Multimedia content recommendation method and device, electronic equipment and storage medium

By displaying the multimedia content recommendation stream in the dialogue interface between the user and the agent and determining the recommended content based on historical interactive data, the machine learning model is used to improve the accuracy and user experience of multimedia content recommendation, and solve the limitations of recommended content in the existing technology. The problem.

CN119096235APending Publication Date: 2024-12-06BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202480002117.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-04-25
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Existing multimedia content recommendation streams cannot fully discover information that users are interested in, resulting in limited types of recommended content.

Method used

Display the recommendation flow entry of multimedia content in the dialogue interface between the user and the agent, and determine the recommended content based on the historical interaction data between the user and the agent, use machine learning models to mine user preferences and improve the accuracy of recommendations.

Benefits of technology

Through the integration of the agent and multimedia content, the recommended multimedia content is more matched with the information that users pay attention to, improving the user experience and recommendation accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119096235A_ABST
    Figure CN119096235A_ABST
Patent Text Reader

Abstract

The invention relates to a multimedia content recommendation method and device, electronic equipment and a storage medium. The multimedia content recommendation method comprises the steps of displaying a first entry of a recommendation stream of multimedia content in a dialogue interface of a user and a first agent; in response to a triggering operation on the first entry, displaying a playing interface of the recommended stream; based on historical interaction data of user authorization of the user and at least one of the first intelligent agent and other intelligent agents except the first intelligent agent, multimedia content recommended to the user is determined; and displaying the multimedia content recommended to the user in a playing interface of the recommendation stream.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of terminal applications, and in particular to a method, device, electronic device, and storage medium for recommending multimedia content. Background Art

[0002] In multimedia applications such as short videos, users can browse multimedia content such as videos, graphic content, and can switch between multiple multimedia content through operations such as switching. For example, if the user is not interested in the current multimedia content, he can quickly switch to the next recommended video. If the user is interested in the current multimedia content, he can interact with the author of the multimedia content by posting comments in the comment area, liking, etc., to express his emotions or learn more about the video. Summary of the invention

[0003] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] According to some embodiments of the present disclosure, a method for recommending multimedia content is provided, comprising: displaying a first entrance to a recommendation stream of multimedia content in a dialogue interface between a user and a first intelligent agent; displaying a playback interface of the recommendation stream in response to a trigger operation on the first entrance; determining multimedia content recommended to the user based on user-authorized historical interaction data between the user and the first intelligent agent and at least one of other intelligent agents other than the first intelligent agent; and displaying the multimedia content recommended to the user in the playback interface of the recommendation stream.

[0005] According to other embodiments of the present disclosure, a multimedia content recommendation device is provided, comprising: a first display module, configured to display a first entrance to a recommendation stream of multimedia content in a dialogue interface between a user and a first intelligent agent; a second display module, configured to display a playback interface of the recommendation stream in response to a trigger operation on the first entrance; a determination module, configured to determine multimedia content recommended to a user based on user-authorized historical interaction data between the user and at least one of the first intelligent agent and other intelligent agents except the first intelligent agent; and a third display module, configured to display the multimedia content recommended to the user in the playback interface of the recommendation stream.

[0006] According to some embodiments of the present disclosure, an electronic device is provided, including: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the multimedia content recommendation method of any embodiment of the present disclosure based on instructions stored in the memory.

[0007] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for recommending multimedia content in any embodiment of the present disclosure is performed.

[0008] According to some embodiments of the present disclosure, a computer program is provided, comprising: instructions, which, when executed by a processor, cause the processor to execute the multimedia content recommendation method of any one of the embodiments of the present disclosure.

[0009] Other features, aspects and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The drawings described herein are used to provide a further understanding of the present disclosure. Each of the drawings together with the following detailed description is included in this specification and forms a part of the specification, and is used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation on the present disclosure. In the drawings:

[0011] Figure 1 A schematic flow chart of a method for recommending multimedia content according to some embodiments of the present disclosure is shown.

[0012] Figure 2 A flowchart of a recommendation method based on historical conversation records according to some embodiments of the present disclosure is shown.

[0013] Figure 3 A schematic diagram of the process of making recommendations based on an intelligent agent according to some embodiments of the present disclosure is shown.

[0014] Figure 4 A schematic diagram of a conversation interface according to some embodiments of the present disclosure is shown.

[0015] Figure 5 A schematic diagram of a playback interface of a recommended stream of multimedia content according to some embodiments of the present disclosure is shown.

[0016] Figure 6 A schematic diagram of a dialogue interface according to some other embodiments of the present disclosure is shown.

[0017] Figure 7 A schematic diagram of the interface of a conversation list according to some embodiments of the present disclosure is shown.

[0018] Figure 8 A schematic diagram of a terminal lock screen interface according to some embodiments of the present disclosure is shown.

[0019] Fig. 9A schematic structural diagram of a multimedia content recommendation device according to some embodiments of the present disclosure is shown.

[0020] Fig.10 A schematic structural diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0021] Fig.11 A schematic diagram of the structure of a computer system according to some embodiments of the present disclosure is shown.

[0022] It should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship. The same or similar reference numerals are used in the various drawings to represent the same or similar parts. Therefore, once an item is defined in one drawing, it may not be further discussed in subsequent drawings. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure, but it is obvious that the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The following description of the embodiments is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein.

[0024] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be performed in different orders, and / or performed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown in the execution. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.

[0025] The term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". In addition, the term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". Therefore, include is synonymous with include. The term "based on" means "based at least in part on".

[0026] References throughout this specification to "one embodiment," "some embodiments," or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearances of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout this specification do not necessarily all refer to the same embodiment, but may do so.

[0027] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, the concepts of "first", "second", etc. are not intended to imply that the objects described in this way must be in a given order in time, space, ranking, or any other manner.

[0028] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0029] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0030] The embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined in any suitable manner that will be clear from the present disclosure by a person of ordinary skill in the art.

[0031] In the related art, the recommendation flow of multimedia content often determines the multimedia content recommended to the user based on the preference information set by the user and the user's historical browsing information. However, this information can only reflect the preferences of the user in the process of browsing multimedia content, and cannot fully explore the information that the user is interested in. Therefore, the types of recommended multimedia content have certain limitations.

[0032] With the development of artificial intelligence and machine learning technologies, intelligent agents can be realized using machine learning models. Intelligent agents are virtual objects realized based on artificial intelligence technology. For example, intelligent agents can act as virtual friends or virtual experts in a certain field to receive messages sent by users and reply to messages to users. For example, when users have questions or want to quickly acquire some knowledge, they can communicate with intelligent agents. The interaction records between users and intelligent agents can reflect the information that users are concerned about.

[0033] Therefore, in order to push multimedia content to users more accurately, the present invention integrates the intelligent agent with the recommendation stream of multimedia content, displays the entrance to the recommendation stream in the dialogue interface between the user and the intelligent agent, and determines the multimedia content recommended to the user in the recommendation stream based on the historical interaction data between the user and the intelligent agent, so that the recommended multimedia content is more closely matched with the information that the user is concerned about, thereby improving the user experience.

[0034] Figure 1 FIG. 1 is a flow chart showing a method for recommending multimedia content according to some embodiments of the present disclosure. Figure 1 As shown, the recommended method of this embodiment includes steps S102 to S108.

[0035] In step S102, a first entry of a recommendation stream of multimedia content is displayed in a dialogue interface between a user and a first agent.

[0036] The intelligent agent includes, for example, a robot, a digital human, an intelligent assistant, and a virtual agent of a machine learning model, which is an intelligent object that can automatically reply based on the content input by the user, for example, it can be a conversational robot. The first intelligent agent can be any intelligent agent. In the embodiments of the present disclosure, the first intelligent agent refers to the intelligent agent currently in conversation with the user.

[0037] The agent can generate corresponding content based on the dialogue sent by other subjects in the dialogue scene (such as the first user, the second user, and other users or agents participating in the dialogue). The agent can be implemented in the form of software, hardware, or a combination of software and hardware. The agent can be implemented based on a machine learning model, such as a large language model (LLM) or a foundation model. The machine learning model can be a generative model, which is used to output target content based on input information. The input information of the generative model includes the processing basis of the generative model in the generation process, such as which information is referenced to perform the generation process, the requirements of the output target content, etc. The generative model includes, for example, a model generated based on text, or a model generated based on an image, and the output of the generative model can include text, images, or a combination of the two. Of course, the input or output of the generative model can also be data of other modalities, such as audio, video, or a combination of multiple types of data. The generative model can be a single-modal model, such as a model that generates text from text (referred to as the "text-to-text model") or a model that generates images from images (referred to as the "image-to-image model"). Alternatively, the generative model can be a cross-modal model, that is, a model whose input and output belong to different modalities, such as a model that generates images from text (referred to as the "text-to-image model"). Alternatively, the input of the generative model can include multiple modalities, and the output can also include multiple modalities.

[0038] In the dialogue interface, the user can send a message to the first agent, and the message may include one or more of text, image, video, voice, and link. The first agent can generate a reply message based on the message sent by the user, and the reply message may also include one or more of text, image, video, voice, and link. The specific type of the message can be determined based on the type supported by the application and the type supported by the first agent.

[0039] The recommendation stream of multimedia content (or simply referred to as multimedia stream) includes multiple multimedia contents, such as video, audio, graphic content, graphic notes, etc. The recommendation stream can make recommendations to users based on their preferences. The multimedia content in the recommendation stream can be created and uploaded by the current user or other users, or published by the application platform. The first entrance of the recommendation stream is used to trigger the display of the recommendation stream. The first entrance can be located at a fixed position in the dialogue interface, or in a message sent by the first agent. In the process of users using the recommendation stream, the videos in the recommendation stream can be continuously increased or changed as the user's browsing progresses. For example, when a specified first amount of multimedia content is recommended to the user at one time, and the user has browsed a specified proportion or a specified second amount of them, new multimedia content recommended to the user can continue to be determined.

[0040] In step S104, in response to the triggering operation on the first entry, a playback interface of the recommended stream is displayed.

[0041] The triggering operation on the first entry includes, for example, a click operation, a slide operation, etc. For example, when the first entry is a button, it can be triggered by a click operation; when the first entry is an undisplayed tab page, it can be triggered by sliding the currently displayed tab page.

[0042] In some embodiments, the playback interface of the recommended stream displays the multimedia content in an immersive manner, such as full screen display. The user can browse the videos recommended for the user by switching the multimedia content (such as sliding up and down).

[0043] In step S106, multimedia content recommended to the user is determined based on historical interaction data authorized by the user and at least one of the first agent and other agents other than the first agent.

[0044] The historical interaction data is used to reflect the user's historical operation information related to the agent, which may include historical dialogue records, information about the used agents, and information about the created agents. The historical interaction data between the user and the agent can reflect the information that the user pays attention to, needs, or may be interested in during the interaction between the user and the agent, so the user's preferences can be mined.

[0045] Steps S104 and S106 may be executed in any order or in parallel, and the embodiments of the present disclosure do not limit this.

[0046] In step S108, the multimedia content recommended to the user is displayed in the playback interface of the recommended stream.

[0047] Since the multimedia content that can be displayed on the playback interface at one time is limited (for example, only one is displayed at a time), some of the multimedia content recommended for the user can be played first, and then other recommended multimedia content can be played for the user in response to the user's switching operation. When the user has browsed all the multimedia content that has been determined and recommended for the user or has browsed a specified proportion or a specified amount, a batch of recommended multimedia content can be determined for the user again based on step S106 and displayed to the user through the playback interface of the recommendation stream.

[0048] The above embodiment sets the recommendation flow of multimedia content in the dialogue interface between the user and the agent, so that the user can browse the multimedia content recommended for the user during the dialogue with the agent. In addition, the recommended multimedia content is determined based on the historical interaction data between the user and the current agent or other agents, so that the recommended multimedia content is more compatible with the user's preferences, thereby improving the user experience.

[0049] The following describes an embodiment of the present disclosure for determining multimedia content recommended to a user in combination with several different types of historical interaction data.

[0050] Figure 2 FIG. 1 is a flow chart showing a method for recommending based on historical conversation records according to some embodiments of the present disclosure. Figure 2 As shown, the recommendation method of this embodiment includes steps S202 to S206. The historical conversation record referred to in this embodiment is the conversation record between the user and the agent in the current conversation (ie, the first agent).

[0051] In step S202, one or more first key information is extracted from the user's historical conversation records.

[0052] The first key information refers to the information that has been discussed in the historical messages between the user and the agent and can represent the topic of the conversation. Different key information can be the same or different information extracted from historical messages generated in different time periods, or different information extracted from historical messages generated in the same time period. For example, a user and an agent talked about movie A in the morning of a certain day, and talked about movie A and travel guide to city B in the afternoon of the same day. From the messages in these historical conversations, the three key information "movie A", "movie A", and "travel guide to city B" can be extracted, or the three key information "movie", "movie", and "travel" can be extracted.

[0053] In step S204, the importance of each piece of first key information is determined. The importance can be represented by a numerical value, a grade, a category, or the like.

[0054] In some embodiments, one or more first key information are extracted from the historical messages of the historical conversation record between the user and the first agent, and the importance of each first key information is determined according to the sending time of the historical message. The generation time of the first key information can be determined according to the sending time of the historical message corresponding to each first key information, and the importance of the first key information can be determined according to the distance between the generation time of each first key information and the current time. For example, the distance and the importance can be negatively correlated, that is, the closer the generation time of the first key information is to the current time, the higher its importance.

[0055] In some embodiments, one or more first key information is extracted from the historical conversation records between the user and the first agent, and other agents other than the first agent, and the importance of each first key information is determined according to the time when the historical conversation was generated and whether the historical conversation record is from the first agent. For example, when other conditions remain unchanged, the importance of the first key information from the first agent is higher than the importance of the first key information from other first agents.

[0056] In step S206, multimedia content recommended to the user is determined based on one or more first key information and the importance of each first key information. When other conditions remain unchanged, multimedia content associated with first key information with high importance is more likely to be recommended to the user.

[0057] This embodiment determines reference basis for recommending multimedia content based on historical conversation records between the user and the intelligent agent, and determines the importance of the reference basis based on the sending time of the message in the historical conversation record or whether it comes from the first intelligent agent in the current conversation. This can prioritize recommending to the user multimedia content that includes information that the user has recently paid attention to, or content that is more relevant to the message on the current interface, thereby improving the accuracy of the recommendation and thus enhancing the user experience.

[0058] Figure 3 FIG. 2 shows a flow chart of making recommendations based on an intelligent agent according to some embodiments of the present disclosure. Figure 3 As shown, the recommended method of this embodiment includes steps S302 to S306.

[0059] In step S302, key information corresponding to each agent is determined based on the setting information of the agent that the user has interacted with. The interacted agent can be an agent created by the user or an agent that has been used. The setting information of the agent includes, for example, the attributes and type of the agent. The attributes include, for example, tags, personality, introduction, etc. The type includes, for example, its functional type, such as life type, emotion type, knowledge type, etc.

[0060] In step S304, the importance of each key information corresponding to each agent is determined.

[0061] In some embodiments, when the interacted agent is a used agent, the key information is the second key information. The importance of each second key information is determined according to at least one of the use time and the use frequency of the agent.

[0062] In some embodiments, when the interacted agent is a user-created agent, the key information is the third key information. The importance of each piece of the third key information is determined based on at least one of the creation time, usage time, and usage frequency of the agent.

[0063] The representation form and importance of the second and third key information can be referred to Figure 2 The description of the first key information in the embodiment will not be repeated here.

[0064] The usage time indicates when the user used the agent, which can reflect the user's usage time or the time when the agent was last used. The usage time can be positively correlated with the importance of the second key information. The length of time between the last time the agent was used and the current time can be negatively correlated with the importance. The usage frequency indicates the number of times the agent is used per unit time, which can be positively correlated with the importance.

[0065] In step S306, multimedia content recommended to the user is determined based on one or more key information and the importance of each key information. Under the condition that other conditions remain unchanged, multimedia content associated with key information with high importance is more likely to be recommended to the user.

[0066] The intelligent agents that the user has interacted with reflect the type of information the user wants to know. Therefore, by recommending multimedia content based on the intelligent agents that the user has interacted with, the recommended multimedia content can be matched with the user's interests, thereby improving the accuracy of the recommendation and the user experience.

[0067] In some embodiments, the multimedia content recommended to the user may be comprehensively determined based on the importance of part or all of the first key information, the second key information, and the third key information. For example, the recommendation reference value of each key information is determined based on the weighted result of the weight and importance of each key information, and the multimedia content recommended to the user is determined based on the recommendation reference value.

[0068] In some embodiments of the present disclosure, the first entry may be set in a message sent by the agent, or may be set as a fixed position in the dialogue interface. Various implementations are described in detail below by way of example.

[0069] In some embodiments, in the dialogue interface between the user and the first agent, a first message sent by the agent to the user and a first preview control of the first multimedia content corresponding to the first message are displayed, wherein the first preview control is the first entry of the recommendation stream of the multimedia content, and the first multimedia content is included in the multimedia content recommended for the user. That is, the message sent by the agent to the user includes a preview control of the multimedia content, and by triggering the preview control, the playback interface of the recommended stream can be displayed. Figure 4 This embodiment is described exemplarily.

[0070] The dialogue interface includes messages sent between the user and the agent. For example, it may include only messages sent by the user, only messages sent by the agent, or messages sent by both the user and the agent. Figure 4 A schematic diagram of a conversation interface according to some embodiments of the present disclosure is shown. Figure 4 In the dialogue interface 4 shown, the messages aligned on the right are sent by the user, for example, message 41 "Show me the latest science and technology news" is sent by the user. The messages aligned on the left are sent by the agent, for example, the videos in the first preview controls 421, 422, 423 and message 43 are sent by the agent. In some embodiments, the dialogue interface 4 may also display message prompt controls 441, 442, and 443, and in response to the user triggering a message prompt control, the message in the message prompt control may be automatically sent to the user.

[0071] In some embodiments, in the dialogue interface, a second message sent by the user to the agent is displayed; based on the second message, a first message for responding to the second message and a video corresponding to the first message are generated. Figure 4 In the example shown, the video in the first preview controls 421, 422, and 423 and the message 43 are all used to reply to the message 41 sent by the user, that is, the reply content of the agent can be generated according to the message 41 sent by the user, and the reply content includes video and text. The video preview control serves as the entrance to the recommendation stream. For example, in response to the user triggering (e.g., clicking) any one of the first preview controls 421, 422, and 423, the interface of the recommendation stream is displayed, and the video corresponding to the video preview control triggered by the user is displayed in the interface of the recommendation stream. In addition to the corresponding multimedia content in the message, the recommendation stream also includes other multimedia content determined based on historical interaction data.

[0072] Figure 5 A schematic diagram of a playback interface of a recommended stream of multimedia content according to some embodiments of the present disclosure is shown. Figure 5As shown, in the playback interface 5 of the recommendation stream of multimedia content, multimedia content 51 recommended to the user is displayed. In some embodiments, the playback interface 5 may also include an interactive control 52 between the user and the agent, so that the user can interact with the agent at any time during the process of browsing the multimedia content.

[0073] In addition to replying to the second message sent by the user, the agent can also actively send a message to the user, and carry the entrance to the recommendation stream of multimedia content in the message. In some embodiments, in response to the display of the dialogue interface, the time when the dialogue interface was last displayed to the user is determined; in response to the interval between the time when the dialogue interface was last displayed to the user and the current time exceeding the specified threshold, a first message for welcoming the user back and a video corresponding to the first message are generated. For example, if a user has not used an agent for a period of time, when the user accesses the dialogue interface corresponding to the agent, the agent can actively send a "Welcome Back" message to the user, which can be generated based on the user's historical messages or current hot information. The message can include only a video preview control, or it can include both a video preview control and text content. Thus, after the user has not used the agent for a long time, the user can be guided to interact with the agent and access the recommendation stream by sending a welcome return message.

[0074] Figure 6 Schematic diagrams of dialogue interfaces according to other embodiments of the present disclosure are shown. In this embodiment, the interval between the time when the dialogue interface was last displayed to the user and the current time exceeds a specified threshold. When the user accesses the dialogue interface again, Figure 6 As shown, the conversation interface 6 includes the last message 61 sent by the agent to the user. In addition, it also includes the message sent by the agent to the user, which includes the first preview controls 621, 622 and 623 corresponding to several videos and the message 63 "Welcome back, recommending videos that you may be interested in".

[0075] In some embodiments, a first entry of a recommended stream of multimedia content is displayed at a fixed position of a dialogue interface between the user and the first agent. Figure 4 As shown, the conversation interface 4 may also include a fixed entry 46 for the recommendation stream of multimedia content (video in this example). In this example, the conversation interface and the interface of the recommendation stream are two parallel tabs. The display of the interface of the recommendation stream can be triggered by triggering a tag (e.g., entry 46) of the recommendation stream tab. Figure 5In some embodiments, the interface 5 of the recommendation stream can also trigger the display of the interface of the recommendation stream by performing a sliding operation (e.g., swiping left) in the dialogue interface 4. Thus, the user can access the recommendation stream at any time, which improves the user experience. In some embodiments, the interface 5 of the recommendation stream can also include a label 53 of the dialogue interface, and the display of the dialogue interface can be triggered by triggering the label 53 of the dialogue tab, or by performing a sliding operation (e.g., swiping right) in the interface 5 of the recommendation stream. In some embodiments, the interface 5 can also include a return control 54, and in response to triggering the return control 54, the dialogue interface can be displayed.

[0076] Some embodiments of the present disclosure may also provide an entry to a recommended stream of multimedia content in a conversation list with an agent, thereby making it easier for users to access the recommended stream. In some embodiments, an interface including a conversation list is displayed, the conversation list includes an entry to a conversation interface with one or more agents, and a second entry to a recommended stream of multimedia content; in response to a trigger operation on the second entry, a playback interface of the recommended stream is displayed. Thus, the user can more quickly access the interface of the recommended stream of multimedia content while using the application.

[0077] Figure 7 FIG. 1 shows a schematic diagram of an interface of a conversation list according to some embodiments of the present disclosure. Figure 7 As shown, the interface 7 of the conversation list includes a conversation list, in which several items 72, 73, 74, and 75 are exemplarily shown, wherein items 72, 73, and 74 correspond to intelligent agents, that is, in response to triggering any one of the items 72, 73, and 74, the conversation interface of the intelligent agent corresponding to the triggered item is displayed; 75 corresponds to the recommendation stream of multimedia content, that is, in response to triggering item 75, the interface of the recommendation stream is displayed.

[0078] The interface where the conversation list is located can also directly display preview controls for some multimedia content recommended for the user, and display the interface of the recommended stream of multimedia content in response to the triggering of the preview controls. In some embodiments, an interface including a conversation list and a third entry for the recommended stream of multimedia content is displayed, the conversation list includes an entry for a conversation interface with one or more agents, and the third entry includes one or more second preview controls for second multimedia content recommended for the user; in response to the triggering operation of the second preview control, a playback interface for the recommended stream is displayed; in the playback interface for the recommended stream, the second multimedia content and other multimedia content recommended for the user are displayed. Figure 7As shown, in some embodiments, interface 7 may also include second preview controls 711, 712, and 713 corresponding to the videos recommended for the user. By directly displaying a preview of the multimedia content recommended for the user, the user can be guided to access the recommended stream of the multimedia content by displaying the actual recommended object. In the case where the second preview control is set in the interface of the conversation list, the conversation list may include a second entry (e.g., entry 75) for the recommended stream of the multimedia content, or may not include the second entry. In the case where the second entry is included in the conversation list, the interface of the conversation list may include a second preview control, or may not include the second preview control.

[0079] Outside the application, users can be guided to access the recommended stream of multimedia content by pushing messages. For example, information related to the recommended multimedia content can be sent to users by pushing system messages. In some embodiments, a third message is pushed to the user's user device through a second agent. The third message is associated with a third multimedia content. The second agent is the same as or different from the first agent, that is, the second agent can be any agent. In response to the triggering operation of the pushed third message, a dialogue interface between the user and the second agent is displayed. The dialogue interface can refer to the aforementioned embodiments and will not be repeated here. In the dialogue interface between the user and the second agent, a third preview control of the third message and the third multimedia content is displayed; in response to the triggering operation of the third preview control, a playback interface of the recommended stream is displayed; in the playback interface of the recommended stream, the third multimedia content and the multimedia content recommended to the user are displayed. The third message, the third multimedia content, and the third preview control are only used to distinguish the names in different embodiments. Their specific implementation and interface style can refer to the description of the corresponding controls and content in the dialogue interface in the aforementioned embodiments, which will not be repeated here. Refer to the following Figure 8 Provide a detailed description of the message push interface.

[0080] Figure 8 FIG. 1 shows a schematic diagram of a terminal lock screen interface according to some embodiments of the present disclosure. Figure 8 As shown, in the lock screen interface 8, a message 81 pushed to the user by agent A is displayed, and the message 81 includes an interpretation of recent hot news, and the message is related to the third multimedia content (i.e., the multimedia content pushed by the user), for example, it can be a description text carried by these multimedia contents, or it can be information generated by semantic understanding of the multimedia content. In response to the user's triggering operation on message 81, it can jump to the application where the agent is located, and open the dialogue interface with agent A in the application. Figure 8 The lock screen interface is just used as an example for description. In addition, the pushed message 81 may also be displayed on the operating system desktop of the user terminal or on the display interface of other applications through the information push function of the operating system, which will not be described in detail here.

[0081] The above describes various embodiments of the method of the present disclosure. The following further describes devices for implementing the methods of the above embodiments.

[0082] Fig. 9 FIG. 2 shows a schematic diagram of a structure of a multimedia content recommendation device according to some embodiments of the present disclosure. Fig. 9 As shown, the multimedia content recommendation device 9 of this embodiment includes: a first display module 901, configured to display a first entrance of a recommendation stream of multimedia contents in a dialogue interface between a user and a first intelligent agent; a second display module 902, configured to display a playback interface of the recommendation stream in response to a trigger operation on the first entrance; a determination module 903, configured to determine multimedia contents recommended to the user based on historical interaction data authorized by the user between the user and at least one of the first intelligent agent and other intelligent agents except the first intelligent agent; and a third display module 904, configured to display multimedia contents recommended to the user in the playback interface of the recommendation stream.

[0083] In some embodiments, the historical interaction data authorized by the user includes historical conversation records, and the determination module 903 is further configured to: extract one or more first key information from historical messages in the historical conversation records between the user and the first intelligent agent; determine the importance of each first key information based on the sending time of the historical messages; and determine the multimedia content recommended to the user based on the one or more first key information and the importance of each first key information.

[0084] In some embodiments, the historical interaction data authorized by the user includes historical conversation records, and the determination module 903 is further configured to: extract one or more first key information from the historical conversation records between the user and the first intelligent agent, and other intelligent agents except the first intelligent agent; determine the importance of each first key information according to the time when the historical conversation was generated and whether the historical conversation record is from the first intelligent agent; determine the multimedia content recommended to the user according to the one or more first key information and the importance of each first key information.

[0085] In some embodiments, the historical interaction data authorized by the user includes setting information of the intelligent agent used by the user, and the determination module 903 is further configured to: determine the second key information corresponding to each intelligent agent based on the setting information of the intelligent agent used by the user; determine the importance of each second key information based on at least one of the usage time and usage frequency of one or more intelligent agents; determine the multimedia content recommended for the user based on one or more second key information and the importance of each second key information.

[0086] In some embodiments, the historical interaction data authorized by the user includes the setting information of the intelligent agent created by the user, and the determination module 903 is further configured to: determine the third key information corresponding to each intelligent agent based on the setting information of the intelligent agent created by the user; determine the importance of each piece of third key information based on at least one of the creation time, usage time, and usage frequency of one or more intelligent agents; determine the multimedia content recommended for the user based on one or more pieces of third key information and the importance of each piece of third key information.

[0087] In some embodiments, the setting information includes at least one of an attribute and a type.

[0088] In some embodiments, the first display module 901 is further configured to: display a first message sent by the intelligent agent to the user and a first preview control of the first multimedia content corresponding to the first message in a dialogue interface between the user and the first intelligent agent, wherein the first preview control is the first entry of the recommendation stream of the multimedia content, and the first multimedia content is included in the multimedia content recommended for the user.

[0089] In some embodiments, the multimedia content recommendation device 9 further includes a generation module 905 .

[0090] In some embodiments, the generation module 905 is further configured to: display a second message sent by the user to the agent in the dialogue interface; and generate a first message for responding to the second message and a video corresponding to the first message based on the second message.

[0091] In some embodiments, the generation module 905 is further configured to: in response to the display of the dialogue interface, determine the last time the dialogue interface was displayed to the user; in response to the interval between the last time the dialogue interface was displayed to the user and the current time exceeding a specified threshold, generate a first message for welcoming the user back, and a video corresponding to the first message.

[0092] In some embodiments, the first display module 901 is further configured to: display a first entrance to a recommendation stream of multimedia content at a fixed position of a dialogue interface between the user and the first agent.

[0093] In some embodiments, the multimedia content recommendation device 9 also includes a fourth display module 906, which is configured to: display an interface including a conversation list, the conversation list including an entrance to a conversation interface with one or more intelligent agents, and a second entrance to a recommendation stream of multimedia content; and display a playback interface of the recommendation stream in response to a trigger operation on the second entrance.

[0094] In some embodiments, the multimedia content recommendation device 9 also includes a fifth display module 907, which is configured to: display an interface including a conversation list and a third entrance to a recommendation stream of multimedia content, wherein the conversation list includes an entrance to a conversation interface with one or more intelligent agents, and the third entrance includes one or more second preview controls for second multimedia content recommended to the user; in response to a triggering operation on the second preview control, display a playback interface of the recommendation stream; in the playback interface of the recommendation stream, display the second multimedia content and other multimedia content recommended to the user.

[0095] In some embodiments, the multimedia content recommendation device 9 also includes a sixth display module 908, which is configured to: push a third message to the user device of the user through the second agent, the third message is associated with the third multimedia content, and the second agent is the same as or different from the first agent; in response to a trigger operation on the pushed third message, display a dialogue interface between the user and the second agent; in the dialogue interface between the user and the second agent, display a third preview control of the third message and the third multimedia content; in response to a trigger operation on the third preview control, display a playback interface of the recommendation stream; in the playback interface of the recommendation stream, display the third multimedia content and the multimedia content recommended for the user.

[0096] It should be noted that the above-mentioned units are only logical modules divided according to the specific functions implemented by them, and are not used to limit the specific implementation methods. For example, they can be implemented in software, hardware, or a combination of software and hardware. In actual implementation, the above-mentioned units can be implemented as independent physical entities, or can also be implemented by a single entity (for example, a processor (CPU or DSP, etc.), an integrated circuit, etc.). In addition, the above-mentioned units are shown with dotted lines in the drawings to indicate that these units may not actually exist, and the operations / functions implemented by them can be implemented by the processing circuit itself.

[0097] In addition, although not shown, the device may also include a memory, which may store various information generated by the device, various units contained in the device during operation, programs and data for operation, data to be sent by the communication unit, etc. The memory may be a volatile memory and / or a non-volatile memory. For example, the memory may include, but is not limited to, a random access memory (RAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), a read-only memory (ROM), and a flash memory. Of course, the memory may also be located outside the device. Optionally, although not shown, the device may also include a communication unit, which may be used to communicate with other devices. In one example, the communication unit may be implemented in a suitable manner known in the art, such as including communication components such as an antenna array and / or a radio frequency link, various types of interfaces, communication units, etc. It will not be described in detail here. In addition, the device may also include other components not shown, such as a radio frequency link, a baseband processing unit, a network interface, a processor, a controller, etc. It will not be described in detail here.

[0098] Some embodiments of the present disclosure also provide an electronic device. Fig.10 A schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure is shown. For example, in some embodiments, the electronic device 10 can be various types of devices, for example, can include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 10 may include a display panel for displaying data and / or execution results used in the scheme according to the present disclosure. For example, the display panel can be in various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel, etc. In addition, the display panel can be not only a flat panel, but also a curved panel, or even a spherical panel.

[0099] like Fig.10 As shown, the electronic device 10 of this embodiment includes: a memory 101 and a processor 102 coupled to the memory 101. It should be noted that Fig.10 The components of the electronic device 10 shown are only exemplary and non-limiting. The electronic device 10 may also have other components according to actual application requirements. The processor 102 may control other components in the electronic device 10 to perform desired functions.

[0100] In some embodiments, the memory 101 is used to store one or more computer-readable instructions. When the processor 102 is used to execute the computer-readable instructions, the computer-readable instructions are executed by the processor 102 to implement the method according to any of the above embodiments. For the specific implementation of each step of the method and related explanations, please refer to the above embodiments, and the repetitions will not be repeated here.

[0101] For example, the processor 102 and the memory 101 may communicate with each other directly or indirectly. For example, the processor 102 and the memory 101 may communicate with each other through a network. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 102 and the memory 101 may also communicate with each other through a system bus, which is not limited in the present disclosure.

[0102] For example, the processor 102 may be embodied as various appropriate processors, processing devices, etc., such as a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc.; it may 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 gates or transistor logic devices, discrete hardware components. The central processing unit (CPU) may be an X86 or ARM architecture, etc. For example, the memory 101 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The memory 101 may include, for example, a system memory, which may store, for example, an operating system, an application, a boot loader, a database, and other programs. Various applications and various data may also be stored in the storage medium.

[0103] In addition, according to some embodiments of the present disclosure, various operations / processes according to the present disclosure, when implemented by software and / or firmware, can be transmitted from a storage medium or a network to a computer system having a dedicated hardware structure, such as Fig.11 The computer system 110 shown installs the programs constituting the software. When the various programs are installed, the computer system can perform various functions, including the functions described above. Fig.11 A schematic diagram of the structure of a computer system according to some embodiments of the present disclosure is shown.

[0104] exist Fig.11In the embodiment, a central processing unit (CPU) 1101 performs various processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage section 1108 to a random access memory (RAM) 1103. In the RAM 1103, data required when the CPU 1101 performs various processes, etc., is also stored as needed. The central processing unit is merely exemplary, and it may also be other types of processors, such as the various processors described above. The ROM 1102, the RAM 1103, and the storage section 1108 may be various forms of computer-readable storage media, as described below. It should be noted that although Fig.11 ROM 1102, RAM 1103, and storage device 1108 are shown separately in FIG. 1 , but one or more of them may be combined or located in the same or different memory or storage modules.

[0105] The CPU 1101, the ROM 1102, and the RAM 1103 are connected to one another via a bus 1104. To the bus 1104, an input / output interface 1105 is also connected.

[0106] The following components are connected to the input / output interface 1105: an input portion 1106, such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output portion 1107, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage portion 1108, including a hard disk, a magnetic tape, etc.; and a communication portion 1109, including a network interface card such as a LAN card, a modem, etc. The communication portion 1109 allows communication processing to be performed via a network such as the Internet. It is easy to understand that although Fig.11 The various devices or modules in the computer system 110 are shown to communicate via the bus 1104, but they 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 networks and wired networks.

[0107] A drive 1110 is also connected to the input / output 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 mounted on the drive 1110 as needed so that a computer program read therefrom is installed into the storage section 1108 as needed.

[0108] In the case where the above-described series of processing is implemented by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 1111 .

[0109] According to an embodiment of the present disclosure, the process described above with reference to the flowchart 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 medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 1109, or installed from the storage device 1108, or installed from the ROM 1102. When the computer program is executed by the CPU 1101, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0110] It should be noted that in the context of the present disclosure, a computer-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. A computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by an instruction execution system, device or device or used in combination with it. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, 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 cables, RF (radio frequency), etc., or any suitable combination of the above.

[0111] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0112] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to execute any of the methods of the above embodiments. For example, the instructions may be embodied as computer program codes.

[0113] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In situations involving a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0114] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The modules, components or units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the modules, components or units do not, in some cases, limit the modules, components or units themselves.

[0116] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0117] The above descriptions are only some embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, a technical solution formed by replacing the above features with the technical features with similar functions disclosed in the present disclosure (but not limited to).

[0118] In the description provided herein, many specific details are set forth. However, it is understood that embodiments of the present invention can be implemented without these specific details. In other cases, well-known methods, structures, and techniques are not presented in detail in order not to obscure the understanding of the description.

[0119] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0120] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for recommending multimedia content, comprising: In a dialogue interface between a user and a first agent, displaying a first entry of a recommendation stream of multimedia content; In response to a triggering operation on the first entrance, displaying a playback interface of the recommended stream; Determine multimedia content recommended for the user based on historical interaction data authorized by the user with at least one of the first agent and other agents other than the first agent; In the playback interface of the recommendation stream, the multimedia content recommended for the user is displayed.

2. The recommendation method according to claim 1, wherein: The historical interaction data authorized by the user includes historical conversation records, and the multimedia content determined to be recommended for the user includes: Extracting one or more first key information from historical messages of historical conversation records between the user and the first agent; Determining the importance of each piece of first key information according to the sending time of the historical message; The multimedia content recommended for the user is determined according to the one or more pieces of first key information and the importance of each piece of first key information.

3. The recommendation method according to claim 1 or 2, wherein: The historical interaction data authorized by the user includes historical conversation records, and the multimedia content determined to be recommended for the user includes: Extracting one or more first key information from historical conversation records between the user and the first agent, and other agents except the first agent; Determine the importance of each piece of first key information according to the generation time of the historical conversation and whether the historical conversation record comes from the first agent; The multimedia content recommended for the user is determined according to the one or more pieces of first key information and the importance of each piece of first key information.

4. The recommendation method according to any one of claims 1 to 3, wherein: The historical interaction data authorized by the user includes setting information of the intelligent agent used by the user, and the multimedia content determined to be recommended for the user includes: Determining second key information corresponding to each agent according to setting information of the agent used by the user; Determining the importance of each piece of second key information according to at least one of the use time and the use frequency of the one or the agent; The multimedia content recommended for the user is determined according to the one or more pieces of second key information and the importance of each piece of second key information.

5. The recommendation method according to any one of claims 1 to 4, wherein: The historical interaction data authorized by the user includes setting information of the agent created by the user, and the multimedia content determined to be recommended for the user includes: Determining third key information corresponding to each agent according to the setting information of the agent created by the user; Determining the importance of each piece of third key information according to at least one of the creation time, usage time, and usage frequency of the one or the agent; The multimedia content recommended for the user is determined according to the one or more pieces of third key information and the importance of each piece of third key information.

6. The recommendation method according to claim 4 or 5, wherein: The setting information includes at least one of an attribute and a type.

7. The recommendation method according to any one of claims 1 to 6, wherein: The first entry for displaying the recommendation stream of multimedia content in the dialogue interface between the user and the first agent includes: In the dialogue interface between the user and the first agent, a first message sent by the agent to the user and a first preview control of first multimedia content corresponding to the first message are displayed, wherein the first preview control is the first entry of the recommendation stream of the multimedia content, and the first multimedia content is included in the multimedia content recommended for the user.

8. The recommendation method according to claim 7, further comprising: In the dialogue interface, displaying a second message sent by the user to the agent; According to the second message, the first message for responding to the second message and a video corresponding to the first message are generated.

9. The recommendation method according to claim 7 or 8, further comprising: In response to displaying the dialogue interface, determining a time when the dialogue interface was last displayed to the user; In response to the interval between the time when the dialogue interface was last displayed to the user and the current time exceeding a specified threshold, the first message for welcoming the user back and the video corresponding to the first message are generated.

10. The recommendation method according to any one of claims 1 to 9, wherein: The first entry for displaying the recommendation stream of multimedia content in the dialogue interface between the user and the first agent includes: The first entrance of the recommendation stream of the multimedia content is displayed at a fixed position of the dialogue interface between the user and the first agent.

11. The recommendation method according to any one of claims 1 to 10, further comprising: Displaying an interface including a conversation list, wherein the conversation list includes an entry of a conversation interface with one or more agents and a second entry of a recommended stream of the multimedia content; In response to a triggering operation on the second entrance, a playback interface of the recommended stream is displayed.

12. The recommendation method according to any one of claims 1 to 11, further comprising: Displaying an interface including a conversation list and a third entry of a recommendation stream of the multimedia content, wherein the conversation list includes an entry of a conversation interface with one or more agents, and the third entry includes one or more second preview controls of second multimedia content recommended for the user; In response to a triggering operation on the second preview control, displaying a playback interface of the recommended stream; In the playback interface of the recommendation stream, the second multimedia content and other multimedia content recommended to the user are displayed.

13. The recommendation method according to any one of claims 1 to 12, further comprising: Pushing a third message to a user device of the user through a second agent, wherein the third message is associated with third multimedia content, and the second agent is the same as or different from the first agent; In response to a triggering operation on the pushed third message, displaying a dialogue interface between the user and the second agent; In the dialogue interface between the user and the second agent, displaying the third message and a third preview control of the third multimedia content; In response to a triggering operation on the third preview control, displaying a playback interface of the recommended stream; In the playback interface of the recommendation stream, the third multimedia content and the multimedia content recommended to the user are displayed.

14. A multimedia content recommendation device, comprising: A first display module is configured to display a first entry of a recommendation stream of multimedia content in a dialogue interface between a user and a first agent; A second display module, configured to display a playback interface of the recommended stream in response to a triggering operation on the first entrance; a determination module configured to determine multimedia content recommended for the user based on historical interaction data authorized by the user with at least one of the first agent and other agents other than the first agent; The third display module is configured to display the multimedia content recommended to the user in the playback interface of the recommendation stream.

15. An electronic device, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the multimedia content recommendation method according to any one of claims 1 to 13 based on instructions stored in the memory.

16. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for recommending multimedia content according to any one of claims 1 to 13 is implemented.

17. A computer program product, when the computer program product is executed on a computer, enables the computer to implement the multimedia content recommendation method according to any one of claims 1 to 13.

18. A computer program comprising: Instructions, when executed by a processor, cause the processor to perform the multimedia content recommendation method according to any one of claims 1 to 13.

Citation Information

Cited By

  • Recommended information processing method and device, electronic equipment, storage medium and product

    CN119299417A

  • Interaction method and device, electronic equipment, storage medium and program product

    CN119829697A

  • Intelligent agent operation method, electronic equipment, storage medium and program product

    CN122489164A

  • Media resource processing method and apparatus, and device, medium and program product

    WO2026157898A1