue entry point at a preset location on the details interface, providing users with an interactive way to directly initiate a topic dialogue from the details interface. Users can trigger an operation on the set dialogue entry point in the details interface of the topic card. In response to the operation, the terminal displays the dialogue interface and a dialogue content input area for the topic card, allowing the user to input initial dialogue content for that topic card. Thus, users can enter the dialogue interface with a single click through the dialogue entry point on the details interface, where the dialogue content input area for the topic card is displayed, eliminating the need to manually reference or reselect the topic card, making the operation convenient.

[0092] In an exemplary embodiment, the dialogue processing method of this application can be used by an intelligent agent to summarize its dialogue content with a user account into topic cards and store them in the user account's topic interface. The user can subsequently initiate dialogues on these topic cards in two ways: proactive (triggering a dialogue initiation operation in the topic card's details interface) and referential (triggering a dialogue initiation operation by referencing the topic card in the dialogue interface). Both methods allow the intelligent agent to provide a coherent response based on the topic context of the topic card without requiring the user to restate the background. For example, if a user previously inquired about mountaineering equipment and this was stored as a topic card titled "10 pieces of mountaineering equipment for beginners," and later, when discussing unrelated topics (such as driving and lane changes) in the dialogue interface, the user can temporarily reference this topic card to ask "recommendations for windbreaker brands," and the intelligent agent can provide an appropriate response based on the topic context of that topic card.

[0093] Specifically, the proactive initiation of dialogues based on topic cards is suitable for scenarios where users wish to explore a topic in depth and continuously. Users can click on a topic card on the topic interface, and the terminal will display a details screen for the topic card. This details screen can show a dialogue entry point. Users can click on the dialogue entry point, and the terminal will display a dialogue interface and an input area for dialogue content related to that topic card. Users input the first dialogue content for that topic card. The terminal, based on the topic context of the topic card (including existing dialogue content corresponding to the topic card) and the first dialogue content, submits it to the intelligent agent. The intelligent agent can then generate a second dialogue content based on this. The terminal can retrieve this second dialogue content from the intelligent agent and display it on the dialogue interface. The intelligent agent can update the topic card based on the first and second dialogue content, allowing the topic card's content to continuously grow.

[0094] For the reference-based initiation of dialogues targeting topic cards, applicable scenarios include users discussing other topics within the dialogue interface, wanting to temporarily add a question about a historical topic without interrupting the current conversation (which may already contain multiple rounds of dialogue). Users can select a historical topic card through the card reference entry provided in the dialogue interface (the "Reference Card" button attached to the input box, @mention, etc.). This topic card can be presented above the input box as target content (vertical line on the left, thumbnail, visually weakened, etc.). The user enters the first dialogue content for that topic card. The terminal submits the first dialogue content to the agent based on the topic context of the topic card (including existing dialogue content corresponding to the topic card) and the first dialogue content. The current dialogue is not considered as historical context to avoid topic contamination. The agent can generate a second dialogue content based on the topic context of the topic card and the first dialogue content. The terminal can retrieve this second dialogue content from the agent and display it in the dialogue interface. The agent can update the topic card based on the first and second dialogue content, allowing the topic card's content to continuously grow.

[0095] For both methods of initiating dialogues around topic cards, the new first and second dialogue contents can be used by the agent to update the topic card. This topic card can serve as a persistent container for consistent topic context across user entry points and can be reused.

[0096] Specifically, the above dialogue processing method will be explained with reference to the interactive interface diagram.

[0097] Among them, such as Figure 3 As shown, the terminal can display a topic interface 300 for user accounts, and the topic interface 300 can display topic cards 310 containing user accounts. It is understandable that... Figure 3 The example shown is a topic card. In actual application, the topic interface 300 can display various topic cards under a user account in a waterfall layout, and there can be multiple of them. Users can click on topic card 310 in the topic interface 300, such as... Figure 4 As shown, the terminal can display the details interface 400 of topic card 310 (in this example, the details interface of a travel guide topic card for a certain place). This details interface 400 can display a dialogue entry point, which the user can click on, such as... Figure 5As shown, the terminal displays a dialogue interface 500 and a dialogue content input area 510 for the topic card 310. The user inputs the first dialogue content 310, which is a follow-up question for the topic card. The terminal submits the first dialogue content to the agent based on the topic context of the topic card 310 (including the existing dialogue content corresponding to the topic card). The agent can generate the second dialogue content based on this. The terminal can obtain the second dialogue content from the agent and display it in the dialogue interface 500 (not shown in the figure). The agent can update the topic card 310 according to the first and second dialogue content, so that the content of the topic card 310 continues to grow.

[0098] Among them, such as Figure 6 As shown, for a dialogue initiated by referencing a topic card, the terminal can display a dialogue interface 600. Dialogue interface 600 can display ongoing dialogues (such as discussions about lane changing). The user can reference the topic card "10 pieces of beginner mountaineering gear" in dialogue interface 600 and enter the first dialogue content 610 for that topic card (e.g., requesting recommendations for outdoor jacket brands). Figure 7 As shown, the agent can generate a second dialogue content 620 (recommending a brand of outdoor clothing) based on the topic context of the topic card "10 pieces of mountaineering equipment for beginners" and the first dialogue content 610 (requesting a brand of outdoor clothing). The terminal can obtain the second dialogue content 620 (recommending a brand of outdoor clothing) from the agent and display it in the dialogue interface. The agent can update the topic card "10 pieces of mountaineering equipment for beginners" based on the first dialogue content 610 (requesting a brand of outdoor clothing) and the second dialogue content 620 (recommending a brand of outdoor clothing), so that the content of the topic card continues to grow.

[0099] The dialogue processing method in this application can automatically summarize the dialogue content between the user account and the intelligent agent and store it in the form of topic cards on the user account's topic interface, achieving structured storage and persistent retention of dialogue content. Simultaneously, it adapts to the need for continuous dialogue in different user interaction scenarios through two topic card dialogue initiation methods: proactive and reference-based. On the one hand, when using the proactive initiation method, users can enter the topic card's details interface from the topic interface and quickly initiate a dialogue for the topic card through the dialogue entry point. This is suitable for use scenarios involving in-depth and continuous exploration of the same topic. Relying on the topic context inherent in the topic card, the intelligent agent can respond accordingly without the user needing to repeat the dialogue background. Furthermore, newly added first and second dialogue contents can continuously iterate and update the topic card, achieving dynamic accumulation and improvement of the topic card content. On the other hand, when using the reference-based initiation method, users can select historical topic cards at any time during the current unrelated dialogue to temporarily ask follow-up questions through the card reference entry in the dialogue interface, without interrupting the existing dialogue session. This method also isolates the current unrelated dialogue context, avoiding topic contamination, and responds to the user's dialogue content only based on the topic context of the referenced topic card. This balances the need for temporary follow-up questions with the independence of the original dialogue. Simultaneously, the referenced topic cards can be displayed in a specific visual style in the dialogue interface, enhancing the recognizability of the corresponding topic's dialogue content. Both dialogue initiation methods are convenient to operate, and the newly generated dialogue content can be uniformly used to update topic cards. This makes topic cards a persistent, reusable, cross-entry topic context carrier, simplifying the user's cost of repeatedly laying out topic backgrounds, improving the efficiency and user experience of human-computer dialogue interaction, and also enabling the accumulation, dynamic updating, and reuse of dialogue topics, ensuring the consistency and accuracy of the agent's responses.

[0100] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0101] Based on the same inventive concept, this application also provides a dialogue processing apparatus for implementing the dialogue processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more dialogue processing apparatus embodiments provided below can be found in the limitations of the dialogue processing method described above, and will not be repeated here.

[0102] In one exemplary embodiment, such as Figure 8 As shown, a dialogue processing apparatus 800 is provided, which may include:

[0103] The card determination module 801 is used to determine the topic cards of the user account; the topic cards are obtained by summarizing the topics based on the existing dialogue content between the intelligent agent and the user account.

[0104] The dialogue initiation module 802 is used to respond to a dialogue initiation operation for the topic card and display a dialogue content input area for the topic card in the dialogue interface; the dialogue content input area is used by the user account to input the first dialogue content for the topic card.

[0105] The content display module 803 is used to display, on the dialogue interface, the second dialogue content replied by the intelligent agent based on the existing dialogue content corresponding to the topic card and the first dialogue content, according to the first dialogue content entered by the user account in the dialogue content input area; the first dialogue content and the second dialogue content are used to update the topic card.

[0106] In one exemplary embodiment, the dialogue initiation operation includes a dialogue initiation operation triggered in the dialogue interface or a dialogue initiation operation triggered in the details interface of the topic card.

[0107] In an exemplary embodiment, the dialogue initiation module 802 is configured to display a dialogue interface; in response to a card referencing operation triggered on the dialogue interface, display referable topic cards; and in response to a dialogue initiation operation triggered on a referable topic card, display a dialogue content input area for the topic card on the dialogue interface.

[0108] In one exemplary embodiment, the dialogue interface provides a card reference entry; the dialogue initiation module 802 is used to display referenceable topic cards in response to an operation triggered by the card reference entry.

[0109] In an exemplary embodiment, the dialogue initiation module 802 is further configured to display the dialogue content between the agent and the user account in progress on the dialogue interface; the topic of the dialogue content may or may not be related to the topic card.

[0110] In an exemplary embodiment, the dialogue initiation module 802 is used to display a topic interface of the user account; the topic interface displays topic cards of the user account; in response to a card selection operation triggered on the topic interface, a details interface of the topic card is displayed; in response to a dialogue initiation operation triggered on the details interface, a dialogue interface is displayed and a dialogue content input area for the topic card is displayed on the dialogue interface.

[0111] In one exemplary embodiment, the details interface displays a dialogue entry point; the dialogue initiation module 802 is used to display the dialogue interface and display a dialogue content input area for the topic card in the dialogue interface in response to the operation triggered by the dialogue entry point of the details interface.

[0112] In an exemplary embodiment, the content display module 803 is further configured to display the first dialogue content in the dialogue interface in the form of target content based on the first dialogue content entered by the user account in the dialogue content input area for the topic card; the target content form is used to present that the first dialogue content is dialogue content entered by the user account for the topic card.

[0113] In an exemplary embodiment, the card determination module 801 is further configured to obtain the updated topic card if the topics of the first dialogue content and the second dialogue content are related to the topic card.

[0114] Each module in the aforementioned dialogue processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can invoke and execute the operations corresponding to each module.

[0115] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a dialogue processing method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0116] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0117] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0118] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0119] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0121] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0122] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0123] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A dialog processing method characterized by, The method includes: The topic cards for the user account are determined; the topic cards are obtained by summarizing the topics based on the existing dialogue content between the agent and the user account. In response to a dialogue initiation operation for the topic card, a dialogue content input area for the topic card is displayed on the dialogue interface; the dialogue content input area is used by the user account to input the first dialogue content for the topic card. Based on the first dialogue content for the topic card entered by the user account in the dialogue content input area, the second dialogue content replied by the agent based on the existing dialogue content corresponding to the topic card and the first dialogue content is displayed on the dialogue interface; the first dialogue content and the second dialogue content are used to update the topic card.

2. The method of claim 1, wherein, The dialogue initiation operation includes a dialogue initiation operation triggered in the dialogue interface or a dialogue initiation operation triggered in the details interface of the topic card.

3. The method of claim 2, wherein, The response to initiating a dialogue for the topic card, displaying a dialogue content input area for the topic card in the dialogue interface, includes: Display the dialog interface; In response to a card referencing operation triggered in the dialogue interface, display referable topic cards; In response to a dialogue initiation action triggered by a referable topic card, a dialogue content input area for the topic card is displayed in the dialogue interface.

4. The method of claim 3, wherein, The dialogue interface provides a card reference entry; in response to a card reference operation triggered on the dialogue interface, referenceable topic cards are displayed, including: In response to an operation triggered by the card reference entry, referenceable topic cards are displayed.

5. The method of claim 3, wherein, Following the display of the dialog interface, the following is also included: The dialogue interface displays the ongoing conversation between the agent and the user account; the topic of the conversation may or may not be related to the topic card.

6. The method of claim 2, wherein, The response to initiating a dialogue for the topic card, displaying a dialogue content input area for the topic card in the dialogue interface, includes: The topic interface of the user account is displayed; the topic interface displays topic cards of the user account. In response to a card selection operation triggered on the topic interface, a details screen for the topic card is displayed; In response to a conversation initiation action triggered on the details screen, a conversation interface is displayed, and a conversation content input area for the topic card is displayed on the conversation interface.

7. The method of claim 6, wherein, The details interface displays a dialogue entry point; the response to a dialogue initiation operation triggered on the details interface, displaying a dialogue interface and a dialogue content input area for the topic card on the dialogue interface, includes: In response to an operation triggered by a dialogue entry on the details screen, a dialogue interface is displayed, and a dialogue content input area for the topic card is displayed on the dialogue interface.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Based on the first dialogue content entered by the user account in the dialogue content input area for the topic card, the first dialogue content is displayed in the dialogue interface in the form of target content; the target content form is used to present that the first dialogue content is the dialogue content entered by the user account for the topic card.

9. The method according to any one of claims 1 to 7, characterized in that, After the first dialogue content for the topic card is entered in the dialogue content input area according to the user account, and the second dialogue content is displayed on the dialogue interface after the agent replies with the existing dialogue content corresponding to the topic card and the first dialogue content, the method further includes: If the topics of the first and second dialogue contents are related to the topic card, then the updated topic card is obtained.

10. A dialogue processing apparatus characterized by comprising: The device includes: The card determination module is used to determine the topic cards of a user account; the topic cards are obtained by summarizing topics based on the existing dialogue content between the agent and the user account. The dialogue initiation module is used to respond to a dialogue initiation operation for the topic card and display a dialogue content input area for the topic card in the dialogue interface; the dialogue content input area is used by the user account to input the first dialogue content for the topic card. The content display module is used to display, on the dialogue interface, the second dialogue content replied by the agent based on the existing dialogue content corresponding to the topic card and the first dialogue content, according to the first dialogue content entered by the user account in the dialogue content input area; the first dialogue content and the second dialogue content are used to update the topic card. 11.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-10 when the computer program is executed by the processor. When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images