Content interaction method and device based on intelligent agent, equipment and medium

Abstract

The invention provides an agent-based content interaction method, which can be applied to the technical field of artificial intelligence. The method comprises the following steps: in response to the situation that to-be-replied interactive content published on a content interaction platform meets a preset reply condition, generating reply content for the to-be-replied interactive content by utilizing a target agent in at least one agent; and displaying the reply content of the target agent in a reply area corresponding to the to-be-replied interactive content. The invention further provides a content interaction device and equipment based on the intelligent agent, a medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and more particularly, to an agent-based content interaction method, apparatus, device, medium, and program product. Background Art

[0002] A content interaction platform refers to an online platform that supports user-generated content (UGC) and enables multi-directional interaction, mainly including forums, communities, social applications, comment areas, Q&A platforms, etc. Its core function is to allow users to publish content (such as posts, comments, videos, etc.) and interact with other users or the system through likes, replies, forwards, private messages, etc.

[0003] In the process of implementing the concept of the present disclosure, the inventors found that at least the following problems exist in the related art: The content interaction platforms in the related art generally adopt a content interaction mode dominated by real users, which requires maintaining a large-scale real operation team and has a high labor cost; in addition, it is difficult for humans to respond to a large amount of user interaction content in a timely manner, resulting in a poor user experience. Summary of the Invention

[0004] In view of this, the present disclosure provides an agent-based content interaction method, apparatus, device, medium, and program product.

[0005] One aspect of the present disclosure provides an agent-based content interaction method, which is applied to a content interaction platform configured with at least one agent. The method includes: in response to the to-be-replied interaction content published on the content interaction platform satisfying a preset reply condition, using a target agent among the at least one agent to generate a reply content for the to-be-replied interaction content; and displaying the reply content of the target agent in a reply area corresponding to the to-be-replied interaction content.

[0006] According to an embodiment of the present disclosure, displaying the reply content of the target agent in a reply area corresponding to the to-be-replied interaction content includes: displaying the reply content of the target agent and an agent mark in a reply area corresponding to the to-be-replied interaction content, where the agent mark represents the agent attribute.

[0007] According to an embodiment of the present disclosure, the reply area further includes a session jump entry for linking to a session window of the target agent.

[0008] According to an embodiment of the present disclosure, the above method further includes: in response to a trigger operation on the session jump entry, displaying a session window of the target agent, where the session window is used for the current user to have a session with the target agent.

[0009] According to an embodiment of the present disclosure, the above method further includes: when there are historical session messages between the current user and the target intelligent agent, displaying the historical session messages in the session window.

[0010] According to an embodiment of the present disclosure, the above method further includes: when there are no historical session messages between the current user and the target intelligent agent, displaying a preset role message from the target intelligent agent in the session window, where the preset role message includes profile information of the target intelligent agent.

[0011] According to an embodiment of the present disclosure, the reply content includes a target mapping address, and the target mapping address is used to link to an extended content page corresponding to the reply content; the above method further includes: in response to a trigger operation on the target mapping address, displaying the extended content page corresponding to the target mapping address.

[0012] According to an embodiment of the present disclosure, the target mapping address includes a product transaction address; displaying the extended content page corresponding to the target mapping address includes: displaying a product transaction interface corresponding to the product transaction address.

[0013] According to an embodiment of the present disclosure, the above method further includes: in response to the number of replies of the target intelligent agent to the interactive content to be replied meeting a preset threshold, displaying a prompt message for changing the interaction method, where the prompt message includes a session jump entry for the target intelligent agent.

[0014] According to an embodiment of the present disclosure, the intelligent agent has a role attribute; the above method further includes: determining a target intelligent agent from at least one intelligent agent according to the content type of the interactive content to be replied and the role attributes of each of the at least one intelligent agent.

[0015] According to an embodiment of the present disclosure, the preset reply conditions include at least one of the following: the current time meets a preset duration from the release time of the interactive content to be replied, the type of the interactive content to be replied belongs to a preset target type, and the interactive content to be replied contains a preset keyword.

[0016] Another aspect of the present disclosure provides an electronic device, including:

[0017] One or more processors;

[0018] A memory for storing one or more programs,

[0019] wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described above.

[0020] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, and the instructions are used to implement the method as described above when executed.

[0021] Another aspect of the present disclosure provides a computer program product, which includes computer-executable instructions that, when executed, are used to implement the method described above.

[0022] According to an embodiment of the present disclosure, since multiple agents are configured on the content interaction platform, when the to-be-replied interaction content published by a user on the content interaction platform meets a preset reply condition, a target agent in at least one of the agents is used to automatically generate a reply content for the to-be-replied interaction content, and the reply content is displayed in the reply area. Therefore, at least partially, the technical problems of high labor costs and difficulty for humans to respond to a large amount of user interaction content in a timely manner, resulting in poor user experience, are overcome. Furthermore, the technical effects of improving the interaction efficiency of the content interaction platform and reducing labor costs are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Through the following description of the embodiments of the present disclosure with reference to the drawings, the above and other objects, features, and advantages of the present disclosure will become clearer. In the drawings:

[0024] Figure 1 Schematically shows an exemplary system architecture to which the agent-based content interaction method according to an embodiment of the present disclosure can be applied;

[0025] Figure 2 Schematically shows a flowchart of the agent-based content interaction method according to an embodiment of the present disclosure;

[0026] Figure 3 Schematically shows a schematic diagram of a comment area interface according to an embodiment of the present disclosure;

[0027] Figure 4 Schematically shows a flowchart of the content interaction method according to an embodiment of the present disclosure in a comment scenario;

[0028] Figure 5 Schematically shows a schematic diagram of a session window interface according to an embodiment of the present disclosure;

[0029] Figure 6 Schematically shows a flowchart of the content interaction method according to an embodiment of the present disclosure in a private message scenario;

[0030] Figure 7 Schematically shows a flowchart of the content interaction method according to an embodiment of the present disclosure in a follow-up comment scenario;

[0031] Figure 8 Schematically shows a schematic diagram of a home page according to an embodiment of the present disclosure;

[0032] Figure 9ASchematically shows a schematic diagram of a reply content including a product transaction address according to an embodiment of the present disclosure;

[0033] Figure 9B Schematically shows a schematic diagram of a reply content including a target mapping address according to an embodiment of the present disclosure;

[0034] Figure 10 Schematically shows a block diagram of an agent-based content interaction device according to an embodiment of the present disclosure; and

[0035] Figure 11 Schematically shows a block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure. Detailed implementation manners

[0036] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth in order to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

[0037] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0038] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0039] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but is not limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0040] In the embodiments of the present disclosure, in aspects such as the collection, update, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the involved data (for example, including but not limited to user personal information), it complies with the provisions of relevant laws and regulations, is used for legal purposes, and does not violate public order and good customs. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and to safeguard user personal information security and network security.

[0041] In the embodiments of the present disclosure, before obtaining or collecting user personal information, the authorization or consent of the user is obtained.

[0042] The embodiments of the present disclosure provide an agent-based content interaction method, which is applied to a content interaction platform. The content interaction platform is configured with at least one agent. The method includes: in response to the to-be-replied interaction content published on the content interaction platform satisfying a preset reply condition, using a target agent among the at least one agent to generate a reply content for the to-be-replied interaction content; and displaying the reply content of the target agent in the reply area corresponding to the to-be-replied interaction content.

[0043] Figure 1 Exemplary system architecture 100 to which the agent-based content interaction method according to the embodiments of the present disclosure can be applied is schematically shown. It should be noted that Figure 1 What is shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0044] As Figure 1 shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a content interaction platform 105. The network 104 is used as a medium to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the content interaction platform 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0045] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the content interaction platform 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as interaction applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only as examples).

[0046] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop computers, desktop computers, and so on.

[0047] The content interaction platform 105 can be configured with at least one agent. For example, the content interaction platform can be configured with Agent 1, Agent 2,..., Agent n, etc. Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to log in to the content interaction platform 105 and publish interactive content on the content interaction platform 105. The agents configured on the content interaction platform 105 can automatically comment on the interactive content.

[0048] It should be noted that the agent-based content interaction method provided by the embodiments of the present disclosure can generally be executed by the content interaction platform 105. Correspondingly, the agent-based content interaction device provided by the embodiments of the present disclosure can generally be set in the content interaction platform 105.

[0049] It should be understood that Figure 1 the numbers of the terminal devices, networks, and content interaction platforms in are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and content interaction platforms.

[0050] According to an embodiment of the present disclosure, the agent-based content interaction method can be applied to a content interaction platform, and the content interaction platform can be configured with at least one agent.

[0051] The present disclosure does not limit the configuration method of the agent. In one example, the agent can be configured by the following method: log in to the content interaction platform, create an agent number, and then define the basic persona of the agent, such as specifying the role of the agent, designing the language style of the reply, presetting the reply strategy, restricting the answer range of the agent, etc., to make the conversation more in line with the user's expectations. In addition, role skills can be added. For example, the agent can have skills such as publishing content, commenting on content, and private messaging. For the content publishing skill, the agent can generate content according to a preset strategy for publishing. For the private messaging skill, it supports square private messaging, home page path private messaging, and comment area path private messaging.

[0052] Figure 2 Schematically shows a flowchart of the agent-based content interaction method according to an embodiment of the present disclosure.

[0053] As Figure 2 shown, the agent-based content interaction method in this embodiment 200 includes operations S210 to S220.

[0054] In operation S210, in response to the to-be-replied interactive content published on the content interaction platform meeting the preset reply conditions, the target agent in at least one agent is utilized to generate a reply content for the to-be-replied interactive content.

[0055] According to an embodiment of the present disclosure, the content interaction platform may include at least one of the following: a forum, a knowledge community.

[0056] According to an embodiment of the present disclosure, the preset reply conditions may include at least one of the following: the current time is separated from the publication time of the to-be-replied interactive content by a preset duration, the type of the to-be-replied interactive content belongs to a preset target type, and the to-be-replied interactive content contains a preset keyword.

[0057] For example, the preset reply condition may be 2 - 7 days after the user publishes the interactive content, and avoid replying during the early morning hours. Again, the preset reply condition may also be to reply 10 - 30 minutes after the user publishes the interactive content. By judging whether the interval between the current time and the publication time of the to-be-replied interactive content reaches the preset duration, delayed reply, timed reminder, or filtering of expired content can be realized, optimizing the response timeliness. In addition, selecting an appropriate reply time can also achieve the effect of simulating a real person's reply, improving the user experience.

[0058] Again, the preset reply condition may be that the to-be-replied interactive content contains "consultation", "fitness", etc. In operation S220, the reply content of the target agent is displayed in the reply area corresponding to the to-be-replied interactive content.

[0059] According to an embodiment of the present disclosure, because the technical means of configuring multiple agents on the content interaction platform, when the to-be-replied interactive content published by the user on the content interaction platform meets the preset reply conditions, the target agent in at least one agent is used to automatically generate a reply content for the to-be-replied interactive content and display the reply content in the reply area is adopted, at least partially overcoming the technical problems of high labor costs and the difficulty for manual to timely respond to a large amount of user interactive content, resulting in poor user experience, and thus achieving the technical effects of improving the interaction efficiency of the content interaction platform and reducing labor costs.

[0060] According to an embodiment of the present disclosure, the agent has a role attribute. The method may further include: determining the target agent from at least one agent according to the content type of the to-be-replied interactive content and the respective role attributes of at least one agent.

[0061] The role attribute is used to characterize the identity of the agent. For example, the agent may be a medical role, a general health role. For the medical role, a pediatrician role, a nutritionist role, a traditional Chinese medicine role, etc. may be configured. For the general health role, a beauty person role, a fitness person role, a health preservation person role, etc. may be configured.

[0062] While meeting copyright and compliance requirements, you can also configure famous characters, such as historical characters, cartoon characters, literary characters, etc.

[0063] The agent can participate in the corresponding interactive content response in the content interaction platform according to the role attributes. For example, an agent with the role attribute of a pediatrician can participate in the discussion of interactive content related to children's health issues. Therefore, the target agent can be determined according to the role attributes and the content type of the interactive content to be responded to. For example, if the content type of the interactive content to be responded to belongs to the fitness type, the target agent can be the agent of the fitness expert role; for example, if the content type of the interactive content to be responded to belongs to the children's health type, the target agent can be the agent of the pediatrician role.

[0064] In one of the examples, if a user on the content interaction platform posts the following content, “What to do if your baby has skin eczema,” there is a higher probability that he or she will receive comments and answers from an agent with the role of a pediatrician.

[0065] According to the embodiments of the present disclosure, by configuring role attributes for the intelligent agent, the intelligent agent can automatically match the interactive content in related fields according to the preset role attributes (such as pediatricians, fitness people, etc.), ensure the professionalism and pertinence of the reply, improve the quality of interaction, and enhance the credibility of the platform. In addition, by combining the dual matching mechanism of role attributes and content types, it can not only improve the professionalism and user experience of the interaction, but also improve the automated operation efficiency of the platform, which is suitable for diversified scenarios such as customer service, community Q&A, and health consultation.

[0066] According to an embodiment of the present disclosure, generating reply content for interactive content to be replied using a target agent among at least one agent may include: generating reply content according to the interactive content to be replied and a preset reply generation strategy.

[0067] For example, the preset reply strategy may include generating a "mutual encouragement" reply when "specific goals" are mentioned in the interactive content to be replied. Specifically, if the interactive content to be replied is "I am going to challenge 7 kilometers next week. Are there any friends who will join me?", the generated reply content may be "Come on! 7 kilometers is definitely worth the challenge. Remember to warm up before running. I am also preparing for a half marathon. Let's stick with it!"

[0068] For example, the preset reply strategy may include generating "motivational" reply content when the interactive content to be replied to mentions "I can't run anymore", for example, "Take it slow, every progress is a victory! Try interval running, it will be much easier."

[0069] The agent-based content interaction method provided by the embodiments of the present disclosure can be applied to comment scenarios, follow-up comment scenarios, private message scenarios, posting scenarios, etc.

[0070] According to an embodiment of the present disclosure, displaying the response content of the target agent in the response area corresponding to the interactive content to be replied includes: displaying the response content of the target agent and the agent mark in the response area corresponding to the interactive content to be replied. The agent mark characterizes the agent attribute. The agent mark can be a text label, a visual identifier, etc.

[0071] By displaying the agent mark, the identity identifier of the agent can be clarified, the AI response can be intuitively distinguished from the human response, the user's awareness of the information source can be enhanced, the transparency can be improved, and the user can be prevented from being misled.

[0072] The text label can be at the suffix or prefix of the user name, such as "AI User123" or "User123 AI". The text label can also be marked beside the content, such as marking "AI Generated" or "AI Response" beside the response content.

[0073] The visual identifier can add an exclusive icon beside the user avatar or the user name, such as a robot icon, a star icon, etc. Specifically, a robot badge can be added to the user avatar.

[0074] The display of the text label (such as "AI User123" or "AI Generated") or the visual identifier (such as the robot badge or the exclusive icon) beside the user name, avatar or content can ensure that the user quickly identifies the agent attribute.

[0075] Displaying the response content of the target agent and the agent mark in the response area corresponding to the interactive content to be replied can include: displaying the response content in the first sub-area of the response area and displaying the agent mark in the second sub-area of the response area.

[0076] The response content and the agent mark are displayed in separate areas, making the layout of the response area interface clear, avoiding information mixing, and improving readability.

[0077] According to an embodiment of the present disclosure, the response area further includes an agent avatar and a session jump entry, and the session jump entry is used to link to the session window of the target agent. For example, the agent avatar and the session jump entry can be displayed in the second sub-area.

[0078] Specifically, the session jump entry can be set beside the user avatar or the user name.

[0079] According to an embodiment of the present disclosure, by displaying the session jump entry in the response area, a function of directly accessing the agent's private message window with one key is provided, the operation path is reduced, seamless connection from public interaction to private domain service is realized, and the interaction efficiency is improved.

[0080] The session jump entry can be displayed in one of the following forms: text hyperlink form, button form, icon form, card or bubble prompt form, etc. Specifically, the hyperlink text can directly guide the jump with clickable text (such as blue underlined or highlighted keywords), for example, "Send a private message to TA". The button form can display prominent buttons in the second sub-region, such as the "Start consultation" button and the "Send a private message to TA" button. The icon form can use common icons (message bubble, arrow) for display.

[0081] The session jump entry supports multiple display forms, which can adapt to different platform styles, ensuring clear interaction guidance and conforming to user habits. The session jump entry adopts the form of the "Start consultation" button and the "Send a private message to TA" button, clearly defining the jump entry, reducing the user's cognitive load, making the navigation of the intelligent agent more intuitive, and improving the human-computer interaction experience. Figure 3 Schematically shows a schematic diagram of a comment area interface according to an embodiment of the present disclosure.

[0082] As Figure 3 As shown, the comment area interface 310 of this embodiment 300 includes a content publishing area 320 and a reply area 330. In the content publishing area 320, the interactive content 321 published by user abc is displayed. The reply area 330 includes a first sub-region and a second sub-region. The first sub-region can be located below the second sub-region. For example, the position where the reply content 331 is located is the first sub-region, and the position where the avatar and username of user 123 are located is the second sub-region. In addition, the intelligent agent mark "AI" and the session jump entry "Send a private message to TA" are also displayed in the second sub-region. The session jump entry "Send a private message to TA" in this embodiment can be in the form of hyperlink text or button form.

[0083] Figure 4 Schematically shows a flowchart of the content interaction method in a comment scenario according to an embodiment of the present disclosure.

[0084] As Figure 4 As shown, the content interaction method of this embodiment 400 includes operations S410 to S480.

[0085] In operation S410, obtain the interactive content to be replied published by the user on the content interaction platform.

[0086] In operation S420, determine whether there is an intelligent agent comment on the interactive content to be replied. If so, execute operation S480; if not, execute operation S430.

[0087] In operation S430, determine whether the type of the interactive content to be replied conforms to a preset target type. If so, execute operation S440; if not, execute operation S480.

[0088] In operation S440, it is determined whether the interactive content to be replied meets the preset reply conditions. If so, operations S450 to S470 are executed; if not, operation S480 is executed.

[0089] In operation S450, according to the content type of the interactive content to be replied and the respective role attributes of at least one agent, a target agent is determined from at least one agent.

[0090] In operation S460, according to the content information of the interactive content to be replied, a reply content is generated using the target agent.

[0091] In operation S470, the reply content, the user avatar, the agent mark, and the session jump entry are displayed in the reply area of the interactive content to be replied.

[0092] In operation S480, no comment is made.

[0093] According to an embodiment of the present disclosure, the above method further includes: in response to a trigger operation on the session jump entry, displaying a session window of the target agent, where the session window is used for the current user to have a session with the target agent.

[0094] The session jump entry can be triggered by any user logged in to the content interaction platform. For example, it can be the user who publishes the interactive content to be replied clicks the session jump entry, or it can be a visitor clicks the session jump entry.

[0095] The session window of the target agent can be, for example, a session window for one-on-one conversation with the target agent. The session window can display the user avatar, the user name, the agent mark, etc. The session window also includes a chat input box, a "chat record" button, and a "traditional Chinese medicine conditioning" button.

[0096] According to an embodiment of the present disclosure, the above method further includes: in the case where there are historical session messages between the current user and the target agent, displaying the historical session messages in the session window.

[0097] According to an embodiment of the present disclosure, the above method further includes: in the case where there are no historical session messages between the current user and the target agent, displaying a preset role message from the target agent in the session window, where the preset role message includes the profile information of the target agent.

[0098] Before displaying the session window of the target agent, it may further include determining whether the current user who triggers the session jump entry is a new user. For example, it can be determined by whether there are historical session messages between the current user and the target agent. In the case where there are historical session messages between the current user and the target agent, it indicates that the current user is not a new user; in the case where there are no historical session messages between the current user and the target agent, it indicates that the current user is a new user.

[0099] When the current user is not a new user, obtain historical conversation messages and display them in the conversation window. Additionally, according to the content of the interaction to be replied and preset strategies, guiding copywriting and guiding follow-up questions can be generated and displayed after the historical conversation messages.

[0100] For example, when the current user is a new user, according to the content of the interaction to be replied and preset strategies, guiding copywriting and guiding follow-up questions are generated, and the preset role message, guiding copywriting, and guiding follow-up questions of the target intelligent agent are displayed in the conversation window. Among them, the preset role message can include the profile information of the target intelligent agent.

[0101] The number of guiding follow-up questions can be pre-configured, such as 2, 3, etc.

[0102] For example, if the role attribute of the target intelligent agent is a health preservation person, the guiding follow-up questions can be "I wonder what kind of tea you like to drink the most usually?", "Do you have any special requirements for daily conditioning?", "Can you share a recipe for conditioning the body?".

[0103] Another example, if the role attribute of the target intelligent agent is a fitness expert role, the guiding follow-up questions can be "How to improve the 5-kilometer pace?", "How to break through the deadlift weight?", etc.

[0104] The quick conversation switching function is implemented by setting a "conversation jump entry", enabling the user to quickly switch to the private chat conversation interface with the target intelligent agent through a triggering operation (such as clicking), which improves the interaction efficiency in the multi-intelligent agent scenario. Additionally, after jumping to the private chat conversation, the complete conversation window of the target intelligent agent is directly displayed, retaining the historical conversation context between the current user and this intelligent agent to ensure the continuity of the conversation.

[0105] Figure 5 Schematically shows a schematic diagram of the conversation window interface according to an embodiment of the present disclosure.

[0106] As Figure 5 shown, the conversation window interface 510 of this embodiment 500 includes a user information area 520 and a chat area 530. The user avatar and user name can be displayed in the user information area 520. The chat area 530 can include a chat input box 531, a "chat record" button 532, and chat contents 533 to 536. When the current user is a new user, the chat content 534 can be a role message, and the chat contents 535, 536, 534 can be three guiding follow-up questions. In the case where the current user is an old user, the chat content 534 can be historical messages, and the chat contents 535, 536, 534 can be three guiding follow-up questions.

[0107] Figure 6 Schematically shows a flowchart of the content interaction method according to an embodiment of the present disclosure in a private message scenario.

[0108] As Figure 6 shown, the content interaction method of this embodiment 600 includes operations S610 to S660.

[0109] In operation S610, in response to the user clicking on the session jump entry.

[0110] In operation S620, determine whether the current user is a new user. If so, execute operations S650 to S660; if not, execute operations S630 to S640.

[0111] In operation S630, generate a guiding copywriting and a guiding follow-up question according to the content of the interaction to be replied and a preset strategy.

[0112] In operation S640, display the session window of the target intelligent agent, and sequentially display the historical message session, the guiding copywriting, and the guiding follow-up question within the session window.

[0113] In operation S650, generate a guiding copywriting and a guiding follow-up question according to the content of the interaction to be replied and a preset strategy.

[0114] In operation S660, display the session window of the target intelligent agent, and sequentially display the preset role message of the target intelligent agent, the guiding copywriting, and the guiding follow-up question within the session window.

[0115] According to the embodiment of the present disclosure, by classifying new users and old users and combining the content of the preset strategy, personalized guidance after session jump is realized. For new users, the cognitive cost of new users can be reduced through preset role information, while for old users, historical messages are directly reused to reduce repeated interactions. In addition, preset strategies are used to uniformly generate copywriting to ensure interaction consistency.

[0116] In the follow-up review scenario, when the number of interactions between the current user and the target intelligent agent exceeds a preset threshold, the target intelligent agent can display a prompt message for changing the interaction method to prompt the user to conduct one-on-one interaction. Specifically, the above method may further include: in response to the number of replies of the target intelligent agent to the content of the interaction to be replied meeting the preset threshold, display a prompt message for changing the interaction method, where the prompt message includes a session jump entry for the target intelligent agent.

[0117] By monitoring the number of replies of the target intelligent agent to the content of the interaction to be replied, enabling the target intelligent agent to actively guide the user into a one-on-one private message session helps to reduce ineffective interactions in the public comment area, avoid information redundancy in the comment area, and improve the conversation efficiency.

[0118] The specific value of the preset threshold can be determined according to the actual situation, and the present disclosure does not limit this. In some embodiments, the preset threshold can be 4, 5, 6, etc.

[0119] When the topic initiating user or other users frequently reply to the target intelligent agent, it indicates that the target intelligent agent can display a prompt message in the comment to guide the user to send a private message to TA. The prompt message can include, for example, "Click 'Send Private Message to TA' to get more recommendations" and "Want exclusive answers and communication? Send me a private message and I will provide one-on-one service for you".

[0120] The session jump entry can be in the form of a text hyperlink. By embedding a jumpable keyword such as "Send Private Message to TA" in the prompt message, and the keyword can be underlined, bolded or highlighted to guide the jump to the session window interface.

[0121] Combined with underlining or highlighting, the prompt message can intuitively guide the user to switch to the private message session, improving the convenience of user operations. Figure 7 Schematically shows a flowchart of the content interaction method according to an embodiment of the present disclosure in the follow-up review scenario.

[0122] As Figure 7 shown, the content interaction method of this embodiment 700 includes operation S710 to operation S750.

[0123] In operation S710, when the current user comments on the reply content of the target intelligent agent, obtain the comment content of the current user.

[0124] In operation S720, determine whether the interaction times between the current user and the target intelligent agent exceed 4 times. If so, execute operation S740; if not, execute operation S730 to operation S740.

[0125] In operation S730, generate a reply content for the comment content according to the comment content of the current user.

[0126] In operation S740, display the reply content for the comment content in the reply area of the comment content of the current user

[0127] In operation S750, display a prompt message for changing the interaction method in the reply area of the comment content of the current user. The prompt message includes a session jump entry for the target intelligent agent.

[0128] In operation S760, in response to a trigger operation for the session jump entry included in the prompt message, display the session window interface of the target intelligent agent. The session window interface can be as Figure 5 shown in the session window interface.

[0129] According to an embodiment of the present disclosure, the above method may further include: in response to a trigger operation on the agent avatar, displaying the home page of the target agent, where an agent mark is displayed at a target position on the home page.

[0130] Figure 8 Schematically shows a schematic diagram of the home page according to an embodiment of the disclosure.

[0131] As Figure 8 shown, in the first area 820 of the home page 810 of this embodiment 800, an agent avatar 821, an agent mark 822, a user name 823, a "Follow" button 824, a "Private Message" button 825, etc. can be displayed. In the second area 830, the content published by the agent can be displayed, such as content 831, content 832, content 833, etc.

[0132] From Figure 8 it can be seen that the user can enter the conversation window interface of the agent through the "Private Message" button on the agent's home page.

[0133] According to an embodiment of the present disclosure, the agent can automatically publish content according to a preset rule, such as Figure 8 the content 831, content 832, content 833 shown.

[0134] According to an embodiment of the present disclosure, the reply content includes a target mapping address, and the target mapping address is used to link to an extended content page corresponding to the reply content; the above method further includes: in response to a trigger operation on the target mapping address, displaying the extended content page corresponding to the target mapping address. The extended content page can include a tutorial page, a document page, an order details page, etc.

[0135] Embedding the target mapping address in the agent's reply content enables the user to directly access the extended content page related to the current conversation, such as tutorials, documents, order details, etc., improving the information acquisition efficiency and reducing the search cost.

[0136] According to an embodiment of the present disclosure, the target mapping address can be visually distinguished from other text content in the reply content. For example, the target mapping address can be in the visual style of a hyperlink, the target mapping address can adopt a color not used for ordinary text, and is displayed in an underlined style.

[0137] According to an embodiment of the present disclosure, it may further include: when the mouse hovers over the target mapping address, a prompt message can be displayed, such as a brief description of the target page or the domain name pointed to by the target mapping address, enhancing the user's predictability of the target mapping address.

[0138] It should be noted that the target mapping address can correspond to different extended pages according to different business scenarios. For example, the target mapping address embedded in some knowledge Q&A responses, when clicked, can not only jump to the page but also display the abstract information of the reference material in a specific area of the page; for another example, the product link embedded in e-commerce-related responses, when clicked, can pop up a quick preview window of the product, including key information such as pictures, improving the user experience.

[0139] Exemplarily, the target mapping address includes a product transaction address; displaying the extended content page corresponding to the target mapping address includes: displaying the product transaction interface corresponding to the product transaction address.

[0140] The product transaction address can include a product link, a transaction entry, etc. The product transaction interface can include a product details page, a shopping cart page, an order confirmation page, a payment page, etc.

[0141] Embedding the product transaction address in the response content, users can directly jump to the product transaction interface such as the product details page, the order placement page, etc. by clicking, realizing the function of quickly triggering the AI comment to the shopping scenario, without the user having to search on the e-commerce platform again, shortening the path from consultation to transaction, improving the user experience, and helping to increase the transaction success rate.

[0142] Figure 9A Schematically shows a schematic diagram of the response content including the product transaction address according to an embodiment of the present disclosure.

[0143] As Figure 9A shown, the response content 911 in the comment interface 910 in this embodiment 900A includes the product transaction address "×× Nursing Encyclopedia", and clicking on this product transaction address can jump to the transaction interface 920. According to an embodiment of the present disclosure, the above method may further include embedding the target mapping address in the interaction content during the interaction process between the session window interface and the user.

[0144] According to an embodiment of the present disclosure, by including the target mapping address in the response content, it is convenient for the user to jump to the detailed page after triggering the target mapping address, meeting the user's in-depth needs.

[0145] Figure 9B Schematically shows a schematic diagram of the response content including the target mapping address according to an embodiment of the present disclosure.

[0146] As Figure 9B shown, the response content 931 in the comment interface 930 in this embodiment 900B includes the target mapping address "peach blossom", and clicking on this target mapping address can jump to the detailed introduction page of the peach blossom.

[0147] Figure 10A block diagram of an agent-based content interaction device according to an embodiment of the present disclosure is schematically shown.

[0148] According to an embodiment of the present disclosure, the agent-based content interaction device can be applied to a content interaction platform configured with at least one agent.

[0149] As Figure 10 shown, the agent-based content interaction device 1000 may include a generation module 1010 and a first display module 1020.

[0150] The generation module 1010 is configured to, in response to the to-be-replied interactive content published on the content interaction platform satisfying a preset reply condition, use a target agent among the at least one agent to generate a reply content for the to-be-replied interactive content.

[0151] The first display module 1020 is configured to display the reply content of the target agent in the reply area corresponding to the to-be-replied interactive content.

[0152] According to an embodiment of the present disclosure, the first display module is further configured to display the reply content of the target agent and an agent mark in the reply area corresponding to the to-be-replied interactive content, where the agent mark characterizes the agent attribute.

[0153] According to an embodiment of the present disclosure, the reply area further includes a session jump entry for linking to the session window of the target agent.

[0154] According to an embodiment of the present disclosure, the device further includes: a second display module.

[0155] The second display module is configured to, in response to a trigger operation on the session jump entry, display the session window of the target agent, where the session window is used for the current user to have a session with the target agent.

[0156] According to an embodiment of the present disclosure, the second display module includes a first display sub-module.

[0157] The first display sub-module is configured to, when there are historical session messages between the current user and the target agent, display the historical session messages in the session window.

[0158] According to an embodiment of the present disclosure, the second display module further includes a second display sub-module.

[0159] The second display sub-module is configured to, when there are no historical session messages between the current user and the target agent, display preset role messages from the target agent in the session window, where the preset role messages include profile information of the target agent.

[0160] According to an embodiment of the present disclosure, the reply content includes a target mapping address, and the target mapping address is used to link to an extended content page corresponding to the reply content.

[0161] According to an embodiment of the present disclosure, the device further includes: a third display module.

[0162] The third display module is configured to display an extended content page corresponding to the target mapping address in response to a trigger operation on the target mapping address.

[0163] According to an embodiment of the present disclosure, the target mapping address includes a product transaction address.

[0164] According to an embodiment of the present disclosure, the third display module is further configured to display a product transaction interface corresponding to the product transaction address.

[0165] According to an embodiment of the present disclosure, the device further includes: a fourth display module.

[0166] The fourth display module is configured to display a prompt message for changing the interaction mode in response to the number of replies of the target agent to the to-be-replied interaction content meeting a preset threshold, where the prompt message includes a session jump entry for the target agent.

[0167] According to an embodiment of the present disclosure, the agent has a role attribute.

[0168] According to an embodiment of the present disclosure, the device further includes: a determination module.

[0169] The determination module is configured to determine a target agent from at least one agent according to the content type of the to-be-replied interaction content and the respective role attributes of the at least one agent.

[0170] According to an embodiment of the present disclosure, the preset reply conditions include at least one of the following: the current time is separated from the release time of the to-be-replied interaction content by a preset duration, the type of the to-be-replied interaction content belongs to a preset target type, and the to-be-replied interaction content contains a preset keyword.

[0171] According to an embodiment of the present disclosure, the content interaction platform includes at least one of the following: a forum, a knowledge community.

[0172] Any of a plurality of modules, sub-modules, units, and sub-units according to embodiments of the present disclosure, or at least part of the functions of any of the foregoing may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure may be split into multiple modules for implementation. Any one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure may be at least partially implemented as a hardware circuit, such as a field-programmable gate array (FPGA), programmable logic array (PLA), system-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or may be implemented by any other reasonable manner of integrating or packaging circuits, or in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure may be at least partially implemented as a computer program module, and when the computer program module runs, corresponding functions may be executed.

[0173] For example, any of the generation module 1010 and the first display module 1020 may be combined and implemented in one module / unit / sub-unit, or any one of the modules / units / sub-units may be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units may be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to embodiments of the present disclosure, at least one of the generation module 1010 and the first display module 1020 may be at least partially implemented as a hardware circuit, such as a field-programmable gate array (FPGA), programmable logic array (PLA), system-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or may be implemented by any other reasonable manner of integrating or packaging circuits, or in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, at least one of the generation module 1010 and the first display module 1020 may be at least partially implemented as a computer program module, and when the computer program module runs, corresponding functions may be executed.

[0174] It should be noted that the part of the agent-based content interaction device in the embodiments of the present disclosure corresponds to the part of the agent-based content interaction method in the embodiments of the present disclosure. For the description of the part of the agent-based content interaction device, reference may be specifically made to the part of the agent-based content interaction method, and details are not repeated here.

[0175] Figure 11A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 11 The illustrated electronic device is merely an example and should not impose any limitation on the functions and the scope of use of the embodiments of the present disclosure.

[0176] As Figure 11 shown, the electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage section 1108 into a random access memory (RAM) 1103. The processor 1101 may include, for example, a general microprocessor (e.g., CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (e.g., an application specific integrated circuit (ASIC)), etc. The processor 1101 may also include on-board memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0177] In the RAM 1103, various programs and data required for the operation of the electronic device 1100 are stored. The processor 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. The processor 1101 performs various operations of the method flow according to an embodiment of the present disclosure by executing the programs in the ROM 1102 and / or the RAM 1103. It should be noted that the programs may also be stored in one or more memories other than the ROM 1102 and the RAM 1103. The processor 1101 may also perform various operations of the method flow according to an embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0178] According to an embodiment of the present disclosure, the electronic device 1100 may further include an input / output (I / O) interface 1105, and the input / output (I / O) interface 1105 is also connected to the bus 1104. The electronic device 1100 may further include one or more of the following components connected to the input / output (I / O) interface 1105: an input part 1106 including a keyboard, a mouse, etc.; an output part 1107 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part 1108 including a hard disk, etc.; and a communication part 1109 including a network interface card such as a LAN card, a modem, etc. The communication part 1109 performs communication processing via a network such as the Internet. The drive 1110 is also connected to the input / output (I / O) interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed so that a computer program read from thereon can be installed into the storage part 1108 as needed.

[0179] According to an embodiment of the present disclosure, the method flow according to the embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1109, and / or installed from the removable medium 1111. When the computer program is executed by the processor 1111, the above functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the above-described system, device, apparatus, module, unit, etc. can be implemented by computer program modules.

[0180] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0181] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include but is not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0182] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include one or more memories other than the above-described ROM 1102 and / or RAM 1103 and / or ROM 1102 and RAM 1103.

[0183] An embodiment of the present disclosure also includes a computer program product, which includes a computer program that contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the agent-based content interaction method provided by the embodiment of the present disclosure.

[0184] When the computer program is executed by the processor 1101, the above functions defined in the system / apparatus of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0185] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium and downloaded and installed through the communication part 1109, and / or installed from the removable medium 1111. The program code contained in the computer program may be transmitted by any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0186] In accordance with embodiments of the present disclosure, program code for executing the computer programs provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The programming languages include, but are not limited to, programming languages such as Java, C++, Python, the "C" language, or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0187] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions. Those skilled in the art can understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0188] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. An agent-based content interaction method, applied to a content interaction platform, where the content interaction platform is configured with at least one agent, and the method includes: Responding to the to-be-replied interactive content published on the content interaction platform satisfying a preset reply condition, and using the target agent among the at least one agent to generate a reply content for the to-be-replied interactive content; And Displaying the reply content of the target agent in the reply area corresponding to the to-be-replied interactive content.

2. The method according to claim 1, wherein, The displaying the reply content of the target agent in the reply area corresponding to the to-be-replied interactive content includes: Displaying the reply content of the target agent and an agent marker in the reply area corresponding to the to-be-replied interactive content, where the agent marker represents agent attributes.

3. The method according to claim 2, wherein, The reply area further includes a session jump entry, and the session jump entry is used to link to the session window of the target agent.

4. The method according to claim 3, further includes: Responding to a trigger operation on the session jump entry, and displaying the session window of the target agent, where the session window is used for the current user to have a session with the target agent.

5. The method according to claim 4, further includes: When there are historical session messages between the current user and the target agent, displaying the historical session messages in the session window.

6. The method according to claim 4 or 5, further includes: When there are no historical session messages between the current user and the target agent, displaying a preset role message from the target agent in the session window, where the preset role message includes profile information of the target agent.

7. The method according to claim 2, wherein, The reply content includes a target mapping address, and the target mapping address is used to link to an extended content page corresponding to the reply content; The method further includes: Responding to a trigger operation on the target mapping address, and displaying an extended content page corresponding to the target mapping address.

8. The method according to claim 7, wherein The target mapping address includes a product transaction address; The displaying an extended content page corresponding to the target mapping address includes: Displaying a product transaction interface corresponding to the product transaction address.

9. The method according to claim 1, further includes: Responding to the number of replies of the target agent to the to-be-replied interactive content satisfying a preset threshold, and displaying a prompt message for changing the interaction method, where the prompt message includes a session jump entry for the target agent.

10. The method according to claim 1, wherein The agent has a role attribute; The method further includes: Determining the target agent from the at least one agent according to the content type of the to-be-replied interactive content and the respective role attributes of the at least one agent.

11. The method according to claim 1, wherein, The preset reply condition includes at least one of the following: the current time satisfies a preset duration from the publication time of the to-be-replied interactive content, the type of the to-be-replied interactive content belongs to a preset target type, and the to-be-replied interactive content contains a preset keyword.

12. An agent-based content interaction device is applied to a content interaction platform, and at least one agent is configured in the content interaction platform. The device includes: A generation module, configured to, in response to that the to-be-replied interactive content published on the content interaction platform meets a preset reply condition, generate a reply content for the to-be-replied interactive content by using a target agent among the at least one agent; And A first display module, configured to display the reply content of the target agent in a reply area corresponding to the to-be-replied interactive content.

13. An electronic device includes: One or more processors; A memory, configured to store one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor is caused to implement the method according to any one of claims 1 to 11.

15. A computer program product includes a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images