Content distribution method and device, electronic equipment, storage medium and product

Abstract

The invention relates to a content distribution method and device, electronic equipment, a storage medium and a product, and relates to the technical field of computers. The content distribution method comprises the steps that in response to operation of a first user in a target scene, one or more topic posts are displayed, and the one or more topic posts are content generated by a second user; the one or more topic posts are determined according to at least one of the information related to the operation, the information related to the historical operation of the first user and the information related to the current time, and the use of the information related to the operation and the information related to the historical operation is authorized by the first user; and in response to triggering of a target topic post in the one or more topic posts, displaying a page of the target topic post. According to the embodiment of the invention, the user generation content can be provided for the user in the target scene. Therefore, the comprehensiveness of the information in the intelligent agent application is improved, and the information acquisition efficiency of the user is improved.

Description

Technical Field

[0001] This disclosure relates to the field of computers, and in particular to a content distribution method, apparatus, electronic device, storage medium, and product. Background Technology

[0002] With the development of artificial intelligence technology, users can obtain information by conversing with intelligent agents. For example, when a user asks an intelligent agent a question, the agent will use the model's reasoning capabilities and existing knowledge base to provide an answer. Thus, intelligent agent-related applications can provide information to users through AI-generated content. Summary of the Invention

[0003] According to some embodiments of this disclosure, a content distribution method is provided, comprising: displaying one or more topic posts in response to an operation by a first user in a target scenario, wherein the one or more topic posts are content generated by a second user, and the one or more topic posts are determined based on at least one of information related to the operation, information related to the first user's historical operations, and information associated with the current time, wherein the use of the information related to the operation and the information related to historical operations is authorized by the first user; and displaying a page of the target topic post in response to triggering a target topic post among the one or more topic posts.

[0004] According to some embodiments of this disclosure, a content distribution apparatus is provided, comprising: a first display module configured to display one or more topic posts in response to an operation by a first user in a target scenario, wherein the one or more topic posts are content generated by a second user, and the one or more topic posts are determined based on at least one of information related to the operation, information related to the first user's historical operations, and information associated with the current time, wherein the use of the information related to the operation and the information related to historical operations is authorized by the first user; and a second display module configured to display a page of the target topic post in response to triggering of a target topic post among the one or more topic posts.

[0005] According to some embodiments of the present disclosure, an electronic device is provided, including: a memory; and a processor coupled to the memory, the processor being configured to perform the methods of any embodiment of the present disclosure based on instructions stored in the memory.

[0006] According to some embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the methods of any embodiment of the present disclosure.

[0007] According to some embodiments of the present disclosure, a computer program product is provided that, when run on a computer, causes the computer to implement the methods of any embodiment of the present disclosure.

[0008] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0009] Embodiments of this disclosure are described below with reference to the accompanying drawings. It should be understood that the drawings described below are merely illustrative of some embodiments of this disclosure and are not intended to limit the scope of this disclosure. In the drawings:

[0010] Figure 1 A flowchart illustrating a content distribution method according to some embodiments of the present disclosure is shown.

[0011] Figure 2 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown.

[0012] Figure 3 A schematic diagram of a dialog interface according to other embodiments of the present disclosure is shown.

[0013] Figure 4 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown.

[0014] Figure 5 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown.

[0015] Figure 6 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown.

[0016] Figure 7 A schematic diagram of a topic recommendation flow according to some embodiments of the present disclosure is shown.

[0017] Figure 8 A schematic diagram of a topic page according to some embodiments of the present disclosure is shown.

[0018] Figure 9 A schematic diagram of the structure of a content distribution apparatus according to some embodiments of the present disclosure is shown.

[0019] Figure 10 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0020] Figure 11 Block diagrams of electronic devices according to other embodiments of the present disclosure are shown. Detailed Implementation

[0021] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0022] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement of components and steps set forth in these embodiments should be interpreted as merely exemplary and does not limit the scope of this disclosure.

[0023] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". The term "based on" means "at least partially based on".

[0024] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0025] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0026] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0027] 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 disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals shall be provided for users to choose to authorize or refuse.

[0028] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0029] Analysis revealed that intelligent agent applications primarily involve interaction between the agent and the user. The agent excels at reasoning based on existing knowledge bases and user questions to generate responses. This significantly improves information retrieval efficiency for users in application scenarios requiring the agent to provide general knowledge or perform text processing.

[0030] However, the reasoning of intelligent agents may sometimes fail to match the more precise needs of some users, especially when it involves experiential or timely information from real people. For example, when a user asks an intelligent agent before the Spring Festival whether there will be many people at the train station, the agent might infer "many" based on its knowledge base, or provide an estimate based on historical passenger flow data. However, the former is not accurate for the user, as the agent's answer does not reveal the exact number of people. Similarly, simply providing statistical data does not provide the user with an intuitive understanding and is not helpful for obtaining relevant information. Therefore, improving the efficiency of information retrieval has become an urgent problem to be solved.

[0031] To further enhance the information provided by the intelligent agent, embodiments of this disclosure provide a content distribution method. This method distributes user-generated content, thereby improving the comprehensiveness of information in intelligent agent applications.

[0032] Figure 1 A flowchart illustrating a content distribution method according to some embodiments of this disclosure is shown. Figure 1 As shown, the content distribution method of this embodiment includes steps S11 to S12.

[0033] In step S11, in response to the first user's operation in the target scenario, one or more topic posts are displayed, wherein the one or more topic posts are content generated by the second user, and the one or more topic posts are determined based on at least one of the following: information related to the operation, information related to the first user's historical operations, and information associated with the current time, wherein the use of the information related to the operation and the information related to historical operations is authorized by the first user.

[0034] Target scenarios can include dialogue scenarios between users and agents, or recommendation stream scenarios, etc. Target scenarios can include interaction interfaces with agents, or scenarios related to agents. For example, a recommendation stream could be a recommendation stream within an agent application, or the recommendation stream interface could include input controls for interacting with agents.

[0035] User actions within the target scenario can include triggering the display of a page within the target scenario, sending a message within the target scenario, or triggering an object within the target scenario.

[0036] The displayed topic posts can be shown independently or aggregated. For example, in an aggregated display, one or more topic posts may belong to one or more topics. The objects corresponding to each topic can be displayed first, and then the topic posts can be displayed in response to a trigger on the topic object.

[0037] User-generated content (UGC) refers to content created by users who provide information. However, users can utilize artificial intelligence (AI) tools to assist in the creation process. For example, users can provide images for the content to be generated and use AI tools to modify them; or users can input text for the content to be generated and use AI tools to polish the text. Even when only AI tools are used to assist in creation, the generated content is still defined as user-generated content. That is, the main information of user-generated content is provided or conceived by the user.

[0038] A topic post can include one or more of the following data: text, images, audio, and video. Other users can reply to topic posts.

[0039] One or more topic posts can be determined based on information related to the current action. For example, the current action may include user instructions or user intent. Therefore, topic posts can be used to respond to the user's current action.

[0040] One or more topic posts can also be determined based on information related to the first user's historical actions. For example, it can be determined based on the user's historical conversations, browsing history, and other related information. Thus, user-generated content distributed to the user can be determined based on the user's historical actions.

[0041] One or more topic posts can also be determined based on information associated with the current time. This associated information could be time-sensitive or information that has been followed or discussed by multiple users within a short period of time. This allows users to promptly access user-generated content that they may be interested in or follow.

[0042] In some embodiments, one or more topic posts originate from a first topic, which is generated by clustering multiple topic posts based on target information. The target information can be determined based on the historical actions of multiple users or information associated with the current time. Alternatively, it can be the topics of each category obtained after unsupervised clustering of topic posts.

[0043] In step S12, in response to the triggering of a target topic post in one or more topic posts, the page of the target topic post is displayed.

[0044] The target topic post's page can include the post's content, such as the title, text, images, author, etc. Users can then comment on the content, or forward, save, etc., the topic post as needed.

[0045] The above embodiments are able to respond to the first user's operation in the target scene and distribute user-generated content, thereby providing the user with user-generated content in the target scene. Therefore, this disclosure improves the comprehensiveness of information in intelligent agent applications, thereby improving the user's information acquisition efficiency.

[0046] The format for displaying one or more topic posts can vary depending on the target scenario. In some embodiments, displaying one or more topic posts includes: displaying one or more topic posts respectively in response to a dialogue scenario between a first user and an agent; and displaying one or more aggregated topic posts in response to a recommendation stream scenario.

[0047] In a conversational context, one or more topic posts can be displayed independently, allowing users to directly obtain information from them. In a recommendation feed context, however, one or more topic posts can be aggregated into a higher-level display, enabling users to first understand the common characteristics of the posts before deciding whether to further browse the aggregated content or other aggregated objects.

[0048] The following sections will provide further details on the dialogue and recommendation stream scenarios.

[0049] In the context of a dialogue between a first user and an agent, this operation involves sending a message to the agent. Displaying one or more topic posts includes: displaying a first message from the first user; and displaying a second message from the agent, wherein the second message is used to reply to the first message and in response to the first message meeting specified conditions, and the second message includes or is associated with one or more topic posts.

[0050] For example, messages sent by the first user and the agent can be displayed in the dialogue interface. After the user sends a message, the agent can generate a reply message for the first user and display it in the dialogue interface.

[0051] An intelligent agent is a virtual intelligent object capable of responding to dialogue messages sent by a user. Intelligent agents can be implemented using models. For example, the dialogue messages sent by the user are input into the model, and the intelligent agent's response message is generated based on the model's output. Intelligent agents can also be called digital humans or virtual agents of machine learning models. Intelligent agents can be implemented using machine learning models, such as Large Language Models (LLMs) or Foundation Models. Machine learning models can be generative models, which output target content based on input information. The input information of a generative model includes the processing criteria used by the generative model during the generation process, such as which information to refer to during the generation process, the requirements for the target output content, etc. Generative models include, for example, models that generate data based on text or images, and the output of a generative model can include text, images, or a combination of both. Of course, the input or output of a generative model can also be data of other modalities, such as audio, video, or a combination of multiple types of data. Generative models can be single-modal models, such as text-to-text models (referred to as "text-to-text models") or image-to-image models (referred to as "image-to-image models"); or, generative models can be cross-modal models, that is, models whose inputs and outputs belong to different modalities, such as text-to-image models (referred to as "text-to-image models"); or, the inputs of generative models can include multiple modalities, and the outputs can also include multiple modalities.

[0052] In embodiments of this disclosure, if the first message meets specified conditions, the agent's response is enhanced using topic posts. If the first message does not meet the specified conditions, the second message may not include or may not be associated with topic posts.

[0053] The second message sent by the agent includes: the text of the second message sent by the agent, and previews of one or more topic posts. Each topic post preview includes the topic and summary information of the topic post, and the previews of one or more topic posts are inserted into the text of the second message. Thus, the previews of the topic posts can be displayed first, allowing the user to decide whether to further browse the details of the topic posts.

[0054] Figure 2 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown. Figure 2 As shown, the dialogue interface 2 includes message 21 sent by user 1, "Is exhibition B in city A worth seeing?", and message 22 sent by the agent. Message 22 is a response to message 21. Message 21 may include user-generated content (i.e., "experience posts") to enhance the message sent by the agent by referencing the user-generated content.

[0055] For example, message 22 includes the text 221 "To sum it up: I don't really recommend going there. The exhibition is... The venue setup is nice, but...", and also includes previews of multiple topic posts 222 and 223. If multiple topic posts are referenced, the previews 222 and 223 can be swiped horizontally to display more preview content.

[0056] Users can also send more messages to the agent through the input control 23 in interface 2.

[0057] Thus, the intelligent agent can enhance the credibility and usefulness of its replies by referencing topic posts published by other users, thereby improving the efficiency of information acquisition for users in human-computer dialogue scenarios.

[0058] Figure 2 The preview of the topic post shown includes images, title, poster, etc. Alternatively, the preview of the topic post can also be displayed in another format. Figure 3 A schematic diagram of a dialog interface according to other embodiments of this disclosure is shown. For example... Figure 3 As shown, it is similar to Figure 2 The difference lies in the style of the topic posts, which has changed from 222 and 223 to 224 and 225. Previews 224 and 225 include the topic post's title and part of the text, allowing users to preview more textual information about the topic post. When multiple topic posts are referenced, previews 224 and 225 can be swiped horizontally to display more preview content.

[0059] exist Figure 2 and Figure 3 In the illustrated approach, the preview of a topic post can be located within the text of the second message. That is, one or more topic posts can be interspersed within the text. The adjacent text of a topic post is related to its content. For example, topic posts can be used to divide the agent's message text into multiple paragraphs, each generated based on adjacent topic posts. Thus, the agent can use topic posts to generate reply text, allowing users to easily switch between the intelligent summary of the topic post and the original content.

[0060] Figure 4 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown. In this embodiment, the second message 22 itself does not include a preview of the topic post, but previews 24 and 25 of the topic post associated with the second message 22 may be displayed after the second message 22 is displayed. That is, the second message is displayed in association with the topic post.

[0061] After a user triggers a preview of a topic post, the post's details page can be displayed. Furthermore, if the topic post belongs to a specific topic, it can include topic tags. Triggering these tags will display the topic's page.

[0062] In a dialogue scenario, providing topic posts can be triggered by various conditions; that is, there are multiple ways to implement specified conditions. Based on these conditions, it can be determined whether the agent's response should include or be associated with the topic post. An example is provided below.

[0063] In some embodiments, the specified conditions include: a first message instructing the agent to provide information about an entity object at a specified time; one or more topic posts including information about the entity object at a specified time; the time difference between the specified time and the current time being less than a first threshold; or, the specified time being the time corresponding to a specified event. That is, when the agent needs to provide time-sensitive information, it can reply by referencing user-generated content. Time-sensitive information can be information closer to the current time or information within a specific time period.

[0064] For example, when a user asks about the attendance of a currently running temporary exhibition, the agent might be unable to obtain this information due to insufficient publicly available data. Alternatively, the agent's definition of "many" or "few" might differ from the user's perception. Or, even if the agent obtains the daily attendance figures, the user may not be able to intuitively gauge the level of crowding. In such cases, by referencing posts from other users, the first user can intuitively obtain the desired information through images or descriptions from other users (such as wait times, exhibition experiences, etc.).

[0065] For example, when a user asks whether train stations are crowded during the Spring Festival, user-generated content can be used to help the user understand the actual situation.

[0066] Therefore, when the first user requests information from the agent at a specified time, the agent's response can be enhanced using topic posts. By leveraging the agent's information acquisition and summarization capabilities to efficiently convey information, and by utilizing time-sensitive user-generated content, the reliability and usability of the information provided by the agent can be improved. Thus, the user's information acquisition efficiency is enhanced.

[0067] In some embodiments, the specified conditions include: a first message instructing the agent to provide operational or experiential information about the entity object; and one or more topic posts including operational information about the entity object. That is, when the agent needs to provide information requiring human intervention, it can reply using user-generated content.

[0068] An entity object is the object involved in the first message. Entity objects can appear directly in the first message, for example, determined through named entity recognition. Alternatively, entity objects can be determined through semantic understanding of the first message. The objects for semantic understanding can be text, images, videos, voice messages, etc., sent by the user. By using text processing, image processing, or sound processing models, the semantic or descriptive information of the user-sent message can be determined, further identifying the entity objects associated with the first message. Or, entity objects may not appear directly or indirectly in the user's conversation messages, but are associated with them. For example, if a user sends a photo of an appliance, the name of the appliance can be determined through target recognition of the photo.

[0069] Operational information can include methods for using or creating an entity object. When the entity object is a location or scene, experiential information might include tour routes or impressions of the tour. Because operational and experiential information is often detailed, and different people's actions and feelings vary, referencing user-generated content can provide more relevant information to the first user. Therefore, the efficiency of information acquisition for users is improved.

[0070] In some embodiments, the specified conditions include: a first message matching a first topic, where topic posts have category tags. One or more topic posts may be from a topic, which is an aggregation of topic posts with similar themes. After the first user sends a message, the topic matching the first message can be determined first, and then topic posts can be selected from that topic to enhance the agent's message.

[0071] Topics within a topic can include multiple category tags, which can further subdivide these posts. When selecting topics from a topic, you can choose based on the level of detail of the initial message, combined with the category tags.

[0072] For example, in response to a first message matching a first topic and a first category tag within that first topic, one or more topic posts include those with the first category tag. Let the first topic be Exhibition B, which includes topic posts tagged with categories such as positive reviews, negative reviews, viewing routes, and exhibits. If the first message asks the agent "What is the viewing route for Exhibition B?", then the agent can directly select topic posts related to "viewing routes" from the first topic. Thus, the topic posts referenced by the agent are more closely matched to the first message.

[0073] For example, in response to the first message matching the first topic but not matching any category tag of the first topic, one or more topic posts include multiple topic posts within the first topic with different category tags. For instance, if the first message sent by a user is broad, topic posts associated with multiple category tags can be selected to provide the user with information from multiple perspectives. For example, if the first message is "Talk about Exhibition B," topic posts can be selected from categories such as positive reviews, negative reviews, exhibition routes, and exhibits to enhance the message and allow the user to gain a more comprehensive understanding of the information.

[0074] If the second message includes or is associated with a topic post from the first topic, the user can be directed to the first topic after the second message is displayed to browse more user-generated content that may be of interest. In some embodiments, in response to the display of the second message, an entry point to the first topic is displayed, and one or more topic posts originate from the first topic; in response to triggering the entry point to the first topic, a page for the first topic is displayed, which includes topic posts that match the first topic.

[0075] Figure 5 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown. For example... Figure 5 As shown, the dialogue interface 5 in this embodiment includes a first message 51 from the user and a second message 52 from the intelligent agent. The second message 52 includes previews of multiple topic posts, such as 521 and 522. After the second message 52, some prompts are also displayed, one of which, prompt 53, is the entry point to the first topic "B Exhibition". After triggering prompt 53, the page for topic "B Exhibition" can be displayed.

[0076] While the above embodiments are described using a dialogue between a single user and an agent as an example, the embodiments disclosed herein are not limited to this. As needed, in a dialogue interface between multiple users, the first user among the multiple users can request a reply from the agent by referencing it. In a group chat scenario between the user and the agent, the agent can also reply by referencing a topic post.

[0077] In addition to agents referencing topic posts, users can also send topic posts or topics during conversations. For example, a user can send a topic post or topic to an agent for parsing or searching for relevant content; or, a user can send a topic post or topic to other users to discuss its content through conversation. Figure 6 A schematic diagram of a dialog interface according to some embodiments of the present disclosure is shown. Figure 6 Two implementation methods are shown. Figure 6 In interface 6 shown in part (a), the message sent by user A includes a reference to topic post 61. Figure 6 In interface 6 shown in section (b), the message sent by user A includes a reference to topic 63. The topic or topic post can be shared by the user from other pages to the conversation page, or it can be something the user has previously saved and sent from the conversation page. Furthermore, the user can bring an agent into the conversation by triggering control 62, for example, by asking the agent for its opinion on the aforementioned discussion. When responding, the agent can also reference the topic or topic post.

[0078] Next, we will further introduce the target scenario of recommendation flow.

[0079] In some embodiments, one or more topic posts match a first topic, and the operation is a triggering operation on the first topic. Displaying one or more topic posts includes: displaying a recommendation stream of the topic, the recommendation stream of the topic including multiple topics; and in response to the triggering operation on the first topic among the multiple topics, displaying a page of the first topic, the page of the first topic including one or more topic posts that match the first topic.

[0080] A topic recommendation stream refers to a content stream that includes multiple topics recommended to users. Topics in the stream can be determined based on at least one of the following: information related to the user's current action, information related to the user's historical actions, and information associated with the current time. For example, topics can be determined based on those triggered during the user's current browsing process or those triggered during historical browsing. Alternatively, the dialogue between the user and the agent can also be considered when making recommendations in the topic recommendation stream. Furthermore, current trending topics or time-sensitive topics can also be recommended in the stream.

[0081] For example, topics in the recommendation stream are determined based on the agent's responses to the first user. The agent's responses reveal the topics the user has followed throughout historical conversations, thus increasing the weight of such topics in the recommendation process. One example is statistically analyzing the topics covered by the agent's responses to identify topics with frequencies exceeding a threshold for recommendation. The topics in the responses can be determined through semantic understanding of the responses.

[0082] Figure 7 A schematic diagram of a topic recommendation flow according to some embodiments of the present disclosure is shown. Figure 7 As shown, the recommendation stream page 7 in this embodiment includes previews of multiple topics 71 to 73, and can display previews of more topics in response to the user's swiping operation.

[0083] Each topic preview may include, for example, the topic name, a brief description, and image information, so that users can efficiently determine whether they need to browse further posts within that topic.

[0084] In some embodiments, the recommendation stream pages may also include interactive controls for the agent. For example, page 7 may include interactive control 74. Users can use interactive control 74 to adjust the topic recommendation strategy or ask questions to the agent.

[0085] Topics in the recommendation stream are generated by clustering multiple topic posts based on target information. The target information is determined either by events within a specified time period or by the topic attributes of the agent's historical responses. Target information can be understood as pre-determined topics or pre-determined information that expresses a topic. This makes topic generation more purposeful. The specified time period can include the current time, making the target information timely and presenting users with currently relevant topics. The agent's historical responses can be responses from conversations between the agent and multiple users, with the use of this information authorized by those users. That is, by determining the topic attributes of historical responses, such as discussion frequency and occurrence, topics of interest to multiple users can be identified, which can then be used as a basis for clustering.

[0086] The topic page can be triggered in both dialogue and recommendation feed scenarios. The following description uses the first topic as an example.

[0087] In some embodiments, the page for the first topic also includes descriptive information for the first topic, which is generated based on topic posts for the first topic. For example, semantic analysis can be performed on topic posts under this topic to generate the descriptive information.

[0088] Figure 8 A schematic diagram of a topic page according to some embodiments of this disclosure is shown. For example... Figure 8 As shown, the topic page 8 in this embodiment includes a representative image of the topic, namely the topic image 81, and a description of the topic 82. The description 82 can be generated based on user-generated content in the topic. A topic may include one or more topic posts, such as topic posts 84. Figure 8 The example in the text uses the label "experience" to indicate that it is a topic post where users share their experiences.

[0089] In some embodiments, the description information is regenerated in response to updates to topic posts in the first topic. Thus, as topic posts in the topic increase or other changes occur, the automatically generated description information can be updated. This makes the topic description information more closely match the topic posts in the topic, improving the efficiency of information retrieval for users.

[0090] Interface 8 may also include category tags 83, which can be used to filter content belonging to a specific tag within a topic by triggering different tags. In some embodiments, topic tags may also be dynamically generated and updated based on topic posts within a topic. For example, topic posts within a topic may be clustered periodically, and category tags may be determined based on the common themes of topic posts in each category.

[0091] When a topic is initially created, since the number of posts in the topic may be small, some multimedia content can be introduced, such as content 85 in interface 8, which is exemplarily labeled as "video" in this embodiment. In some embodiments, the page of the first topic includes topic posts and multimedia content, with the multimedia content matching the first topic. The ranking weight of the multimedia content is negatively correlated with the number of topic posts in the first topic. For example, with the permission of the creator of the multimedia content, it can be included in the first topic, and the multimedia content matches the first topic. The multimedia content can come from a multimedia stream. As the number of topic posts in the first topic increases, topic posts can be displayed first, and the weight of multimedia content can be reduced. Of course, when sorting the content in the topic, in addition to considering whether it belongs to the topic post type or the multimedia content type in the media stream, it can also be sorted comprehensively based on the relevance of the content to the topic, the number of views, the publication time, etc. In this way, the content in the topic can be enriched and the amount of information in the topic can be increased.

[0092] The page for the first topic may also include entry points to other topics to facilitate user switching between different topics. In some embodiments, in response to the number of posts in the first topic exceeding a first threshold, the page for the first topic includes an entry point to a second topic related to the first topic. That is, when there are many posts in a topic, users can be guided to visit related topics. Related topics can be sub-topics of the current topic to facilitate users browsing content within sub-topics. For example, in interface 8, 86 marks an entry point to another topic, "Must-See Exhibitions in November".

[0093] A single post can be categorized into multiple topics simultaneously. These topics can be at different levels or from different perspectives. For example, when creating a post, the author can choose the topic to publish it to, such as choosing to publish it to the first topic. Subsequently, if the post is detected to be associated with a second topic page, it can be further associated with the second topic as well.

[0094] Interface 8 may also include an invitation control 87, used to send invitations to other users to view or reply to the multimedia information posted by the current user. For example, when a user posts multimedia information that includes questions, other users can assist in answering the questions upon receiving the invitation.

[0095] Interface 8 may also include a sharing control 88, which users can use to trigger the creation and posting of new topic threads.

[0096] The structured organization of topics and topic posts described above is equivalent to automatically annotating user-provided topic posts. With authorization from the topic post's publisher, the topic post and its associated topic are used to train the model, which then generates messages for the agent. Thus, the high-quality user-generated corpus improves the model's training performance, enabling the agent to provide higher-quality responses to users.

[0097] The methods of various embodiments of this disclosure have been described above. Apparatus for implementing the methods of the above embodiments is described below.

[0098] Figure 9 A schematic diagram of the structure of a content distribution apparatus according to some embodiments of the present disclosure is shown. For example... Figure 8 As shown, the content distribution device 9 of this embodiment includes: a first display module 91, configured to display one or more topic posts in response to an operation by a first user in a target scenario, wherein the one or more topic posts are content generated by a second user, and the one or more topic posts are determined based on at least one of the following: information related to the operation, information related to the first user's historical operations, and information associated with the current time, wherein the use of the information related to the operation and the information related to the historical operations is authorized by the first user; and a second display module 92, configured to display the page of the target topic post in response to the triggering of a target topic post among the one or more topic posts.

[0099] In some embodiments, the first display module 91 is configured to: display one or more topic posts in response to a dialogue scenario between a first user and an agent; and display one or more aggregated topic posts in response to a recommendation stream scenario.

[0100] In some embodiments, the target scenario is a dialogue scenario between a first user and an agent, the operation is an operation of sending a message to the agent, and the first display module 91 is configured to: display a first message from the first user; display a second message from the agent, wherein the second message is used to reply to the first message and in response to the first message meeting specified conditions, and the second message includes or is associated with one or more topic posts.

[0101] In some embodiments, the specified conditions include: a first message instructing the agent to provide information about an entity object at a specified time; one or more topic posts including information about the entity object at a specified time; the time difference between the specified time and the current time being less than a first threshold; or, the specified time being the time corresponding to a specified event.

[0102] In some embodiments, the specified conditions include: a first message instructing the agent to provide operation information or experience information on the entity object; and one or more topic posts including operation information on the entity object.

[0103] In some embodiments, the specified conditions include: a first message matching a first topic, wherein topic posts in the first topic have category tags; in response to a first message matching a first topic and a first category tag in the first topic, one or more topic posts include topic posts with the first category tag; in response to a first message matching a first topic but not matching any category tag in the first topic, one or more topic posts include multiple topic posts in the first topic that have different category tags.

[0104] In some embodiments, the first display module 91 is configured to display the text of a second message sent by the agent, and previews of one or more topic posts, each topic post preview including the topic and summary information of the topic post, and the previews of one or more topic posts are inserted into the text of the second message.

[0105] In some embodiments, the content distribution device 9 further includes a third display module configured to: display an entry point to a first topic in response to the display of a second message, wherein one or more topic posts are from the first topic; and display a page of the first topic in response to the triggering of the entry point to the first topic, wherein the page of the first topic includes topic posts that match the first topic.

[0106] In some embodiments, one or more topic posts match a first topic, and the operation is a trigger operation on the first topic. The first display module 91 is configured to: display a recommendation stream of topics, the recommendation stream of topics including multiple topics; and in response to the trigger operation on the first topic among the multiple topics, display a page of the first topic, the page of the first topic including one or more topic posts that match the first topic.

[0107] In some embodiments, the topics in the recommendation stream are determined based on the agent's response information to the first user.

[0108] In some embodiments, topics in the recommendation stream are generated by clustering multiple topic posts based on target information, which is determined based on events within a specified time period or on topic attributes of the agent's historical response information.

[0109] In some embodiments, the page of the first topic also includes description information of the first topic, which is generated based on the topic posts of the first topic, and the description information is regenerated in response to updates to the topic posts in the first topic.

[0110] In some embodiments, the page for the first topic includes topic posts and multimedia content, the multimedia content being matched with the first topic, and the ranking weight of the multimedia content being negatively correlated with the number of topic posts for the first topic.

[0111] In some embodiments, in response to the number of topic posts in a first topic exceeding a first threshold, the page of the first topic includes an entry to a second topic, which is related to the first topic.

[0112] Embodiments of this disclosure can distribute user-generated content in response to an operation by a first user in a target scenario, thereby providing the user with user-generated content in the target scenario. Therefore, this disclosure improves the comprehensiveness of information in intelligent agent applications, thereby increasing the efficiency of information acquisition for users.

[0113] According to some embodiments of the present disclosure, an electronic device is provided, including: a memory; and a processor coupled to the memory, the processor being configured to perform the methods of any of the embodiments described in the present disclosure based on instructions stored in the memory.

[0114] Figure 10 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0115] Memory 101 is used to store one or more computer-readable instructions. Memory 101 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 101 may, for example, store operating systems, applications, bootloaders, databases, and other programs, as well as various applications and various data.

[0116] The processor 102 is configured to execute computer-readable instructions to implement the method described in any of the foregoing embodiments. Specific implementations of each step of the method can be found in the above embodiments; repeated details will not be elaborated upon here.

[0117] The processor 102 can be configured to perform the steps of the foregoing embodiments. The processor 102 can be embodied in various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The central processing unit (CPU) can be an x86 or ARM architecture, etc.

[0118] The processor 102 and the memory 101 can communicate with each other directly or indirectly. For example, the processor 102 and the memory 101 can communicate via a network. The network can include a wireless network, a wired network, and / or any combination of wireless and wired networks. The processor 102 and the memory 101 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0119] It should be noted that Figure 10 The components of the electronic device 10 shown are merely exemplary and not limiting; the electronic device 10 may have other components as needed for the actual application. The processor 102 can control other components in the electronic device 10 to perform desired functions.

[0120] Electronic device 10 can be implemented by software, firmware and / or hardware, and can be integrated into a device with relevant applications installed.

[0121] Figure 11 Block diagrams of electronic devices according to other embodiments of the present disclosure are shown.

[0122] Figure 11 The electronic device 11 shown can be a computer system with a dedicated hardware structure, which can perform corresponding functions when the relevant application is installed.

[0123] Electronic devices include, but are not limited to, mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet computers (PCs), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.

[0124] like Figure 11 As shown, the Central Processing Unit (CPU) 111 performs various processes based on a program stored in the Read-Only Memory (ROM) 112 or a program loaded from the storage section 118 into the Random Access Memory (RAM) 113. The RAM 113 stores data required as needed when the CPU 111 performs various processes, etc. The CPU is merely exemplary; it could also be other types of processors, such as the various processors described above. The ROM 112, RAM 113, and storage section 118 can be various forms of computer-readable storage media. It should be noted that although... Figure 11 The image shows ROM 112, RAM 113 and storage section 118, but one or more of them may be combined or located in the same or different memory or storage modules.

[0125] CPU 111, ROM 112 and RAM 113 are interconnected via bus 114. Input / output interface 115 is also connected to bus 114.

[0126] The following components are connected to the input / output interface 115: input section 116, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 117, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 118, including hard disk, magnetic tape, etc.; and communication section 119, including network interface cards such as LAN cards, modems, etc. The communication section 119 allows communication processing to be performed via a network such as the Internet. It is easy to understand that, although... Figure 11 The portion of the electronic device 11 shown communicates via bus 114, but it may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0127] As needed, drive 1110 is also connected to input / output interface 115. Removable media 1111, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 1110 as needed, so that computer programs read from them can be installed into storage section 118 as needed.

[0128] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as a removable medium 1111.

[0129] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to perform the methods described in any of the foregoing embodiments. The computer program product includes computer instructions carried on a computer-readable medium, containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer instructions can be downloaded and installed from a network via communication section 119, or installed from storage section 118, or installed from ROM 112. When the computer program is executed by CPU 111, the methods of embodiments of this disclosure are performed.

[0130] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0131] According to some embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the methods of any of the embodiments described in the present disclosure.

[0132] According to some embodiments of the present disclosure, a computer program product is provided that, when the computer program product is run on a computer, causes the computer to implement the methods of any of the embodiments described in the present disclosure.

[0133] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0134] Computer-readable storage media include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. Computer instructions are stored on the computer-readable storage medium that, when executed by a processor, implement the methods described in any of the foregoing embodiments.

[0135] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0136] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0137] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the methods described in any of the foregoing embodiments. For example, the instructions may be embodied in computer program code.

[0138] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0140] The functions described above can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0141] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A content distribution method, comprising: In response to an operation by a first user in a target scenario, one or more topic posts are displayed, wherein the one or more topic posts are content generated by a second user, and the one or more topic posts are determined based on at least one of the information involved in the operation, the information involved in the first user's historical operations, and the information associated with the current time, wherein the use of the information involved in the operation and the information involved in the historical operations is authorized by the first user. In response to a triggering of a target topic post in one or more topic posts, the page of the target topic post is displayed.

2. The content distribution method according to claim 1, wherein, The display of one or more topic posts includes: In response to the target scenario being a dialogue scenario between the first user and the intelligent agent, one or more topic posts are displayed respectively; In response to the target scenario being a recommendation feed scenario, the aggregated one or more topic posts are displayed.

3. The content distribution method according to claim 1, wherein, The target scenario is a dialogue scenario between the first user and the intelligent agent; the operation is an operation of sending a message to the intelligent agent; and displaying one or more topic posts includes: Display the first message from the first user; Display a second message from the agent, wherein the second message is used to reply to the first message and, in response to the first message meeting specified conditions, the second message includes or is associated with the one or more topic posts.

4. The content distribution method according to claim 3, wherein, The specified conditions include: the first message is used to instruct the intelligent agent to provide information about the entity object at a specified time; The one or more topic posts include information about the entity object at the specified time; The time difference between the specified time and the current time is less than a first threshold, or the specified time is the time corresponding to the specified event.

5. The content distribution method according to claim 3, wherein, The specified conditions include: the first message is used to instruct the intelligent agent to provide operation information or experience information on the entity object; The one or more topic posts include the operation information of the entity object.

6. The content distribution method according to claim 3, wherein, The specified conditions include: the first message matches the first topic, and the topic posts in the first topic have category tags; In response to the first message matching the first topic and the first category tag in the first topic, the one or more topic posts include topic posts with the first category tag; In response to the first message matching the first topic but not matching any category tag of the first topic, the one or more topic posts include multiple topic posts in the first topic that have different category tags.

7. The content distribution method according to claim 3, wherein, The second message sent by the intelligent agent includes: The text of the second message sent by the agent is displayed, along with previews of the one or more topic posts. Each topic post preview includes the topic and summary information of the topic post, and the previews of the one or more topic posts are inserted into the text of the second message.

8. The content distribution method according to claim 3, further comprising: In response to the display of the second message, an entry point to the first topic is displayed, wherein the one or more topic posts originate from the first topic; In response to the triggering of the entry point to the first topic, the page of the first topic is displayed, and the page of the first topic includes topic posts that match the first topic.

9. The content distribution method according to claim 1, wherein, The one or more topic posts match the first topic, the operation is a trigger operation on the first topic, and displaying the one or more topic posts includes: The recommendation stream of the topic is displayed, and the recommendation stream of the topic includes multiple topics; In response to a triggering operation on the first topic among the plurality of topics, a page for the first topic is displayed, the page for the first topic including one or more topic posts that match the first topic.

10. The content distribution method according to claim 9, wherein, The topics in the recommendation stream are determined based on the agent's response information to the first user.

11. The content distribution method according to claim 9, wherein, The topics in the recommendation stream are generated by clustering multiple topic posts based on target information. The target information is determined based on events within a specified time period or on topic attributes of the agent's historical response information.

12. The content distribution method according to claim 8 or 9, wherein, The page for the first topic also includes descriptive information for the first topic, which is generated based on the topic posts of the first topic, and is regenerated in response to updates to the topic posts in the first topic.

13. The content distribution method according to claim 8 or 9, wherein, The page for the first topic includes topic posts and multimedia content, the multimedia content being matched with the first topic, and the ranking weight of the multimedia content being negatively correlated with the number of topic posts for the first topic.

14. The content distribution method according to claim 8 or 9, wherein, In response to the number of topic posts in the first topic exceeding a first threshold, the page of the first topic includes an entry to a second topic, which is related to the first topic.

15. A content distribution device, comprising: The first display module is configured to display one or more topic posts in response to an operation by a first user in a target scenario, wherein the one or more topic posts are content generated by a second user, and the one or more topic posts are determined based on at least one of the information involved in the operation, the information involved in the first user's historical operations, and the information associated with the current time, wherein the use of the information involved in the operation and the information involved in the historical operations is authorized by the first user. The second display module is configured to display the page of the target topic post in response to the triggering of the target topic post in the one or more topic posts.

16. An electronic device comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the content distribution method as described in any one of claims 1 to 14 based on instructions stored in the memory.

17. A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the content distribution method of any one of claims 1 to 14.

18. A computer program product, when run on a computer, causes the computer to implement the content distribution method according to any one of claims 1 to 14.

Images